Obstacle position determination method, apparatus, and electronic device

Abstract

The present disclosure provides a method and device for determining the position of an obstacle and an electronic device, and relates to the technical field of artificial intelligence such as environment perception and automatic driving. The specific implementation scheme is: when determining the position of the obstacle, the scene image of the road to be detected can be recognized first to determine the first obstacle included in the scene image; the scene point cloud data of the road to be detected is recognized to determine the second obstacle included in the scene point cloud data; then the first obstacle and the second obstacle are matched, and the position of the first obstacle is determined according to the matching result. In this way, the position of the first obstacle can be effectively determined in combination with the scene point cloud data, thereby improving the accuracy of the determined position of the first obstacle.

Description

Technical Field

[0001] This disclosure relates to the field of image processing technology, and more particularly to the field of artificial intelligence technology such as environmental perception and autonomous driving, specifically to a method, apparatus and electronic device for determining the location of an obstacle. Background Technology

[0002] In autonomous driving scenarios, accurately identifying the location of obstacles on the road is crucial for improving the safety of autonomous driving.

[0003] In existing technologies, when identifying the location of obstacles on the road, the location of obstacles is usually determined based on the scene images of the road captured by a monocular camera set at the front of the vehicle.

[0004] However, due to the lack of depth information, the accuracy of determining the location of obstacles is relatively low. Summary of the Invention

[0005] This disclosure provides a method, apparatus, and electronic device for determining the location of obstacles, which improves the accuracy of obstacle location determination based on scene images.

[0006] According to a first aspect of this disclosure, a method for determining the location of an obstacle is provided, the method comprising:

[0007] The scene image of the road to be detected is identified to determine the first obstacle included in the scene image.

[0008] The scene point cloud data of the road to be detected is identified to determine the second obstacle included in the scene point cloud data.

[0009] The first obstacle and the second obstacle are matched, and the position of the first obstacle is determined based on the matching result.

[0010] According to a second aspect of this disclosure, an obstacle location determination device is provided, which may include:

[0011] The first determining unit is used to identify the scene image of the road to be detected and determine the position of the first obstacle in the scene image.

[0012] The second determining unit is used to identify the scene point cloud data of the road to be detected and determine the second obstacle included in the scene point cloud data.

[0013] The processing unit is used to match the first obstacle and the second obstacle, and determine the position of the first obstacle based on the matching result.

[0014] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the obstacle location determination method described in the first aspect above.

[0018] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the obstacle location determination method described in the first aspect above.

[0019] According to a fifth aspect of this disclosure, a computer program product is provided, the computer program product comprising: a computer program stored in a readable storage medium, wherein at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the obstacle location determination method described in the first aspect above.

[0020] According to the technical solution disclosed herein, the accuracy of obstacle location determination based on scene images is improved.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0022] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0023] Figure 1 This is a flowchart illustrating the method for determining the location of an obstacle according to the first embodiment of this disclosure;

[0024] Figure 2 This is a flowchart illustrating a method for determining the position of a first obstacle based on a matching result, according to a second embodiment of this disclosure.

[0025] Figure 3 This is a schematic diagram of the obstacle location determination device provided according to the third embodiment of this disclosure;

[0026] Figure 4This is a schematic block diagram of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0027] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0028] In the embodiments of this disclosure, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the access relationship of the matched objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. In the textual description of this disclosure, the character " / " generally indicates that the preceding and following matched objects have an "or" relationship. Furthermore, in the embodiments of this disclosure, "first," "second," "third," "fourth," "fifth," and "sixth" are only used to distinguish the content of different objects and have no other special meaning.

[0029] The technical solutions provided in this disclosure can be applied to artificial intelligence technologies such as environmental perception and autonomous driving. Taking autonomous driving scenarios as an example, accurately identifying the location of obstacles on the road is crucial for improving the safety of autonomous driving.

[0030] In existing technologies, the location of obstacles in the road is usually determined based on scene images captured by a monocular camera at the front of the vehicle. However, because monocular cameras lack depth information, the accuracy of the determined obstacle locations is relatively low.

[0031] To improve the accuracy of obstacle location determination based on scene images, scene point cloud data of obstacles collected by other heterogeneous sensors, such as LiDAR or millimeter-wave radar, or obstacles identified based on point clouds, can be combined to jointly determine the obstacle location based on scene image recognition. This corrects the obstacle location determined based on scene images, thereby improving the accuracy of obstacle location determination based on scene images.

[0032] However, when combining scene point cloud data to determine the location of obstacles based on scene image recognition, the differences between obstacle recognition technology based on point cloud data and obstacle recognition technology based on image data lead to a mismatch between the obstacles determined by scene point cloud data and those determined by scene images. Furthermore, blindly fusing scene image data and scene point cloud data results in a large computational load for the fused data.

[0033] Therefore, when combining point cloud data to determine the location of obstacles identified based on scene images, in order to effectively utilize the obstacle recognition information and avoid the computational burden of fusing image data and point cloud data, the obstacles identified based on scene images can be matched with those identified based on scene point cloud data first, and the location of the obstacles can be determined based on the matching results. This effectively utilizes the obstacle recognition information to correct the location of obstacles determined based on road images, thereby improving the accuracy of obstacle location determined based on road images.

[0034] Based on the above technical concept, this disclosure provides a method for determining the location of an obstacle. The method for determining the location of an obstacle provided by this disclosure will be described in detail below through specific embodiments. It is understood that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0035] Example 1

[0036] Figure 1 This is a flowchart illustrating a method for determining the location of an obstacle according to the first embodiment of this disclosure. This method can be executed by software and / or hardware devices, such as a terminal or a server. For example, please refer to [link to example]. Figure 1 As shown, the method for determining the location of the obstacle may include:

[0037] S101. Recognize the scene image of the road to be detected and determine the first obstacle included in the scene image.

[0038] For example, when acquiring a scene image of the road to be detected, the scene image of the road to be detected can be received from other electronic devices, such as a scene image of the road to be detected captured by a camera; the scene image of the road to be detected can also be searched from local storage; or the scene image of the road to be detected can be acquired through other methods. The specific method can be set according to actual needs. Here, the method for acquiring the scene image of the road to be detected is not specifically limited in this embodiment.

[0039] After obtaining the scene image of the road to be detected, image recognition technology can be used to identify the scene image and determine the obstacles in the scene image. In order to distinguish them from the obstacles subsequently determined based on the scene point cloud data of the road to be detected, for example, in this embodiment of the disclosure, the obstacles determined based on the scene image can be recorded as the first obstacle, and the obstacles subsequently determined based on the scene point cloud data can be recorded as the second obstacle.

[0040] Since monocular cameras lack depth information, the positions of obstacles determined based on scene images may contain errors. To improve the accuracy of obstacle positions determined based on scene images, other heterogeneous sensors, such as lidar or millimeter-wave radar, can be combined to collect scene point cloud data of the road to be detected and identify the second obstacle included in the scene point cloud data, i.e., execute the following S102; in this way, the position of the first obstacle identified based on scene images can be determined by combining the second obstacle included in the scene point cloud data, so as to correct the position of the first obstacle.

[0041] S102. Identify the scene point cloud data of the road to be detected and determine the second obstacle included in the scene point cloud data.

[0042] For example, the number of first obstacles can be one or more, and can be set according to actual needs. Here, this embodiment of the disclosure does not impose a specific limit on the number of first obstacles.

[0043] For example, when acquiring scene point cloud data of the road to be detected, scene point cloud data of the road to be detected can be received from other electronic devices, such as point cloud data collected by lidar or millimeter-wave radar; scene point cloud data of the road to be detected can also be retrieved from local storage; scene point cloud data of the road to be detected can also be acquired through other methods. The specific method can be set according to actual needs. Here, the method for acquiring scene point cloud data of the road to be detected is not specifically limited in this embodiment.

[0044] Based on the description in S101 above, to improve the accuracy of obstacle positions determined based on scene images, scene point cloud data can be used to jointly determine the position of the first obstacle identified based on scene images, thereby correcting the position of the first obstacle. It should be noted that when jointly determining the position of obstacles based on scene image recognition using scene point cloud data, the differences between obstacle recognition technologies based on point cloud data and those based on image data mean that obstacles determined based on scene point cloud data and those determined based on scene images may not correspond perfectly and cannot be fully matched. In this case, blindly fusing scene image data and scene point cloud data would result in a large computational load for the fused data.

[0045] Therefore, when combining scene point cloud data to jointly determine the position of obstacles determined based on scene images, the first obstacle identified based on scene images and the second obstacle identified based on scene point cloud data can be matched first, and the position of the obstacle can be determined according to the matching result. This can effectively correct the position of the first obstacle determined based on scene images, that is, execute the following S103 to improve the accuracy of the position of the first obstacle determined based on scene images.

[0046] S103. Match the first obstacle and the second obstacle, and determine the position of the first obstacle based on the matching result.

[0047] For example, the number of second obstacles can be one or more, and can be set according to actual needs. Here, this embodiment of the disclosure does not impose a specific limit on the number of second obstacles.

[0048] For example, when matching the first obstacle and the second obstacle, a data matching algorithm can be used, such as a one-to-one matching algorithm, a multiple hypothesis matching algorithm, or a random finite set (RFS) tracking matching algorithm, etc., which can be set according to actual needs. For example, a one-to-one matching algorithm can be the Hungarian matching algorithm, etc.; a multiple hypothesis matching algorithm can be a multiple hypothesis tracking algorithm, etc., which can be set according to actual needs.

[0049] When matching the first obstacle and the second obstacle, assuming that the first obstacle identified based on the scene image includes obstacle a, obstacle b, obstacle c and obstacle d, and the obstacle identified based on the point cloud data includes obstacle a, obstacle b and obstacle c, then the matching result is: among the first obstacles, the obstacles that successfully match the second obstacle include obstacle a, obstacle b and obstacle c; the obstacle that does not successfully match the second obstacle includes obstacle d.

[0050] As can be seen, in this embodiment of the present disclosure, when determining the location of an obstacle, the scene image of the road to be detected can be identified first to determine the first obstacle included in the scene image; and the scene point cloud data of the road to be detected can be identified to determine the second obstacle included in the scene point cloud data; then the first obstacle and the second obstacle are matched, and the location of the first obstacle is determined according to the matching result. This can effectively combine the scene point cloud data to determine the location of the first obstacle, thereby improving the accuracy of the determined location of the first obstacle.

[0051] Example 2

[0052] Figure 2This is a flowchart illustrating a method for determining the position of a first obstacle based on a matching result, according to a second embodiment of this disclosure. This method can also be executed by software and / or hardware devices. For an example, please refer to [link to example]. Figure 2 As shown, the method may include:

[0053] S201. For the third obstacle in the first obstacle that does not match the second obstacle, determine the target point cloud data that matches the third obstacle from the scene point cloud data based on the characteristics of the third obstacle.

[0054] The target point cloud data can be understood as the point cloud data of the third obstacle.

[0055] It is understood that, in this embodiment of the disclosure, although the obstacles identified based on the scene point cloud data do not include the third obstacle, the obstacle identification result may be due to differences in the obstacle identification technology. In fact, the scene point cloud data of the road to be detected obtained includes the point cloud data of the third obstacle. Therefore, when determining the position of the third obstacle, in order to effectively utilize the point cloud data of the third obstacle, the point cloud data that matches the third obstacle can be filtered from the scene point cloud data of the road to be detected. For ease of distinction, in this embodiment of the disclosure, the point cloud data that matches the third obstacle can be recorded as the target point cloud data.

[0056] For example, when determining target point cloud data that matches a third obstacle from scene point cloud data based on the characteristics of the third obstacle, the scene point cloud data of the road to be detected can be projected onto the scene image first. Using the two-dimensional bounding box recognized by the camera, the initial point cloud data corresponding to the third obstacle can be initially filtered from the scene point cloud data of the road to be detected. This can effectively eliminate the amount of point cloud data that does not contain the third obstacle. Then, based on the characteristics of the third obstacle, the target point cloud data that matches the third obstacle can be determined from the filtered initial point cloud data.

[0057] For example, when determining target point cloud data that matches the third obstacle from the initial point cloud data based on the characteristics of the third obstacle, the initial point cloud data can first be clustered to obtain multiple clusters; then, from the multiple clusters, the cluster that matches the characteristics of the third obstacle can be determined; and the cluster that matches the characteristics of the third obstacle can be determined as the target point cloud data.

[0058] For example, when performing clustering processing on the initial point cloud data, existing clustering algorithms can be used to perform clustering processing on the initial point cloud data. For specific implementation, please refer to the implementation of existing clustering algorithms. Here, the embodiments of this disclosure will not be described in detail.

[0059] After determining the target point cloud data that matches the third obstacle, the position of the third obstacle can be determined by combining the image data of the third obstacle in the scene image with the target point cloud data, i.e., by executing the following S202:

[0060] S202. Determine the position of the third obstacle based on the image data of the third obstacle and the target point cloud data in the scene image.

[0061] For example, when determining the position of a third obstacle based on the image data and target point cloud data of the third obstacle in the scene image, the image data of the third obstacle and the target point cloud data corresponding to the third obstacle can be fused first to obtain fused data; then the position of the third obstacle can be determined based on the fused data.

[0062] As can be seen, in this embodiment of the present disclosure, when determining the location of an obstacle by combining point cloud data, for the third obstacle among the first obstacles that does not match the second obstacle, the target point cloud data that matches the third obstacle can be determined specifically from the scene point cloud data of the road to be detected based on the characteristics of the third obstacle; then the image data of the third obstacle and the target point cloud data are fused to determine the location of the third obstacle. This not only improves the accuracy of the determined location of the third obstacle, but also reduces the amount of data fused.

[0063] When determining the position of the first obstacle based on the matching results of the first obstacle and the second obstacle, the above should be considered. Figure 2 The illustrated second embodiment details how to effectively combine scene point cloud data to accurately determine the position of a third obstacle that does not match the second obstacle within the first obstacle set. Below, we will describe in detail how to effectively combine scene point cloud data to accurately determine the position of a fourth obstacle that matches the second obstacle within the first obstacle set.

[0064] For example, regarding the fourth obstacle that successfully matches the second obstacle within the first obstacle, to accurately determine the position of the fourth obstacle by combining point cloud data, the image recognition information of the fourth obstacle in the scene image and the point cloud recognition information of the fourth obstacle in the point cloud data can be directly fused to obtain fused information; then, the position of the fourth obstacle can be determined based on the fused information. This method of combining the point cloud recognition information of the fourth obstacle to jointly determine its position can effectively improve the accuracy of the determined position of the fourth obstacle.

[0065] Based on any of the above embodiments, the position of the first obstacle can be accurately determined using the technical solution of this disclosure. Furthermore, the speed of the vehicle acquiring the scene image can be determined based on the position of the first obstacle at different times, thus providing a reference for the vehicle's movement by collecting the vehicle's speed.

[0066] For example, when determining the speed of the scene image acquisition vehicle based on the position of the first obstacle at different times, assuming that the different times include the first time and the second time, the distance traveled by the acquisition vehicle within the time period formed by the determined position of the first obstacle at the first time and the position of the second obstacle at the second time can be used to determine the distance traveled by the acquisition vehicle within the time period formed by the two times; then, based on the distance traveled by the acquisition vehicle and the time period, the speed of the acquisition vehicle can be calculated, thereby determining the speed of the acquisition vehicle.

[0067] Example 3

[0068] Figure 3 This is a schematic diagram of the obstacle location determination device 30 provided according to the third embodiment of this disclosure. For example, please refer to [link / reference]. Figure 3 As shown, the obstacle location determination device 30 may include:

[0069] The first determining unit 301 is used to identify the scene image of the road to be detected and determine the first obstacle included in the scene image.

[0070] The second determining unit 302 is used to identify the scene point cloud data of the road to be detected and determine the second obstacle included in the scene point cloud data.

[0071] The matching unit 303 is used to match the first obstacle and the second obstacle, and determine the position of the first obstacle based on the matching result.

[0072] Optionally, the matching unit 303 includes a first matching module and a second matching module.

[0073] The first matching module is used to determine the target point cloud data that matches the third obstacle in the first obstacle that has not been successfully matched with the second obstacle, based on the characteristics of the third obstacle, from the scene point cloud data.

[0074] The second matching module is used to determine the position of the third obstacle based on the image data of the third obstacle in the scene image and the target point cloud data.

[0075] Optionally, the first matching module includes a first matching submodule and a second matching submodule.

[0076] The first matching submodule is used to perform clustering processing on scene point cloud data to obtain multiple clusters.

[0077] The second matching submodule is used to identify the cluster that matches the features of the third obstacle from among multiple clusters as the target point cloud data.

[0078] Optionally, the second matching module includes a third matching submodule and a fourth matching submodule.

[0079] The third matching submodule is used to fuse the image data of the third obstacle in the scene image and the target point cloud data to obtain fused data.

[0080] The fourth matching submodule is used to determine the position of the third obstacle based on the fused data.

[0081] Optionally, the matching unit 303 includes a third matching module and a fourth matching module.

[0082] The third matching module is used to fuse the image recognition information of the fourth obstacle in the scene image and the point cloud recognition information of the fourth obstacle in the point cloud data for the first obstacle that is successfully matched with the second obstacle, to obtain fused information.

[0083] The fourth matching module is used to determine the position of the fourth obstacle based on the fusion information.

[0084] Optionally, the obstacle location determination device 30 includes a third determination unit.

[0085] The third determining unit is used to determine the speed of the vehicle acquiring the scene image based on the position of the first obstacle at different times.

[0086] The obstacle location determination device 30 provided in this embodiment can execute the technical solution of the obstacle location determination method shown in any of the above embodiments. Its implementation principle and beneficial effects are similar to those of the obstacle location determination method. Please refer to the implementation principle and beneficial effects of the obstacle location determination method. It will not be repeated here.

[0087] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0088] According to embodiments of this disclosure, this disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, at least one processor of an electronic device being able to read the computer program from the readable storage medium, and the at least one processor executing the computer program causing the electronic device to perform the scheme provided in any of the above embodiments.

[0089] Figure 4This is a schematic block diagram of an electronic device 40 provided in an embodiment of this disclosure. 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 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, 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 present disclosure described and / or claimed herein.

[0090] like Figure 4 As shown, device 40 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into random access memory (RAM) 403. RAM 403 may also store various programs and data required for the operation of device 40. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0091] Multiple components in device 40 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0092] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 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 computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the obstacle location determination method. For example, in some embodiments, the obstacle location determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 40 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the obstacle location determination method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the obstacle location determination method by any other suitable means (e.g., by means of firmware).

[0093] 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), complex 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.

[0094] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0095] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0096] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. 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).

[0097] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments 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., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0098] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via 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. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0099] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0100] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. 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 disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining a position of an obstacle, comprising: identifying a scene image of a road to be detected to determine a first obstacle included in the scene image; identifying scene point cloud data of the road to be detected to determine a second obstacle included in the scene point cloud data; matching the first obstacle and the second obstacle to obtain a matching result, the matching result including a third obstacle that is not successfully matched with the second obstacle in the first obstacle; for the third obstacle, determining target point cloud data matched with the third obstacle from the scene point cloud data according to a feature of the third obstacle; fusing image data of the third obstacle in the scene image and the target point cloud data to obtain fusion information; determining a position of the third obstacle according to the fusion information.

2. The method of claim 1, wherein, The determining of the target point cloud data matched with the third obstacle from the scene point cloud data according to the feature of the third obstacle comprises: performing clustering processing on the scene point cloud data to obtain a plurality of clusters; determining a cluster matched with the feature of the third obstacle in the plurality of clusters as the target point cloud data.

3. The method of claim 1, wherein, The matching result further includes a fourth obstacle that is successfully matched with the second obstacle in the first obstacle, and the method further comprises: for the fourth obstacle that is successfully matched with the second obstacle in the first obstacle, fusing image recognition information of the fourth obstacle in the scene image and point cloud recognition information of the fourth obstacle in the point cloud data to obtain fusion information; determining a position of the fourth obstacle according to the fusion information. 4.The method according to any one of claims 1-3, comprising: determining a driving speed of a vehicle collecting the scene image according to positions of the first obstacle at different time points. 5.An apparatus for determining a position of an obstacle, comprising: a first determining unit configured to identify a scene image of a road to be detected to determine a first obstacle included in the scene image; a second determining unit configured to identify scene point cloud data of the road to be detected to determine a second obstacle included in the scene point cloud data; a matching unit configured to match the first obstacle and the second obstacle to obtain a matching result; the matching result including a third obstacle that is not successfully matched with the second obstacle in the first obstacle; the matching unit including a first matching module and a second matching module; the first matching module configured to, for the third obstacle, determine target point cloud data matched with the third obstacle from the scene point cloud data according to a feature of the third obstacle; the second matching module configured to determine a position of the third obstacle according to image data of the third obstacle in the scene image and the target point cloud data; the second matching module including a third matching sub-module and a fourth matching sub-module; The third matching submodule is configured to fuse the image data of the third obstacle in the scene image and the target point cloud data to obtain fusion data. The fourth matching submodule is configured to determine the position of the third obstacle according to the fusion data.

6. The apparatus of claim 5, wherein, The first matching module includes a first matching submodule and a second matching submodule. The first matching submodule is configured to perform clustering processing on the scene point cloud data to obtain a plurality of clusters. The second matching submodule is configured to determine, as the target point cloud data, a cluster that matches the features of the third obstacle from the plurality of clusters.

7. The apparatus of claim 5 or 6, wherein, The matching unit includes a third matching module and a fourth matching module. The third matching module is configured to fuse image recognition information of a fourth obstacle in the scene image and point cloud recognition information of the fourth obstacle in the point cloud data for the fourth obstacle that matches the second obstacle successfully from the first obstacles to obtain fusion information. The fourth matching module is configured to determine the position of the fourth obstacle according to the fusion information.

8. The apparatus according to any one of claims 5-7, the apparatus comprising a third determining unit; The third determining unit is configured to determine the driving speed of a collection vehicle of the scene image according to the positions of the first obstacle at different time instants.

9. An electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for determining the position of the obstacle according to any one of claims 1-4.

10. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method for determining the position of the obstacle according to any one of claims 1-4.

11. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for determining the position of the obstacle according to any one of claims 1-4.

Images