Detailed Description
Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.
It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
It will be understood by those of skill in the art that the terms "first," "second," and the like in the embodiments of the present disclosure are used merely to distinguish one element from another, and are not intended to imply any particular technical meaning, nor is the necessary logical order between them.
It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more and "at least one" may refer to one, two or more.
It is also to be understood that any reference to any component, data, or structure in the embodiments of the disclosure, may be generally understood as one or more, unless explicitly defined otherwise or stated otherwise.
In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, such as a and/or B, and may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.
It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Embodiments of the present disclosure may be implemented in electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with an electronic device, such as a terminal device, computer system, or server, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.
Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks may be performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
Summary of the disclosure
In the process of realizing the disclosure, the inventor finds that although the types of skill training in the society are rich at present, the training of the skill of the traditional woodworker is rare. For those interested in traditional carpentry, it is often difficult to find a master that can teach the carpentry.
At present, computer vision technology is widely applied to the fields of security monitoring, intelligent business and the like, and if the computer vision technology can be introduced into the field of wood product processing, people interested in traditional wood craft can be helped.
Brief description of the drawings
An example of an application scenario of the technical solution of the present disclosure is shown in fig. 1.
In fig. 1, a program (such as APP) for assisting a user in processing a wooden product is installed in a terminal device (a smartmobile phone 100, a tablet computer 101, alaptop computer 102, or a desktop computer 103) of the user.
Assume that the user's terminal device is a tablet computer 101. The user opens an APP in the tablet pc 101 for assisting the user in implementing wood product processing, the APP displays a picture containing various pieces of furniture according to the user's furniture browsing operation, and an example of the furniture picture displayed by the APP is shown on the left side of fig. 1.
After the user selects a piece of furniture (e.g., the furniture 104 in fig. 1) from the furniture picture displayed by the APP, the user can adjust the length, width, height, etc. of the furniture 104 according to the actual needs thereof by using the furniture size modification function provided by the APP. After the user determines the size of the furniture 104, the APP can control the point light source array to project processing light on the wood to be processed corresponding to each partition piece included in the furniture 104, so as to assist the user in drawing processing lines on the wood to be processed. The APP can also provide a variety of prompts for the user, such as prompts for tools that the user needs to use to manually make the furniture (as shown in fig. 2), tool alternatives for tools that the user lacks, machining techniques, and notes in manually making the furniture, so as to assist the user in successfully completing the manual making of the furniture 104.
Fig. 2 shows tools required by a user to manually make the furniture in the form of pictures, and the present disclosure may also show tools required by the user to manually make the furniture in the form of characters.
Exemplary method
FIG. 3 is a flow chart of one embodiment of a method of processing a wood product of the present disclosure. The method shown in fig. 3 comprises: s300, S301, and S302. The following describes each step.
S300, determining the processing line information of each partition of the wooden product to be processed and the processing sequence information of each partition.
The wooden product to be processed in the present disclosure may be furniture, toys, ornaments, artware or the like. The wood product to be processed in the present disclosure is generally a target wood product obtained based on a selection of a user. Each divided piece of the wood product to be processed in the present disclosure may refer to all the components for combining to form the wood product to be processed. The processing line information of the partition in the present disclosure may refer to a line for prompting a user of a processing position of the wood to be processed corresponding to the partition so that the wood to be processed forms the partition, for example, a line for prompting a cutting position, or the like. The processing order information of each partition in the present disclosure may refer to information for planning the order of processing all the partitions of the wooden article to be processed for the user.
All the sections included in the wood product to be processed are usually planned in advance, and each section usually has default processing line information. The processing sequence information of each divided piece is also generally planned and designed in advance.
S301, determining the placement position information of the wood to be processed corresponding to the current dividing piece according to the processing sequence information of each dividing piece.
The method and the device can determine the current segmentation piece according to the processing sequence information of each segmentation piece, and obtain the placement position information of the wood to be processed corresponding to the current segmentation piece through target detection. For example, the present disclosure may detect the placement position information of the timber to be processed corresponding to the current partition using computer vision technology.
The placement position information in the present disclosure may refer to coordinate information of a plurality of key points of the timber to be processed, for example, three-dimensional space coordinates of each apex of the timber to be processed, or the like.
S302, projecting processing light rays to the wood to be processed corresponding to the current dividing piece according to the placement position information of the wood to be processed corresponding to the current dividing piece and the processing line information of the current dividing piece.
The processing light in this disclosure is used for instructing the processing position of the timber to be processed that the present segmentation piece corresponds, and when processing the timber to be processed according to this processing position, the timber to be processed can form the present segmentation piece.
The wood processing method comprises the steps of sequentially projecting processing light rays for the wood to be processed corresponding to each partition piece respectively according to the processing sequence of each partition piece, and obtaining all partition piece entities of the wood product to be processed after the wood to be processed is processed correspondingly according to the corresponding processing light rays, so that the wood product entity to be processed can be formed by assembling the partition piece entities.
According to the method, the processing line information of each partition piece of the wooden product to be processed is formed, the processing light is projected on the wood to be processed corresponding to each partition piece, so that important reference information for processing the wooden product is provided for a user, and the phenomenon that the wood to be processed is wasted due to unreasonable design of the processing line in the process that the user independently designs the processing line of each partition piece can be avoided; thereby this disclosure not only is favorable to reducing the processing degree of difficulty of woodwork, and the supplementary user accomplishes the woodwork processing, still is favorable to improving the yield of woodwork processing.
In an alternative example, the wood product to be processed of the present disclosure may be a wood product to be processed based on a mortise and tenon structure. The piece of cutting apart of waiting to process woodwork in this disclosure promptly can be for the piece of cutting apart based on tenon fourth of twelve earthly branches structure. That is, the determination of the processing line information of each partition of the wooden product to be processed in the present disclosure may be specifically the determination of the processing line information of each partition of the wooden product to be processed based on the mortise and tenon joint structure.
Optionally, when the wooden article to be processed is a wooden article to be processed based on the mortise and tenon structure, the processing line information of the partition piece of the wooden article to be processed may include: and (4) processing line information of the tenon and mortise of the cutting piece. The tenon-and-mortise processing line information is used for forming the tenon-and-mortise structure of the segmentation piece.
Alternatively, an example of the partition based on the mortise and tenon structure is shown in fig. 4A and 4B. Fig. 4A shows the two segments based on the mortise and tenon structure after they are assembled (e.g., inserted) together, and fig. 4B shows the respective structures of the two segments based on the mortise and tenon structure when they are not assembled (e.g., inserted) together.
The structure of each partition piece of a wood product based on a mortise and tenon structure is generally complex, and the complex structure of the partition piece generally affects the yield of the wood product. This is disclosed through making the processing line information of the piece of cutting apart of treating processing woodwork based on mortise and tenon structure include mortise and tenon processing line information, is favorable to reducing the processing degree of difficulty that each cuts apart the respective pending timber that corresponds to be favorable to improving the yield of woodwork.
In an alternative example, the wood product to be processed in the present disclosure may be a wood product having a default size. The default size may also be referred to as the original size. After the user has individualized the size of target woodwork according to its actual demand, the default size of waiting to process the woodwork is changed, waits to process the woodwork and becomes the woodwork that has individualized size. In the case where the user individually adjusts the size of the target wooden article according to the actual need thereof, the manner of determining the processing line information of each partition of the wooden article to be processed in S300 of the present disclosure may be as shown in fig. 5.
In fig. 5, S500, default processing line information of each partition of the wooden article to be processed and shape adjustment information of the wooden article to be processed are acquired.
Optionally, the default processing line information of each partition in the present disclosure is: in the case where the wooden article to be processed is a wooden article having a default size, the processing line information of each partition. The default processing line information may also be referred to as original processing line information. The default processing line information of each segment is generally known information stored in advance in the terminal device or the network-side device. In the case where the default processing line information of each partition is stored in the network-side device in advance, the present disclosure may download the default processing line information of each partition of a wooden product to be processed from the network-side device after the wooden product to be processed is selected by the user.
Alternatively, the shape adjustment information of the wooden product to be processed in the present disclosure may include, but is not limited to: scaling of at least one of the length, width, and height of the wood product to be processed as a whole. For example, the overall height of the wood product to be processed is reduced by a factor of five.
Alternatively, the shape adjustment information of the wooden product to be processed of the present disclosure may include, but is not limited to: a scaled dimension of at least one of a length, a width, and a height of an entirety of the wood product to be processed. For example, the overall height of the wood product to be processed is reduced by five centimeters.
Alternatively, the shape adjustment information of the wooden product to be processed of the present disclosure may include, but is not limited to: scaling of at least one of length, width and height of a localized area of the wood product to be processed. For example, in the case where the wooden article to be processed is a chair as shown in fig. 6A and 6B, the shape adjustment information may include: the height of the backrest of the chair is reduced by one fifth. The chair in fig. 6A and 6B may be dimensioned as a default size for the wood product to be processed.
Alternatively, the shape adjustment information of the wooden product to be processed of the present disclosure may include, but is not limited to: a scaled size of at least one of a length, a width, and a height of a localized area of the wood product to be processed. For example, in the case where the wooden article to be processed is a chair as shown in fig. 6A and 6B, the shape adjustment information may include: the height of the back of the chair is reduced by five centimeters.
S501, according to the shape adjustment information of the wooden product to be processed, converting the default processing line information of the corresponding partition of the wooden product to be processed, and determining the processing line information of each partition of the wooden product to be processed.
Optionally, this disclosure can be according to the shape adjustment information of treating the processing woodwork, from treating all segmentation spare of processing woodwork, screen out the user and treat the segmentation spare that needs the resize that individualized adjustment of processing woodwork related. All the pieces that need to be resized form a set (hereinafter referred to as a resized set). If there are partitions that do not need to be resized, all partitions that do not need to be resized form a set (referred to below as a default size set). For any of the divided pieces in the default size set, the default machining line information of the divided piece is set as the machining line information of the divided piece. For any piece in the size adjustment set, the default processing line information of the piece is converted according to the shape adjustment information of the wooden product to be processed, so as to obtain the processing line information of the piece.
As an example, the shape adjustment information of the wooden article to be processed in the present disclosure includes: in the case of the overall length scaling, the width scaling, and the high scaling of the wooden product to be processed, all the divided pieces of the wooden product to be processed may belong to the set of size adjustment. For any partition in the resizing set, the present disclosure may scale each piece of default processing line information of the partition according to the long scaling ratio, the wide scaling ratio, and the high scaling ratio, respectively, so as to obtain the processing line information of the partition.
As another example, the shape adjustment information on the wood product to be processed in the present disclosure includes: in the case of the overall length-scaled size, width-scaled size, and height-scaled size of the wooden product to be processed, all the divided pieces of the wooden product to be processed may belong to the set of size adjustment. This openly can be earlier treat that the holistic length of processing woodwork scales, wide scale and high scale size convert respectively into the holistic length scale, wide scale and high scale of waiting to process woodwork, then, to arbitrary segmentation in the adjustment of size set, this disclosure can be according to length scale, wide scale and high scale, carries out scaling adjustment respectively to each default processing line information of this segmentation to obtain the processing line information of this segmentation.
As still another example, the shape adjustment information of the wooden article to be processed in the present disclosure includes: in the case of at least one of the long scale, the wide scale, and the high scale (the high scale will be described below as an example) of the partial region of the wood product to be processed, all the pieces included in the partial region may belong to the resizing set, and all the pieces included in the other regions may belong to the default size set. For any partition in the resizing set, the present disclosure may perform scaling adjustment on each piece of default processing line information (including straight lines and curved lines) relating to the high direction of the partition according to the high scaling of the local area, respectively, and all pieces of processing line information relating to the high direction after scaling adjustment form the processing line information of the partition together with other pieces of default processing line information of the partition.
As still another example, the shape adjustment information of the wooden article to be processed in the present disclosure includes: in the case of at least one of the long zoom size, the wide zoom size, and the high zoom size of the partial region of the wood product to be processed (hereinafter, the high zoom size is exemplified), all of the pieces included in the partial region may belong to the resizing set, and all of the pieces included in the other regions may belong to the default size set. For any partition in the size adjustment set, the local high scaling size of the wooden product to be processed can be converted into the high scaling ratio of the local area of the wooden product to be processed, then, for any partition in the size adjustment set, the scaling adjustment can be respectively carried out on each piece of default processing line information (including straight lines and curves) related to the height direction of the partition according to the high scaling ratio, and all pieces of processing line information related to the height direction after scaling adjustment and other pieces of default processing line information of the partition form the processing line information of the partition.
This is disclosed through the individualized adjustment to the size of target wooden article according to the user, adjusts the processing line information of treating each partition piece of processing wooden article, is favorable to improving the flexibility and the variety of wooden article processing.
In an alternative example, in the case where a current partition is selected from all the partitions based on the processing sequence information of the partitions, the present disclosure may employ a computer vision technique to determine the placement position information of the wood to be processed corresponding to the current partition. One example of determining the placement position information of the wood to be treated corresponding to the current partition in S301 of the present disclosure may be as shown in fig. 7.
In fig. 7, S700, a target object recognition process is performed on the binocular image of the wood to be processed corresponding to the current partition.
Alternatively, the present disclosure may implement the target object recognition process using a neural network.
In one example, the wood to be processed corresponding to the current partition piece is placed in a predetermined space area, and the predetermined space area is photographed by using a binocular camera device, so that binocular images of the wood to be processed, namely a left eye image containing a picture of the wood to be processed and a right eye image containing a picture of a target to be processed, are obtained. And then, the binocular image of the wood to be processed is taken as an input image and is provided for a neural network, and the input image is subjected to processing such as feature extraction, detection frame prediction, target object classification, target object edge prediction and the like through the neural network, so that the target object identification processing result can be obtained according to the output information of the neural network. The result of the target object recognition process may include: the outer contour of the target object in the image, the coordinates of each vertex of the target object in the image, and the like.
In another example, the timber to be processed corresponding to the current partition piece is placed in a preset space area, and the preset space area is photographed by using a monocular camera device, so that a monocular image of the timber to be processed is obtained. The monocular image can be processed (such as mirror image processing) by the present disclosure, so as to obtain a binocular image of the wood to be processed, namely, a left eye image containing a picture of the wood to be processed and a right eye image containing a picture of a target to be processed. And then, the binocular image of the wood to be processed is taken as an input image and is provided for a neural network, and the input image is subjected to processing such as feature extraction, detection frame prediction, target object classification, target object edge prediction and the like through the neural network, so that the target object identification processing result can be obtained according to the output information of the neural network. The result of the target object recognition process may include: the outer contour of the target object in the image, the coordinates of each vertex of the target object in the image, and the like.
S701, acquiring depth information of the binocular image of the wood to be processed.
Optionally, the depth information of the binocular image in the present disclosure may include, but is not limited to: point cloud data of a plurality of pixel points in the binocular image. For example, the point cloud data including a predetermined spatial region can be obtained by using equipment such as a laser radar, the point cloud data can be subjected to region range screening, point cloud data corresponding to a binocular image can be obtained, and each point in the point cloud data can show the depth information of the point in an actual three-dimensional space, so that the depth information of a plurality of points in the binocular image can be obtained. Under the condition that the point cloud data are sparse point cloud data, the point cloud data can be supplemented to obtain dense point cloud data, and then the dense point cloud data is used for obtaining depth information of a plurality of points in the binocular image.
Optionally, the depth information of the binocular image in the present disclosure may include, but is not limited to: and the depth values of a plurality of pixel points in the binocular image. The manner of obtaining the depth values of the binocular image of the present disclosure may be: providing the binocular images as input images to a neural network (e.g., a convolutional neural network), and performing disparity prediction processing on the binocular images via the neural network, so that binocular disparity maps (e.g., a left disparity map and a right disparity map) of the binocular images can be obtained according to information output by the neural network; then, the depth value of each pixel point in the binocular image can be obtained according to the binocular disparity map of the binocular image. For example, a binocular disparity map is used as an input of another neural network, and depth prediction processing is performed on the input binocular disparity map via the neural network, so that depth information of each pixel point in a binocular image can be obtained according to information output by the neural network.
S702, determining coordinate information of each vertex of the timber to be processed corresponding to the current segmentation piece in a three-dimensional space according to the depth information and the result of the target object identification processing.
Optionally, the result of the target object identification processing in the present disclosure includes: under the condition of the coordinates of the vertexes of the timber to be processed corresponding to the current segmentation piece in the image, the depth information of the corresponding position points can be searched from the depth information of the binocular image by utilizing the coordinates of the vertexes in the image, so that the Z coordinates of the vertexes of the timber to be processed in the three-dimensional space can be obtained. The manner in which the X and Y coordinates of each apex of the timber to be treated are obtained in three dimensions includes, but is not limited to: corresponding calculation is carried out according to the parameters (such as focal length, optical center offset and the like) of the camera device and the X coordinate and the Y coordinate of each vertex of the timber to be processed in the image, and the calculation result is obtained.
According to the method, the computer vision technology is utilized, the coordinate information of each vertex of the wood to be processed corresponding to the current segmentation piece in the three-dimensional space can be conveniently and accurately obtained, so that the coordinate information of each vertex of the wood to be processed in the three-dimensional space is utilized, a three-dimensional image of the wood to be processed can be successfully generated, and the planning of the processing light on the wood to be processed is facilitated.
Optionally, the present disclosure may label the actual size of the three-dimensional stereo image (the actual size may be calculated according to the coordinate information of each vertex in the three-dimensional space) after the three-dimensional stereo image of the wood to be processed is successfully generated, and display the actual size to the user. The interactive interface for modifying the actual dimension of the wood to be processed can be provided for a user, so that the actual dimension of the current mark of the wood to be processed can be conveniently modified by the user, the accuracy of the processing light projected on the wood to be processed can be improved, and the finished product rate of wood product processing can be improved.
In an alternative example, an example of the process of projecting the processing light onto the wood to be processed corresponding to the current partition according to the placement position information of the wood to be processed corresponding to the current partition and the processing line information of the current partition in S302 of the present disclosure is shown in fig. 8 and 9.
In fig. 8, S800, the on/off control information of each point light source in the point light source array is determined according to the placement position information of the wood to be processed corresponding to the current partition and the processing line information of the current partition.
Alternatively, a point light source in this disclosure may refer to a particle light source. The array of point light sources typically includes a plurality of point light sources. The plurality of point light sources are generally located in the same plane, and the plurality of point light sources are generally arranged in a two-dimensional matrix. The size of the point light source array can be designed according to the size of each partition piece of the wood product to be processed. The point light source array in the present disclosure may be specifically an infrared lamp array, a laser lamp array, and the like.
Optionally, the present disclosure generally needs to know the setting position information of the point light source array in advance, for example, coordinates of any point light source in the point light source array in the three-dimensional space are obtained in advance, and an included angle between the point light source array and the horizontal plane and the vertical plane is obtained, because the point light sources in the point light source array are generally distributed at equal intervals and the number of the point light sources is fixed, the present disclosure may calculate coordinates of other point light sources in the point light source array in the three-dimensional space according to the row and column positions of the point light sources with known coordinates and the included angle.
Alternatively, the present disclosure considers a bundle of rays emitted by a point light source as a set of parallel and non-divergent rays, and the projection of the bundle of rays on the surface is a point. This openly can be according to the pending timber that the present segmentation corresponds place positional information and pointolite array and horizontal plane and the contained angle between the perpendicular, determine the projection position of the light of a plurality of pointolites on pending timber (the light of the some pointolites in the pointolite array probably can not be projected on pending timber), thereby this openly can be according to the processing line information of present segmentation, determine the on/off control information of each point light source in the pointolite array.
S801, controlling the on/off state of each point light source in the point light source array according to the on/off control information of each point light source in the point light source array so as to project processing light on the wood to be processed corresponding to the current segmentation piece.
Optionally, each point light source in the point light source array in the present disclosure has an independent switch. And under the condition that the point light source array is an infrared lamp array, the processing light projected on the wood to be processed corresponding to the current partition piece is red processing light.
In the general case where multiple faces (e.g. all faces) of the timber to be treated require projection of the processing light, the present disclosure may prompt the user to turn the timber to be treated so as to project the corresponding processing light on the corresponding face of the timber to be treated. When the user overturns the timber to be processed according to the prompt each time, the placing position information of the timber to be processed corresponding to the current dividing piece needs to be obtained again.
Alternatively, an example of the processing light projected on the wood to be processed corresponding to the current partition by using the point light source array is shown in fig. 9. In fig. 9, the processing sequence of thewood material 902 to be processed is 1, i.e., the present division is the 1 st division of the wood product to be processed. Multiple processing rays are projected by the pointlight source array 900 on both sides of thewood 902 to be processed. Although the pointlight source array 900 in fig. 9 is fixedly disposed on theimage pickup device 901, in practical applications, the pointlight source array 900 may be disposed separately from theimage pickup device 901. The present disclosure does not limit the relative position between the pointlight source array 900 and theimage pickup apparatus 901.
Alternatively, the user may draw a processing line (e.g. a black line, etc.) on the wood to be processed in accordance with the projected processing light. After all the processing light rays are projected on the wood to be processed or all the processing light rays of one surface of the wood to be processed are projected on the surface, the prompt information of the processing lines of the current segmentation pieces can be generated and displayed to a user. For example, the present disclosure may calculate a horizontal distance or a vertical distance between different processing lines, etc., and prompt the user. For another example, the present disclosure may prompt the user to: the position relationship between the processing lines on one surface of the wood to be processed and the processing lines on the other surface (for example, the processing lines on the two surfaces have a common end point) and the like, so that a user can conveniently check and correct the processing lines (for example, ink lines and the like) painted on the wood to be processed, the yield of the divided pieces is improved, and the yield of the wood product processing is improved.
This is disclosed through the on/off state of each point light source in the control pointolite array, can be convenient form the processing light on pending timber, be favorable to swift and accurate formation to cut apart the piece to be favorable to improving the realizability of woodwork processing.
In an alternative example, in a case where the raw material corresponding to the wooden product to be processed needs to be divided to obtain the wood to be processed corresponding to each of the divided pieces of the wooden product to be processed, the present disclosure may assist the user in obtaining the wood to be processed corresponding to each of the divided pieces of the wooden product to be processed. An example of the wood material to be treated for each of the divided pieces for obtaining the wood product to be processed is shown in fig. 10.
In fig. 10, S1000, the information of the dividing line of the raw material corresponding to the wood product to be processed is acquired.
Alternatively, the raw material in this disclosure generally refers to wood, e.g., at least one length of log or the like. The splitting line information of the raw wood in the present disclosure may refer to a splitting line for splitting the raw material so as to form at least one wood material to be processed. The log split line information may include, but is not limited to: a horizontal split line at a predetermined height from the uppermost end of the log, a horizontal split line at a predetermined height from the lowermost end of the log, a vertical split line at a predetermined length from the leftmost end of the log, a vertical split line at a predetermined length from the rightmost end of the log, a position of a longitudinal line at a predetermined distance from the center point of the length of the log, and a position of a transverse split line at a predetermined distance from the center point of the length of the log, etc.
Optionally, this disclosure can set up many money in advance and wait to process the required raw materials information of woodwork, after the user selects a money to wait to process the woodwork from waiting to process the woodwork of many money, to this money required raw materials information of woodwork of waiting to process of user's suggestion. The material information here may include: wood species of the logs, diameter of the logs, length of the logs, number of logs, and the like. The raw material information may include multiple sets, for example, where a set of raw material information includes: the length and number of logs of diameter M, etc., wherein another set of raw material information includes: the length and number of logs of diameter N, etc. For each group of raw material information, the method is provided with corresponding raw material dividing line information in advance.
Optionally, the disclosure may prompt the user for each group of material information, and the user may prepare the corresponding material according to the prompt. In the case that the raw material prepared by the user is basically the same as one group of the prompted raw material information, the present disclosure may directly acquire the dividing line information corresponding to the group of the raw material information. The above-mentioned substantial identity means that the difference between the two is within a predetermined range. Under the condition that the raw materials prepared by the user and any group of prompted raw material information have large differences, the division line information of the raw materials can be obtained by adopting a mode of arranging and combining the to-be-processed woods corresponding to the dividing pieces. One example of the present disclosure to acquire the dividing line information of the raw material corresponding to the wood product to be processed is as described below with respect to fig. 12.
S1001, determining the placing position information of the raw materials.
Alternatively, the present disclosure may employ computer vision techniques to obtain placement location information for the raw materials. As an example, first, a target object recognition process is performed on a binocular image of a raw material; then, acquiring depth information of binocular images of the raw materials; and finally, determining the coordinate information of each key point of the raw material in the three-dimensional space according to the depth information and the result of the target object identification processing. Each of the key points of the material may include each vertex of the material, for example, both end points in the length direction, upper, lower, left, and right end points in the cross-sectional direction, and the like.
Alternatively, the present disclosure may implement the target object recognition process using a neural network.
In one example, the raw material is placed in a predetermined space area, and the predetermined space area is photographed by using a binocular camera, so that binocular images of the raw material, that is, a left eye image including a raw material picture and a right eye image including a raw material picture, are obtained. After that, the binocular image of the raw material is provided to the neural network as an input image of the neural network, and the input image is subjected to processes such as feature extraction, detection frame prediction, target object classification, and target object edge prediction via the neural network, so that the present disclosure can obtain a result of target object recognition processing from output information of the neural network. The result of the target object recognition process may include: the outer contour of the target object in the image, the coordinates of each vertex of the target object in the image, and the like.
As another example, a raw material is placed in a predetermined spatial region and the predetermined spatial region is photographed using a monocular image capturing device to obtain a monocular image of the raw material. The present disclosure may process (e.g., mirror image process, etc.) the monocular image to obtain a binocular image of the material, i.e., a left eye image including the material picture and a right eye image including the material picture. And then, the binocular image of the wood to be processed is taken as an input image and is provided for a neural network, and the input image is subjected to processing such as feature extraction, detection frame prediction, target object classification, target object edge prediction and the like through the neural network, so that the target object identification processing result can be obtained according to the output information of the neural network. The result of the target object recognition process may include: the outer contour of the target object in the image, the coordinates of each vertex of the target object in the image, and the like.
Optionally, the depth information of the binocular image in the present disclosure may include, but is not limited to: point cloud data of a plurality of pixel points in the binocular image. For example, the point cloud data including a predetermined spatial region can be obtained by using equipment such as a laser radar, the point cloud data can be subjected to region range screening, point cloud data corresponding to a binocular image can be obtained, and each point in the point cloud data can show the depth information of the point in an actual three-dimensional space, so that the depth information of a plurality of points in the binocular image can be obtained. Under the condition that the point cloud data are sparse point cloud data, the point cloud data can be supplemented to obtain dense point cloud data, and then the dense point cloud data is used for obtaining depth information of a plurality of points in the binocular image.
Optionally, the depth information of the binocular image in the present disclosure may include, but is not limited to: and the depth values of a plurality of pixel points in the binocular image. The manner of obtaining the depth values of the binocular image of the present disclosure may be: providing the binocular images as input images to a neural network (e.g., a convolutional neural network), and performing disparity prediction processing on the binocular images via the neural network, so that binocular disparity maps (e.g., a left disparity map and a right disparity map) of the binocular images can be obtained according to information output by the neural network; then, the depth value of each pixel point in the binocular image can be obtained according to the binocular disparity map of the binocular image. For example, a binocular disparity map is used as an input of another neural network, and depth prediction processing is performed on the input binocular disparity map via the neural network, so that depth information of each pixel point in a binocular image can be obtained according to information output by the neural network.
Optionally, the result of the target object identification processing in the present disclosure includes: in the case of the coordinates of the vertices of the raw material in the image, the present disclosure may find the depth information of the corresponding position point from the depth information of the binocular image using the coordinates of the vertices in the image, so that the Z-coordinate of the vertices of the raw material in the three-dimensional space may be obtained. The manner in which the present disclosure obtains the X and Y coordinates of each vertex of the feedstock in three-dimensional space includes, but is not limited to: corresponding calculation is performed according to parameters (such as focal length, optical center offset and the like) of the camera device and X coordinates and Y coordinates of each vertex of the raw material in the image, and the calculation result is obtained.
Optionally, the present disclosure may generate a three-dimensional stereoscopic image of the raw material by using coordinate information of each vertex of the raw material in the three-dimensional space, label an actual size for the three-dimensional stereoscopic image (the actual size may be obtained by calculation according to the coordinate information of each vertex in the three-dimensional space), and display the actual size to the user. This is disclosed can provide the interactive interface who is used for revising the actual dimensions of raw materials for the user to make things convenient for the user to revise the actual dimensions of the current mark of raw materials, thereby be favorable to improving the accuracy of the projected processing light on the raw materials, and then be favorable to improving the yield of woodwork processing.
S1002, projecting and dividing light rays on the raw materials according to the placement position information of the raw materials and the dividing line information so as to divide the wood to be processed corresponding to each dividing piece of the wood product to be processed.
Optionally, the split light in the present disclosure is used to indicate the split position of the raw material. After the cutting light is projected for the raw material and the raw material is subjected to the cutting treatment according to the cutting position indicated by each cutting light, the wood to be treated corresponding to each of all the cutting pieces of the wood product to be processed can be obtained.
Alternatively, the present disclosure may use an array of point light sources (such as the array of pointlight sources 1100 in fig. 11) to project split light onto the feedstock. For example, the present disclosure may first determine on/off control information of each point light source in the pointlight source array 1100 based on the placement position information of theraw material 1102 and the dividing line information; thereafter, the present disclosure controls the on/off state of each point light source in the pointlight source array 1100 based on the on/off control information of each point light source in the pointlight source array 1100 to project the split light 1103 on theraw material 1102. A and B in fig. 11 indicate the length and width of an inscribed rectangle formed by the split rays 1103 projected on thematerial 1102.
Optionally, the present disclosure generally needs to know the setting position information of the point light source array in advance, for example, coordinates of any point light source in the point light source array in the three-dimensional space are obtained in advance, and an included angle between the point light source array and the horizontal plane and the vertical plane is obtained, because the point light sources in the point light source array are generally distributed at equal intervals and the number of the point light sources is fixed, the present disclosure may calculate coordinates of other point light sources in the point light source array in the three-dimensional space according to the row and column positions of the point light sources with known coordinates and the included angle.
Optionally, the disclosure may determine the projection positions of the light rays of the plurality of point light sources on the raw material according to the placement position information of the raw material and the included angles between the point light source array and the horizontal plane and the vertical plane (the light rays of the point light sources in the point light source array may not be projected on the raw material), so that the disclosure may determine the on/off control information of each point light source in the point light source array according to the dividing line information of the raw material.
Optionally, in a general case, a plurality of surfaces (such as a cross section, a longitudinal section and the like) of the raw material need to be projected with the split light, and the disclosure may prompt the user to rotate the raw material so as to project the corresponding split light on the corresponding surface of the raw material. The present disclosure requires that the placement position information of the material be retrieved each time the user rotates the material according to the prompt (e.g., having the cross section of the material facing the array of point light sources or having the length of the material facing the array of point light sources).
Alternatively, the user may draw a corresponding cut line (e.g., a line of ink, etc.) on the material based on each of the projected split rays. After all the segmentation rays are projected on the raw material or all the segmentation rays of one surface of the raw material are projected on the surface, the segmentation line prompt information of the raw material can be generated and displayed to a user. For example, the present disclosure may calculate a horizontal distance or a vertical distance between different dividing lines, etc., and prompt the user. For another example, the present disclosure may prompt the user to: the position relation between the dividing line on one surface of the raw material and the dividing line on the other surface (for example, the dividing lines on the two surfaces have a common end point) and the like, so that a user can conveniently verify and correct the dividing line (for example, the drawn ink line and the like) drawn on the raw material, the yield of the wood to be treated can be improved, and the yield of the divided pieces can be improved.
According to the method, the important reference information of the wood product processing is provided for a user by forming each segmentation light ray of the raw material, and the phenomenon that the raw material is wasted due to unreasonable design of the segmentation line in the process of independently segmenting the raw material by the user can be avoided; thereby this disclosure not only is favorable to reducing the processing degree of difficulty of woodwork, and the supplementary user accomplishes the woodwork processing, still is favorable to improving the yield of woodwork processing.
Alternatively, fig. 12 shows an example of obtaining the information of the dividing line of the raw material corresponding to the wood product to be processed in S1000 of the present disclosure.
In fig. 12, S1200, a three-dimensional modeling image of the raw material is generated according to a multi-angle shot image of the raw material corresponding to the wood product to be processed.
Alternatively, the present disclosure may use the camera 1101 (as shown in fig. 11) to shoot theraw material 1102 at least at four angles, front, back, left and right, and the present disclosure may use corresponding modeling algorithms to model images shot by thecamera 1101 from different angles on theraw material 1102, so as to generate a three-dimensional modeling image of the raw material.
And S1201, acquiring the size information of the raw material and the consumable information of the wood product to be processed.
Optionally, the size information of the raw material in the present disclosure may include: length of the feedstock and diameter of the feedstock. The acquisition mode of the size information of the raw materials includes but is not limited to: a corresponding interactive interface is provided to facilitate the input of sizing information for the material by the user. The present disclosure may also utilize computer vision techniques to obtain dimensional information for the feedstock.
Optionally, the consumable information of the wooden product to be processed in the present disclosure may refer to length, width, height, and other size information of the wood material to be processed corresponding to each partition of the wooden product to be processed. The consumable information of the wood product to be processed in the present disclosure is generally a known value set in advance.
And S1202, generating the material dividing line information according to the three-dimensional modeling image, the size information and the consumable material information.
Optionally, the method can splice the timbers to be processed according to the size information of the timbers to be processed in the space range shown by the three-dimensional modeling image. That is, the three-dimensional modeled image is used as a constraint condition for the stitching process, so that the stitching process can be performed only in the spatial range shown by the three-dimensional modeled image. The present disclosure can form the original parting line information according to the result of the stitching process. That is, the dividing line information includes not only: the leftover bits that need get rid of in the raw materials still include: the collinear portion of adjacent segments in the stitching result.
Alternatively, an example of the dividing line information of the raw material may be shown as a line on the cross section of theraw material 1102 in fig. 11 (i.e., 1103 in fig. 11) and a line in the length direction of the raw material 1102 (i.e., 1103 in fig. 11).
This is disclosed through utilizing above-mentioned mode to obtain the cut-off line information of raw materials, is favorable to making the concrete shape unrestricted of the required raw materials of pending woodwork to be favorable to improving the diversification of raw materials.
Exemplary devices
Fig. 13 is a schematic structural view of an example of the wooden product processing apparatus of the present disclosure. The device of the embodiment can be used for realizing the corresponding method embodiment of the disclosure.
The apparatus shown in fig. 13 comprises: an information determination module 1300, a position detection module 1301, and a projection processing line module 1302. Optionally, the apparatus may further include: and a segmentation module 1303.
The determination information module 1300 is used to determine processing line information of each partition of the wooden article to be processed and processing order information of each partition.
Optionally, the information determining module 1300 is configured to determine processing line information of each partition of the wood product to be processed based on the mortise and tenon structure, when the wood product to be processed is the wood product to be processed based on the mortise and tenon structure. The processing line information of the divided pieces may include: and (4) processing line information of the tenon and mortise of the cutting piece.
Optionally, the information determining module 1300 may first obtain default processing line information of each partition of the wooden product to be processed and shape adjustment information of the wooden product to be processed, when the user adjusts the default size of the wooden product to be processed; then, the information determining module 1300 performs conversion processing on the default processing line information of the corresponding partition of the wooden product to be processed according to the shape adjustment information of the wooden product to be processed, thereby determining the processing line information of each partition of the wooden product to be processed.
Alternatively, the default size of the wooden article to be worked, the default processing line information of each partition of the wooden article to be worked, and the processing order information of each partition may be stored in the information set in advance.
The detection position module 1301 is configured to determine the placement position information of the timber to be processed corresponding to the current partition according to the processing sequence information of each partition determined by the determination information module 1300.
Alternatively, for the timber to be processed for which a current partition is used, an example of the information of the placement position of the timber to be processed determined by the detection position module 1301 may be: firstly, the detection position module 1301 performs target object identification processing on a binocular image of timber to be processed corresponding to a current segmentation piece; then, the detection position module 1301 acquires the depth information of the binocular image of the timber to be processed; finally, the detection position module 1301 determines the coordinate information of each vertex of the timber to be processed corresponding to the current segmentation piece in the three-dimensional space according to the depth information and the result of the target object identification processing.
The projection processing line module 1302 is configured to project processing light onto the wood to be processed corresponding to the current partition piece according to the placement position information of the wood to be processed corresponding to the current partition piece determined by the detection position module 1301 and the processing line information of the current partition piece. The processing light is used for indicating the processing position of the wood to be processed corresponding to the current dividing piece, so that the wood to be processed is processed into the current dividing piece.
Optionally, the projection processing line module 1302 may determine on/off control information of each point light source in the point light source array according to the placement position information of the wood to be processed corresponding to the current partition and the processing line information of the current partition; then, the projection processing line module 1302 controls the on/off state of each point light source in the point light source array according to the on/off control information of each point light source in the point light source array, so as to project the processing light on the wood to be processed corresponding to the current partition.
The segmentation module 1303 is configured to obtain segmentation line information of the raw material corresponding to the wood product to be processed, determine placement position information of the raw material, and project segmentation light rays on the raw material according to the placement position information and the segmentation line information of the raw material by the segmentation module 1303, so as to segment the wood material to be processed corresponding to each segmentation piece of the wood product to be processed. Wherein the dividing light is used for indicating the dividing position of the raw material.
Alternatively, the present disclosure may preset, in the information set, raw material information required for a plurality of styles of wood products to be processed. After the user selects a style of wooden product to be processed from among multiple styles of wooden products to be processed, the segmentation module 1303 may prompt the user with raw material information required by the style of wooden product to be processed. The present disclosure can prompt each group of raw material information of the wooden product to be processed to the user, and the user can prepare the corresponding raw material according to the prompt. In the case that the raw material prepared by the user is substantially the same as the set of raw material information, the segmentation module 1303 may directly obtain the segmentation line information corresponding to the set of raw material information. The above-mentioned substantial identity means that the difference between the two is within a predetermined range.
Optionally, under the condition that the raw material prepared by the user has a large difference from any group of prompted raw material information, the segmentation module 1303 may first capture an image according to multiple angles of the raw material corresponding to the wood product to be processed, so as to generate a three-dimensional modeling image of the raw material; then, the segmentation module 1303 acquires the size information of the raw material and the consumable information of the wood product to be processed; finally, the segmentation module 1303 generates segmentation line information of the raw material according to the three-dimensional modeling image, the size information, and the consumable information.
Exemplary electronic device
An electronic device according to an embodiment of the present disclosure is described below with reference to fig. 14. FIG. 14 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure. As shown in fig. 14, electronic device 141 includes one or more processors 1411 and memory 1412.
Processor 1411 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in electronic device 141 to perform desired functions.
Memory 1412 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory, for example, may include: random Access Memory (RAM) and/or cache memory (cache), etc. The nonvolatile memory, for example, may include: read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium and executed by the processor 1411 to implement the wood product processing methods of the various embodiments of the present disclosure described above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.
In one example, the electronic device 141 may further include: an input device 1413, and an output device 1414, among others, interconnected by a bus system and/or other form of connection mechanism (not shown). The input devices 1413 may also include, for example, a keyboard, a mouse, and the like. The output device 1414 can output various information to the outside. The output devices 1414 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 141 relevant to the present disclosure are shown in fig. 14, and components such as buses, input/output interfaces, and the like are omitted. In addition, electronic device 141 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the methods and apparatus described above, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the method of wood product processing according to the various embodiments of the present disclosure described in the "exemplary methods" section of this specification, above.
The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the wood product processing method according to various embodiments of the present disclosure described in the "exemplary method" section above in this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium may include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, and systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," comprising, "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects, and the like, will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.