Target region identification method, device, and equipment and storage medium

Abstract

The present disclosure provides a target area identification method, device and equipment and storage medium, relates to the technical field of artificial intelligence, and in particular to the technical fields of big data, image processing, high-precision map, automatic driving and the like. The target area identification method comprises: determining a target section on a target road based on lane-level trajectory data on the target road; determining a target lane in which a target area on the target road is located based on a target image of the target section; determining position information of a target obstacle in the target image, and determining position information of the target area based on the position information of the target obstacle; and determining the target area based on the position information of the target lane and the target area. The present disclosure can improve the identification accuracy.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, specifically to the fields of big data, image processing, high-precision maps, and autonomous driving, and particularly to a method, apparatus, device, and storage medium for identifying target areas. Background Technology

[0002] When roads are under construction, some lanes may be blocked, making target areas impassable. Promptly alerting navigation users and guiding them to avoid these areas can improve the user experience. Beyond navigation applications, in the field of autonomous driving, it's also crucial to detect construction in advance to provide decision-making basis for automatic lane changes, reducing the rate of human intervention in autonomous driving and enhancing its safety.

[0003] How to accurately identify the target area is a problem that needs to be solved. Summary of the Invention

[0004] This disclosure provides a method, apparatus, device, and storage medium for identifying a target area.

[0005] According to one aspect of this disclosure, a method for identifying a target area is provided, comprising: determining a target road segment on the target road based on lane-level trajectory data on the target road; determining a target lane on the target road where the target area is located based on a target image of the target road segment; determining the location information of a target obstacle in the target image, and determining the location information of the target area based on the location information of the target obstacle; and determining the target area based on the location information of the target lane and the target area.

[0006] According to another aspect of this disclosure, a target area identification device is provided, comprising: a road segment determination module, configured to determine a target road segment on the target road based on lane-level trajectory data on the target road; a lane determination module, configured to determine a target lane on the target road where the target area is located based on a target image of the target road segment; a position determination module, configured to determine the position information of a target obstacle in the target image, and determine the position information of the target area based on the position information of the target obstacle; and an identification module, configured to determine the target area based on the position information of the target lane and the target area.

[0007] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to said at least one processor; wherein the memory stores instructions executable by said at least one processor, said instructions being executed by said at least one processor to enable said at least one processor to perform the method as described in any of the foregoing aspects.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method according to any of the preceding aspects.

[0009] According to another aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method according to any of the preceding aspects.

[0010] According to the technical solution disclosed herein, the accuracy of identification can be improved.

[0011] 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

[0012] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0013] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;

[0014] Figure 2 This is a schematic diagram illustrating an application scenario provided according to embodiments of this disclosure;

[0015] Figure 3 This is a schematic diagram according to the second embodiment of the present disclosure;

[0016] Figure 4 This is a schematic diagram of the trajectory and trajectory line provided according to the embodiments of this disclosure;

[0017] Figure 5 This is a schematic diagram of lane-level trajectory data provided according to embodiments of this disclosure;

[0018] Figure 6 This is a schematic diagram of lane change points provided according to embodiments of the present disclosure;

[0019] Figure 7 This is a schematic diagram illustrating image-based target lane determination according to embodiments of the present disclosure;

[0020] Figure 8 This is a schematic diagram illustrating the determination of obstacle positions based on images according to embodiments of this disclosure;

[0021] Figure 9 This is a schematic diagram according to the third embodiment of the present disclosure;

[0022] Figure 10 This is a schematic diagram according to the fourth embodiment of the present disclosure;

[0023] Figure 11 This is a schematic diagram of an electronic device used to implement the target area identification method of the embodiments of this disclosure. Detailed Implementation

[0024] 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.

[0025] Figure 1 Based on a schematic diagram of the first embodiment of this disclosure, this embodiment provides a method for identifying a target region, the method comprising:

[0026] 101. Based on lane-level trajectory data on the target road, determine the target road segment on the target road.

[0027] 102. Based on the target image of the target road segment, determine the target lane where the target area on the target road is located.

[0028] 103. Determine the location information of the target obstacle in the target image, and determine the location information of the target area based on the location information of the target obstacle.

[0029] 104. Based on the location information of the target lane and the target area, determine the target area.

[0030] In this context, the target road refers to the road to be processed, used to identify whether a target area exists on that road. For example, one or more roads on the map can be selected as target roads based on the analyst's needs.

[0031] The target area refers to the area to be identified. The target area can be a construction area or a traffic police control area, etc.

[0032] Trajectory data refers to the spatiotemporal data of a vehicle during its movement.

[0033] Lane-level trajectory data refers to trajectory data with positioning accuracy at the lane level. In contrast, ordinary trajectory data has positioning accuracy at the road level. That is, ordinary trajectory data can only identify the road the vehicle is traveling on, while lane-level trajectory data can identify which lane the vehicle is traveling in. For example, the positioning accuracy of ordinary trajectory data is 5-10 meters, while the positioning accuracy of lane-level trajectory data is less than 1 meter.

[0034] Specifically, lane-level trajectory data can be obtained from high-precision map data.

[0035] The target road segment refers to the section of the target road that needs to be processed. Taking the identification of construction areas as an example, suspected construction areas can be identified based on lane-level trajectory data, and the road segment where the suspected construction area is located is the target road segment.

[0036] A target image refers to an image corresponding to a target road segment. For example, after a vehicle travels to a target road segment, a road image of the corresponding road segment can be collected as the target image.

[0037] The target road can include multiple lanes. The target lane refers to the lane where the target area is located. For example, if the target area is a construction area, the target lane is the lane where the construction area is located.

[0038] Target obstacles refer to obstacles related to the target area. Taking a construction area as an example, target obstacles include: cones, warning signs, construction workers, etc.

[0039] In this embodiment, target area identification is achieved by combining lane-level trajectory data and images, which improves the accuracy of identification. Furthermore, since lane-level trajectory data has high precision, determining the target road segment based on lane-level trajectory data can improve the accuracy of the target road segment, thereby improving the accuracy of target area identification.

[0040] To better understand the embodiments of this disclosure, the application scenarios to which these embodiments are applicable are described below. This embodiment takes the target area as the construction area as an example.

[0041] like Figure 2 As shown, taking a navigation application as an example, a map application (APP) can be installed on the terminal device 201, which can provide navigation services to users. Terminal devices can be mobile devices (such as mobile phones), in-vehicle terminals, wearable devices, etc. The server can identify construction areas based on lane-level trajectory data and images. The server can be a local server or a cloud server, and can be a single server or a cluster of servers. The terminal device and the server can communicate via wired and / or wireless networks.

[0042] After processing lane-level trajectory data and images, the server can identify construction areas and plot them on a map. The terminal device displays the construction area on the map and can also play voice prompts via speakers or other audio playback devices to promptly remind users to avoid the target area during navigation.

[0043] In this embodiment, the construction area can be at the lane level, meaning it can identify whether a construction area exists on the road, which lane the construction area is located on, and the start and end points of the construction area.

[0044] In conjunction with the above application scenarios, this disclosure also provides a method for identifying target regions.

[0045] Figure 3 Based on a schematic diagram of the second embodiment of this disclosure, this embodiment provides a target region identification method, the method comprising:

[0046] 301. A pre-trained prediction model is used to process lane-level data to identify suspected areas, and the road segment where the suspected area is located is taken as the target road segment.

[0047] Here, "trajectory" refers to the vehicle's location, such as... Figure 4 As shown, the position of the arrow is the trajectory.

[0048] A trajectory line is a line formed by connecting the continuous trajectories of a vehicle's movement, such as... Figure 4 As shown, the arrows connect to form a trajectory line.

[0049] Lane-level trajectory data can specifically include: trajectory centerline, trajectory width, trajectory boundaries, and trajectory lane change points.

[0050] Trajectory centerline: The numerous trajectory lines of a road (e.g.) Figure 5 The series of lines shown form a trajectory region, the center of which is the trajectory centerline, as... Figure 5 As shown.

[0051] Track width: The width of the track region after removing outliers is called the track width, such as... Figure 5 As shown.

[0052] Track boundaries: These include the left and right boundaries of the track. Left and right refer to the left and right directions of the track's travel direction, i.e., the outermost boundaries of the track area. Figure 5 As shown.

[0053] Lane change points: Points where the lane of the trajectory changes, such as... Figure 6 As shown.

[0054] The lane-level trajectory data mentioned above can be obtained based on high-precision map data.

[0055] Taking the identification of construction areas as an example, a suspected area, also known as a suspected construction area, refers to a construction area initially determined based on lane-level trajectory data.

[0056] Specifically, a prediction model can be pre-trained. This prediction model is a deep neural network model, whose input is lane-level trajectory data and output is the predicted construction lane and construction start and end points, i.e., information on the suspected construction area.

[0057] Prediction models, for example, include the Extreme Gradient Boosting (xgboost) model.

[0058] After obtaining information about suspected construction areas through the prediction model, the road segment where the suspected construction area is located can be used as the target road segment.

[0059] In this embodiment, by using a predictive model to process lane-level data to determine suspected areas, more accurate suspected areas can be obtained, thereby improving the accuracy of the target road segment.

[0060] 302. Perform semantic segmentation processing on the target image of the target road segment to obtain the semantic segmentation map, which includes: obstacle area, lane line area and road surface area.

[0061] A target image refers to an image of a target road segment, which can be obtained through a vehicle's camera or a third-party device (such as a dashcam).

[0062] Taking vehicle-based target image acquisition as an example, once the vehicle reaches the target road segment, its onboard camera can be activated to acquire target images of that segment. A single target image can be generated, or multiple target images can form an image sequence.

[0063] Semantic segmentation combines image classification, object detection, and image segmentation. It uses certain methods to segment an image into regions with specific semantic meanings and identifies the semantic category of each region.

[0064] like Figure 7 As shown, a semantic segmentation model (such as deeplabV3+) can be used to process the input target image (acquired image) and output a semantic segmentation map.

[0065] In this embodiment, the semantic segmentation map mainly includes three regions: lane line region, road surface region, and obstacle (such as cone) region. Different regions can be composed of pixels of different colors in the semantic segmentation map.

[0066] 303. Determine the type and location of obstacles within the obstacle area, determine the category and location of lane lines within the lane line area, and determine the road surface connectivity region based on the road surface area.

[0067] For obstacle regions, semantic segmentation can be used to obtain the type (such as cones) and location (absolute location) of obstacles.

[0068] For the lane line region, the position (absolute position) of the lane line can be obtained through semantic segmentation. Additionally, based on the positional information corresponding to the lane line region, the image of the lane line region can be extracted from the target image and input into a classification model. The output of the classification model is the category of the lane line, which includes either a solid white line or a dashed white line.

[0069] Classification models are also pre-trained deep neural network models, such as the ResNet50 model.

[0070] For the road surface area, the image of the road surface area can be extracted from the target image based on the location information corresponding to the road surface area, and the connected component calculation can be performed on the image of the road surface area to obtain the road surface connected component.

[0071] 304. Determine the target lane based on the type and location of the obstacle, the category and location of the lane line, and the road surface connectivity region.

[0072] Once the above information is obtained, a fusion strategy can be applied to determine the target lane.

[0073] Specifically, the type of obstacle can determine whether it is a target obstacle. A target obstacle is an obstacle that corresponds to a target area. Taking a construction area as an example, target obstacles are obstacles related to construction, such as traffic cones, warning signs, and construction workers.

[0074] If the obstacle is a target obstacle, it can be determined whether its location is within the connected domain of the road surface. If so, the target obstacle is located within the road surface. Further, based on the location of the target obstacle and the lane lines, the distance (relative position) between the target obstacle and the lane lines can be calculated. Then, based on this distance and the lane line type, the target lane is determined. For example, if a lane line is a solid white line, and the target obstacle is close to this solid white line (less than a certain preset value), it indicates that the target obstacle does not affect vehicle traffic, and the lane containing the target obstacle is not considered the target lane. Alternatively, if based on the above distance, it is determined that the target obstacle is located between a solid white lane line and a dashed white lane line (e.g., the distance to these two lane lines is approximately equal), then the target obstacle will affect vehicle traffic, and the lane containing the target obstacle is the target lane. Figure 7 As shown, the leftmost lane 2 is determined to be the target lane (construction lane) through the fusion strategy.

[0075] In this embodiment, the target lane is determined based on the type and location of the obstacle, the category and location of the lane line, and the road surface connectivity. Since multiple pieces of information are integrated, the accuracy of target lane identification can be improved.

[0076] 305. Based on the depth image corresponding to the target image, determine the location information of the target obstacle in the target image.

[0077] In this image, each pixel value represents the distance between a point in the scene and the camera.

[0078] A depth image corresponding to the target image can be obtained by using a depth map acquisition device or by converting the target image.

[0079] Target obstacles refer to obstacles related to the target area. Taking the target area as a construction area as an example, target obstacles may include: cones, warning signs, construction personnel, etc.

[0080] Each pixel value in the depth image indicates the distance information between the corresponding point and the acquisition point (such as a camera). For a target obstacle, the pixel value corresponding to the target obstacle in the depth image can be obtained as the location information of the target obstacle. Specifically, the location information is the distance information between the target obstacle and the current position of the vehicle.

[0081] In this embodiment, since depth images can reflect more accurate location information, obtaining the location information of the target obstacle based on depth images can improve the accuracy of the location information.

[0082] 306. Determine the location information of the target area based on the location information of the target obstacle.

[0083] The location information of the target obstacle can be used as the location information of the target area; or, the location information of the target area can be determined based on the location information of the target obstacle and the lane change points in the lane-level trajectory data.

[0084] The aforementioned location information of target obstacles can be the locations of multiple target obstacles in the same target image. For example, taking a construction area as an example, the location information of each target obstacle can be the location information of a construction point. There are usually multiple target obstacles (such as cones), and the location information of multiple target obstacles can constitute the location information of the target area. Or,

[0085] like Figure 8 As shown, multiple target images can be acquired and combined into an image sequence. The same target obstacle corresponds to different position information in different images of the image sequence. Based on the position information in these different images, the position information of the target area can also be formed.

[0086] Alternatively, the initial location information of the target obstacle can be used as the initial location information of the target area. This initial location information can then be adjusted using lane change points to obtain the final location information of the target area. For example, the lane change points can be clustered, and the location information of the cluster centers can be used as the start and end points of the target area. Clustering can be performed using density-based clustering algorithms (DBSCAN).

[0087] In addition, the target lane determined above can be adjusted based on the clustering results of lane change points to determine the final target lane.

[0088] In this embodiment, the location information of the target area can be determined by the location information of the target obstacle, or the location information of the target obstacle and the lane change point, which can improve the accuracy of the location information of the target area and thus improve the accuracy of target area identification.

[0089] 307. Based on the location information of the target lane and the target area, determine the target area.

[0090] The target lane indicates the lane where the target area is located, and the location information of the target area indicates the corresponding location, i.e., distance information. Therefore, based on the target lane and location information, the target area can be determined, such as which lane the construction area is located on, and the specific location of the construction area on that lane.

[0091] In addition, once the target area is identified, it can be plotted on an electronic map and displayed to the user, such as... Figure 8 As shown, this is for user navigation applications. Alternatively, it can be applied to automatic lane-changing scenarios in autonomous driving to improve the safety of autonomous driving.

[0092] In this embodiment, by drawing the target area on an electronic map, the target area can be displayed to the user in a timely manner, improving timeliness and enhancing the user experience.

[0093] In this embodiment, since lane-level trajectory data is high-precision data, construction areas can be mined based on this high-precision data and images to accurately determine whether road construction is taking place and to confirm the lane and specific location of the construction, i.e., to identify the construction area. On the one hand, combined with road network information, construction areas can be drawn on electronic maps to provide timely reminders to users during navigation, improving the user experience; on the other hand, during autonomous driving, it can support corresponding driving decisions and improve the safety of autonomous driving.

[0094] Figure 9 The diagram is based on the third embodiment of the present disclosure. This embodiment provides a target area identification device 900, which includes: a road segment determination module 901, a lane determination module 902, a location determination module 903, and an identification module 904.

[0095] The road segment determination module 901 is used to determine the target road segment on the target road based on lane-level trajectory data on the target road; the lane determination module 902 is used to determine the target lane where the target area on the target road is located based on the target image of the target road segment; the position determination module 903 is used to determine the position information of the target obstacle in the target image, and determine the position information of the target area based on the position information of the target obstacle; the identification module 904 is used to determine the target area based on the position information of the target lane and the target area.

[0096] In this embodiment, target area identification is achieved by combining lane-level trajectory data and images, which improves the accuracy of identification. Furthermore, since lane-level trajectory data has high precision, determining the target road segment based on lane-level trajectory data can improve the accuracy of the target road segment, thereby improving the accuracy of target area identification.

[0097] In some embodiments, the road segment determination module 901 is further configured to: process the lane-level data using a pre-trained prediction model to determine a suspected area; and designate the road segment where the suspected area is located as the target road segment.

[0098] In this embodiment, by using a predictive model to process lane-level data to determine suspected areas, more accurate suspected areas can be obtained, thereby improving the accuracy of the target road segment.

[0099] In some embodiments, the lane determination module 902 is further configured to: perform semantic segmentation processing on the target image to obtain the semantic segmentation map, the semantic segmentation map including: obstacle region, lane line region and road surface region; determine the type and location of obstacles in the obstacle region, determine the category and location of lane lines in the lane line region, and determine the road surface connectivity region based on the road surface region; and determine the target lane based on the type and location of the obstacles, the category and location of the lane lines and the road surface connectivity region.

[0100] In this embodiment, the target lane is determined based on the type and location of the obstacle, the category and location of the lane line, and the road surface connectivity. Since multiple pieces of information are integrated, the accuracy of target lane identification can be improved.

[0101] In some embodiments, the position determination module 903 is further configured to: acquire a depth image corresponding to the target image; and acquire position information of the target obstacle based on the depth image.

[0102] In this embodiment, since depth images can reflect more accurate location information, obtaining the location information of the target obstacle based on depth images can improve the accuracy of the location information.

[0103] In some embodiments, the location determination module 903 is further configured to: use the location information of the target obstacle as the location information of the target area; or, determine the location information of the target area based on the location information of the target obstacle and the lane change points in the lane-level trajectory data.

[0104] In this embodiment, the location information of the target area can be determined by the location information of the target obstacle, or the location information of the target obstacle and the lane change point, which can improve the accuracy of the location information of the target area and thus improve the accuracy of target area identification.

[0105] Figure 10 The diagram is based on the fourth embodiment of the present disclosure. This embodiment provides a target area identification model identification device. The device 1000 includes: a road segment determination module 1001, a lane determination module 1002, a location determination module 1003, and an identification module 1004, and also includes: a display module 1005.

[0106] For a description of the road segment determination module 1001, lane determination module 1002, location determination module 1003 and identification module 1004, please refer to the previous embodiment.

[0107] The display module 1005 is used to draw the target area on an electronic map and display it to the user through the electronic map.

[0108] In this embodiment, by drawing the target area on an electronic map, the target area can be displayed to the user in a timely manner, improving timeliness and enhancing the user experience.

[0109] In this embodiment, since lane-level trajectory data is high-precision data, construction areas can be mined based on this high-precision data and images to accurately determine whether road construction is taking place and to confirm the lane and specific location of the construction, i.e., to identify the construction area. On the one hand, combined with road network information, construction areas can be drawn on electronic maps to provide timely reminders to users during navigation, improving the user experience; on the other hand, during autonomous driving, it can support corresponding driving decisions and improve the safety of autonomous driving.

[0110] It is understood that the same or similar content in different embodiments of this disclosure can be referred to each other.

[0111] It is understood that the terms "first" and "second" in the embodiments of this disclosure are only used for distinction and do not indicate the degree of importance or the order of events.

[0112] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0113] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0114] Figure 11 A schematic block diagram of an example electronic device 1100 that can be used to implement embodiments of the present disclosure is shown. Electronic device 1100 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 1100 may also represent various forms of mobile devices, such as personal digital assistants, 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.

[0115] like Figure 11 As shown, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 11011 into a random access memory (RAM) 1103. The RAM 1103 may also store various programs and data required for the operation of the electronic device 1100. The computing unit 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0116] Multiple components in electronic device 1100 are connected to I / O interface 1105, including: input unit 1106, such as keyboard, mouse, etc.; output unit 1107, such as various types of displays, speakers, etc.; storage unit 1108, such as disk, optical disk, etc.; and communication unit 1109, such as network card, modem, wireless transceiver, etc. Communication unit 1109 allows electronic device 1100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0117] The computing unit 1101 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 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 1101 performs the various methods and processes described above, such as the target region identification method. For example, in some embodiments, the target region identification method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1100 via ROM 1102 and / or communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of the target region identification method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the target region identification method by any other suitable means (e.g., by means of firmware).

[0118] 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.

[0119] 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 the processor or controller of a general-purpose computer, special-purpose computer, or other programmable load balancing device, 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 the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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 identifying a target region, comprising: Determining the target road segment based on lane-level trajectory data on the target road includes: processing the lane-level trajectory data using a pre-trained prediction model to identify suspected areas; and designating the road segment where the suspected area is located as the target road segment. Based on the target image of the target road segment, determining the target lane where the target area on the target road is located includes: performing semantic segmentation processing on the target image to obtain a semantic segmentation map, the semantic segmentation map including: obstacle area, lane line area and road surface area; determining the type and location of obstacles in the obstacle area, determining the category and location of lane lines in the lane line area, and determining the road surface connectivity region based on the road surface area; if the obstacle belongs to the target obstacle and is located within the road surface connectivity region, calculating the distance based on the location of the target obstacle and the location of the lane line, and determining the target lane based on the distance and the category of the lane line. Determining the location information of a target obstacle in the target image, and determining the location information of the target region based on the location information of the target obstacle, includes: using the location information of the target obstacle as initial location information, performing clustering processing on lane change points in the lane-level trajectory data, and using the location information of the cluster center points as the start and end points of the target region; the location information of the target obstacle is determined based on the depth image corresponding to the target image, and the location information is the distance information between the target obstacle and the current position of the vehicle; The target area is determined based on the location information of the target lane and the target area.

2. The method according to claim 1, further comprising: The target area is plotted on an electronic map and displayed to the user via the electronic map.

3. A target area identification device, comprising: The road segment determination module is used to determine the target road segment on the target road based on lane-level trajectory data on the target road, including: processing the lane-level trajectory data using a pre-trained prediction model to determine suspected areas; and taking the road segment where the suspected area is located as the target road segment. The lane determination module is used to determine the target lane where the target area on the target road is located based on the target image of the target road segment. This includes: performing semantic segmentation processing on the target image to obtain a semantic segmentation map, the semantic segmentation map including: an obstacle area, a lane line area, and a road surface area; determining the type and location of obstacles within the obstacle area, determining the category and location of lane lines within the lane line area, and determining a road surface connectivity region based on the road surface area; if the obstacle belongs to the target obstacle and is located within the road surface connectivity region, calculating the distance based on the location of the target obstacle and the location of the lane line, and determining the target lane based on the distance and the category of the lane line. A location determination module is used to determine the location information of a target obstacle in the target image and to determine the location information of the target region based on the location information of the target obstacle. This includes: using the location information of the target obstacle as initial location information; performing clustering processing on lane change points in the lane-level trajectory data; and using the location information of the cluster center points as the start and end points of the target region. The location information of the target obstacle is determined based on the depth image corresponding to the target image, and the location information is the distance information between the target obstacle and the current position of the vehicle. The identification module is used to determine the target area based on the location information of the target lane and the target area.

4. The apparatus according to claim 3, further comprising: The display module is used to draw the target area on an electronic map and display it to the user through the electronic map.

5. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-2.

6. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-2.

7. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-2.

Images