A method for all-weather detection of traffic incidents based on millimeter-wave radar

Abstract

The embodiment of the present invention discloses an all-weather detection method for traffic incidents based on millimeter-wave radar, and the field of road traffic technology. The method includes: In the first aspect, the embodiment of the present invention provides an all-weather detection method for traffic incidents based on millimeter-wave radar, including: obtaining at least one target object that is preliminarily judged to be in a stopped state through multiple millimeter-wave radars along the entire highway; judging whether the historical maximum speed of each target object is greater than a first threshold; if so, judging whether the current speed of each target object is less than a second threshold, wherein the second threshold is less than the first threshold; if so, judging whether the position difference between the current frame and the previous frame of each target object is less than a set range; if so, generating and reporting parking events for each target object. This embodiment solves the problems of insufficient location accuracy of traffic incident detection, low accuracy of detection of severe weather events at night, and coverage perception in the prior art.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of road traffic technology, and in particular to an all-weather detection method for traffic incidents based on millimeter-wave radar. Background Art

[0002] Traffic incidents refer to abnormal traffic conditions and behaviors on the road that affect the passage of vehicles and traffic safety, mainly including typical types of incidents such as stopping incidents, wrong-way incidents, pedestrian incidents, spilled objects incidents, congestion incidents, and motor vehicle departure incidents.

[0003] Existing highway video traffic event detectors mainly rely on monitoring videos along the highway to analyze traffic events, and the specifications adopted are the National Standard of the People's Republic of China GB / T 28789-2012. After converting the camera video signal (digital or analog), the video traffic event detector uses three core technologies: video-based moving object detection, target tracking and pattern recognition, to achieve real-time monitoring of the event process that affects the normal traffic order on the road, and analyze the operating status and road condition information of motor vehicles on the road. When abnormal road driving conditions are found (such as parking, reverse driving, pedestrians, congestion, spilled objects, etc.), an alarm is immediately sent to the client.

[0004] This method has the following defects: 1) The event pile number is provided according to the location of the road test monitoring camera (generally at the kilometer level), but the specific location and lane of the event cannot be determined, and the video needs to be manually checked to determine the scope of the event and the affected lane; 2) At night or in bad weather conditions, the accuracy of event perception is greatly reduced, resulting in a large number of false alarms and missed reports. 3) In highway applications, since cameras are installed back-to-back in pairs per kilometer, the perception coverage of two adjacent cameras reaches 1 kilometer. At present, the effective detection range of the video event detector is about 200 to 250 meters, and there is a blind spot of about 30 to 50 meters below the camera, that is, the actual effective perception range of the video event detector is 30 to 250 meters, which is difficult to achieve coverage perception on highways, resulting in a large number of missed events. Summary of the invention

[0005] An embodiment of the present invention provides an all-weather detection method for traffic incidents based on millimeter-wave radar to solve at least one of the above technical problems.

[0006] In a first aspect, an embodiment of the present invention provides an all-weather detection method for traffic incidents based on millimeter-wave radar, comprising:

[0007] Using multiple millimeter-wave radars along the entire highway, at least one target object is initially determined to be in a stopped state;

[0008] Determine whether the historical maximum speed of each target object is greater than a first threshold;

[0009] If yes, determining whether the current speed of each target object is less than a second threshold, wherein the second threshold is less than the first threshold;

[0010] If yes, determine whether the position difference between the current frame and the previous frame of each target object is less than the set range;

[0011] If yes, generate and report parking events for each target object.

[0012] In a second aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0013] one or more processors;

[0014] a memory for storing one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the all-weather detection method for traffic incidents based on millimeter-wave radar as described in any embodiment.

[0016] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the all-weather detection method for traffic incidents based on millimeter-wave radar as described in any embodiment.

[0017] In summary, the embodiment of the present invention detects target objects along the entire highway based on millimeter-wave radar, and can realize all-weather perception at night and in adverse weather conditions such as rain, school, and fog. Relying on the parking / accident event perception method of this patent, it can realize all-weather kilometer-level (road section level) coverage perception of traffic events; analyze the real-time data of each vehicle target, and gradually determine the parking conditions from the perspectives of current speed, historical maximum speed, and front and rear frame position movement, thereby improving the accuracy of parking status recognition and completing event production. The above methods jointly solve the problems of insufficient location accuracy of traffic event detection, low accuracy of nighttime adverse weather event detection, and coverage perception in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 is a flow chart of an all-weather detection method for traffic incidents based on millimeter-wave radar provided by an embodiment of the present invention;

[0020] Figure 2 This is a flow chart of a full-segment parking event judgment provided by an embodiment of the present invention;

[0021] Figure 3 This is a flow chart of a radar stopping vehicle detection provided by an embodiment of the present invention;

[0022] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0024] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0025] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0026] Figure 1 1 is a flow chart of a method for all-weather detection of traffic incidents based on millimeter wave radar provided by an embodiment of the present invention. The method is applicable to the detection of parking incidents and accident incidents on expressways and is executed by electronic equipment. Figure 1 As shown, the method specifically includes:

[0027] S110. Acquire at least one target object that is preliminarily determined to be in a stopped state by using multiple millimeter-wave radars along the entire highway.

[0028] The traffic events in this embodiment mainly refer to parking events and accident events. In order to achieve all-weather detection of traffic events, this embodiment uses millimeter-wave radar to collect real-time vehicle information of all lines and sections as the data source of the entire method. Compared with traditional video detection technology, millimeter-wave radar is not affected by light and weather, and can achieve all-weather detection of traffic events.

[0029] Optionally, the millimeter wave radar can obtain data such as the position, speed, acceleration, etc. of the vehicle, and analyze the vehicle status in real time based on these data. In a specific embodiment, each millimeter wave radar performs the following operations: identify at least one vehicle from the current frame detection data; determine whether the vehicle is in a parked state based on the speed, position, and orientation detection of each vehicle, thereby identifying the parked vehicle as a preliminary identification mechanism for the parked vehicle of the entire method; then, correct the position of the parked vehicle through multiple frames of continuous detection data; and report the corrected parked vehicle and its position as a target object preliminarily determined to be in a parked state.

[0030] It should be emphasized that the data uploaded at this time is the target data of the parked vehicle determined by the radar, but for the electronic device receiving the data, the data is only a preliminary recognition result and is not completely accurate. In fact, these targets may be parked vehicles, or they may be low-speed vehicles or other low-speed objects, such as objects thrown by vehicles, etc. Therefore, it is necessary to execute S120-S140 to further determine whether the object is a parked vehicle.

[0031] S120: Determine whether the historical maximum speed of each target object is greater than a first threshold.

[0032] S130: If yes, determine whether the current speed of each target object is less than a second threshold, wherein the second threshold is less than the first threshold.

[0033] S140: If yes, determine whether the position difference between the current frame and the previous frame of each target object is less than a set range.

[0034] Optionally, the first threshold is 2 m / s, the second threshold is 8 m / s, and the setting range is [-0.15, 0.15]. That is, if the target object satisfies the following conditions in sequence, it can be determined that it is a vehicle in a parked state:

[0035]

[0036] Where V represents the current speed of the target object, V max is the historical maximum speed of the target object, (x, y) represents the current position of the target object, (x pre ,y pre) is the position of the target object in the previous frame. In the above conditions, V<2m / s is used to determine that the target object's speed is low enough, V max >8m / s is used to determine that the target object is not an object that is continuously traveling at a low speed, and the remaining two conditions are used to finally determine that the target object is not an object that is traveling at a low speed. When the three conditions are met at the same time, it can be determined that it is a vehicle in a stopped state.

[0037] Optionally, before S120, it is also possible to first determine whether each target object is a spilled object. If not, subsequent operations are performed; if not, the determination process for the current target object is terminated. Optionally, it is possible to determine whether each target object is a spilled object based on the size of each target object. For example, an object with a size less than 3m is a spilled object (the length of a vehicle is generally greater than 5m). In this way, the accuracy of the determination of parking events can be further improved.

[0038] S150: If yes, determine whether each target object corresponds to a parking event.

[0039] After S120-S140, if the current target object is determined to be a vehicle in a stopped state, a parking event is generated. After each target object is judged, the number of vehicles in a stopped state on the entire line is counted, and an event number is assigned to the parking event to form an event reporting structure for reporting. The above overall process is as follows Figure 2 shown.

[0040] Furthermore, in a specific embodiment, the process of the millimeter-wave radar preliminarily reporting a stopped vehicle may also include the following method: each millimeter-wave radar distributed along the entire highway performs the following operations respectively: two lists (a parking list and a start-stop mapping table) are created and initialized to 0, wherein the parking list is used to record the ID, location and other information of the parked vehicles identified by the millimeter-wave radar, and the start-stop mapping table is used to record each starting trajectory, starting position, and the vehicle ID corresponding to the trajectory. After the millimeter-wave radar obtains each frame of detection data, it first traverses its parking mapping list and maps the starting target ID in the current frame to the ID before parking; then it determines the area, vehicle type and speed of each target, identifies the stopped vehicle (i.e., the parking target), and adds the parking target to the parking list; then it corrects the parking position and associates the just-started track with the track in the parking list: if the starting position of a starting track and the position of a vehicle in the parking list meet the similarity condition (the distance is less than the set threshold and is closest), the vehicle ID in the parking list is associated with the starting track; finally, the vehicle and its position in the parking list that are not associated with the starting track are reported as target objects that are preliminarily judged to be in a stopped state. That is, the parking list records the stopped vehicles of the historical frame and the current frame. If the vehicle is associated with the starting track, it means that the stopped vehicle has started. However, in order to record the start and stop history of the vehicle, the vehicle will not be directly deleted from the parking list, but will be marked as a starting vehicle according to the association relationship, thereby excluding it from the reporting range. The entire process is as follows: Figure 3 shown.

[0041] In another specific implementation, after the millimeter wave radar performs the above-mentioned association matching, it reports the information in the parking list and the association relationship to the electronic equipment of the entire road section, and the electronic equipment generates a parking event after performing S120-S140 judgment based on the information in the parking list, and then marks the historical parking events and the newly generated parking events based on the association relationship to record the start and stop history of each vehicle. This method can record the start and stop history of each vehicle from the perspective of the entire road section, which is more conducive to the target management of vehicles in the entire road section.

[0042] In summary, this embodiment detects target objects along the entire expressway based on millimeter-wave radar, and can realize all-weather perception at night and in adverse weather conditions such as rain, school, and fog. Relying on this patented parking / accident event perception method, it can realize all-weather kilometer-level (road section-level) coverage perception of traffic events; analyze the real-time data of each vehicle target, and gradually determine the parking conditions from the perspectives of current speed, historical maximum speed, and front and rear frame position movement, thereby improving the accuracy of parking status recognition; for single radar data, a parking list and a start-stop mapping table are constructed based on each frame of real-time data, and the vehicle start-stop track data is associated with the parking list to realize vehicle target ID association, thereby assisting in event production. The above methods jointly solve the problems of insufficient location accuracy of traffic event detection, low accuracy of nighttime adverse weather event detection, and coverage perception in the prior art.

[0043] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of processors 60 in the device can be one or more. Figure 4 A processor 60 is taken as an example; the processor 60, the memory 61, the input device 62 and the output device 63 in the device can be connected by a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0044] The memory 61 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the all-weather detection method for traffic incidents based on millimeter-wave radar in the embodiment of the present invention. The processor 60 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 61, that is, realizing the above-mentioned all-weather detection method for traffic incidents based on millimeter-wave radar.

[0045] The memory 61 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 61 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 61 may further include a memory remotely arranged relative to the processor 60, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0046] The input device 62 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 63 may include a display device such as a display screen.

[0047] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the all-weather detection method for traffic incidents based on millimeter-wave radar of any embodiment.

[0048] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0049] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0050] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0051] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0052] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for all-weather detection of traffic incidents based on millimeter-wave radar, characterized in that: include: Each millimeter-wave radar distributed along the entire highway performs the following operations respectively: a parking list and a start-stop mapping table are created and initialized to 0, wherein the parking list is used to record the ID and position information of the parked vehicle identified by the millimeter-wave radar, and the start-stop mapping table is used to record each just-started track, the starting position, and the vehicle ID corresponding to the track; after the millimeter-wave radar obtains each frame of detection data, it first traverses the start-stop mapping table and maps the starting target ID in the current frame to the ID before parking; then the area, vehicle type and speed of each target are determined, the stopped vehicle is identified, and the stopped vehicle is added to the parking list; then the parking position is corrected, and the just-started track is associated with the track in the parking list: if the starting position of a starting track and the position of a vehicle in the parking list meet the similarity condition, the vehicle ID in the parking list is associated with the starting track; finally, the vehicle and its position in the parking list that are not associated with the starting track are reported as target objects that are preliminarily judged to be in a stopped state, and the information and association relationship in the parking list are reported at the same time; wherein the similarity condition is that the distance is less than a set threshold and is the closest; According to the information in the parking list, it is determined whether the historical maximum speed of each target object is greater than a first threshold, wherein the first threshold is 8 m / s, and this condition is used to determine that the target object is not an object that is continuously traveling at a low speed; if the historical maximum speed of each target object is greater than the first threshold, it is determined whether the current speed of each target object is less than a second threshold, wherein the second threshold is 2 m / s, and this condition is used to determine that the traveling speed of the target object is low enough; if the current speed of each target object is less than the second threshold, it is determined whether the position difference between the current frame and the previous frame of each target object is less than a set range, and this condition is used to finally determine that the target object is not an object that is traveling at a low speed; if the position difference between the current frame and the previous frame of each target object is less than a set range, it is determined that each target object corresponds to a parking event, and the historical parking events and the newly generated parking events are marked according to the association relationship to record the start and stop history.

2. The method according to claim 1, characterized in that Before determining whether the historical maximum speed of each target object is greater than the first threshold, the method further includes: Determine whether each target object is a spilled object, and if not, perform subsequent operations.

3. The method according to claim 2, characterized in that The step of determining whether each target object is a thrown object comprises: Based on the size and speed of each target object in the millimeter-wave radar detection data, it is determined whether each target object is a scattered object.

4. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the all-weather detection method for traffic incidents based on millimeter-wave radar as described in any one of claims 1-3.

5. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the all-weather detection method for traffic incidents based on millimeter-wave radar as described in any one of claims 1-3 is implemented.

Images