Target identification method and device, electronic equipment, storage medium and vehicle

Abstract

The invention provides a target identification method and device, electronic equipment, a storage medium and a vehicle, and relates to the technical field of vehicles. The method comprises the following steps: acquiring laser radar data, wherein the laser radar data comprises environment information or position information of a laser radar; according to the point cloud feedback information, determining a first view area corresponding to the laser radar data and a first angular resolution corresponding to the first view area; according to the first angular resolution, the target object in the first visual field area is recognized, only the angular resolution of the ground area and the angular resolution of the area of interest are needed in the recognition process of the target object, the angular resolution of the sky area or the non-attention area does not need to be considered, redundancy of the visual field area is avoided, the recognition cost is reduced, and the recognition efficiency is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle technology, and in particular to a target recognition method, device, electronic device, storage medium and vehicle. Background Art

[0002] On-board sensors can identify people or cars in a variety of ways, the most common of which is through laser radar (LIDAR). Lidar is a sensor that emits laser beams and can detect the distance, speed and shape of objects, thereby helping the on-board assisted driving system to identify people or cars.

[0003] However, the related technologies generally use a field of view of 120°*25° and an angular resolution of 0.1°*0.2° to identify the target object. In the process of identifying the target through LiDAR, some redundant field of view angles will be obtained, which may point to the sky or other non-interest areas, resulting in a waste of resource costs. Summary of the invention

[0004] The present disclosure provides a target recognition method, device, electronic device, storage medium and vehicle.

[0005] According to a first aspect of the present disclosure, a target recognition method is provided, the method comprising: acquiring laser radar data, the laser radar data including environmental information or position information of the laser radar; determining a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area based on point cloud feedback information, wherein the point cloud feedback information is a pre-stored rule for dividing the field of view area of ​​the laser radar into a core area of ​​interest and a non-area of ​​interest, and the first field of view area is a core area of ​​interest; based on the first angular resolution, identifying a target object in the first field of view area.

[0006] In some embodiments, the lidar data includes environmental information, and determining the first field of view area corresponding to the lidar data and the first angular resolution corresponding to the first field of view area based on the point cloud feedback information includes: obtaining the first point cloud data of the second field of view area corresponding to the environmental information based on the environmental information, the second field of view area including the core area and the non-core area; determining the second angular resolution corresponding to the first point cloud data; determining the first field of view area in response to the point cloud feedback information, and adjusting the second angular resolution of the second field of view area to obtain the first angular resolution.

[0007] In some embodiments, in response to point cloud feedback information, determining a first field of view area, and adjusting the second angular resolution of the second field of view area to obtain a first angular resolution includes: in response to demand feedback information, deleting non-core areas in the second field of view area and lowering the second angular resolution of some core areas to obtain the first angular resolution of the first field of view area.

[0008] In some embodiments, the lidar data includes the position information of the lidar, and determining the first field of view area corresponding to the lidar data and the first angular resolution corresponding to the first field of view area based on the point cloud feedback information includes: determining the first field of view area and the visible points of the first field of view area based on the position information and the point cloud feedback information; obtaining second point cloud data of the first field of view area based on the visible points; and determining the first angular resolution of the first field of view area corresponding to the second point cloud data.

[0009] In some embodiments, the visible point includes a first visible point and a second visible point. Based on the position information, determining the visible point of the first field of view includes: based on the position information, point cloud feedback information and vehicle information, determining the first field of view and the first visible point, the first visible point being the intersection of the boundary of the first field of view and the ground; based on the area of ​​interest of the first field of view, determining the second visible point, the second visible point being the intersection of the boundary of the area of ​​interest and the ground.

[0010] In some embodiments, identifying the target object in the first field of view according to the first angular resolution includes: determining the position of the target object in the first field of view according to the first angular resolution and a target recognition algorithm.

[0011] According to an embodiment of the present disclosure, laser radar data is acquired, the laser radar data includes environmental information or position information of the laser radar; based on the point cloud feedback information, a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area are determined; based on the first angular resolution, a target object in the first field of view area is identified, so that only the angular resolution of the ground area and the area of ​​interest is required in the process of identifying the target object, and the angular resolution of the sky area or the area of ​​non-interest does not need to be considered, thereby avoiding redundancy of the field of view area, reducing recognition cost, and improving recognition efficiency.

[0012] According to a second aspect of the present disclosure, a target recognition device is provided, which includes: an acquisition unit for acquiring laser radar data; a determination unit for determining a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area based on point cloud feedback information, wherein the point cloud feedback information is a pre-stored rule for dividing the field of view area of ​​the laser radar into a core area of ​​interest and a non-area of ​​interest, and the first field of view area is a core area of ​​interest; and an identification unit for identifying a target object in the first field of view area based on the first angular resolution.

[0013] According to an embodiment of the present disclosure, laser radar data is acquired, the laser radar data includes environmental information or position information of the laser radar; based on the point cloud feedback information, a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area are determined; based on the first angular resolution, a target object in the first field of view area is identified, and the angular resolution of the sky area or non-focus area is filtered out during the identification process of the target object, thereby avoiding redundancy of the field of view area, reducing recognition cost, and improving recognition efficiency.

[0014] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0015] at least one processor; and

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

[0017] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the at least one processor to perform the method of the first aspect described above.

[0018] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the method of the aforementioned first aspect.

[0019] According to a fifth aspect of the present disclosure, a vehicle is provided, comprising a target recognition device as described in the second aspect or an electronic device as described in the third aspect.

[0020] According to an embodiment of the present disclosure, laser radar data is acquired; based on point cloud feedback information, a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area are determined; based on the first angular resolution, a target object in the first field of view area is identified, and the angular resolution of the sky area or non-focus area is filtered out during the recognition of the target object, thereby avoiding redundancy of the field of view area, reducing recognition costs, and improving recognition efficiency.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0023] Figure 1 A schematic diagram of a distribution of a viewing area of ​​120°*25° provided in an embodiment of the present disclosure;

[0024] Figure 2A schematic diagram of a distribution with an angular resolution of 0.1°*0.2° provided in an embodiment of the present disclosure

[0025] Figure 3 A flowchart of a target recognition method provided by an embodiment of the present disclosure;

[0026] Figure 4 A flowchart of a target recognition method provided by an embodiment of the present disclosure;

[0027] Figure 5 A schematic diagram of a first field of view area distribution provided by an embodiment of the present disclosure;

[0028] Figure 6 A schematic diagram of a first angular resolution distribution provided in an embodiment of the present disclosure;

[0029] Figure 7 A schematic diagram of a target recognition result provided by an embodiment of the present disclosure;

[0030] Figure 8 A flowchart of a target recognition method provided by an embodiment of the present disclosure;

[0031] Fig. 9 A schematic diagram of the structure of a target recognition device provided by an embodiment of the present disclosure;

[0032] Fig.10 A schematic block diagram of an exemplary electronic device 1000 provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0034] A target recognition method, device, electronic device, and storage medium according to an embodiment of the present disclosure are described below with reference to the accompanying drawings.

[0035] There are many ways that vehicle radar can identify people or cars, the most common of which is through laser radar (LIDAR). Lidar is a sensor that emits laser beams and can detect the distance, speed and shape of objects, thus helping the vehicle radar to identify people or cars.

[0036] The related technology generally uses a field of view of 120°*25° and an angular resolution of 0.1°*0.2° to identify the target object. Figure 1 The distribution of the visual field area shown and Figure 2 The size of the angular resolution shown is used to identify the target object, so that the angular resolution of each frame of the image is evenly distributed during the identification process, and the field of view area is fully covered with the same resolution.

[0037] However, in the process of identifying targets through LiDAR, some redundant point cloud data corresponding to the field of view will be obtained. These redundancies may point to the sky or other non-interested areas, resulting in a waste of resource costs. At the same time, in order to increase the size of the covered field of view in related technologies, more transmitting devices and receiving devices are required, and the total amount of point cloud data in each frame of the image increases, requiring higher data processing capabilities. Figure 2 The angular resolution shown is uniform for each frame, with the core area unable to achieve long-range detection.

[0038] In view of the problems of the above-mentioned related technologies, the target recognition method disclosed in the present invention is used to design a more reasonable field of view size according to the requirements of autonomous driving, and obtain a more reasonable angular resolution according to the field of view size and vehicle information (such as vehicle wiring harness), which greatly reduces the cost of laser radar for passenger cars.

[0039] The target recognition method proposed in the present disclosure can be applied to devices with laser radar, such as unmanned driving, artificial intelligence, military, 3D printing, VR / AR and other scenarios. The application scenarios are not limited in the embodiments of the present disclosure. The present disclosure mainly takes the vehicle-mounted target recognition scenario as an example.

[0040] The following describes in detail a target recognition method, device, electronic device, storage medium, and program product proposed in the present disclosure in conjunction with the accompanying drawings.

[0041] Figure 3 The following is a flow chart of a target recognition method provided by an embodiment of the present disclosure. Figure 3 As shown, the method is applied to a vehicle, and the method comprises the following steps:

[0042] Step 101, obtaining laser radar data, where the laser radar data includes environmental information or laser radar location information.

[0043] In one implementation of the present disclosure, the laser radar data includes surrounding environmental information and current laser radar position information, wherein the environmental information can be obtained by collecting surrounding environment through the laser radar, and the current laser radar position information can be obtained through user feedback information.

[0044] LiDAR is usually composed of a laser transmitter, a receiver, a scanning system, and a computing unit. The laser transmitter generates a series of laser pulses, which are then rotated or adjusted in direction by the scanning system to irradiate the laser beam onto the target object. The receiver receives the reflected laser and converts it into an electrical signal. The computing unit processes and analyzes the received signal to calculate the position and distance of the target object. The surrounding environmental data is obtained through the above preliminary identification of the target object.

[0045] Step 102: Determine a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area based on the point cloud feedback information.

[0046] In the present disclosure, the point cloud feedback information is a pre-stored rule for dividing the field of view of the laser radar into a core focus area and a non-focus area, and the first field of view area is the core focus area.

[0047] The core focus area may specifically include a ground area and an area of ​​interest, and the non-core focus area may specifically include a sky area. The area of ​​interest may specifically refer to an area of ​​interest that the current vehicle needs to identify and is determined based on the vehicle information of the vehicle and user feedback information.

[0048] In one implementation of the present disclosure, the point cloud feedback information refers to the requirement for point cloud density for identifying target objects in the first field of view. In the present disclosure, the requirement for point cloud density is related to angular resolution. The denser the point cloud density requirement, the smaller the required angular resolution, that is, the more laser points are distributed within a unit spatial angle, and the stronger its ability to resolve objects will be. In response to the point cloud feedback information, the first angular resolution of the first field of view can be obtained based on environmental information and / or the position of the laser radar. Among them, the first field of view needs to be determined before determining the first angular resolution. The first field of view refers to a necessary field of view based on user needs, that is, a ground area and an area of ​​interest. The first angular resolution is obtained through point cloud data in the first field of view, specifically, based on the point cloud feedback information in the first field of view, the required point cloud data in the first field of view is determined, and based on the point cloud data, the current first angular resolution is determined.

[0049] It should be noted that in the present disclosure, the first angular resolution of the ground area and the first angular resolution of the area of ​​interest can be the same or different. The specific angular resolution size can be set according to vehicle information and user needs, and is not limited in the embodiments of the present disclosure.

[0050] Step 103: Identify a target object in a first field of view according to the first angular resolution.

[0051] In one embodiment of the present disclosure, according to the first angle resolution determined above, the first field of view area is identified by a laser radar to identify a target object in the first field of view area. The target object refers to an identifiable object in the first field of view area, such as a pedestrian, a vehicle, a cone, a carton, etc.

[0052] In the process of identifying the target object, a target recognition algorithm can be combined to identify small targets at close range, so as to fully identify the target object in the first field of view under the requirement of low cost.

[0053] Therefore, according to an embodiment of the present disclosure, by acquiring lidar data; determining a first angular resolution of a first field of view corresponding to the lidar data, the first field of view includes a ground area and an area of ​​interest; and identifying a target object in the first field of view based on the first angular resolution, so that only the angular resolution of the ground area and the area of ​​interest is required in the process of identifying the target object, and the angular resolution of the sky area or the area of ​​non-interest does not need to be considered, thereby avoiding redundancy of the field of view area, reducing recognition costs, and improving recognition efficiency.

[0054] Figure 4 A flowchart of a target recognition method provided in an embodiment of the present disclosure. Figure 4 based on Figure 3 In the embodiment shown, step 102 and step 103 are further defined. Figure 4 In the embodiment shown, step 102 includes step 202, step 203, and step 204, and step 103 includes step 205. Figure 4 As shown, the method includes the following steps.

[0055] Step 201, obtaining lidar data.

[0056] In one embodiment of the present disclosure, the laser radar data includes environmental information, and step 201 has the same or similar function as the above-mentioned step 101. Its implementation can be performed with reference to the above-mentioned embodiment and will not be repeated here.

[0057] Step 202: acquiring first point cloud data of a second field of view area corresponding to the environmental information according to the environmental information, wherein the second field of view area includes a core area and a non-core area.

[0058] In one embodiment of the present disclosure, the laser radar obtains first point cloud data in the second field of view based on the initially identified environmental information. Point cloud data refers to a data set of spatial points scanned by a three-dimensional laser radar device. The second field of view refers to the traditional field of view of the laser radar, such as a field of view of 120°*25°, which includes a core area and a non-core area, specifically, an area of ​​interest in the ground area and a sky area.

[0059] It should be noted that the sizes of the core area and the non-core area (ie, the ground area, the sky area, and the area of ​​interest) in the second field of view can be set according to actual needs and are not limited in the embodiments of the present disclosure.

[0060] Step 203: determine a second angular resolution corresponding to the first point cloud data.

[0061] In some embodiments of the present disclosure, the second angular resolution is determined based on the first point cloud data obtained in step 202. In the present disclosure, the second angular resolution is uniformly distributed in the first field of view. Angular resolution may also refer to the density of point cloud data. In the present disclosure, the second angular resolution may be as follows: Figure 2 The range shown is 0.1°*0.2°.

[0062] Step 204 , in response to the point cloud feedback information, determine the first field of view area, and adjust the second angular resolution of the second field of view area to obtain the first angular resolution.

[0063] In some embodiments of the present disclosure, in response to point cloud feedback information, non-core areas in the second field of view are deleted and the second angular resolution of some core areas is lowered to obtain the first angular resolution of the first field of view.

[0064] In the present disclosure, the sky area in the second field of view may be deleted, and the angular resolution of the ground area in the core area may be lowered. That is, part of the core area may specifically refer to the ground area.

[0065] In the present disclosure, according to the user's point cloud feedback information (i.e., point cloud demand), such as Figure 5 The figure shows the distribution of the first field of view, where the area pointing to the sky does not need to be collected in practical applications, so the sky area can be deleted; similarly, the ground area intersects with the ground within 24 meters, so the angular resolution of the ground area can be reduced, and the area of ​​interest (i.e., the central area 6 to 7°) is a long-distance area of ​​interest, and the angular resolution can still be maintained the same as the second angular resolution.

[0066] It is understandable that the point cloud feedback information is set according to actual conditions and is not limited in the embodiments of the present disclosure.

[0067] Step 205 : Identify the target object in the first field of view according to the first angular resolution and the target recognition algorithm.

[0068] In the present disclosure, the position of the target object in the first field of view area can be determined according to the first angular resolution and the target recognition algorithm.

[0069] In some embodiments of the present disclosure, according to Figure 6The first angular resolution finally determined as shown is used to identify the target object in the first field of view area, and the identification result is as follows: Figure 7 As shown, the recognition results for target objects that are close and small in size are poor, so it is necessary to combine the target recognition algorithm to solve the above problems. The target recognition algorithm can include the Lidar tracking algorithm and the visual occupancy algorithm. The Lidar tracking algorithm can track the position and speed of the target object and supplement the information of the close-range small target by analyzing these data. In addition, the visual occupancy algorithm can also provide information about the surrounding environment. The above target recognition technology uses a camera and a computer vision algorithm to generate a two-dimensional image of the surrounding environment, and uses this image to infer the position of the object in three-dimensional space. By combining Lidar data with the visual occupancy algorithm, small target objects in the surrounding environment can be perceived more accurately.

[0070] To summarize, according to the embodiments of the present disclosure, the data collected by the lidar is processed, that is, the point cloud data corresponding to each area is first determined, and the corresponding angular resolution (or point cloud density) requirements in each point cloud data are determined, and then the collected data is deleted and other operations are performed according to the requirements, thereby reducing the consumption of subsequent processing resources, avoiding redundancy in the field of view, reducing recognition costs, and improving recognition efficiency.

[0071] Figure 8 A flowchart of a target recognition method provided in an embodiment of the present disclosure. Figure 8 based on Figure 3 In the embodiment shown, step 102 and step 103 are further defined. Figure 8 In the embodiment shown, step 102 includes step 302, step 303, and step 304, and step 103 includes step 305. Figure 8 As shown, the method includes the following steps.

[0072] Step 301, obtaining lidar data.

[0073] In one embodiment of the present disclosure, the laser radar data includes the location information of the laser radar, and step 301 has the same or similar function as the above-mentioned step 101. Its implementation can be performed with reference to the above-mentioned embodiment and will not be repeated here.

[0074] Step 302: Determine a first field of view area and visible points in the first field of view area based on the position information and the point cloud feedback information.

[0075] In some embodiments of the present disclosure, the location information refers to the installation location information of the laser radar fed back by the user. Based on the location information, the point cloud feedback information and the vehicle information, the first field of view area and the first visible point are determined, and the first visible point is the intersection of the boundary of the first field of view area and the ground; based on the area of ​​interest of the first field of view area, the second visible point is determined, and the second visible point is the intersection of the boundary of the area of ​​interest and the ground.

[0076] In an optional embodiment of the present disclosure, the third visible point may also be determined based on the area of ​​interest of the first visual field area.

[0077] In the present disclosure, the first visible point refers to the intersection of the lower boundary of the first field of view and the ground, the second visible point refers to the intersection of the region of interest and the ground, and the third visible point refers to the intersection of the region of interest and the ground within the error range taking into account the installation error of the laser radar. The installation error is determined according to the actual situation and is not limited in the embodiments of the present disclosure.

[0078] Step 303: Acquire second point cloud data of the first field of view area based on the visible point.

[0079] In some embodiments of the present disclosure, the second point cloud data of the first field of view area is directly collected through the visible point, that is, the second point cloud data of the area of ​​interest and the ground area is directly collected through the first visible point and the second visible point.

[0080] Since, in an optional embodiment of the present disclosure, a third visible point can also be determined, the second point cloud data of the area of ​​interest and the ground area can be directly collected through the first visible point, the second visible point and the third visible point.

[0081] Step 304: determine a first angular resolution of a first field of view area corresponding to the second point cloud data.

[0082] In some embodiments of the present disclosure, according to the second point cloud data determined above, Figure 6 The first angular resolution is shown.

[0083] Step 305: Identify the target object in the first field of view according to the first angular resolution and the target recognition algorithm.

[0084] Step 305 has the same or similar function as the above-mentioned step 205, and its implementation method can be performed with reference to the above-mentioned embodiment, which will not be described in detail here.

[0085] To summarize, according to the embodiments of the present disclosure, by obtaining the laser radar installation position information of the target vehicle model, the first visible point is determined using the laser radar installation position information and the body information of the target vehicle model, and the second visible point is determined using the area of ​​interest, the position of the visible point is changed to avoid redundancy in the field of view, reduce recognition costs, and improve recognition efficiency.

[0086] Corresponding to the above-mentioned target recognition method, the present disclosure also proposes a target recognition device. Fig. 9 FIG. 9 is a schematic diagram of a target recognition device 900 provided in an embodiment of the present disclosure. Fig. 9 As shown, the device is configured in a vehicle, and the device includes:

[0087] An acquisition unit 910 is used to acquire laser radar data, where the laser radar data includes environmental information or position information of the laser radar;

[0088] A determination unit 920 is used to determine a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area according to the point cloud feedback information, wherein the point cloud feedback information is a pre-stored rule for dividing the field of view area of ​​the laser radar into a core focus area and a non-focus area, and the first field of view area is the core focus area;

[0089] The identification unit 930 is used to identify the target object in the first field of view according to the first angular resolution.

[0090] In some embodiments, the lidar data includes environmental information, and the determination unit 920 is used to: obtain first point cloud data of a second field of view corresponding to the environmental information based on the environmental information, the second field of view including a core area and a non-core area; determine a second angular resolution corresponding to the first point cloud data; determine the first field of view in response to point cloud feedback information, and adjust the second angular resolution of the second field of view to obtain the first angular resolution.

[0091] In some embodiments, the determination unit 920 is used to: in response to the demand feedback information, delete the non-core area in the second field of view area and lower the second angular resolution of some core areas to obtain the first angular resolution of the first field of view area.

[0092] In some embodiments, the lidar data includes the position information of the lidar, and the determination unit 920 is used to: determine the first field of view area and the visible point of the first field of view area based on the position information and the point cloud feedback information; obtain the second point cloud data of the first field of view area based on the visible point; determine the first angular resolution of the first field of view area corresponding to the second point cloud data.

[0093] In some embodiments, the visible point includes a first visible point and a second visible point, and the determination unit 920 is used to: determine the first field of view area and the first visible point based on the position information, point cloud data and vehicle information, the first visible point being the intersection of the boundary of the first field of view area and the ground; determine the second visible point based on the area of ​​interest of the first field of view area, the second visible point being the intersection of the boundary of the area of ​​interest and the ground.

[0094] In some embodiments, the recognition unit 930 is used to determine the position of the target object in the first field of view according to the first angular resolution and the target recognition algorithm.

[0095] According to an embodiment of the present disclosure, laser radar data is acquired, the laser radar data includes environmental information or position information of the laser radar; based on the point cloud feedback information, a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area are determined; based on the first angular resolution, a target object in the first field of view area is identified, so that only the angular resolution of the ground area and the area of ​​interest is required in the process of identifying the target object, and the angular resolution of the sky area or the area of ​​non-interest does not need to be considered, thereby avoiding redundancy of the field of view area, reducing recognition cost, and improving recognition efficiency.

[0096] It should be noted that since the device embodiment of the present disclosure corresponds to the above-mentioned method embodiment, the above-mentioned explanation of the method embodiment is also applicable to the device of the present embodiment, and the principle is the same. For details not disclosed in the device embodiment, reference can be made to the above-mentioned method embodiment, and they will not be repeated in this disclosure.

[0097] According to an embodiment of the present disclosure, the present disclosure provides a vehicle, the aforementioned target recognition method can be applied to the vehicle, and the aforementioned target recognition device can be configured in the vehicle.

[0098] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0099] Fig.10 A schematic block diagram of an example electronic device 1000 that can be used to implement an embodiment of the present disclosure 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 processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0100] like Fig.10As shown, the device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 1002 or a computer program loaded from a storage unit 1008 to a RAM (Random Access Memory) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An I / O (Input / Output) interface 1005 is also connected to the bus 1004.

[0101] A number of components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0102] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as a method for target recognition. For example, in some embodiments, the method for target recognition may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute the aforementioned target recognition method in any other appropriate manner (eg, by means of firmware).

[0103] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0104] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0105] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0106] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).

[0107] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0108] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0109] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0110] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0111] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A target recognition method, characterized in that: The method is applied to a vehicle, and comprises: Acquire laser radar data, where the laser radar data includes environmental information or installation location information of the laser radar; Determine, according to the point cloud feedback information, a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area, wherein the point cloud feedback information is a pre-stored rule for dividing the field of view area of ​​the laser radar into a core area of ​​interest and a non-area of ​​interest, and the first field of view area is a core area of ​​interest; A target object in the first field of view is identified according to the first angular resolution.

2. The method according to claim 1, characterized in that The laser radar data includes environmental information, and determining, according to the point cloud feedback information, a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area includes: Acquire, according to the environmental information, first point cloud data of a second field of view area corresponding to the environmental information, wherein the second field of view area includes a core focus area and a non-focus area; Determining a second angular resolution corresponding to the first point cloud data; In response to the point cloud feedback information, the first field of view area is determined, and the second angular resolution of the second field of view area is adjusted to obtain the first angular resolution.

3. The method according to claim 2, characterized in that The determining the first field of view area in response to the point cloud feedback information, and adjusting the second angular resolution of the second field of view area to obtain the first angular resolution includes: In response to the point cloud feedback information, a non-core area in the second field of view is deleted and the second angular resolution of part of the core area is lowered to obtain the first angular resolution of the first field of view.

4. The method according to claim 1, characterized in that: The laser radar data includes position information of the laser radar, and determining, according to the point cloud feedback information, a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area includes: Determine the first field of view area and visible points in the first field of view area based on the position information and the point cloud feedback information; Based on the visible point, obtaining second point cloud data of the first field of view area; A first angular resolution of a first field of view area corresponding to the second point cloud data is determined.

5. The method according to claim 4, characterized in that The visible points include a first visible point and a second visible point, and based on the position information, determining the visible points of the first visual area includes: Based on the position information, the point cloud feedback information and the vehicle information, determine a first visual area and a first visible point, where the first visible point is an intersection of a boundary of the first visual area and the ground; Based on the area of ​​interest of the first visual area, a second visible point is determined, where the second visible point is an intersection point of a boundary of the area of ​​interest and the ground.

6. The method according to claim 1, characterized in that The identifying the target object in the first field of view area according to the first angular resolution includes: The position of the target object in the first field of view is determined according to the first angular resolution and a target recognition algorithm.

7. A target recognition device, characterized in that: The device comprises: An acquisition unit, used to acquire laser radar data, wherein the laser radar data includes environmental information or position information of the laser radar; a determination unit, configured to determine, according to point cloud feedback information, a first field of view area corresponding to the laser radar data and a first angular resolution corresponding to the first field of view area, wherein the point cloud feedback information is a pre-stored rule for dividing the field of view area of ​​the laser radar into a core area of ​​interest and a non-area of ​​interest, and the first field of view area is a core area of ​​interest; An identification unit is used to identify a target object in the first field of view according to the first angular resolution.

8. An electronic device, characterized in that: include: 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, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

11. A vehicle, characterized in that: The device comprises the target identification device as claimed in claim 7 or the electronic device as claimed in claim 8.

Images