Vehicle speeding detection methods, devices, equipment and storage media

Abstract

This invention discloses a vehicle speeding identification method, device, equipment, and storage medium. The method includes: when a vehicle is detected traveling on the road, determining the vehicle's position offset within a target time period based on the vehicle's position coordinates in a target coordinate system at different times; determining the vehicle's positioning interval time; determining the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period; determining the current driving speed based on the vehicle's position offset within the target time period; and comprehensively identifying the vehicle as speeding based on the driving speed at each stage and the current driving speed. By using the above method, determining the vehicle's position offset within the target time period based on its position coordinates at different times, determining the current driving speed, and determining the driving speed at each stage based on the positioning interval time, and then comprehensively identifying the vehicle as speeding based on the target speed limit, the accuracy of identifying vehicle speeding can be effectively improved, and the identification cost can be reduced.

Description

Technical Field

[0001] This invention relates to the field of intelligent device technology, and in particular to a method, apparatus, device, and storage medium for vehicle speeding identification. Background Technology

[0002] With the continuous increase in the number of vehicles, traffic management has become increasingly burdensome. To facilitate management, more and more traffic intersections have been equipped with cameras to identify speeding behavior. However, camera monitoring has at least two drawbacks. First, camera monitoring has technical limitations, such as unstable image quality and poor night shooting effect. Second, the installation and maintenance costs of cameras are high, and they also require regular maintenance and repair. Cameras used for monitoring must have high definition, wide angle, night vision and other functions. The increase in functions will undoubtedly increase the identification cost. Therefore, the above methods of identifying speeding vehicles are less accurate and more expensive.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a method, apparatus, device, and storage medium for identifying vehicle speeding, aiming to solve the technical problems of low accuracy and high cost in existing technologies for identifying vehicle speeding.

[0005] To achieve the above objectives, the present invention provides a vehicle speeding identification method, which includes the following steps:

[0006] When a vehicle is detected traveling on the road, the vehicle's position offset within the target time period is determined based on the vehicle's position coordinates in the target coordinate system at different times.

[0007] Determine the vehicle positioning interval time, and determine the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period;

[0008] The current driving speed is determined based on the vehicle's position offset within the target time period;

[0009] The vehicle is identified as speeding based on a combination of the speed at each stage and the current speed.

[0010] Optionally, when a vehicle traveling on the road is detected, determining the vehicle's position offset within a target time period based on the vehicle's position coordinates in the target coordinate system at different times includes:

[0011] When a vehicle is detected traveling on the road, the vehicle is located at different times using a target localization model to obtain the coordinates of the vehicle in the target coordinate system.

[0012] The vehicle's position coordinates at the start and end times are obtained based on the vehicle's position coordinates in the target coordinate system.

[0013] Calculate the current position offset based on the vehicle's position coordinates at the start and end times;

[0014] Calculate the target time period based on the start and end times;

[0015] The vehicle's position offset within the target time period is calculated based on the current position offset and the target time period.

[0016] Optionally, determining the driving speed at each stage based on the positioning interval and the vehicle's position offset within the target time period includes:

[0017] The position offset of the vehicle within the target time is segmented according to the positioning interval time to obtain the position offset within each interval time period.

[0018] The driving speed for each stage is calculated based on the position offset within each time interval.

[0019] Optionally, the step of comprehensively identifying the vehicle for speeding based on the driving speed at each stage and the current driving speed includes:

[0020] Obtain the road type of the road on which the vehicle is traveling;

[0021] The driving lane is determined based on the vehicle's position coordinates in the target coordinate system, the coordinates of the road boundary, and the width of each lane.

[0022] The target speed limit is determined based on the road type, the driving lane, and the vehicle model.

[0023] The vehicle is identified as speeding based on a combination of the current driving speed, the target speed limit, and the driving speed at each stage.

[0024] Optionally, after identifying the vehicle for speeding based on the current driving speed, the target speed limit, and the driving speed at each stage, the method further includes:

[0025] When the current driving speed is greater than the target speed limit, the driving speed at each stage is compared with the target speed limit.

[0026] If the comparison result shows that the vehicle's speed exceeds the target speed limit at any stage, the current image of the vehicle is acquired.

[0027] The vehicle's identification information is obtained based on the current image;

[0028] The target image is obtained by increasing the value of the target channel of the current image;

[0029] The target image is displayed, and the identification information and target image are uploaded to the cloud managed by the traffic management department.

[0030] Optionally, obtaining the vehicle's identification information based on the current image includes:

[0031] The visibility detection algorithm is used to detect the visibility of the area in the current driving scenario, and the pixel values ​​of the visibility detection image are obtained.

[0032] When the pixel value of the visibility detection image is less than a preset pixel value threshold, the current image is deblurred.

[0033] The blurred current image is cropped to obtain the target region image;

[0034] The target area image is identified to obtain various identification information;

[0035] The identification information is classified using a classification network with fully connected layers;

[0036] The vehicle's identification information is determined based on the classification results of the identification information.

[0037] Optionally, after displaying the target image and uploading the identification information and the target image to the cloud managed by the traffic management department, the method further includes:

[0038] Upon receiving a successful upload notification from the cloud-based system controlled by the traffic management department, the identification information and target image are deleted from the local storage area.

[0039] Furthermore, to achieve the above objectives, the present invention also proposes a vehicle speeding identification device, the vehicle speeding identification device comprising:

[0040] The offset determination module is used to determine the vehicle's position offset within a target time period based on the vehicle's position coordinates in the target coordinate system at different times when a vehicle traveling on the road is detected.

[0041] The driving speed determination module is used to determine the vehicle's positioning interval time and determine the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period.

[0042] The driving speed determination module is also used to determine the current driving speed based on the vehicle's position offset within the target time period;

[0043] The identification module is used to identify the vehicle for speeding based on the combined driving speed at each stage and the current driving speed.

[0044] Furthermore, to achieve the above objectives, the present invention also proposes a vehicle speeding identification device, which includes: a memory, a processor, and a vehicle speeding identification program stored in the memory and executable on the processor, wherein the vehicle speeding identification program is configured to implement the vehicle speeding identification method as described above.

[0045] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a vehicle speeding identification program, which, when executed by a processor, implements the vehicle speeding identification method as described above.

[0046] The vehicle speeding identification method proposed in this invention determines the vehicle's position offset within a target time period based on the vehicle's position coordinates in the target coordinate system at different times when a vehicle is detected traveling on the road; determines the vehicle's positioning interval time; determines the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period; determines the current driving speed based on the vehicle's position offset within the target time period; and identifies the vehicle as speeding by combining the driving speeds at each stage and the current driving speed. Through this method, by determining the vehicle's position offset within the target time period based on the vehicle's position coordinates in the target coordinate system at different times, then combining this with the positioning interval time to determine the driving speed at each stage, determining the current driving speed based on the vehicle's position offset within the target time period, and finally combining this with the target speed limit to comprehensively identify the vehicle as speeding, the accuracy of vehicle speeding identification can be effectively improved, and the identification cost can be reduced. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the structure of a vehicle speeding recognition device in the hardware operating environment involved in the embodiments of the present invention;

[0048] Figure 2 This is a flowchart illustrating the first embodiment of the vehicle speeding identification method of the present invention;

[0049] Figure 3 This is a flowchart illustrating the second embodiment of the vehicle speeding identification method of the present invention;

[0050] Figure 4 This is a schematic diagram of the overall process of an embodiment of the vehicle speeding identification method of the present invention;

[0051] Figure 5 This is a functional module diagram of the first embodiment of the vehicle speeding recognition device of the present invention.

[0052] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0053] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0054] Reference Figure 1 , Figure 1 This is a schematic diagram of the vehicle speeding recognition device structure in the hardware operating environment involved in the embodiments of the present invention.

[0055] like Figure 1 As shown, the vehicle speeding detection device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0056] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the vehicle speeding detection device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0057] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a vehicle speeding recognition program.

[0058] exist Figure 1In the vehicle speeding recognition device shown, the network interface 1004 is mainly used for data communication with the network integrated platform workstation; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the vehicle speeding recognition device of the present invention can be set in the vehicle speeding recognition device, and the vehicle speeding recognition device calls the vehicle speeding recognition program stored in the memory 1005 through the processor 1001 and executes the vehicle speeding recognition method provided in the embodiment of the present invention.

[0059] Based on the above hardware structure, an embodiment of the vehicle speeding identification method of the present invention is proposed.

[0060] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the vehicle speeding identification method of the present invention.

[0061] In the first embodiment, the vehicle speeding identification method includes the following steps:

[0062] Step S10: When a vehicle traveling on the road is detected, the position offset of the vehicle in the target time period is determined based on the position coordinates of the vehicle in the target coordinate system at different times.

[0063] It should be noted that the executing entity in this embodiment is a vehicle speeding recognition device, but it can also be other devices that can achieve the same or similar functions, such as a smart device controller. This embodiment does not limit this; in this embodiment, a smart device controller will be used as an example for explanation.

[0064] It should be understood that position coordinates refer to the coordinates of the vehicle's current position in the target coordinate system after it enters the detection range. This target coordinate system can be the world coordinate system. Since the vehicle is in motion, its position coordinates are different at different times. For example, the vehicle's position coordinates at the beginning are (x1, y1), and its position coordinates at the end are (x2, y2).

[0065] It is understandable that the position offset refers to the amount of displacement of the vehicle's position at the beginning of the journey relative to its position at the end of the journey. The larger the position offset, the farther the vehicle has traveled within the target time period. This position offset can be determined by the vehicle's position coordinates in the target coordinate system at different times.

[0066] It should be emphasized that the application scenario of this implementation is for users to wear AR glasses to identify vehicles speeding on the road. The user's location can be a traffic intersection, and the user can be a traffic management officer or a speed measurement personnel from the vehicle manufacturer. This embodiment does not impose any restrictions on this.

[0067] Further, step S10 includes: when a vehicle traveling on the road is detected, locating the vehicle at different times using a target localization model to obtain the vehicle's position coordinates in the target coordinate system; obtaining the vehicle's position coordinates at the start time and end time based on the vehicle's position coordinates in the target coordinate system; calculating the current position offset based on the vehicle's position coordinates at the start time and end time; calculating the target time period based on the start time and end time; and calculating the vehicle's position offset within the target time period based on the current position offset and the target time period.

[0068] It is understandable that the target localization model refers to the model used to locate the position coordinates of an object in the target coordinate system. This target localization model can be a 3D AVOD localization model. When a vehicle is detected driving on the road, the target localization model is used to locate the vehicle in motion and obtain the position coordinates of the vehicle in the target coordinate system at different times.

[0069] It should be understood that the current position offset refers to the amount of displacement of the vehicle from its starting position to its ending position. The target time period refers to the duration of the vehicle's journey from its starting position to its ending position. The starting time refers to the moment the vehicle enters the detection range, and the ending time refers to the moment it leaves the detection range. For example, if the starting time is 2023:09:09:15:28:15 and the ending time is 2023:09:09:15:28:11, then the target time period is 4 seconds. The position coordinates at the ending time are (x1, y1), and the position coordinates at the starting time are (x2, y2). The vehicle's position offset within the target time period is...

[0070] Step S20: Determine the vehicle's positioning interval time, and determine the driving speed for each stage based on the positioning interval time and the vehicle's position offset within the target time period.

[0071] It is understandable that the positioning interval time refers to the interval time between the target positioning model locating the vehicle, and the driving speed at each stage refers to the driving speed of the vehicle at different stages. The shorter the positioning interval time, the closer the driving speed at each stage is to the real-time vehicle speed.

[0072] Further, step S20 includes: segmenting the vehicle's position offset within the target time according to the positioning interval to obtain the position offset within each interval time period; and calculating the driving speed at each stage based on the position offset within each interval time period.

[0073] It should be understood that after determining the positioning interval time, the positioning interval time is calculated according to the positioning interval time. For example, if the positioning interval time is 1 second, the position offset within each interval time period is: the position offset within 0-1 second, the position offset within 1-2 seconds, the position offset within 2-3 seconds, and the position offset within 3-4 seconds. Then, the driving speed for each stage is calculated based on the position offset within each interval time period, namely: the driving speed within 0-1 seconds, the driving speed within 1-2 seconds, the driving speed within 2-3 seconds, and the driving speed within 3-4 seconds.

[0074] Step S30: Determine the current driving speed based on the vehicle's position offset within the target time period.

[0075] It should be understood that after obtaining the vehicle's position offset within the target time period, the current driving speed is determined based on the offset within the target time period, specifically as follows:

[0076] v = s' / t.

[0077] Where v represents the current driving speed, s' represents the position offset within the target time period, and t represents the unit time.

[0078] Step S40: Based on the combined driving speed at each stage and the current driving speed, the vehicle is identified as speeding.

[0079] Understandably, after calculating the current driving speed and the driving speed at each stage, the vehicle is identified as speeding based on a combination of the current driving speed, the driving speed at each stage, and the target speed limit. Specifically, if the current driving speed is greater than the target speed limit or any driving speed at each stage is greater than the target speed limit, the vehicle is determined to be speeding. If the current driving speed and the driving speed at each stage are all less than or equal to the target speed limit, the vehicle is determined to be driving normally. That is, speeding identification of vehicles is achieved through both whole-segment and interval methods.

[0080] This embodiment determines the vehicle's position offset within a target time period based on the vehicle's position coordinates in the target coordinate system at different times when a vehicle is detected traveling on the road; determines the vehicle's positioning interval time; determines the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period; determines the current driving speed based on the vehicle's position offset within the target time period; and comprehensively identifies the vehicle as speeding based on the driving speed at each stage and the current driving speed. By using the above method, the vehicle's position offset within the target time period is determined based on its position coordinates in the target coordinate system at different times, then the driving speed at each stage is determined in conjunction with the positioning interval time, the current driving speed is determined based on the vehicle's position offset within the target time period, and finally the target speed limit is combined to comprehensively identify the vehicle as speeding. This effectively improves the accuracy of identifying speeding vehicles and reduces the identification cost.

[0081] In one embodiment, such as Figure 3 The second embodiment of the vehicle speeding identification method of the present invention, based on the first embodiment, includes step S40, which includes:

[0082] Step S401: Obtain the road type of the road on which the vehicle travels.

[0083] It should be understood that road type refers to the type of road on which the vehicle is traveling. The maximum speed limit is different for different roads. For example, the maximum speed limit is 30 km / h for urban roads without a center line, and 40 km / h for urban power roads without a center line.

[0084] Step S402: Determine the driving lane based on the vehicle's position coordinates in the target coordinate system, the coordinates of the road boundary, and the width of each lane.

[0085] It is understandable that for roads in the same area, the speed limits for different lanes are different. For example, the speed limit for the overtaking lane is higher than the speed limit for other driving lanes. First, the distance between the vehicle and the road boundary is determined based on the vehicle's position coordinates in the target coordinate system and the coordinates of the road boundary. Then, the driving lane is determined by combining the width of each lane.

[0086] Step S403: Determine the target speed limit based on the road type, the driving lane, and the vehicle model.

[0087] It should be understood that the target speed limit refers to the maximum speed allowed for a vehicle on the road. For the same lane, the speed limit may vary for different vehicle models. In other words, the target speed limit can be determined comprehensively based on the road type, the lane, and the vehicle model.

[0088] Step S404: Based on the current driving speed, the target speed limit, and the driving speed at each stage, the vehicle is identified as speeding.

[0089] Furthermore, after step S404, the method further includes: when the current driving speed is greater than the target speed limit, comparing the driving speed at each stage with the target speed limit; when the comparison result shows that the driving speed at any stage is greater than the target speed limit, acquiring the current image of the vehicle; obtaining the vehicle's identification information based on the current image; increasing the value of the target channel in the current image to obtain a target image; displaying the target image; and uploading the identification information and the target image to the cloud managed by the traffic management department.

[0090] Understandably, the vehicle identification information can be the vehicle's license plate number. When the current driving speed exceeds the target speed limit or the driving speed at any stage exceeds the target speed limit, it indicates that the vehicle is speeding. At this time, the current image of the vehicle is collected by sensors. In order to more intuitively show the speeding vehicle to users wearing smart devices, the value of the target channel of the current image needs to be increased to highlight the speeding vehicle. This target channel can be the R channel. At the same time, in order to facilitate the management of the above-mentioned speeding violations by traffic management departments, the identification information and target image will also be uploaded to the cloud controlled by the traffic management department to prevent drivers from making the same mistake again.

[0091] Further, obtaining the vehicle's identification information based on the current image includes: performing visibility detection on the area in the current driving scene using a visibility detection algorithm to obtain visibility detection image pixel values; when the visibility detection image pixel values ​​are less than a preset pixel value threshold, performing deblurring processing on the current image; cropping the blurred current image to obtain a target area image; identifying the target area image to obtain various identification information; classifying the identification information using a fully connected layer classification network; and determining the vehicle's identification information based on the identification information classification results.

[0092] It should be understood that before cropping the image, it is necessary to determine whether blurring is required. Specifically, this involves using a gradient filter to perform visibility detection on the region in the current driving scene based on a visibility detection algorithm. That is, the gradient filter outputs the visibility detection image pixel values, specifically:

[0093]

[0094] Where O(i,j) represents the visibility detection image pixel value, I(i+m,j+n) represents the region pixel value in the current driving scene, K represents the detection coefficient of the gradient filter, m represents the length of the gradient filter, and n represents the width of the filter.

[0095] Understandably, when the visibility detection image pixel value is less than a preset pixel value threshold, it indicates that there are partially blurred areas in the current image of the vehicle. Therefore, before identifying the vehicle's identification information, deblurring is required. This involves using a pre-trained MSSNet model to deblur the current image. The target region image refers to an image containing only the vehicle's identification information. This means cropping the current image after blurring and then using a 2D YOLOv5 detection model to identify the target region image. The identified individual identification information includes letters, numbers, and abbreviations of various regions. The detection boxes are then used to crop out each of these identification information, and a fully connected classification network is used to classify each identification information. Finally, the classified identification information is stitched together according to the cropping order to obtain the vehicle's identification information.

[0096] Furthermore, after displaying the target image and uploading the identification information and target image to the cloud controlled by the traffic management department, the method further includes: upon receiving the successful upload information from the cloud controlled by the traffic management department, deleting the identification information and target image from the local storage area.

[0097] Understandably, after uploading the identification information and target image to the cloud managed by the traffic management department, it is necessary to monitor in real time whether a successful upload message is received from the cloud. If so, it indicates that the cloud has successfully received and stored the identification information and target image. Since the local storage area of ​​the smart device is limited, in order to avoid the monitoring effect of the smart device being affected by insufficient memory, it is necessary to delete the identification information and target image from the local storage area to free up storage space for monitoring other vehicles.

[0098] refer to Figure 4 , Figure 4The overall process is illustrated below: After the smart device is detected to be turned on, it is determined whether a vehicle traveling on the road is detected. If so, the vehicle's position coordinates in the target coordinate system at different times are located using the target localization model. Then, the vehicle's position offset within the target time period is determined based on the vehicle's position coordinates in the target coordinate system at different times. The driving speed at each stage is determined by combining the vehicle's positioning interval. The current driving speed is then determined based on the vehicle's position offset within the target time period. It is then determined whether the current driving speed or the driving speed at each stage is greater than the target speed limit. If any of the above conditions are met, the current image of the vehicle is deblurred. Then, the vehicle's identification information is identified based on the deblurred current image, and the identification information and the target image are uploaded.

[0099] This embodiment obtains the road type of the road on which the vehicle is traveling; determines the driving lane based on the vehicle's coordinates in the target coordinate system, the coordinates of the road boundary, and the width of each lane; determines the target speed limit based on the road type, the driving lane, and the vehicle model; and identifies the vehicle as speeding based on the current speed, the target speed limit, and the speed at each stage. Through this method, after obtaining the road type, the driving lane is determined based on the vehicle's coordinates in the target coordinate system, the coordinates of the road boundary, and the width of each lane. Then, the target speed limit is determined in conjunction with the vehicle model. Finally, the vehicle's current speed (determined by its coordinates in the target coordinate system), the speed at each stage, and the comparison with the target speed limit are used to determine whether the vehicle is speeding. This effectively improves the accuracy of identifying speeding vehicles.

[0100] Furthermore, this embodiment of the invention also proposes a storage medium storing a vehicle speeding identification program, which, when executed by a processor, implements the steps of the vehicle speeding identification method described above.

[0101] Since this storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0102] In addition, refer to Figure 5 This invention also proposes a vehicle speeding identification device, which includes:

[0103] The offset determination module 10 is used to determine the position offset of the vehicle within a target time period based on the position coordinates of the vehicle in the target coordinate system at different times when a vehicle traveling on the road is detected.

[0104] The driving speed determination module 20 is used to determine the vehicle's positioning interval time and determine the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period.

[0105] The driving speed determination module 20 is also used to determine the current driving speed based on the vehicle's position offset within the target time period.

[0106] The identification module 30 is used to identify the vehicle for speeding based on the combined driving speed at each stage and the current driving speed.

[0107] This embodiment determines the vehicle's position offset within a target time period based on the vehicle's position coordinates in the target coordinate system at different times when a vehicle is detected traveling on the road; determines the vehicle's positioning interval time; determines the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period; determines the current driving speed based on the vehicle's position offset within the target time period; and comprehensively identifies the vehicle as speeding based on the driving speed at each stage and the current driving speed. By using the above method, the vehicle's position offset within the target time period is determined based on its position coordinates in the target coordinate system at different times, then the driving speed at each stage is determined in conjunction with the positioning interval time, the current driving speed is determined based on the vehicle's position offset within the target time period, and finally the target speed limit is combined to comprehensively identify the vehicle as speeding. This effectively improves the accuracy of identifying speeding vehicles and reduces the identification cost.

[0108] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0109] In addition, for technical details not described in detail in this embodiment, please refer to the vehicle speeding identification method provided in any embodiment of the present invention, which will not be repeated here.

[0110] In one embodiment, the offset determination module 10 is further configured to, when a vehicle traveling on the road is detected, locate the vehicle at different times using a target localization model to obtain the vehicle's position coordinates in a target coordinate system; obtain the vehicle's position coordinates at the start time and end time based on the vehicle's position coordinates in the target coordinate system; calculate the current position offset based on the vehicle's position coordinates at the start time and end time; calculate a target time period based on the start time and end time; and calculate the vehicle's position offset within the target time period based on the current position offset and the target time period.

[0111] In one embodiment, the driving speed determination module 20 is further configured to segment the position offset of the vehicle within the target time according to the positioning interval time to obtain the position offset within each interval time period; and calculate the driving speed of each stage according to the position offset within each interval time period.

[0112] In one embodiment, the identification module 30 is further configured to: acquire the road type of the road on which the vehicle travels; determine the driving lane based on the vehicle's position coordinates in the target coordinate system, the coordinates of the road boundary, and the width of each lane; determine the target speed limit based on the road type, the driving lane, and the vehicle model; and identify the vehicle as speeding based on the current driving speed, the target speed limit, and the driving speed at each stage.

[0113] In one embodiment, the identification module 30 is further configured to: compare the driving speed at each stage with the target speed limit when the current driving speed is greater than the target speed limit; acquire the current image of the vehicle when the comparison result shows that the driving speed at any stage is greater than the target speed limit; obtain the vehicle's identification information based on the current image; increase the value of the target channel of the current image to obtain a target image; display the target image; and upload the identification information and the target image to the cloud managed by the traffic management department.

[0114] In one embodiment, the identification module 30 is further configured to perform visibility detection on the area under the current driving scenario using a visibility detection algorithm to obtain visibility detection image pixel values; when the visibility detection image pixel values ​​are less than a preset pixel value threshold, perform deblurring processing on the current image; crop the blurred current image to obtain a target area image; identify the target area image to obtain various identification information; classify the identification information using a fully connected layer classification network; and determine the vehicle's identification information based on the identification information classification results.

[0115] In one embodiment, the identification module 30 is further configured to delete the identification information and target image from the local storage area when it receives the successful upload information from the cloud controlled by the traffic management department.

[0116] Other embodiments or implementation methods of the vehicle speeding recognition device described in this invention can be referred to the above-described method embodiments, and will not be repeated here.

[0117] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or up to five stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0118] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0119] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0120] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, all-in-one platform workstation, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0121] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for identifying vehicle speeding, characterized in that, The vehicle speeding identification method includes the following steps: When a vehicle is detected traveling on the road, the vehicle's position offset within the target time period is determined based on the vehicle's position coordinates in the target coordinate system at different times. Determine the vehicle positioning interval time, and determine the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period; The current driving speed is determined based on the vehicle's position offset within the target time period; The vehicle is identified as speeding based on a combination of the speed at each stage and the current speed. After identifying the vehicle for speeding based on the combined driving speed at each stage and the current driving speed, the method further includes: When the current driving speed is greater than the target speed limit, the driving speed at each stage is compared with the target speed limit. If the comparison result shows that the vehicle's speed exceeds the target speed limit at any stage, the current image of the vehicle is obtained. The vehicle's identification information is obtained based on the current image; The target image is obtained by increasing the value of the target channel of the current image; The target image is displayed, and the identification information and target image are uploaded to the cloud managed by the traffic management department.

2. The vehicle speeding identification method as described in claim 1, characterized in that, When a vehicle is detected traveling on the road, determining the vehicle's position offset within a target time period based on the vehicle's position coordinates in the target coordinate system at different times includes: When a vehicle is detected traveling on the road, the vehicle is located at different times using a target localization model to obtain the coordinates of the vehicle in the target coordinate system. The vehicle's position coordinates at the start and end times are obtained based on the vehicle's position coordinates in the target coordinate system. Calculate the current position offset based on the vehicle's position coordinates at the start and end times; Calculate the target time period based on the start and end times; The vehicle's position offset within the target time period is calculated based on the current position offset and the target time period.

3. The vehicle speeding identification method as described in claim 1, characterized in that, The step of determining the driving speed at each stage based on the positioning interval and the vehicle's position offset within the target time period includes: The position offset of the vehicle within the target time is segmented according to the positioning interval time to obtain the position offset within each interval time period. The driving speed for each stage is calculated based on the position offset within each time interval.

4. The vehicle speeding identification method as described in claim 1, characterized in that, The process of identifying speeding based on a combination of the vehicle's speed at each stage and the current speed includes: Obtain the road type of the road on which the vehicle is traveling; The driving lane is determined based on the vehicle's position coordinates in the target coordinate system, the coordinates of the road boundary, and the width of each lane. The target speed limit is determined based on the road type, the driving lane, and the vehicle model. The vehicle is identified as speeding based on a combination of the current driving speed, the target speed limit, and the driving speed at each stage.

5. The vehicle speeding identification method as described in claim 1, characterized in that, The step of obtaining the vehicle's identification information based on the current image includes: The visibility detection algorithm is used to detect the visibility of the area in the current driving scene, and the pixel values ​​of the visibility detection image are obtained. When the pixel value of the visibility detection image is less than a preset pixel value threshold, the current image is deblurred. The blurred current image is cropped to obtain the target region image; The target area image is identified to obtain various identification information; The identification information is classified using a classification network with a fully connected layer; The vehicle's identification information is determined based on the classification results of the identification information.

6. The vehicle speeding identification method as described in claim 1, characterized in that, After displaying the target image and uploading the identification information and target image to the cloud managed by the traffic management department, the method further includes: Upon receiving a successful upload notification from the cloud-based system controlled by the traffic management department, the identification information and target image are deleted from the local storage area.

7. A vehicle speeding detection device, characterized in that, The vehicle speeding detection device includes: The offset determination module is used to determine the vehicle's position offset within a target time period based on the vehicle's position coordinates in the target coordinate system at different times when a vehicle traveling on the road is detected. The driving speed determination module is used to determine the vehicle's positioning interval time and determine the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period. The driving speed determination module is also used to determine the current driving speed based on the vehicle's position offset within the target time period; The identification module is used to identify the vehicle for speeding based on the combined driving speed at each stage and the current driving speed. The identification module is further configured to: compare the driving speed at each stage with the target speed limit when the current driving speed is greater than the target speed limit; acquire the current image of the vehicle when the comparison result shows that the driving speed at any stage is greater than the target speed limit; obtain the vehicle's identification information based on the current image; increase the value of the target channel of the current image to obtain a target image; display the target image; and upload the identification information and the target image to the cloud managed by the traffic management department.

8. A vehicle speeding detection device, characterized in that, The vehicle speeding identification device includes: a memory, a processor, and a vehicle speeding identification program stored in the memory and executable on the processor, wherein the vehicle speeding identification program is configured to implement the vehicle speeding identification method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a vehicle speeding identification program, which, when executed by a processor, implements the vehicle speeding identification method as described in any one of claims 1 to 6.

Images