Disclosure of Invention
The embodiment of the application aims to provide a pedestrian collision avoidance early warning method, device, electronic equipment and storage medium for a vehicle, which can carry out emergency early warning on sudden conditions in the running process of the vehicle, improve the safety performance of the vehicle, reduce potential safety hazards of the vehicle in the running process, and effectively avoid collision between the vehicle and pedestrians.
In a first aspect, an embodiment of the present application provides a pedestrian collision avoidance early warning method for a vehicle, where the method includes:
Acquiring a vehicle front image of the vehicle, wherein the vehicle front image is shot by a binocular camera and comprises a left-eye vehicle front image and a right-eye vehicle front image;
Identifying the front image of the vehicle according to a pre-constructed pedestrian identification model to obtain an identification result;
correcting the front image of the vehicle according to the identification result to obtain a corrected front image of the vehicle;
parallax processing is carried out on the corrected front image of the vehicle to obtain distance data of the vehicle and pedestrians;
obtaining current speed data of the vehicle according to the wheel speed sensor data;
And carrying out anti-collision early warning according to the current vehicle speed data, the identification result and the distance data.
In the implementation process, the distance between the vehicle and the pedestrian is obtained through the front image of the vehicle, and then the recognition result of the pedestrian and the current vehicle speed are combined for anti-collision early warning, so that emergency early warning can be carried out on the emergency in the running process of the vehicle, the safety performance of the vehicle is improved, the potential safety hazard of the vehicle in the running process is reduced, and the collision between the vehicle and the pedestrian is effectively avoided.
Further, the step of identifying the front image of the vehicle according to the pre-constructed pedestrian identification model to obtain an identification result includes:
Inputting the vehicle front image into the pedestrian recognition model for feature extraction to obtain a feature map;
performing feature coding on the feature map to obtain coding information;
Transforming the coding information according to a convolution transformation function to obtain feature mapping;
and obtaining the identification result according to the feature map.
In the implementation process, the feature extraction is carried out on the front image of the vehicle according to the pedestrian recognition model to obtain the recognition result, so that the recognition accuracy and recognition efficiency can be improved, the vehicle can be facilitated to rapidly recognize the pedestrians in front, and the potential safety hazard is reduced.
Further, the step of correcting the vehicle front image according to the recognition result to obtain a corrected vehicle front image includes:
judging whether the pedestrian is identified by the identification result;
If yes, carrying out three-dimensional correction on the front image of the vehicle to obtain horizontal features and vertical features of the front image of the vehicle;
and carrying out smoothing processing on the horizontal characteristic and the vertical characteristic to obtain the corrected front image of the vehicle.
In the implementation process, the stereo correction is carried out on the image in front of the vehicle, and the smoothing treatment is carried out on the horizontal characteristic and the vertical characteristic after the correction, so that the error can be reduced, and the processing efficiency and the processing speed of the image can be improved.
Further, the step of smoothing the horizontal feature and the vertical feature to obtain the corrected front image of the vehicle includes:
respectively carrying out edge extraction on the horizontal features and the vertical features according to a Sobel algorithm to obtain the horizontal features after edge extraction and the vertical features after edge extraction;
and correcting the horizontal features after the edge extraction and the vertical features after the edge extraction according to Gaussian filtering to obtain the corrected front image of the vehicle.
In the implementation process, the horizontal features and the vertical features are subjected to edge extraction and then corrected, so that deviation in the front image of the vehicle can be repaired, and the usability of the image is improved.
Further, the step of performing parallax processing on the corrected front image of the vehicle to obtain distance data between the vehicle and the pedestrian includes:
Performing parallax optimization on the front left-eye vehicle image and the front right-eye vehicle image according to an SGBM algorithm to obtain an optimized front left-eye vehicle image and an optimized front right-eye vehicle image;
generating a parallax image according to the optimized left-eye vehicle front image and the optimized right-eye vehicle front image;
And obtaining distance data between the vehicle and the pedestrian according to the parallax map.
In the implementation process, parallax optimization is performed on the front left-eye vehicle image and the front right-eye vehicle image, so that the accuracy of the front left-eye vehicle image and the front right-eye vehicle image can be improved, the accuracy of distance data is improved, and errors are reduced.
Further, the step of performing collision avoidance early warning according to the current vehicle speed data, the identification result and the distance data includes:
judging whether the distance data is smaller than a preset distance or not;
if yes, converting the current vehicle speed data, the distance data and the identification result according to a pre-constructed conversion function to obtain an early warning result.
In the implementation process, the early warning result is obtained according to the current vehicle speed data, the distance data and the recognition result, so that the early warning result can comprise data analysis of multiple dimensions, and the accuracy of the early warning result is improved.
Further, the step of obtaining current vehicle speed data of the vehicle from the wheel speed sensor data includes:
Acquiring a first voltage in wheel speed sensor data;
Obtaining a pulse voltage according to the first voltage;
obtaining pulse frequency according to the period of the pulse voltage;
And obtaining current speed data of the vehicle according to the pulse frequency.
In the implementation process, the current vehicle speed data is obtained in real time according to the wheel speed sensor, so that the timeliness and accuracy of obtaining the current vehicle speed data can be improved, and the anti-collision early warning can be conveniently and rapidly carried out according to the current vehicle speed data.
In a second aspect, an embodiment of the present application further provides a pedestrian collision avoidance early warning device for a vehicle, where the device includes:
the acquisition module is used for acquiring a vehicle front image of the vehicle, wherein the vehicle front image is shot by a binocular camera and comprises a left-eye vehicle front image and a right-eye vehicle front image;
The recognition module is used for recognizing the front image of the vehicle according to a pre-constructed pedestrian recognition model to obtain a recognition result;
The correction module is used for correcting the front image of the vehicle according to the identification result to obtain a corrected front image of the vehicle;
the parallax processing module is used for carrying out parallax processing on the corrected front image of the vehicle to obtain distance data of the vehicle and pedestrians;
the data acquisition module is used for acquiring current speed data of the vehicle according to the wheel speed sensor data;
And the early warning module is used for carrying out anti-collision early warning according to the current vehicle speed data, the identification result and the distance data.
In the implementation process, the distance between the vehicle and the pedestrian is obtained through the front image of the vehicle, and then the recognition result of the pedestrian and the current vehicle speed are combined for anti-collision early warning, so that emergency early warning can be carried out on the emergency in the running process of the vehicle, the safety performance of the vehicle is improved, the potential safety hazard of the vehicle in the running process is reduced, and the collision between the vehicle and the pedestrian is effectively avoided.
In a third aspect, an electronic device provided in an embodiment of the present application includes: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to any one of the first aspects when the computer program is executed.
In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, where instructions are stored, when the instructions are executed on a computer, to cause the computer to perform the method according to any one of the first aspects.
In a fifth aspect, embodiments of the present application provide a computer program product, which when run on a computer causes the computer to perform the method according to any of the first aspects.
Additional features and advantages of the disclosure will be set forth in the description which follows, or in part will be obvious from the description, or may be learned by practice of the techniques of the disclosure.
And can be implemented in accordance with the teachings of the specification, the following detailed description of the preferred embodiments of the application, taken in conjunction with the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
The following describes in further detail the embodiments of the present application with reference to the drawings and examples. The following examples are illustrative of the application and are not intended to limit the scope of the application.
Example 1
Fig. 1 is a flow chart of a pedestrian collision avoidance early warning method of a vehicle according to an embodiment of the present application, as shown in fig. 1, the method includes:
S1, acquiring a vehicle front image of a vehicle, wherein the vehicle front image is shot by a binocular camera and comprises a left-eye vehicle front image and a right-eye vehicle front image;
S2, recognizing the front image of the vehicle according to a pre-constructed pedestrian recognition model to obtain a recognition result;
S3, correcting the front image of the vehicle according to the identification result to obtain a corrected front image of the vehicle;
s4, performing parallax processing on the corrected front image of the vehicle to obtain distance data of the vehicle and pedestrians;
S5, obtaining current speed data of the vehicle according to the wheel speed sensor data;
and S6, carrying out anti-collision early warning according to the current vehicle speed data, the identification result and the distance data.
In the implementation process, the distance between the vehicle and the pedestrian is obtained through the front image of the vehicle, and then the recognition result of the pedestrian and the current vehicle speed are combined for anti-collision early warning, so that emergency early warning can be carried out on the emergency in the running process of the vehicle, the safety performance of the vehicle is improved, the potential safety hazard of the vehicle in the running process is reduced, and the collision between the vehicle and the pedestrian is effectively avoided.
Further, S2 includes:
Inputting the front image of the vehicle into a pedestrian recognition model for feature extraction to obtain a feature map;
Carrying out feature coding on the feature map to obtain coding information;
transforming the coding information according to the convolution transformation function to obtain feature mapping;
and obtaining a recognition result according to the feature mapping.
In the implementation process, the feature extraction is carried out on the front image of the vehicle according to the pedestrian recognition model to obtain the recognition result, so that the recognition accuracy and recognition efficiency can be improved, the vehicle can be facilitated to rapidly recognize the pedestrians in front, and the potential safety hazard is reduced.
The pedestrian recognition model of the application is implemented using a modified YOLOv s algorithm, and the pedestrians are recognized to include children, young and old. In order to improve the efficiency of YOLOv s algorithm in the identification process, the application adds an attention mechanism in the Neck layer of YOLOv s algorithm, improves the edge detection effect and improves the identification efficiency and speed.
YOLOv5s can be divided into four parts: the input end and Backbone, neck, head, wherein the input end takes a color image as input, firstly, an image set is expanded by a Mosaic data enhancement technology, 4 images are randomly selected from the input front images of the vehicle by the Mosaic data enhancement technology, randomly scaled, randomly cut, spliced together in a random arrangement mode to form more new images, and then the images are processed by a backbox part, a Focus structure and a CSP structure to obtain a feature map as Neck layers of input.
The vehicle front image acquired by the embodiment of the application is an RGB three-channel color image, and can be converted into oneComprises a multi-dimensional matrix of heightWidth of (width of)Sum channel numberAnd C is 3, performing Focus structure operation in a backlight layer of YOLOv5s, processing the image by using a plurality of convolution layers to obtain a feature map, performing CSP structure operation, splitting the feature map by the CSP structure, performing convolution operation on one part, and fusing features of the other part and the previous part to obtain an output feature map of the backlight. The feature map output by the backup is the input feature map of Neck layers, namely the input of the CA attention mechanism.
The size of the feature map input at this time isGlobal average pooling is performed on the feature images in the width and height directions respectively, and in the embodiment of the application, the feature images are respectively in two spatial rangesAndAnd respectively obtaining the sum of the values of the characteristic image blocks under each channel along the horizontal coordinate and the vertical coordinate, dividing the sum by the corresponding space range, and taking the sum as the code of the corresponding space range under the channel to obtain corresponding code information, wherein the method comprises the following specific steps of: for characteristic diagram NoThe channels are positioned at the same heightA kind of electronic deviceThe values of the feature blocks are overlapped and divided by the width value of the feature diagramPooling the width to obtain the characteristic diagram at the heightIs the first of (2)The size of the obtained characteristic diagram after the information under the channel is processed is as follows。
；
For characteristic diagram NoThe channels are positioned at the same widthA kind of electronic deviceThe values of the feature blocks are overlapped and divided by the height value of the feature diagramPooling the height to obtain the width of the characteristic diagramIs the first of (2)The size of the obtained characteristic diagram after the information under the channel is processed is as follows。
；
Wherein,At a height ofAt the time of the firstThe output of the channel is provided with a signal,To be of widthAt the time of the firstThe output of the channel is provided with a signal,For the width of the feature map,Is the height of the feature map.
Re-pairingPerforming transposition operation to obtainThen stacking, merging the wide and high features together to produce a pair of direction-aware feature mapsThen pass through oneIs a convolution kernel of (2)Convolving the feature map, introducing a reduction factor in the processChanging the size of the feature map to increase the operation speed, obtaining a spatial feature information (feature map) integrating the horizontal direction and the vertical direction, wherein the size of the feature map is as followsThen through a nonlinear activation functionThe feature values of the output feature map are converted into nonlinear output, and the expression of the process is as follows:
；
Wherein,In order to reduce factors, the scale of the feature map is reduced to a certain extent by the reduction factors, the operation efficiency of the algorithm is improved, and the nonlinear activation function selected in the embodiment of the application is as followsA function.
Will thenDecomposing the feature map into 2 separate quantities along the spatial dimensionAndUsing twoIs a convolution kernel of (2)Will respectivelyThe conversion is carried out to the same channel number as the input color image, namely 3 channels, and the sizes of the two channels are respectivelyAndAnd then toPerforming one-time transposition operation to obtain a product with a size ofA kind of electronic device. The feature map is then multiplied by a nonlinear activation function to obtain attention weight information across width and height, respectivelyAnd：
；
；
Wherein,As the attention weight in height,As the attention weight in terms of width,Is thatA function, the expression of which is:
；
Multiplying the obtained attention weight feature map in two dimensions with the input feature map of Neck layers to obtain a feature map output with spatial attention feature weights:
；
Wherein,Refers to the first of the input feature graphsUnder the channel, the firstLine 1The values of the characteristic tiles of the column,Refers to at the firstIn the under-channel high concentration weight, the firstThe weight value of the row is used to determine,Refers to at the firstIn the width attention weight under the channel, the firstThe weight value of the column,Refers toOutput value after multiplication of attention weights in two dimensions as the first in the output feature mapUnder the channel, the firstLine 1The values of the characteristic tiles of the column.
The pedestrian recognition model is trained by utilizing pedestrian data, and the data set with three types of pedestrians of children, young and old people is used for carrying out multi-round training, so that a trained algorithm with accurate recognition effect is obtained.
Further, S3 includes:
judging whether the pedestrian is identified by the identification result;
if yes, carrying out three-dimensional correction on the front image of the vehicle to obtain the horizontal characteristic and the vertical characteristic of the front image of the vehicle;
And smoothing the horizontal characteristic and the vertical characteristic to obtain a corrected front image of the vehicle.
In the implementation process, the stereo correction is carried out on the image in front of the vehicle, and the smoothing treatment is carried out on the horizontal characteristic and the vertical characteristic after the correction, so that the error can be reduced, and the processing efficiency and the processing speed of the image can be improved.
Carrying out three-dimensional correction on the horizontal characteristic and the vertical characteristic by utilizing Bouguet algorithm;
；
；
Wherein,Refers to the normalized abscissa and ordinate of the pixel point after the stereo correction,For the radial distortion correction parameters of the image,For the tangential distortion correction parameters of the image,For the abscissa and ordinate of the pixel in the distorted image,Is the pixel point under polar coordinatesDistance from the origin of the coordinate axes.
Further, the step of smoothing the horizontal feature and the vertical feature to obtain a corrected front image of the vehicle includes:
Respectively carrying out edge extraction on the horizontal features and the vertical features according to a Sobel algorithm to obtain the horizontal features after edge extraction and the vertical features after edge extraction;
and correcting the horizontal features after edge extraction and the vertical features after edge extraction according to Gaussian filtering to obtain corrected front images of the vehicle.
In the implementation process, the horizontal features and the vertical features are subjected to edge extraction and then corrected, so that deviation in the front image of the vehicle can be repaired, and the usability of the image is improved.
According to the application, the Sobel operator is selected for processing, and the Gaussian filter module is added into the Sobel operator to carry out smoothing processing on the image, so that the edge detection effect is improved.
The gaussian filter module is as follows:
；
wherein sigma represents the standard deviation of the gaussian kernel,The weight value of the point is represented, x is the abscissa of the pixel in the vehicle front image, y is the ordinate of the pixel in the vehicle front image, and the size and standard deviation of the gaussian kernel determine the range and shape of the weight distribution, thereby affecting the quality of the smoothing effect.
Further, S4 includes:
performing parallax optimization on the front left-eye vehicle image and the front right-eye vehicle image according to an SGBM algorithm to obtain an optimized front left-eye vehicle image and an optimized front right-eye vehicle image;
Generating a parallax image according to the optimized left-eye vehicle front image and the optimized right-eye vehicle front image;
distance data between the vehicle and the pedestrian is obtained according to the disparity map.
In the implementation process, parallax optimization is performed on the front left-eye vehicle image and the front right-eye vehicle image, so that the accuracy of the front left-eye vehicle image and the front right-eye vehicle image can be improved, the accuracy of distance data is improved, and errors are reduced.
The application selects a semi-global matching algorithm (SGBM) algorithm based on parallax in computer binocular vision to perform parallax optimization on binocular images, outputs a parallax map, calculates the depth of pedestrians according to the binocular parallax map, and can obtain the distance between the pedestrians and vehicles.
Further, S6 includes:
Judging whether the distance data is smaller than a preset distance;
if yes, converting the current vehicle speed data, the distance data and the identification result according to a pre-constructed conversion function, and obtaining an early warning result.
In the implementation process, the early warning result is obtained according to the current vehicle speed data, the distance data and the recognition result, so that the early warning result can comprise data analysis of multiple dimensions, and the accuracy of the early warning result is improved.
If the distance between the vehicle and the person is less than 50 meters, converting the current vehicle speed data, the distance data and the pedestrian recognition junction to obtain an early warning result, calculating the early warning result, and outputting the grade of the early warning decision.
The current vehicle speed data is recorded asThe distance data is recorded asThe pedestrian recognition result is recorded asThe decision result of the vehicle speed is recorded asThe decision result of the distance between the person and the vehicle is recorded asThe pedestrian marking result is recorded asThe early warning calculation result is recorded asThe early warning decision result is recorded as。
And executing a corresponding early warning instruction according to the early warning grade of the early warning decision, and judging whether to add early warning reminding aiming at children or old people to the driver according to the pedestrian type recognition result of the pedestrian recognition module.
And receiving a pedestrian recognition result, if the result is a child or an old person, executing an increase prompt, and prompting the driver that the child or the old person is in front of the vehicle by voice broadcasting, prompting the vehicle-outside pedestrian to pay attention to the coming vehicle by voice broadcasting, and then receiving an early warning decision grade and carrying out early warning according to the corresponding grade.
Further, S5 includes:
Acquiring a first voltage in wheel speed sensor data;
obtaining a pulse voltage according to the first voltage;
Obtaining a pulse frequency according to the period of the pulse voltage;
Current speed data of the vehicle is obtained according to the pulse frequency.
In the implementation process, the current vehicle speed data is obtained in real time according to the wheel speed sensor, so that the timeliness and accuracy of obtaining the current vehicle speed data can be improved, and the anti-collision early warning can be conveniently and rapidly carried out according to the current vehicle speed data.
The application can provide stable and real-time vehicle speed data, the original data is received by the vehicle speed sensor, the current vehicle speed data is obtained after being processed by the electronic control unit (Electronic Control Unit, ECU), the Hall wheel speed sensor is selected to collect the data, the current vehicle speed data is obtained through calculation by the electronic controller unit, and the working flow is shown in figure 2.
The wheel rotates to drive the Hall wheel speed sensor to generate a first voltageAfter being processed by the voltage processing circuit, the pulse voltage is outputECU collects pulse voltageIs of the period of (2)And calculates the pulse frequency per unit time according to the following formula。
And then obtaining current vehicle speed data according to a built-in vehicle speed calculation formula in the ECU:
；
；
Wherein,Is the radius of the automobile wheel.
The application is based on an improved YOLOv algorithm model, can detect the type of the pedestrian ahead in real time in the driving process of the automobile, provides a reliable recognition result for an early warning decision module, combines the current speed, the distance between the pedestrian and the automobile and the type of the pedestrian to carry out early warning grade decision, can provide corresponding early warning information for the current traffic condition, helps a driver to better distribute attention in the driving process, and carries out special driving reminding for children and old people: after the pedestrian type is identified, aiming at the identification results of children and old people, the driver is subjected to additional early warning reminding, so that the driver is helped to know the current road condition.
Example two
In order to execute a corresponding method of the above embodiment to achieve the responsive function and technical effect, a pedestrian anti-collision early warning device of a vehicle is provided below, as shown in fig. 3, the device includes:
An acquisition module 1 for acquiring a vehicle front image of a vehicle, the vehicle front image being photographed by a binocular camera, including a left-eye vehicle front image and a right-eye vehicle front image;
The recognition module 2 is used for recognizing the front image of the vehicle according to a pre-constructed pedestrian recognition model to obtain a recognition result;
A correction module 3, configured to correct the front image of the vehicle according to the recognition result, so as to obtain a corrected front image of the vehicle;
The parallax processing module 4 is used for performing parallax processing on the corrected front image of the vehicle to obtain distance data of the vehicle and pedestrians;
A data obtaining module 5 for obtaining current speed data of the vehicle according to the wheel speed sensor data;
And the early warning module 6 is used for carrying out anti-collision early warning according to the current vehicle speed data, the identification result and the distance data.
In the implementation process, the distance between the vehicle and the pedestrian is obtained through the front image of the vehicle, and then the recognition result of the pedestrian and the current vehicle speed are combined for anti-collision early warning, so that emergency early warning can be carried out on the emergency in the running process of the vehicle, the safety performance of the vehicle is improved, the potential safety hazard of the vehicle in the running process is reduced, and the collision between the vehicle and the pedestrian is effectively avoided.
Further, the identification module 2 is further configured to:
Inputting the front image of the vehicle into a pedestrian recognition model for feature extraction to obtain a feature map;
Carrying out feature coding on the feature map to obtain coding information;
transforming the coding information according to the convolution transformation function to obtain feature mapping;
and obtaining a recognition result according to the feature mapping.
In the implementation process, the feature extraction is carried out on the front image of the vehicle according to the pedestrian recognition model to obtain the recognition result, so that the recognition accuracy and recognition efficiency can be improved, the vehicle can be facilitated to rapidly recognize the pedestrians in front, and the potential safety hazard is reduced.
Further, the correction module 3 is further configured to:
judging whether the pedestrian is identified by the identification result;
if yes, carrying out three-dimensional correction on the front image of the vehicle to obtain the horizontal characteristic and the vertical characteristic of the front image of the vehicle;
And smoothing the horizontal characteristic and the vertical characteristic to obtain a corrected front image of the vehicle.
In the implementation process, the stereo correction is carried out on the image in front of the vehicle, and the smoothing treatment is carried out on the horizontal characteristic and the vertical characteristic after the correction, so that the error can be reduced, and the processing efficiency and the processing speed of the image can be improved.
Further, the correction module 3 is further configured to:
Respectively carrying out edge extraction on the horizontal features and the vertical features according to a Sobel algorithm to obtain the horizontal features after edge extraction and the vertical features after edge extraction;
and correcting the horizontal features after edge extraction and the vertical features after edge extraction according to Gaussian filtering to obtain corrected front images of the vehicle.
In the implementation process, the horizontal features and the vertical features are subjected to edge extraction and then corrected, so that deviation in the front image of the vehicle can be repaired, and the usability of the image is improved.
Further, the parallax processing module 4 is further configured to:
performing parallax optimization on the front left-eye vehicle image and the front right-eye vehicle image according to an SGBM algorithm to obtain an optimized front left-eye vehicle image and an optimized front right-eye vehicle image;
Generating a parallax image according to the optimized left-eye vehicle front image and the optimized right-eye vehicle front image;
distance data between the vehicle and the pedestrian is obtained according to the disparity map.
In the implementation process, parallax optimization is performed on the front left-eye vehicle image and the front right-eye vehicle image, so that the accuracy of the front left-eye vehicle image and the front right-eye vehicle image can be improved, the accuracy of distance data is improved, and errors are reduced.
Further, the early warning module 6 is further configured to:
Judging whether the distance data is smaller than a preset distance;
if yes, converting the current vehicle speed data, the distance data and the identification result according to a pre-constructed conversion function, and obtaining an early warning result.
In the implementation process, the early warning result is obtained according to the current vehicle speed data, the distance data and the recognition result, so that the early warning result can comprise data analysis of multiple dimensions, and the accuracy of the early warning result is improved.
Further, the data obtaining module 5 is further configured to:
Acquiring a first voltage in wheel speed sensor data;
obtaining a pulse voltage according to the first voltage;
Obtaining a pulse frequency according to the period of the pulse voltage;
Current speed data of the vehicle is obtained according to the pulse frequency.
In the implementation process, the current vehicle speed data is obtained in real time according to the wheel speed sensor, so that the timeliness and accuracy of obtaining the current vehicle speed data can be improved, and the anti-collision early warning can be conveniently and rapidly carried out according to the current vehicle speed data.
The pedestrian collision avoidance early warning device of the vehicle may implement the method of the first embodiment. The options in the first embodiment described above also apply to this embodiment, and are not described in detail here.
The rest of the embodiments of the present application may refer to the content of the first embodiment, and in this embodiment, no further description is given.
Example III
The embodiment of the application provides electronic equipment, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic equipment to execute the pedestrian collision avoidance early warning method of the vehicle in the first embodiment.
Alternatively, the electronic device may be a server.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include a processor 41, a communication interface 42, a memory 43, and at least one communication bus 44. Wherein the communication bus 44 is used to enable direct connection communication of these components. The communication interface 42 of the device in the embodiment of the present application is used for performing signaling or data communication with other node devices. The processor 41 may be an integrated circuit chip with signal processing capabilities.
The processor 41 may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), and the like; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. The general purpose processor may be a microprocessor or the processor 41 may be any conventional processor or the like.
The Memory 43 may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc. The memory 43 has stored therein computer readable instructions which, when executed by the processor 41, enable the apparatus to perform the steps described above in relation to the embodiment of the method of fig. 1.
Optionally, the electronic device may further include a storage controller, an input-output unit. The memory 43, the memory controller, the processor 41, the peripheral interface, and the input/output unit are electrically connected directly or indirectly to each other to realize data transmission or interaction. For example, the components may be electrically coupled to each other via one or more communication buses 44. The processor 41 is arranged to execute executable modules stored in the memory 43, such as software functional modules or computer programs comprised by the device.
The input-output unit is used for providing the user with the creation task and creating the starting selectable period or the preset execution time for the task so as to realize the interaction between the user and the server. The input/output unit may be, but is not limited to, a mouse, a keyboard, and the like.
It will be appreciated that the configuration shown in fig. 4 is merely illustrative, and that the electronic device may also include more or fewer components than shown in fig. 4, or have a different configuration than shown in fig. 4. The components shown in fig. 4 may be implemented in hardware, software, or a combination thereof.
In addition, the embodiment of the application also provides a computer readable storage medium, which stores a computer program, and the computer program realizes the pedestrian collision avoidance early warning method of the vehicle of the first embodiment when being executed by a processor.
The present application also provides a computer program product which, when run on a computer, causes the computer to perform the method described in the method embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based devices which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The above description is merely illustrative of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the scope of the present application, and the application is intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be defined by the protection scope of the claims.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.