Disclosure of Invention
The application provides a lifting appliance size confirmation method and device based on image processing and a field bridge, which are used for solving the technical problem that the lifting appliance size measured in the prior art is not accurate enough.
In a first aspect, the present application provides a method for confirming the size of a lifting appliance based on image processing, including:
Acquiring a target image containing a target lifting appliance, and determining a first end point position of the target lifting appliance in the target image based on a deep learning algorithm, wherein the target lifting appliance characterizes the lifting appliance waiting for size confirmation, and the target lifting appliance is presented in the target image in a top view mode;
mapping a preset lifting appliance to the target image, and determining the position of a second endpoint of the preset lifting appliance in the target image, wherein the preset lifting appliance represents lifting appliances with different sizes and the same shape as the target lifting appliance;
Matching the first endpoint position with the second endpoint position, and determining a target endpoint position which coincides with the first endpoint position in the second endpoint position, wherein the second endpoint position comprises the target endpoint position;
Acquiring a preset real size of a preset lifting appliance corresponding to the target endpoint position, and determining the preset real size as a target real size of the target lifting appliance.
In one possible design, the determining the first end point position of the target spreader in the target image based on the deep learning algorithm includes:
Generating a corresponding pixel level mask for a target lifting appliance in the target image based on a first preset method in the deep learning algorithm;
identifying an edge profile of a target spreader in the target image based on the pixel level mask; and determining a first end point position of the target lifting appliance in the target image based on the edge profile.
In one possible design, the determining a first end point position of the target spreader in the target image based on the edge profile includes:
calculating an external boundary rectangle containing the edge profile based on a preset function;
The method comprises the steps of determining four vertexes of the circumscribed boundary rectangle and corresponding first vertex positions, determining the first vertex positions as first endpoint positions of a target lifting appliance in the target image, wherein the first vertex positions represent the positions of the four vertexes of the circumscribed boundary rectangle.
In one possible design, the determining the first end point position of the target spreader in the target image based on the deep learning algorithm further includes:
Labeling a target rectangular boundary frame for a target lifting appliance in the target image based on a second preset method in the deep learning algorithm;
The method comprises the steps of determining four vertexes of the target rectangular boundary frame and corresponding second vertex positions, and determining the second vertex positions as first endpoint positions of target lifting appliances in the target image, wherein the second vertex positions represent the positions of the four vertexes of the target rectangular boundary frame.
In one possible design, the target spreader in the target image includes four end points, and the four end points can form a rectangle;
the method further comprises the steps of:
calculating the length and the width of the target rectangle, and determining the hanger image size of the target hanger in the target image based on the length and the width;
Determining a target fixed reference object included in the target lifting appliance, determining the real size of the reference object of the target fixed reference object, and determining the image size of the reference object in the target image;
And calculating the target real size of the target lifting appliance based on the real size of the reference object, the image size of the reference object and the image size of the lifting appliance.
In one possible design, the method further comprises:
Classifying the target lifting appliance in the target image based on a preset classification model to obtain the target type of the target lifting appliance;
And determining the target real size of the target lifting appliance from a pre-established preset size specification table based on the target type, wherein the preset size specification table is used for storing the standard sizes of lifting appliances of various types.
In one possible design, the classifying the target lifting appliance in the target image based on the preset classification model includes:
The method comprises the steps of obtaining an image dataset containing different types of lifting appliances, marking the type of the lifting appliance for each image in the image dataset, and obtaining a lifting appliance type label corresponding to each image;
Taking the image dataset as input data, taking the lifting appliance type tag as output data, and performing model training to generate a preset classification model;
Classifying the target lifting appliance in the target image based on the preset classification model.
In a second aspect, the present application provides a hanger size confirmation apparatus based on image processing, including:
the acquisition module is used for acquiring a target image containing the target lifting appliance;
The determining module is used for determining a first end point position of a target lifting appliance in the target image based on a depth learning algorithm, wherein the target lifting appliance represents a lifting appliance waiting for size confirmation, and the target lifting appliance is presented in the target image in a top view mode;
The determining module is further used for mapping a preset lifting appliance to the target image and determining a second endpoint position of the preset lifting appliance in the target image, wherein the preset lifting appliance represents lifting appliances with different sizes and the same shape as the target lifting appliance;
the matching module is used for matching the first endpoint position with the second endpoint position;
The determining module is further configured to determine a target endpoint position that coincides with the first endpoint in the second endpoint positions, where the second endpoint positions include the target endpoint position;
the acquisition module is further used for acquiring a preset real size of a preset lifting appliance corresponding to the target endpoint position;
The determining module is further configured to determine the preset real size as a target real size of the target lifting appliance.
In one possible design, the determining module further comprises a generating module, an identifying module,
The generating module is used for generating a corresponding pixel level mask for a target lifting appliance in the target image based on a first preset method in the deep learning algorithm;
The identification module is used for identifying the edge contour of the target lifting appliance in the target image based on the pixel level mask;
the determining module is further configured to determine a first endpoint position of a target spreader in the target image based on the edge profile.
In one possible design, the determining module further includes a calculating module for calculating a circumscribed bounding rectangle containing the edge contour based on a preset function;
The determining module is further configured to determine four vertices of the circumscribed bounding rectangle and corresponding first vertex positions, determine the first vertex positions as first endpoint positions of a target lifting appliance in the target image, where the first vertex positions represent positions of the four vertices of the circumscribed bounding rectangle.
In one possible design, the determining module further comprises a labeling module, a target rectangular bounding box labeling the target lifting appliance in the target image based on a second preset method in the deep learning algorithm;
the determining module is further configured to determine four vertices of the target rectangular bounding box and corresponding second vertex positions, and determine the second vertex positions as first endpoint positions of the target lifting appliance in the target image, where the second vertex positions represent positions of the four vertices of the target rectangular bounding box.
In one possible design, the target spreader in the target image includes four end points, and the four end points can form a rectangle;
the determining module is further configured to determine a target rectangle formed by the four endpoints based on the first endpoint position;
The calculating module is also used for calculating the length and the width of the target rectangle;
the determining module is further configured to:
determining the hanger image size of the target hanger in the target image based on the length and the width;
Determining a target fixed reference object included in the target lifting appliance, determining the real size of the reference object of the target fixed reference object, and determining the image size of the reference object in the target image;
The calculation module is further used for calculating the target real size of the target lifting appliance based on the real size of the reference object, the image size of the reference object and the image size of the lifting appliance.
In one possible design, the hanger size confirmation device based on image processing further comprises a classification module, a classification module and a display module, wherein the classification module is used for classifying the target hanger in the target image based on a preset classification model to obtain the target type of the target hanger;
The determining module is further used for determining the target real size of the target lifting appliance from a pre-established preset size specification table based on the target type, wherein the preset size specification table is used for storing standard sizes of lifting appliances of various types.
In one possible design, the acquisition module is further configured to acquire an image dataset containing different types of spreaders;
The labeling module is further used for labeling the type of the lifting appliance for each image in the image data set to obtain a lifting appliance type label corresponding to each image;
The hanger size confirmation device based on image processing further comprises a training module, a model training module and a model analysis module, wherein the training module is used for taking the image data set as input data and the hanger type label as output data to perform model training so as to generate a preset classification model;
the classification module is further used for classifying the target lifting appliance in the target image based on the preset classification model.
In a third aspect, embodiments of the present application provide a field bridge comprising an apparatus as described in the above second aspect and various possible designs.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, implement the method as described in the first aspect and various possible designs above.
In a fifth aspect, embodiments of the present application provide a computer program product comprising a computer program which, when executed by a processor, implements the method as described above for the first aspect and the various possible designs of the first aspect.
According to the hanger size confirmation method and device based on image processing and the field bridge, a target image comprising a target hanger is obtained, wherein the target hanger is a hanger waiting for size confirmation and is presented in the target image in a top view mode. Since the vision system can capture high-resolution images, detailed visual information is provided, and the detailed information of the target lifting appliance can be accurately measured through the target image. Further, because the image processing technology can identify complex contours and features, the first end point position of the target lifting appliance in the target image can be accurately determined through a deep learning algorithm in the image processing technology. And mapping the preset lifting appliance to the target image, and determining the second end point position of the preset lifting appliance in the target image by adopting the same method, wherein the preset lifting appliance is of the same shape as the target lifting appliance and different sizes. And matching the first end point position with the second end point position, and determining a target end point position which coincides with the first end point position in the second end point position, wherein the first end point position of the target lifting appliance is accurate to the second end point position of the preset lifting appliance, and the target end point position which coincides with the first end point is also accurate. The method comprises the steps of obtaining the preset real size of the preset lifting appliance corresponding to the position of the target endpoint, determining the preset real size as the target real size of the target lifting appliance, and obtaining the preset real size through an image processing technology, so that the target real size of the target lifting appliance can be accurately reflected.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein.
In embodiments of the application, words such as "exemplary" or "such as" are used to mean examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with related laws and regulations and standards, and provide corresponding operation entries for the user to select authorization or rejection.
Confirming the size of the spreader is a critical safety and handling issue, especially in situations involving lifting, moving and placing weights, the correct spreader size ensures that the weights are firmly grasped and placed. If the spreader is not properly sized, it may result in the spreader not being able to properly grasp or place the weight, increasing the likelihood of dropping, tilting or other accidents, which may damage not only the weight, but also personnel and equipment.
The existing hanger size confirmation method mainly relies on a laser ranging sensor or an ultrasonic sensor to confirm the hanger size. The laser ranging sensor measures a distance by emitting a laser beam to a target object (hanger) and receiving the reflected laser beam, and the ultrasonic sensor measures a distance by emitting an ultrasonic signal and receiving an ultrasonic signal reflected from the target object.
Both the laser ranging sensor and the ultrasonic sensor rely on the time difference between the measured signal from the sensor to the target object surface and back again to calculate the distance. In order to comprehensively measure each dimension of the lifting appliance, the laser ranging sensor or the ultrasonic sensor can be arranged at different positions of the lifting appliance to measure the length, the width, the height and other dimensions of the lifting appliance.
However, confirming the spreader size by a laser ranging sensor or an ultrasonic sensor may have a problem of insufficient accuracy. This is because the material and shape of the spreader surface may affect the reflective properties of the laser beam or ultrasonic wave, a high reflectivity spreader surface may cause excessive reflection of the signal, while a low reflectivity spreader surface may cause absorption of the signal. At the same time, rough or irregular spreader surfaces may also lead to signal scattering.
In addition, the spreader may have complex geometries such that a single measurement point does not accurately reflect the overall dimensions of the spreader, especially when multiple dimensions need to be measured. And dust, humidity, temperature changes, etc. in the environment may also affect the performance of the laser ranging sensor or the ultrasonic sensor.
In view of the above technical problems, considering that the sensor is easily interfered by the characteristics of the spreader itself and environmental factors, it is necessary to select a method for confirming the size of the spreader, which can work under more complex geometric shapes and surface conditions and has low sensitivity to environmental factors. Based on the above, the inventor thinks that by adopting a vision-based hanger size confirmation method, a vision system can measure multiple dimensions at the same time by using a camera or a stereoscopic vision technology, not just single-point measurement, and the measurement comprehensiveness is improved. Meanwhile, the vision system can identify and measure complex contours and features through an image processing algorithm, has low sensitivity to environmental factors, and can keep high precision under various environmental conditions.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The embodiment of the application provides a lifting appliance size confirmation method based on image processing. Fig. 1 is a schematic flow chart of a method for confirming the size of a lifting appliance based on image processing according to an embodiment of the present application, as shown in fig. 1, the method for confirming the size of the lifting appliance based on image processing includes:
S101, acquiring a target image containing a target lifting appliance, and determining a first endpoint position of the target lifting appliance in the target image based on a deep learning algorithm.
The target lifting appliance is a lifting appliance waiting for size confirmation, and is displayed in a target image in a top view mode.
For explanation, fig. 2 is a schematic structural diagram of a method for confirming the size of a lifting appliance based on image processing according to an embodiment of the present application. As shown in fig. 2, the target hoist is suspended from a movable vehicle, which may be a crane, a forklift, a mobile crane, or the like, by a wire rope, without being particularly limited thereto. The target spreader is typically suspended from the boom of a mobile vehicle, for example, in the case of a mobile crane, the spreader may be suspended from the end of a telescopic boom, and in the case of a forklift, the spreader may be attached to the fork arm of the forklift.
The lower surface of the boom of the movable vehicle is also provided with a camera for taking an image of the object containing the object spreader, while also ensuring that the horizontal relative position of the camera and the object spreader remains unchanged. One or more cameras can be mounted on the lower surface of the suspension arm, and the field of view of the cameras can cover the lifting appliance with each size. It will be appreciated that since the camera is mounted on the lower surface of the boom and the spreader is located below the camera, the target spreader is presented in a top view in the target image.
After the target image containing the target sling is shot by the camera, the target image is analyzed by adopting a deep learning algorithm so as to identify the target sling in the target image and determine the first endpoint position of the target sling. It should be noted that in standardized industrial equipment, the design of the spreader is often regular to accommodate specific functional requirements, and the top view of the spreader is typically rectangular.
Thus, the target spreader in the target image comprises four end points, and these four end points can form a rectangle, the first end point being used to indicate the positions of the four end points.
In one possible implementation method, a pixel level mask may be generated for the target spreader in the target image based on a first preset method (such as an image segmentation method) in the depth learning algorithm, where the pixel level mask can accurately identify which pixels in the target image belong to the target spreader. Thereafter, an edge contour of the target spreader in the target image is identified by detecting an intersection line of a target region (target spreader) and a background region (other region than the target spreader in the target image) in the pixel level mask, and a first end point position of the target spreader in the target image is determined based on the edge contour.
Specifically, based on a preset function, calculating an external boundary rectangle containing an edge contour, and determining four vertexes of the external boundary rectangle and corresponding first vertex positions. The circumscribed boundary rectangle refers to a smallest rectangle capable of completely surrounding the edge outline of the target lifting appliance, and the positions of four vertexes of the circumscribed boundary rectangle are represented by the positions of the first vertexes. And determining the first vertex position as the first endpoint position of the target lifting appliance in the target image.
In another possible implementation manner, a target rectangular bounding box can be marked for a target lifting appliance in the target image based on a second preset algorithm (such as a target detection method) in the depth learning algorithm, and four vertexes of the target rectangular bounding box and corresponding second vertex positions are determined. And determining the second vertex position as the first endpoint position of the target lifting appliance in the target image. Wherein the second vertex position characterizes the positions of the four vertices of the target rectangular bounding box.
It can be seen that determining the first end point position of the target spreader in the target image by the first preset method or the second preset method is dependent on generating a minimum artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) detection frame that completely encloses the target spreader. Fig. 3 is a schematic view of a scenario of a method for confirming the size of a lifting appliance based on image processing according to an embodiment of the present application, as shown in fig. 3, the positions of four vertices of a generated minimum AI detection frame are the first endpoint position of a target lifting appliance in a target image.
S102, mapping the preset lifting appliance to a target image, and determining the second endpoint position of the preset lifting appliance in the target image.
Wherein, preset hoist characterization and the same different size hoist of target hoist shape. It should be explained that, in order to provide higher structural stability and safety, the target spreader of the present embodiment is designed to be telescopic unidirectionally, i.e. the target spreader can only be telescopic adjusted in one direction. Therefore, the preset lifting appliance has the same design and appearance as the target lifting appliance in structure and function, and different sizes can be obtained by performing telescopic adjustment in one direction.
It will be appreciated that in order to ensure that the preset spreader can be compared with the target spreader at the same viewing angle and scale, the preset spreader needs to be mapped to the target image also in top view. After mapping the preset lifting appliance to the target image, the second endpoint position of the preset lifting appliance in the target image can be determined by adopting a first preset method or a second preset method, and details are not repeated here. The second end point positions are used for indicating positions of four end points of a preset lifting appliance in the target image.
And S103, matching the first end point position with the second end point position, and determining a target end point position which coincides with the first end point position in the second end point position.
S104, acquiring a preset real size of the preset lifting appliance corresponding to the target endpoint position, and determining the preset real size as the target real size of the target lifting appliance.
In a specific example, fig. 4 is a schematic diagram of a second scenario of the image processing-based method for determining the size of a lifting appliance according to the embodiment of the present application, as shown in fig. 4, a preset lifting appliance a, a preset lifting appliance B, and a preset lifting appliance C are mapped to a target image, and the positions of the second endpoints of the preset lifting appliance a, the preset lifting appliance B, and the preset lifting appliance C are determined, respectively.
And respectively matching the first end point position of the target lifting appliance with the second end point positions of the preset lifting appliance A, the preset lifting appliance B and the preset lifting appliance C, and finding that the second end point position of the preset lifting appliance A coincides with the first end point position of the target lifting appliance. Meaning that the size of the preset lifting appliance A is the same as the size of the target lifting appliance, namely the preset real size of the preset lifting appliance A is the target real size of the target lifting appliance.
It should be noted that if the second end point position coincident with the first end point position is not found, it indicates that there is no preset spreader having the same size as the target spreader. At this time, other methods need to be considered to determine the target real size of the target spreader.
In one possible implementation, a target rectangle formed by four endpoints of a target spreader in a target image is determined based on the first endpoint location. The hanger image size of the target hanger in the target image can be determined by calculating the length and width of the target rectangle.
Fig. 5 is a schematic view of a third scenario of the method for confirming the size of a lifting appliance based on image processing according to the embodiment of the present application, as shown in fig. 5, a target fixed reference object is selected on a target lifting appliance. A target fixed reference refers to an object that serves as a base or reference during observation, measurement or analysis, typically an object or marker whose position is known and does not change.
The reference real size of the target fixed reference and the reference image size in the target image are determined. The target real size of the target lifting appliance is calculated based on the real size of the reference object, the image size of the reference object and the image size of the lifting appliance, and a specific calculation formula is that the target real size of the target lifting appliance = the real size of the reference object/(the image size of the reference object × the image size of the lifting appliance.
In addition, the true size of the object can be determined by the type of the object lifting appliance. In another possible implementation manner, the target lifting appliance in the target image is classified based on a preset classification model, so as to obtain the target type of the target lifting appliance. And determining the target real size of the target lifting appliance from a pre-established preset size specification table according to the target type of the target lifting appliance. The preset size specification table is used for storing standard sizes of various lifting appliances.
It will be appreciated that the pre-set classification model is typically a trained machine learning model capable of classifying the target spreader into a pre-defined type based on characteristics of the target spreader in the target image. Specifically, the training process of the preset classification model is to acquire an image dataset containing different types of lifting appliances, wherein the image dataset should be as diverse as possible so that the model can learn the characteristics of various different types of lifting appliances. And then, labeling the type of the lifting appliance for each image in the image data set, namely designating a lifting appliance type label for guiding model learning for each image. In the model training process, an image data set is used as input data, a lifting appliance type label is used as output data, and the input data and the output data are used for model training. The model training process involves adjusting parameters of the model so that it can learn the relationship between the features and the labels. After model training, a preset classification model can be obtained.
Next, an overall flow of confirming the target true size of the target spreader will be described in summary. Fig. 6 is a second flow chart of a method for confirming the size of a lifting appliance based on image processing according to an embodiment of the present application, as shown in fig. 6, the overall flow of the method for confirming the size of the lifting appliance based on image processing is as follows:
s601, acquiring a target image containing a target lifting appliance.
S602, analyzing the target lifting appliance in the target image by adopting an image segmentation method, a target detection method, a size calculation method or a target classification method.
If the image segmentation method or the object detection method is adopted, S602a is executed, if the size calculation method is adopted, S602b is executed, and if the object classification method is adopted, S602c is executed.
S602a, matching a first end point position of a target lifting appliance in the target image with a second end point position of a preset lifting appliance mapped to the target image.
S602b, calculating the lifting tool image size of the target lifting tool in the target image, and determining the real size of the reference object of the target fixed reference object included in the target lifting tool and the image size of the reference object in the target image.
S602c, classifying the target lifting appliance in the target image to obtain the target type of the target lifting appliance.
S603, determining the target real size of the target lifting appliance according to the analysis result.
According to the hanger size confirmation method based on image processing, a target image containing a target hanger is obtained, wherein the target hanger is a hanger waiting for size confirmation and is displayed in the target image in a top view mode. Since the vision system can capture high-resolution images, detailed visual information is provided, and the detailed information of the target lifting appliance can be accurately measured through the target image. Further, because the image processing technology can identify complex contours and features, the first end point position of the target lifting appliance in the target image can be accurately determined through a deep learning algorithm in the image processing technology. Specifically, a corresponding pixel level mask can be generated for the target lifting appliance in the target image based on a first preset method in the deep learning algorithm, and the edge contour of the target lifting appliance in the target image is identified according to the pixel level mask. And calculating an external boundary rectangle containing the edge outline through a preset function, and determining the positions of four vertexes of the external boundary rectangle as the first endpoint position of the target lifting appliance. Or labeling a target rectangular boundary frame for the target lifting appliance in the target image based on a second preset method in the deep learning algorithm, and determining the positions of four vertexes of the target rectangular boundary frame as the first endpoint position of the target lifting appliance in the target image. And mapping the preset lifting appliance to the target image, and determining the second end point position of the preset lifting appliance in the target image by adopting the same method, wherein the preset lifting appliance is of the same shape as the target lifting appliance and different sizes. And matching the first end point position with the second end point position, and determining a target end point position which coincides with the first end point position in the second end point position, wherein the first end point position of the target lifting appliance is accurate to the second end point position of the preset lifting appliance, and the target end point position which coincides with the first end point is also accurate. The method comprises the steps of obtaining the preset real size of the preset lifting appliance corresponding to the position of the target endpoint, determining the preset real size as the target real size of the target lifting appliance, and obtaining the preset real size through an image processing technology, so that the target real size of the target lifting appliance can be accurately reflected. In addition, the real size of the target lifting appliance can be accurately confirmed through a size calculation method or a target classification method.
Fig. 7 is a schematic structural diagram of a device for confirming the size of a lifting appliance based on image processing according to an embodiment of the present application, as shown in fig. 7, the device 700 for confirming the size of a lifting appliance based on image processing includes an acquisition module 701, a determination module 702, and a matching module 703;
the acquiring module 701 is configured to acquire a target image including a target lifting appliance;
a determining module 702, configured to determine a first endpoint position of a target spreader in a target image based on a deep learning algorithm, where the target spreader characterizes a spreader waiting for size confirmation, and the target spreader is presented in the target image in a top view;
The determining module 702 is further configured to map a preset hanger to the target image, and determine a second end point position of the preset hanger in the target image, where the preset hanger represents a hanger with a different size and the same shape as the target hanger;
a matching module 703, configured to match the first endpoint position with the second endpoint position;
The determining module 702 is further configured to determine a target endpoint position that coincides with the first endpoint in the second endpoint positions, where the second endpoint positions include the target endpoint positions;
The acquiring module 701 is further configured to acquire a preset real size of a preset hanger corresponding to the target endpoint position;
The determining module 702 is further configured to determine the preset real size as a target real size of the target spreader.
In one possible design, the determination module 702 further includes a generation module 704, an identification module 705,
A generating module 704, configured to generate a corresponding pixel level mask for a target lifting appliance in a target image based on a first preset method in a deep learning algorithm;
An identification module 705 for identifying an edge profile of the target spreader in the target image based on the pixel level mask;
the determining module 702 is further configured to determine a first endpoint position of the target spreader in the target image based on the edge profile.
In one possible design, the determining module 702 further includes a calculating module 706 configured to calculate a circumscribed bounding rectangle containing the edge contour based on a preset function;
The determining module 702 is further configured to determine four vertices of the bounding rectangle and corresponding first vertex positions, determine the first vertex positions as first endpoint positions of the target spreader in the target image, where the first vertex positions characterize positions of the four vertices of the bounding rectangle.
In one possible design, the determining module 702 further includes a labeling module 707 for labeling a target rectangular bounding box for a target spreader in the target image based on a second preset method in the deep learning algorithm;
the determining module 702 is further configured to determine four vertices of the target rectangular bounding box and corresponding second vertex positions, determine the second vertex positions as first endpoint positions of the target lifting appliance in the target image, wherein the second vertex positions characterize positions of the four vertices of the target rectangular bounding box.
In one possible design, the target spreader in the target image includes four end points, and the four end points can form a rectangle;
The determining module 702 is further configured to determine a target rectangle formed by the four endpoints based on the first endpoint location;
The calculating module 706 is further configured to calculate a length and a width of the target rectangle;
The determining module 702 is further configured to:
determining the hanger image size of a target hanger in the target image based on the length and the width;
Determining a target fixed reference object included in the target lifting appliance, determining the real size of the reference object of the target fixed reference object and the image size of the reference object in a target image;
the calculating module 706 is further configured to calculate a target real size of the target lifting appliance based on the reference real size, the reference image size, and the lifting appliance image size.
In one possible design, the device 700 for confirming the size of the lifting appliance based on image processing further comprises a classification module 708, which is used for classifying the target lifting appliance in the target image based on a preset classification model to obtain the target type of the target lifting appliance;
The determining module 702 is further configured to determine, based on the target type, a target real size of the target spreader from a pre-created preset size specification table, where the preset size specification table is used to store standard sizes of spreaders of various types.
In one possible design, the acquisition module 701 is further configured to acquire an image dataset comprising different types of spreaders;
The labeling module 707 is further configured to label a hanger type for each image in the image dataset, so as to obtain a hanger type label corresponding to each image;
the device 700 for confirming the size of the lifting appliance based on image processing further comprises a training module 709 for taking the image data set as input data and taking the lifting appliance type label as output data to perform model training so as to generate a preset classification model;
the classification module 708 is further configured to classify the target spreader in the target image based on a preset classification model.
The hanger size confirmation device based on image processing provided by the embodiment of the application can be used for executing the hanger size confirmation method based on image processing in any of the embodiments, and the implementation principle and the technical effect are similar, and are not repeated here.
It should be noted that, it should be understood that the division of the modules of the above apparatus is merely a division of a logic function, and may be fully or partially integrated into a physical entity or may be physically separated. The modules can be realized in the form of software which is called by the processing element, in the form of hardware, in the form of software which is called by the processing element, and in the form of hardware. In addition, all or part of the modules may be integrated together or may be implemented independently. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in a software form.
The embodiment of the application also provides a field bridge, which comprises the lifting appliance size confirmation device based on image processing.
The embodiment of the application also provides a computer readable storage medium, wherein computer executable instructions are stored in the computer readable storage medium, and when the computer executable instructions run on a computer, the computer is caused to execute the method provided in any embodiment.
Embodiments of the present application also provide a computer program product, which includes a computer program stored in a computer readable storage medium, from which at least one processor can read the computer program, and the at least one processor can implement the method provided in any of the above embodiments when executing the computer program.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.
In addition, each functional module in the embodiments of the present application may be integrated in one processing unit, or each module may exist alone physically, or two or more modules may be integrated in one unit. The units formed by the modules can be realized in a form of hardware or a form of hardware and software functional units.
The integrated modules, which are implemented in the form of software functional modules, may be stored in a computer readable storage medium. The software functional modules described above are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or processor to perform some of the steps of the methods of the various embodiments of the application.
It should be appreciated that the Processor may be a central processing unit (Central Processing Unit, abbreviated as CPU), or may be other general purpose Processor, digital signal Processor (DIGITAL SIGNAL Processor, abbreviated as DSP), application SPECIFIC INTEGRATED Circuit (ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile memory NVM, such as at least one magnetic disk memory, and may also be a U-disk, a removable hard disk, a read-only memory, a magnetic disk or optical disk, etc.
The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of the present application are not limited to only one bus or to one type of bus.
The storage medium may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an Application SPECIFIC INTEGRATED Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in an electronic control unit or master control device.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of implementing the various method embodiments described above may be implemented by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs the steps comprising the method embodiments described above, and the storage medium described above includes various media capable of storing program code, such as ROM, RAM, magnetic or optical disk.
It should be noted that the above embodiments are merely for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the technical solution described in the above embodiments may be modified or some or all of the technical features may be equivalently replaced, and these modifications or substitutions do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiments of the present application.