An obstacle vehicle identification method, device, equipment and storage medium

Abstract

The application discloses an obstacle vehicle identification method, device and equipment and a storage medium, and comprises the following steps: determining a target scene category of a vehicle driving scene according to a scene image and radar detection information of the vehicle driving scene; determining scene radar clutter according to the target scene category, and determining target radar echoes corresponding to obstacle vehicles in the vehicle driving scene according to the scene radar clutter and the radar detection information; and determining vehicle position information of the obstacle vehicles in the vehicle driving scene according to the target radar echoes. The position information of the obstacle vehicles can be accurately obtained according to the target radar echoes, the misidentification of the scene radar clutter is avoided, and the acquisition efficiency of the vehicle position information of the obstacle vehicles is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of computer, and particularly relate to an obstacle vehicle identification method, device, equipment and storage medium. BACKGROUND

[0002] With the development of automatic driving technology, more and more vehicles are equipped with blind area detection function. When an obstacle vehicle appears around the ego vehicle during the driving of the ego vehicle, the millimeter wave radar can timely identify the obstacle vehicle and determine the position information of the obstacle vehicle, and the indicator light on the left and right outside rearview mirror is always on or flashes, thereby prompting the driver of the ego vehicle that there is an obstacle vehicle around the vehicle and the driver needs to be cautious when changing lanes. When the millimeter wave radar detects the vehicle driving scene, the electromagnetic wave emitted by the millimeter wave radar hits the obstacle in the vehicle driving scene, and the radar echo reflected by the obstacle is obtained. The millimeter wave radar realizes the positioning of the obstacle through the received radar echo. However, for special scenes such as tunnel scenes or high-speed guardrail scenes, when the electromagnetic wave emitted by the millimeter wave radar hits the wall or guardrail, a high-intensity radar echo will also be received, which makes the radar judge that there is an obstacle vehicle behind, resulting in false positives of the obstacle vehicle. Therefore, how to improve the detection accuracy of the millimeter wave radar for the obstacle vehicle and ensure the driving safety of the ego vehicle is a problem to be solved. SUMMARY

[0003] The present application provides an obstacle vehicle identification method, device, equipment and storage medium, which can improve the accuracy of the position information of the obstacle vehicle obtained by the millimeter wave radar when detecting the obstacle vehicle, and ensure the driving safety of the ego vehicle.

[0004] According to an aspect of the present application, an obstacle vehicle identification method is provided, comprising:

[0005] determining a target scene category of the vehicle driving scene according to a scene image and radar detection information of the vehicle driving scene;

[0006] determining a target radar echo corresponding to an obstacle vehicle in the vehicle driving scene according to the target scene category, the scene radar clutter and the radar detection information;

[0007] determining vehicle position information of the obstacle vehicle in the vehicle driving scene according to the target radar echo.

[0008] According to another aspect of the present application, an obstacle vehicle identification device is provided, which comprises:

[0009] a target scene category determination module configured to determine a target scene category of the vehicle driving scene according to a scene image and radar detection information of the vehicle driving scene;

[0010] a target radar echo determination module configured to determine a target radar echo corresponding to the obstacle vehicle in the vehicle driving scene according to the target scene category, the scene radar clutter, and the radar detection information;

[0011] a vehicle position information determination module configured to determine vehicle position information of the obstacle vehicle in the vehicle driving scene according to the target radar echo.

[0012] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0013] at least one processor; and

[0014] a memory connected to the at least one processor in communication; wherein,

[0015] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the obstacle vehicle identification method according to any one of the embodiments of the present application.

[0016] According to another aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium stores computer instructions for enabling a processor to implement the obstacle vehicle identification method according to any one of the embodiments of the present application when executed by the processor.

[0017] The technical solution of the embodiments of the present application determines the target scene category of the vehicle driving scene according to the scene image and the radar detection information of the vehicle driving scene, determines the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene according to the target scene category and the scene radar clutter corresponding to the target scene category, and determines the vehicle position information of the obstacle vehicle in the vehicle driving scene according to the target radar echo. The above solution solves the problem that for special scenes such as tunnel scenes or high-speed guardrail scenes, when the electromagnetic wave emitted by the millimeter wave radar hits the wall or guardrail, the non-obstacle vehicle is identified as an obstacle vehicle, which leads to false reporting of the obstacle vehicle information and affects the driving safety of the ego vehicle. According to the scene category of the vehicle driving scene and the scene radar clutter corresponding to the scene category, the radar detection information obtained by the millimeter wave radar is processed to determine the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene, the accurate position information of the obstacle vehicle can be obtained according to the target radar echo, the misidentification of the scene radar clutter is avoided, and the efficiency of obtaining the vehicle position information of the obstacle vehicle is improved.

[0018] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of an obstacle vehicle identification method provided in Embodiment 1 of the present invention;

[0021] Figure 2 This is a flowchart of an obstacle vehicle identification method provided in Embodiment 2 of the present invention;

[0022] Figure 3 This is a schematic diagram of the structure of an obstacle vehicle recognition device provided in Embodiment 3 of the present invention;

[0023] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first" and "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "etc.", and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] Example 1

[0027] Figure 1A flowchart of an obstacle vehicle identification method is provided for Embodiment One of the present application. The present embodiment can be applied to the case of identifying an obstacle vehicle in a vehicle driving scene. The method can be performed by an obstacle vehicle identification device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. As shown in FIG. 6A, the method comprises the following steps. Figure 1

[0028] S110, determining a target scene category of the vehicle driving scene according to the scene image of the vehicle driving scene and the radar detection information.

[0029] The vehicle driving scene refers to the scene around the ego vehicle during driving. The vehicle driving scene can include pedestrians, static obstacles, and obstacle vehicles. The target scene category can be a guardrail scene, a tunnel scene, a jungle scene, or a regular scene. The guardrail scene refers to a vehicle driving scene in which a certain number of road guardrails are installed. When the electromagnetic wave emitted by the millimeter wave radar hits the road guardrails in the guardrail scene, the millimeter wave radar can receive a high-intensity radar echo, causing the millimeter wave radar to identify the road guardrails as obstacle vehicles. When the electromagnetic wave emitted by the millimeter wave radar hits the walls on both sides of the tunnel in the tunnel scene, the millimeter wave radar can also receive a high-intensity radar echo, causing the millimeter wave radar to identify the walls in the tunnel as obstacle vehicles. The jungle scene often has many trees. When the electromagnetic wave emitted by the millimeter wave radar hits the trees, the millimeter wave radar can receive a weak radar echo. Therefore, when the radar echo is weak, it can be considered that the obstacle corresponding to the radar echo is not an obstacle vehicle.

[0030] Specifically, during driving of the ego vehicle, the scene image of the vehicle driving scene is acquired by an image acquisition device, and the radar detection information of the vehicle driving scene is acquired by the millimeter wave radar installed on the ego vehicle. According to the scene image and the radar detection information, the target scene category of the vehicle driving scene is determined from the candidate scene categories. The candidate scene categories include: a guardrail scene, a tunnel scene, a jungle scene, and a regular scene.

[0031] For example, the method of determining the target scene category of the vehicle driving scene can be: acquiring the scene image of the vehicle driving scene collected by the image acquisition device, and determining the scene features in the scene image; determining the feature distances between the scene features according to the radar detection information, and determining the target scene category of the vehicle driving scene according to the scene features and the feature distances.

[0032] The scene features refer to feature information representing the target scene category. The scene features can be: guardrail features, tunnel features, and tree features.

[0033] ​Specifically, the process involves acquiring scene images of the vehicle driving scenario captured by an image acquisition device, and then extracting scene features from these images using a feature extraction algorithm. Millimeter-wave radar detection information is used to obtain radar detection information, which is then used to determine the feature location information of the scene features. Based on the feature location information, the feature distances between scene features are determined. Finally, based on the scene features, feature distances, and candidate features corresponding to each candidate scene category and the candidate distances between candidate features, the target scene category of the vehicle driving scenario is determined from the candidate scene categories.

[0034] For example, when the scene features include tree features, the distance between tree features is determined. If the number of tree features and the distance between tree features meet the preset feature distance conditions for a jungle scene, then the target scene category is determined to be a jungle scene.

[0035] Understandably, determining the feature distance between scene features in a scene image based on the radar detection information from millimeter-wave radar, and then determining the target scene category based on the feature distance and scene features, can avoid misidentification of the target scene category when the distance between scene features is large, thus improving the accuracy of the determined target scene category.

[0036] S120. Determine the scene radar clutter according to the target scene category, and determine the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene based on the scene radar clutter and radar detection information.

[0037] Among them, scene radar clutter refers to the radar echoes reflected by obstacles other than non-obstacle vehicles when the electromagnetic waves of millimeter-wave radar hit the obstacles.

[0038] Specifically, based on the target scene category, the clutter characteristic information of the scene radar clutter generated by scene features within that category can be determined. This clutter characteristic information can include the frequency and loudness of the scene radar clutter. Different scene features correspond to different scene radar clutter characteristic information. For example, compared to the radar echo corresponding to obstacle vehicles, the scene radar clutter corresponding to scene features in tunnel scenes and guardrail scenes has a higher frequency, while the scene radar clutter corresponding to scene features in jungle scenes has a lower frequency and loudness. Radar detection echoes are determined based on radar detection information. Radar detection echoes refer to the radar echoes reflected by obstacles when electromagnetic waves emitted by millimeter-wave radar hit obstacles in a vehicle-moving scene. Based on the clutter characteristic information of the scene radar clutter, radar echoes reflected by obstacles other than obstacle vehicles are determined from the radar detection echoes. These radar echoes are then removed from the radar detection echoes, and the radar detection echoes remaining after removing these obstacle echoes are taken as the target radar echoes corresponding to obstacle vehicles in the vehicle-moving scene.

[0039] S130. Determine the vehicle position information of obstacle vehicles in the vehicle driving scene based on the target radar echo.

[0040] Specifically, the target radar echo is converted into an electrical signal by millimeter-wave radar, and the converted electrical signal is analyzed to determine the vehicle position information of the obstacle vehicle in the vehicle driving scene, as well as the distance between the obstacle vehicle and the vehicle.

[0041] For example, based on the echo change trend of the target radar echo, it can be determined whether there are duplicate radar echoes corresponding to the same obstacle vehicle in the target radar echo; if so, a third echo to be deleted is determined from the duplicate radar echoes, and the third echo to be deleted is removed from the target radar echo to determine the vehicle radar echo, and the vehicle position information of the obstacle vehicle in the vehicle driving scene is determined based on the vehicle radar echo.

[0042] Among them, repeated radar echoes refer to at least two radar echoes reflected by an obstacle vehicle after the electromagnetic waves emitted by millimeter-wave radar hit the obstacle vehicle. The third echo to be deleted refers to repeated radar echoes that need to be deleted.

[0043] Understandably, identifying repeating radar echoes corresponding to the same obstacle vehicle from the target radar echoes based on their echo patterns, and then eliminating these repeating echoes, can prevent the identification of different obstacle vehicles based on repeating echoes corresponding to the same obstacle vehicle. This avoids errors in identifying the obstacle vehicle's position information and could affect the vehicle's driving safety. Therefore, this method improves the accuracy of obstacle vehicle position information and ensures the vehicle's driving safety.

[0044] The technical solution provided in this embodiment determines the target scene category of the vehicle driving scene based on scene images and radar detection information; determines scene radar clutter based on the target scene category; and determines the target radar echo corresponding to an obstacle vehicle in the vehicle driving scene based on the scene radar clutter and radar detection information; and determines the vehicle position information of the obstacle vehicle in the vehicle driving scene based on the target radar echo. This solution solves the problem that in special scenarios such as tunnels or highway guardrails, when the electromagnetic waves emitted by millimeter-wave radar hit walls or guardrails, they may identify non-obstacle vehicles as obstacle vehicles, leading to false alarms of obstacle vehicle information and affecting the driving safety of the vehicle. By processing the radar detection information acquired by the millimeter-wave radar according to the scene category of the vehicle driving scene and the scene radar clutter corresponding to the scene category, the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene can be determined. Accurate obstacle vehicle position information can be obtained based on the target radar echo, avoiding false identification of scene radar clutter and improving the efficiency of obtaining obstacle vehicle position information.

[0045] Example 2

[0046] Figure 2 This is a flowchart of an obstacle vehicle identification method provided in Embodiment 2 of the present invention. This embodiment optimizes the above embodiment and provides a preferred implementation method that determines scene radar clutter based on the target scene category and determines the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene based on the scene radar clutter and radar detection information. Specifically, as shown... Figure 2 As shown, the method includes:

[0047] S210. Based on the scene image and radar detection information of the vehicle driving scene, determine the target scene category of the vehicle driving scene.

[0048] S220. Based on the target scene category and the correspondence between candidate scene categories and candidate radar clutter, determine the scene radar clutter corresponding to the target scene category from the candidate radar clutter.

[0049] Candidate scene categories include: guardrail scenes, tunnel scenes, jungle scenes, and regular scenes.

[0050] Among them, candidate radar clutter refers to the scene radar clutter corresponding to the candidate scene category.

[0051] Specifically, the correspondence between candidate scene categories and candidate radar clutter is pre-determined. Based on this correspondence, the candidate radar clutter corresponding to the target scene category is identified as the scene radar clutter.

[0052] S230. Extract radar detection echoes from radar detection information, and filter and screen the radar detection echoes according to scene radar clutter to determine the target radar echoes corresponding to obstacle vehicles in the vehicle driving scene.

[0053] Among them, radar detection echo refers to the radar echo reflected by an obstacle when the electromagnetic waves emitted by millimeter-wave radar hit an obstacle in a vehicle driving scene.

[0054] Specifically, radar detection echoes are extracted from radar detection information, and the radar detection echoes are filtered and screened based on scene radar clutter. Radar echoes with high similarity to scene radar clutter are removed from the radar detection echoes, and the filtered radar detection echoes are used as target radar echoes corresponding to obstacle vehicles in the vehicle driving scene.

[0055] For example, the target radar echo corresponding to an obstacle vehicle in a vehicle driving scenario can also be determined through the following sub-steps:

[0056] S2301. Based on the scene radar clutter, determine the first echo to be deleted from the radar detection echo, and remove the first echo to be deleted from the radar detection echo to determine the radar echo to be processed.

[0057] Among them, the first echo to be deleted refers to the radar echo in the radar detection echo that has a high similarity to the scene radar clutter.

[0058] For example, a method for determining the first echo to be deleted from radar detection echoes may be: using a dynamic time warping algorithm to perform similarity matching on candidate detection echoes in scene radar clutter and radar detection echoes to determine the echo similarity between candidate detection echoes and scene radar clutter; and determining the first echo to be deleted from candidate detection echoes based on the echo similarity and a preset similarity threshold.

[0059] The above scheme determines the candidate detection echo with a high similarity to the scene radar clutter as the first echo to be deleted based on the echo similarity between the candidate detection echoes in the scene radar clutter and the radar detection echoes, which can improve the acquisition efficiency of the first echo to be deleted.

[0060] S2302. Based on the preset basic radar clutter, determine the second echo to be deleted from the radar echo to be processed, and remove the second echo to be deleted from the radar echo to be processed, thereby determining the target radar echo corresponding to the obstacle vehicle in the vehicle driving scenario.

[0061] Basic radar clutter refers to radar echoes reflected from obstacles other than other vehicles, trees, road guardrails, and tunnel walls that may exist in the vehicle's driving scenario. For example, other obstacles could be pedestrians in the vehicle's driving scenario.

[0062] Specifically, a dynamic time warping algorithm is used to perform similarity matching between the basic radar clutter and the radar echoes to be processed, determining the similarity between the radar echoes to be processed and the basic radar clutter. Based on a preset similarity threshold and the similarity between the radar echoes to be processed and the basic radar clutter, a second echo to be deleted is determined from the radar echoes to be processed. The second echo to be deleted is removed from the radar echoes to be processed, thus determining the target radar echo corresponding to the obstacle vehicle in the vehicle driving scenario.

[0063] It is understandable that removing scene radar clutter and basic radar clutter fed back by non-obstacle vehicles and scene features in the vehicle driving scene from the radar detection echo can help determine the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene, thereby avoiding the inclusion of radar clutter fed back by other obstacles in the target radar echo and improving the accuracy of the target radar echo.

[0064] S240. Determine the vehicle position information of obstacle vehicles in the vehicle driving scene based on the target radar echo.

[0065] The technical solution of this embodiment determines the target scene category of the vehicle driving scene based on scene images and radar detection information. Based on the target scene category and the correspondence between candidate scene categories and candidate radar clutter, the scene radar clutter corresponding to the target scene category is determined from the candidate radar clutter. Radar detection echoes are extracted from the radar detection information, and the radar detection echoes are filtered and selected based on the scene radar clutter to determine the target radar echoes corresponding to obstacle vehicles in the vehicle driving scene. The vehicle position information of obstacle vehicles in the vehicle driving scene is determined based on the target radar echoes. This solution, by determining the scene radar clutter corresponding to the target scene category based on the pre-set correspondence between candidate scene categories and candidate radar clutter when determining the target radar echoes, can improve the efficiency of scene radar clutter determination, thereby improving the efficiency of radar detection echo filtering and ensuring the real-time nature of the acquired vehicle position information. Filtering and selecting radar detection echoes based on scene radar clutter can avoid misidentification of scene radar clutter, improve the accuracy of the acquired obstacle vehicle position information, and ensure the driving safety of the vehicle.

[0066] Example 3

[0067] Figure 3 This is a schematic diagram of an obstacle vehicle recognition device provided in Embodiment 3 of the present invention. This embodiment is applicable to situations where obstacle vehicles are identified in a vehicle driving scenario. Figure 3 As shown, the obstacle vehicle recognition device includes: a target scene category determination module 310, a target radar echo determination module 320, and a vehicle position information determination module 330.

[0068] The target scene category determination module 310 is used to determine the target scene category of the vehicle driving scene based on the scene image and radar detection information of the vehicle driving scene.

[0069] The target radar echo determination module 320 is used to determine scene radar clutter according to the target scene category, and to determine the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene according to the scene radar clutter and radar detection information.

[0070] The vehicle position information determination module 330 is used to determine the vehicle position information of obstacle vehicles in the vehicle driving scene based on the target radar echo.

[0071] The technical solution provided in this embodiment determines the target scene category of the vehicle driving scene based on scene images and radar detection information; determines scene radar clutter based on the target scene category; and determines the target radar echo corresponding to an obstacle vehicle in the vehicle driving scene based on the scene radar clutter and radar detection information; and determines the vehicle position information of the obstacle vehicle in the vehicle driving scene based on the target radar echo. This solution solves the problem that in special scenarios such as tunnels or highway guardrails, when the electromagnetic waves emitted by millimeter-wave radar hit walls or guardrails, they may identify non-obstacle vehicles as obstacle vehicles, leading to false alarms of obstacle vehicle information and affecting the driving safety of the vehicle. By processing the radar detection information acquired by the millimeter-wave radar according to the scene category of the vehicle driving scene and the scene radar clutter corresponding to the scene category, the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene can be determined. Accurate obstacle vehicle position information can be obtained based on the target radar echo, avoiding false identification of scene radar clutter and improving the efficiency of obtaining obstacle vehicle position information.

[0072] For example, the target radar echo determination module 320 includes:

[0073] The scene radar clutter determination unit is used to determine the scene radar clutter corresponding to the target scene category from the candidate radar clutter based on the target scene category and the correspondence between candidate scene categories and candidate radar clutter; the candidate scene categories include: guardrail scene, tunnel scene, jungle scene and regular scene;

[0074] The target radar echo determination unit is used to extract radar detection echoes from radar detection information, and filter and screen the radar detection echoes according to scene radar clutter to determine the target radar echoes corresponding to obstacle vehicles in the vehicle driving scene.

[0075] For example, a target radar echo determination unit includes:

[0076] The echo to be processed determination subunit is used to determine the first echo to be deleted from the radar detection echo based on the scene radar clutter, and remove the first echo to be deleted from the radar detection echo to determine the radar echo to be processed.

[0077] The target echo determination subunit is used to determine the second echo to be deleted from the radar echo to be processed based on the preset basic radar clutter, and to remove the second echo to be deleted from the radar echo to be processed, thereby determining the target radar echo corresponding to the obstacle vehicle in the vehicle driving scenario.

[0078] For example, the echo determination subunit is specifically used for:

[0079] A dynamic time warping algorithm is used to perform similarity matching on candidate detection echoes in scene radar clutter and radar detection echoes to determine the echo similarity between candidate detection echoes and scene radar clutter.

[0080] Based on echo similarity and a preset similarity threshold, the first echo to be deleted is determined from the candidate probe echoes.

[0081] For example, the target scene category determination module 310 is specifically used for:

[0082] Acquire scene images of vehicle driving scenes captured by image acquisition devices, and determine scene features in the scene images;

[0083] The feature distances between scene features are determined based on radar detection information, and the target scene category of the vehicle driving scene is determined based on the scene features and feature distances.

[0084] For example, the vehicle location information determination module 330 is specifically used for:

[0085] Based on the echo change trend of the target radar echo, determine whether there are duplicate radar echoes corresponding to the same obstacle vehicle in the target radar echo;

[0086] If so, the third echo to be deleted is determined from the repeated radar echoes, and the third echo to be deleted is removed from the target radar echoes to determine the vehicle radar echo. The vehicle position information of the obstacle vehicle in the vehicle driving scene is determined based on the vehicle radar echo.

[0087] The obstacle vehicle recognition device provided in this embodiment can be applied to any of the obstacle vehicle recognition methods provided in the above embodiments, and has the corresponding functions and beneficial effects.

[0088] Example 4

[0089] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0090] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0091] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0092] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as obstacle vehicle recognition methods.

[0093] In some embodiments, the obstacle vehicle recognition method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the obstacle vehicle recognition method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the obstacle vehicle recognition method by any other suitable means (e.g., by means of firmware).

[0094] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0095] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0096] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0097] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0098] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0099] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0100] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0101] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for identifying obstructed vehicles, characterized in that, include: Based on the scene images and radar detection information of the vehicle driving scene, the target scene category of the vehicle driving scene is determined; The scene radar clutter is determined according to the target scene category, and the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene is determined according to the scene radar clutter and the radar detection information. The vehicle position information of the obstacle vehicle in the vehicle driving scene is determined based on the target radar echo.

2. The method according to claim 1, characterized in that, Based on the target scene category, scene radar clutter is determined, and based on the scene radar clutter and the radar detection information, the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene is determined, including: Based on the target scene category and the correspondence between candidate scene categories and candidate radar clutter, the scene radar clutter corresponding to the target scene category is determined from the candidate radar clutter; the candidate scene categories include: guardrail scene, tunnel scene, jungle scene and conventional scene; The radar detection echo is extracted from the radar detection information, and the radar detection echo is filtered and screened according to the scene radar clutter to determine the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene.

3. The method according to claim 2, characterized in that, The radar echoes are filtered and selected based on scene radar clutter to determine the target radar echoes corresponding to obstacle vehicles in the vehicle driving scene, including: Based on the scene radar clutter, a first echo to be deleted is determined from the radar detection echo, and the first echo to be deleted is removed from the radar detection echo to determine the radar echo to be processed. Based on the preset basic radar clutter, a second echo to be deleted is determined from the radar echoes to be processed, and the second echo to be deleted is removed from the radar echoes to be processed, thereby determining the target radar echo corresponding to the obstacle vehicle in the vehicle driving scenario.

4. The method according to claim 3, characterized in that, Based on the scene radar clutter, the first echo to be deleted is determined from the radar detection echo, including: A dynamic time warping algorithm is used to perform similarity matching between the scene radar clutter and the candidate detection echo in the radar detection echo, and to determine the echo similarity between the candidate detection echo and the scene radar clutter. Based on the echo similarity and a preset similarity threshold, the first echo to be deleted is determined from the candidate probe echoes.

5. The method according to claim 1, characterized in that, Based on scene images and radar detection information of the vehicle driving scenario, the target scene category of the vehicle driving scenario is determined, including: Acquire scene images of a vehicle driving scene captured by an image acquisition device, and determine the scene features in the scene images; The feature distance between the scene features is determined based on the radar detection information, and the target scene category of the vehicle driving scene is determined based on the scene features and the feature distance.

6. The method according to claim 1, characterized in that, The vehicle position information of obstacle vehicles in the vehicle driving scene is determined based on the target radar echo, including: Based on the echo change trend of the target radar echo, determine whether there are duplicate radar echoes corresponding to the same obstacle vehicle in the target radar echo; If so, the third echo to be deleted is determined from the repeated radar echoes, and the third echo to be deleted is removed from the target radar echoes to determine the vehicle radar echo. The vehicle position information of the obstacle vehicle in the vehicle driving scene is determined based on the vehicle radar echo.

7. An obstacle vehicle identification device, characterized in that, include: The target scene category determination module is used to determine the target scene category of the vehicle driving scene based on the scene image and radar detection information of the vehicle driving scene; The target radar echo determination module is used to determine scene radar clutter according to the target scene category, and to determine the target radar echo corresponding to the obstacle vehicle in the vehicle driving scene according to the scene radar clutter and the radar detection information. The vehicle position information determination module is used to determine the vehicle position information of obstacle vehicles in the vehicle driving scene based on the target radar echo.

8. The apparatus according to claim 7, characterized in that, The target radar echo determination module also includes: The scene radar clutter determination unit is used to determine the scene radar clutter corresponding to the target scene category from the candidate radar clutter based on the target scene category and the correspondence between candidate scene categories and candidate radar clutter; the candidate scene categories include: guardrail scene, tunnel scene, jungle scene and conventional scene; The target radar echo determination unit is used to extract radar detection echoes from radar detection information, and filter and screen the radar detection echoes according to scene radar clutter to determine the target radar echoes corresponding to the obstacle vehicles in the vehicle driving scene.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the obstacle vehicle recognition method according to any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the obstacle vehicle recognition method according to any one of claims 1-6.

Images