A method and system for detecting road traffic accidents based on holographic perception

Abstract

The application relates to a kind of road traffic accident detection method and system based on holographic perception, method includes: obtaining the holographic perception data of road;According to the target type of holographic perception target according to holographic perception data, detect whether holographic perception target has tripod target, if yes, according to the uniqueness of the number of holographic perception target, detect whether there is tripod target record, if yes, if the time of continuously detecting tripod target reaches predetermined threshold, then output traffic accident event. Through the implementation of the application, according to the business characteristics of urban road traffic accident, in the multi-target scene output by holographic perception data, the target ID persistence and stability can be used as a method of traffic accident determination means. Under the premise of ensuring real-time and accuracy, the false alarm rate of traffic accident is reduced, which is beneficial to traffic law enforcement action, thereby reducing the labor cost.

Description

Technical Field

[0001] This invention relates to the field of vehicle traffic accident detection, and in particular to a road traffic accident detection method and system based on holographic perception. Background Technology

[0002] Existing traffic accident detection and assessment methods rely on alarm results from video coverage area detection, which suffers from low accuracy, high false alarm rates, and inaccurate localization. These methods lack robust assessment criteria and are limited in scope, lacking sufficient holographic target data and vehicle / road condition information for multi-source assessment. Therefore, relying solely on video detection with limited coverage areas presents an unreliable challenge for vehicle detection in urban traffic accidents. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to address at least one deficiency of the related technologies mentioned in the background: how to improve the accuracy of traffic accident detection, and to provide a road traffic accident detection method and system based on holographic perception.

[0004] The technical solution adopted by this invention to solve its technical problem is: to provide a road traffic accident detection method based on holographic perception, comprising the following steps:

[0005] Step S10: Acquire holographic perception data of the road;

[0006] Step S20: Based on the target type of the holographic sensing target in the holographic sensing data, detect whether the holographic sensing target has a tripod target. If so, proceed to step S30.

[0007] Step S30: Based on the uniqueness of the number of the holographic sensing target, detect whether there is a record of the tripod target. If so, proceed to step S40.

[0008] Step S40: If the tripod target time is continuously detected to reach a predetermined threshold, then output a traffic accident event.

[0009] Preferably, step S30 further includes:

[0010] If not, proceed to step S41;

[0011] Step S41: Detect whether the tripod target is on other holographic sensing targets. If not, proceed to step S42.

[0012] Step S42: Record the start time of the detection of the tripod target and execute step S10;

[0013] The detection start time is used to determine when the detection time of the tripod target reaches the predetermined threshold.

[0014] Preferably, detecting whether the tripod target is on other holographic sensing targets includes:

[0015] By determining whether the displacement generated by the tripod target reaches a displacement threshold within a predetermined time range, if the displacement threshold is reached, it is determined that the tripod target is on other holographic sensing targets.

[0016] Preferably, step S40 further includes:

[0017] Step S50: Perform a secondary verification on the traffic accident event. If the detection meets the secondary verification criteria for traffic accidents, output the final traffic accident event.

[0018] Preferably, step S50 includes:

[0019] Step S51: Check if the parking event is enabled. If not, proceed to step S53.

[0020] Step S53: Detect whether the pedestrian event is enabled. If so, proceed to step S54.

[0021] Step S54: Determine whether there is a pedestrian event within the time frame during which the tripod target is continuously detected and the time reaches a predetermined threshold. If so, proceed to step S55.

[0022] Step S55: Output the final traffic accident event.

[0023] Preferably, step S51 further includes:

[0024] If so, proceed to step S52;

[0025] Step S52: Determine whether there is a parking event within the time frame during which the tripod target time is continuously detected to reach a predetermined threshold. If so, proceed to step S53.

[0026] This invention also constructs a road traffic accident detection system based on holographic perception, comprising:

[0027] Acquisition unit, used to acquire holographic perception data of the road;

[0028] The first detection unit is used to detect whether the holographic sensing target has a tripod target based on the target type of the holographic sensing target in the holographic sensing data; if so, the second detection unit is run.

[0029] The second detection unit is used to detect whether the tripod target record exists based on the uniqueness of the number of the holographic sensing target; if so, the judgment unit is executed.

[0030] The judgment unit is used to output a traffic accident event if the continuous detection of the tripod target time reaches a predetermined threshold.

[0031] The system also includes:

[0032] The secondary verification unit is used to perform secondary verification on the traffic accident event. If the detection meets the secondary verification criteria for traffic accidents, the final traffic accident event is output.

[0033] The present invention also constructs an electronic device comprising:

[0034] One or more processors;

[0035] A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the holographic perception-based road traffic accident detection method as described above.

[0036] The present invention also constructs a storage medium storing a computer program thereon, which, when executed by a processor, implements the road traffic accident detection method based on holographic perception as described in any of the preceding claims.

[0037] By implementing this invention, the following beneficial effects are achieved:

[0038] This invention discloses a method and system for detecting road traffic accidents based on holographic perception. The method includes: acquiring holographic perception data of the road; detecting whether there is a tripod target among the holographic perception targets according to the target type of the holographic perception targets in the holographic perception data; if so, detecting whether there is a tripod target record based on the uniqueness of the holographic perception target's number; if so, outputting a traffic accident event if the detection of tripod targets continues for a predetermined threshold time. By implementing this invention, based on the business characteristics of urban road traffic accidents, the persistence and stability of target IDs in multi-target scenarios output by holographic perception data can be used as a method for traffic accident determination. While ensuring real-time performance and accuracy, it reduces the false alarm rate of traffic accidents, which is beneficial to traffic law enforcement actions and thus reduces labor costs. Attached Figure Description

[0039] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings:

[0040] Figure 1 This is a flowchart illustrating the road traffic accident detection method based on holographic perception according to the present invention.

[0041] Figure 2 This is a flowchart illustrating the first embodiment of the present invention;

[0042] Figure 3This is a flowchart illustrating the second embodiment of the present invention;

[0043] Figure 4 This is a block diagram of the road traffic accident detection system based on holographic perception according to the present invention. Detailed Implementation

[0044] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0045] It should be noted that the flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0046] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0047] For holographic perception-based detection and judgment methods for urban road traffic accidents, it is necessary to consider the multi-dimensional target scene states of parked vehicles, pedestrians, and warning triangles (vehicle warning triangles), as well as the trigger time, duration, and target displacement. In lane areas not covered by the camera's field of view, continuous radar tracking can be used. Current video detection methods for urban road traffic accidents have the following characteristics:

[0048] 1) When vehicles in the lane are too close together and all are stopped, a traffic accident warning is triggered, and this is triggered frequently.

[0049] 2) Stopping at intersections or pedestrian crossings while the light is red can easily cause false alarms as pedestrians cross the road.

[0050] 3) The time interval for determining the accident was too long, and no secondary filtering was performed to remove invalid predictions;

[0051] 4) Pure video has a limited field of view and cannot accurately track the target ID for a long time, requiring a long detection time, which leads to the failure to trigger traffic accident warnings in a timely manner;

[0052] 5) The system does not combine the tripod, vehicle stoppage and pedestrian warning status for joint judgment, and cannot continuously track the target because it is not within the camera's field of view.

[0053] In this embodiment, as Figure 1As shown, this invention provides a road traffic accident detection method based on holographic perception, comprising the following steps:

[0054] Step S10: Obtain holographic perception data of the road; obtain holographic perception data through various sensors, such as data fused from cameras and radar. Each frame of data may contain targets such as motor vehicles, non-motor vehicles, pedestrians, tripods, and debris, and each target carries a unique ID.

[0055] Step S20: Based on the target type of the holographic sensing target in the holographic sensing data, detect whether there is a tripod target in the holographic sensing target. If so, proceed to step S30. In the holographic sensing data, targets such as motor vehicles, non-motor vehicles, pedestrians, tripods, and scattered objects are all different target types. Detect whether there is a tripod target.

[0056] In this embodiment, as Figure 2 As shown, when no tripod target is detected in the holographic sensing target, step S10 is repeated until a tripod target is detected in the holographic sensing target.

[0057] Step S30: Based on the uniqueness of the holographic perception target's number, check if there is a tripod target record. If yes, proceed to step S40; otherwise, proceed to step S41.

[0058] Step S40: If the tripod target detection time reaches a predetermined threshold, output a traffic accident event. The predetermined threshold can be configured for different durations according to actual needs; different thresholds can be configured for different scenarios.

[0059] In this embodiment, as Figure 2 As shown, the method also includes step S41: detecting whether the tripod target is on other holographic sensing targets; if not, then proceed to step S42; if the tripod target is detected to be transported on a vehicle, carried by a pedestrian, or fixed on a non-motorized vehicle, then it is determined that the tripod target is on other holographic sensing targets.

[0060] Step S42: Record the start time of tripod target detection and execute step S10;

[0061] The detection start time is used to determine when the detection time of the tripod target reaches a predetermined threshold.

[0062] Furthermore, it detects whether the tripod target is on other holographic sensing targets, including:

[0063] By determining whether the displacement generated by the tripod target reaches a displacement threshold within a predetermined time range, if the displacement threshold is reached, the tripod target is determined to be on other holographic sensing targets.

[0064] In this embodiment, step S40 is followed by:

[0065] Step S50: Perform a secondary verification on the traffic accident event. If the detection meets the secondary verification criteria for traffic accidents, output the final traffic accident event.

[0066] Furthermore, such as Figure 3 As shown, parking incidents and pedestrian incidents are detection methods of the same or independent level as traffic accidents. Step S50 includes:

[0067] Step S51: Detect whether a parking event is enabled. If not, proceed to step S53; if yes, proceed to step S52. The parking event is a vehicle stop warning event, which detects whether a vehicle is stopped within a preset detection area. The vehicle stop warning event is one of the parameter inputs for traffic accident determination.

[0068] Step S52: Determine whether there is a parking event within the time limit of continuously detecting the tripod target. If yes, proceed to step S53; otherwise, re-execute step S10.

[0069] Step S53: Detect whether the pedestrian event is enabled. If yes, proceed to step S54; otherwise, proceed to step S55. The pedestrian event is a pedestrian appearance warning event, which means detecting whether a pedestrian appears in the preset detection area. The pedestrian event is one of the parameter inputs for traffic accident determination.

[0070] Step S54: Determine whether there is a pedestrian event within the time limit of continuously detecting the tripod target. If yes, proceed to step S55; otherwise, re-execute step S10.

[0071] Step S55: Output the final traffic accident event.

[0072] In this embodiment, as Figure 4 As shown, the present invention also constructs a road traffic accident detection system based on holographic perception, comprising:

[0073] Acquisition unit, used to acquire holographic perception data of the road;

[0074] The first detection unit is used to detect whether the holographic sensing target has a tripod target based on the target type of the holographic sensing target in the holographic sensing data. If so, the second detection unit is run.

[0075] The second detection unit is used to detect whether there is a tripod target record based on the uniqueness of the holographic perception target's number. If so, the judgment unit is executed.

[0076] The judgment unit is used to output a traffic accident event if the continuous detection time of the tripod target reaches a predetermined threshold.

[0077] In this embodiment, the system further includes:

[0078] The secondary verification unit is used to perform secondary verification on traffic accident events. If the detection meets the secondary verification criteria for traffic accidents, the final traffic accident event is output.

[0079] Specifically, the specific operational process of the various modules in the holographic perception-based road traffic accident detection system can be referred to the holographic perception-based road traffic accident detection method described above, and will not be repeated here.

[0080] Furthermore, an electronic device of the present invention includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement the holographic perception-based road traffic accident detection method as described above. Specifically, according to embodiments of the present invention, the processes described above with reference to the flowchart can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, when the computer program is downloaded, installed, and executed by an electronic device, it performs the functions defined in the methods of the embodiments of the present invention. The electronic device in the present invention can be a terminal such as a laptop, desktop computer, tablet computer, or smartphone, or it can be a server.

[0081] Furthermore, one type of storage medium of the present invention stores a computer program thereon, which, when executed by a processor, implements the holographic perception-based road traffic accident detection method described above. Specifically, it should be noted that the storage medium described above in the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, wherein computer-readable program code is carried. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0082] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0083] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0084] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0085] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0086] By implementing this invention, the following beneficial effects are achieved:

[0087] This invention discloses a method and system for detecting road traffic accidents based on holographic perception. The method includes: acquiring holographic perception data of the road; detecting whether there is a tripod target among the holographic perception targets according to the target type of the holographic perception targets in the holographic perception data; if so, detecting whether there is a tripod target record based on the uniqueness of the holographic perception target's number; if so, outputting a traffic accident event if the detection of tripod targets continues for a predetermined threshold time. By implementing this invention, based on the business characteristics of urban road traffic accidents, the persistence and stability of target IDs in multi-target scenarios output by holographic perception data can be used as a method for traffic accident determination. While ensuring real-time performance and accuracy, it reduces the false alarm rate of traffic accidents, which is beneficial to traffic law enforcement actions and thus reduces labor costs.

[0088] The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement it accordingly. They do not limit the scope of protection of the present invention. All equivalent changes and modifications made within the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A road traffic accident detection method based on holographic perception, characterized in that, Includes the following steps: step S10: Acquire holographic perception data of the road; Step S20: Based on the target type of the holographic sensing target in the holographic sensing data, detect whether the holographic sensing target has a tripod target. If so, proceed to step S30. Step S30: Based on the uniqueness of the number of the holographic sensing target, detect whether there is a record of the tripod target. If so, proceed to step S40. If not, proceed to step S41; Step S40: If the tripod target time is continuously detected to reach a predetermined threshold, then output a traffic accident event; Step S41: Detect whether the tripod target is on other holographic sensing targets. If not, proceed to step S42. Step S42: Record the detection start time of the tripod target and execute step S10. The detection start time is used to determine that the detection time of the tripod target has reached the predetermined threshold. The step of detecting whether the tripod target is on other holographic sensing targets includes: By determining whether the displacement generated by the tripod target reaches a displacement threshold within a predetermined time range, if the displacement threshold is reached, it is determined that the tripod target is on other holographic sensing targets.

2. The road traffic accident detection method based on holographic perception according to claim 1, characterized in that, The process following step S40 also includes: Step S50: Perform a secondary verification on the traffic accident event. If the detection meets the secondary verification criteria for traffic accidents, output the final traffic accident event.

3. The road traffic accident detection method based on holographic perception according to claim 2, characterized in that, Step S50 includes: Step S51: Check if the parking event is enabled. If not, proceed to step S53. Step S53: Detect whether the pedestrian event is enabled. If so, proceed to step S54. Step S54: Determine whether there is a pedestrian event within the time frame during which the tripod target is continuously detected and the time reaches a predetermined threshold. If so, proceed to step S55. Step S55: Output the final traffic accident event.

4. The road traffic accident detection method based on holographic perception according to claim 3, characterized in that, Step S51 further includes: If so, proceed to step S52; Step S52: Determine whether there is a parking event within the time frame during which the tripod target time is continuously detected to reach a predetermined threshold. If so, proceed to step S53.

5. A road traffic accident detection system based on holographic perception, characterized in that, include: Acquisition unit, used to acquire holographic perception data of the road; The first detection unit is used to detect whether the holographic sensing target has a tripod target based on the target type of the holographic sensing target in the holographic sensing data. If yes, the second detection unit is run; if no, the second detection unit is run. If no, the second detection unit is run. If no, the second detection unit is run. If no, the second detection unit is run. The third detection unit is run. The fourth detection unit is run. The fifth detection unit is run. The sixth detection unit is run. The seventh detection unit is run. The eighth detection unit is run. The ninth detection unit is run. The eighth ... The second detection unit is used to detect whether the tripod target record exists based on the uniqueness of the number of the holographic sensing target; if so, the judgment unit is executed. The judgment unit is used to output a traffic accident event if the continuous detection of the tripod target time reaches a predetermined threshold. The step of detecting whether the tripod target is on other holographic sensing targets includes: By determining whether the displacement generated by the tripod target reaches a displacement threshold within a predetermined time range, if the displacement threshold is reached, it is determined that the tripod target is on other holographic sensing targets.

6. The road traffic accident detection system based on holographic perception according to claim 5, characterized in that, The system also includes: The secondary verification unit is used to perform secondary verification on the traffic accident event. If the detection meets the secondary verification criteria for traffic accidents, the final traffic accident event is output.

7. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the holographic perception-based road traffic accident detection method as described in any one of claims 1-4.

8. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the road traffic accident detection method based on holographic perception as described in any one of claims 1-4.

Images