Method and apparatus for estimating size of target object

Abstract

The present disclosure provides a method for estimating a size of a target object, comprising: obtaining roadside sensing data determined based on radar sensing signals from one or more roadside sensing devices and vehicle-end sensing data determined based on radar sensing signals from the one or more roadside sensing devices, the vehicle-end sensing data being determined based on radar sensing signals from the one or more roadside sensing devices, and the vehicle-end sensing data being determined based on radar sensing signals from the one or more roadside sensing devices; the vehicle end sensing data is determined based on radar sensing signals from one or more vehicle end sensing devices; determining one or more target objects associated with the roadside sensing data and the vehicle end sensing data based on the roadside sensing data and the vehicle end sensing data; and estimating the target object size of at least one target object in the one or more target objects based on the road side sensing data and the vehicle end sensing data.

Description

Technical Field

[0001] The present disclosure generally relates to the field of vehicle driving assistance, and more particularly to a method and apparatus for estimating the size of a target object. Background Art

[0002] With the continuous development of sensing technology, vehicle driving assistance functions are becoming more and more popular. Some driving assistance functions can provide users or vehicle autonomous driving systems with perception information about the vehicle's surrounding environment based on vehicle-side sensing devices (such as cameras, millimeter-wave radars, lidars, etc.), so as to facilitate users or autonomous driving systems to take corresponding control measures. These perception information includes, for example, the position, speed, three-dimensional size of target objects (such as motor vehicles, bicycles, pedestrians, etc.) in the environment around the main vehicle relative to the main vehicle. The accuracy of the above perception information directly affects the user or the autonomous driving system's judgment of the current driving environment.

[0003] However, vehicle-mounted sensing devices are often limited by the vehicle-mounted environment in terms of distance, angle, etc. For example, for some large truck objects, the vehicle-mounted sensing devices of the host vehicle behind them can often only obtain sensing data of the rear and sides of the truck object, and it is difficult to accurately estimate the overall size of the truck object.

[0004] Therefore, it is desirable to provide a method and apparatus that can more accurately estimate the size of a target object, so as to improve the performance of a perception system in estimating the geometric size of a target object. Summary of the invention

[0005] According to one aspect of the present disclosure, a method for estimating the size of a target object is provided, comprising: obtaining roadside perception data and vehicle-side perception data, wherein the roadside perception data is determined based on radar sensing signals from one or more roadside perception devices, and the vehicle-side perception data is determined based on radar sensing signals from one or more vehicle-side perception devices; based on the roadside perception data and the vehicle-side perception data, determining one or more target objects associated with the roadside perception data and the vehicle-side perception data; and estimating the target object size of at least one of the one or more target objects based on the roadside perception data and the vehicle-side perception data.

[0006] According to another aspect of the present disclosure, a device for estimating the size of a target object is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the method according to the present disclosure.

[0007] According to yet another aspect of the present disclosure, a computer-readable medium is provided, which stores a computer program including instructions, which, when executed by a processor, causes the processor to be configured to perform the method according to the present disclosure.

[0008] According to yet another aspect of the present disclosure, a device for estimating a size of a target object is provided, comprising a unit for executing the method according to the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Various embodiments of the claimed subject matter will now be described by way of example with reference to the accompanying drawings. In the different drawings, the same reference numerals are used to designate the same or similar components.

[0010] Figure 1 A schematic diagram of a device for estimating the size of a target object according to an embodiment of the present disclosure is shown.

[0011] Figure 2 A schematic diagram of a system 200 for estimating the size of a target object according to an embodiment of the present disclosure is shown.

[0012] Figure 3 A flow chart of a method 300 for estimating the size of a target object according to an embodiment of the present disclosure is shown.

[0013] Figure 4 A block diagram of a device 400 for estimating the size of a target object according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0014] In the following description, many specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure. However, those skilled in the relevant art will recognize that the present disclosure can be implemented without one or more of the specific details, or alternative methods, components, etc. can be used to implement the present disclosure. In some instances, well-known structures and operations are not shown or described in detail to avoid unnecessarily obscuring the present disclosure.

[0015] Figure 1 FIG. 1 is a schematic diagram of a device for estimating the size of a target object according to an embodiment of the present disclosure. Figure 1 In the embodiment of FIG. 1 , the host vehicle 108 and the target object 112 ( Figure 1 1 , a target truck 112 is shown traveling in the same direction on the road 102 , and the host vehicle 108 is located behind the target truck 112 .

[0016] In order to obtain the three-dimensional size information of the target truck 112 so as to facilitate the host vehicle 108 to take corresponding actions (such as overtaking), the host vehicle 108 is provided with a vehicle-side sensing device 110 for obtaining the size information of the target truck 112. For example, the vehicle-side sensing device 110 may include a device with a depth detection function such as a millimeter wave radar and / or a laser radar. Figure 1 The solid circle located at the rear of the target truck 112 schematically shows some points of the radar point cloud sensed by the vehicle-side sensing device 110. Due to the relative position limitation between the vehicle-side sensing device 110 and the target truck 112, the partial points that can be obtained by the vehicle-side sensing device 110 only cover a part of the rear area of ​​the target truck 112. Due to the lack of sensing data related to the front, side, top and other positions of the target truck 112, it is often difficult to accurately estimate the overall size of the target truck 112 only with the vehicle-side sensing device 110.

[0017] In the disclosed embodiment, one or more roadside sensing devices 104, 106 may be additionally used to estimate the size of the target truck 112. Figure 1 As shown in FIG. 1 , the roadside sensing devices 104 and 106 are disposed on a mounting bracket near the road 102, and can sense the target truck 112 at an angle different from that of the vehicle-side sensing device 110. In one embodiment, the roadside sensing devices 104 and 106 may also include devices such as millimeter wave radars and / or laser radars. Figure 1 The hollow dots located at the front and top of the target truck 112 schematically show some points of the radar point cloud sensed by the radar of the roadside perception device 104, and the dots with diagonal shadows located at the right side and top of the target truck 112 schematically show some points of the radar point cloud sensed by the radar of the roadside perception device 106. By clustering the radar point cloud data obtained by the vehicle-side perception device 110 and the roadside perception devices 104 and 106, the target truck 112 can be identified and its three-dimensional size can be determined.

[0018] It should be understood that although Figure 1 Two roadside sensing devices 104 and 106 are shown in the figure, but one or more than two roadside sensing devices may be used to implement the present disclosure. Figure 1 In FIG. 1 , since the main vehicle 108 and the target truck 112 are shown in a top view, each dot should be understood as covering the three-dimensional surface of the target truck 112 according to the surface shape of the target truck 112. For example, although in Figure 1 The black dots located at the rear of the target truck 112 are shown as being arranged in a straight line, but they should be understood to be distributed in the rear plane of the target truck 112. Figure 1 The number, position, shape and other attributes of each element are only shown in an exemplary manner, and are not intended to impose any specific limitations on the above attributes of each element. Figure 2 The process of estimating the size of the target object is further explained.

[0019] Figure 2A schematic diagram of a system 200 for estimating the size of a target object according to an embodiment of the present disclosure is shown. The system 200 is composed of a roadside subsystem 202 and a vehicle-side subsystem 204 .

[0020] In one embodiment, the roadside subsystem 202 includes a roadside perception unit 206 , a roadside fusion unit 208 and a roadside communication unit 210 ; the vehicle-side subsystem 204 includes a vehicle-side perception unit 212 , a vehicle-side fusion unit 214 and a vehicle-side communication unit 216 .

[0021] The roadside sensing unit 206 may be coupled to Figure 1 One or more roadside perception devices 104, 106 shown in the figure are used to obtain sensor data associated with the target object. For example, the sensor data obtained can be radar point cloud data generated by a millimeter wave radar and / or a laser radar. In one embodiment, the roadside perception unit 206 can also be coupled to one or more cameras. In this embodiment, the sensor data also includes an image signal obtained by an image sensor in the camera (which can be a static picture or a dynamic set of video frames). The roadside perception unit 206 sends the obtained sensor data associated with the target object to the roadside fusion unit 208.

[0022] The roadside fusion unit 208 is used to process the received sensor data to generate roadside perception data. The roadside perception data includes a sensor data set corresponding to a target object. In one embodiment, the roadside fusion unit 208 can analyze the sensor data from multiple roadside perception devices, identify one or more target objects, and determine a sensor data set corresponding to at least one of the one or more target objects. For example, Figure 1 In the example of , the roadside fusion unit 208 can cluster the radar point clouds sensed by the roadside perception devices 104 and 106 respectively to identify the target object (e.g., the target truck 112), and determine the radar point cloud data set associated with the target object. In another embodiment, the roadside fusion unit 208 can also cluster the sensor data from different types of roadside perception devices, for example, the roadside fusion unit 208 can cluster the sensor data from the camera and the lidar to more accurately identify the target object.

[0023] The roadside communication unit 210 is used to send the roadside sensing data generated by the roadside fusion unit 208 to the vehicle-side communication unit 216 of the vehicle-side subsystem 204. The vehicle-side communication unit 216 is used to send the received roadside sensing data to the vehicle-side fusion unit 214.

[0024] The vehicle-side sensing unit 212 in the vehicle-side subsystem 204 can be coupled to Figure 1The vehicle-side perception device 110 shown in is used to obtain corresponding sensor data associated with the target object. For example, the sensor data obtained may be radar point cloud data generated by a vehicle-mounted millimeter-wave radar and / or a laser radar. In one embodiment, the vehicle-side perception unit 212 may also be coupled to one or more vehicle-mounted cameras. In this embodiment, the sensor data also includes an image signal obtained by an image sensor in the vehicle-mounted camera. The vehicle-side perception unit 212 may process the various sensor data obtained to generate vehicle-side perception data. The vehicle-side perception data includes a set of sensor data corresponding to the target object. For example, the vehicle-side perception unit 212 may cluster sensor data from different types of vehicle-side perception devices (such as cameras, laser radars, and millimeter-wave radars) to identify a target object (such as a target truck 112), and determine a set of radar point cloud data associated with the target object.

[0025] The vehicle-side fusion unit 214 determines the corresponding target object and the size of the target object based on the received roadside perception data and vehicle-side perception data. Since the roadside perception device and the vehicle-side perception device have different angles, in one embodiment, the vehicle-side fusion unit 214 needs to perform a coordinate system conversion to determine the relative position and / or relative speed between the radar point cloud associated with the roadside perception data and the radar point cloud associated with the vehicle-side perception data, so as to determine the target object. For example, when it is determined that some points in two groups of point clouds have consistent positions or speeds, it can be determined that the above-mentioned some points belong to the same target object (such as a target truck), and then the three-dimensional size of the target object is estimated based on the some points. In one embodiment, the vehicle-side fusion unit 214 can also determine the target object based on image signals from a roadside camera and / or a vehicle-mounted camera.

[0026] In some embodiments, the roadside fusion unit 208 is optional. The sensor data from the roadside perception unit 206 can be directly sent to the vehicle-side fusion unit 214 via the roadside communication unit 210 and the vehicle-side communication unit 216. In this case, the vehicle-side fusion unit 214 can also directly receive sensor data from the vehicle-side perception device from the vehicle-side perception unit 212, and determine the target object and its size based on all sensor data in the vehicle-side fusion unit 214.

[0027] Compared with the method of relying solely on the host vehicle's own on-board perception equipment to estimate the size of the target object, the present invention utilizes more angles provided by the roadside perception equipment, effectively avoiding the problem of being unable to estimate the overall size of the target object due to, for example, occlusion, and thus can provide target object size information more accurately.

[0028] Figure 3 A flow chart of a method 300 for estimating the size of a target object according to an embodiment of the present disclosure is shown.

[0029] At step S302, method 300 includes obtaining roadside perception data and vehicle-side perception data, wherein the roadside perception data is determined based on radar sensing signals from one or more roadside perception devices, and the vehicle-side perception data is determined based on radar sensing signals from one or more vehicle-side perception devices. In one embodiment, the roadside perception device and the vehicle-side perception device respectively include one or more of the following: millimeter wave radar and laser radar. In one embodiment, the roadside perception data and the vehicle-side perception data include radar point cloud data.

[0030] At step S304, method 300 includes determining one or more target objects associated with the roadside perception data and the vehicle-side perception data based on the roadside perception data and the vehicle-side perception data. In one embodiment, the one or more target objects are further determined based on an image signal from an image sensor. In one embodiment, the one or more target objects are determined based on the relative position and / or relative speed between a radar point cloud associated with the roadside perception data and a radar point cloud associated with the vehicle-side perception data. In one embodiment, the relative position and / or relative speed between the radar point cloud associated with the roadside perception data and the radar point cloud associated with the vehicle-side perception data is determined by coordinate system transformation.

[0031] At step S306 , the method 300 includes estimating a target object size of at least one target object among the one or more target objects based on the roadside perception data and the vehicle-side perception data.

[0032] Figure 4 A block diagram of a device 400 for estimating the size of a target object according to an embodiment of the present disclosure is shown. In one embodiment, the device 400 may include a computing device such as a desktop computer, a notebook computer, and a vehicle electronic control unit (ECU).

[0033] The device 400 includes a processor 402 connected to an internal communication bus 408, and the processor 402 is used to execute instructions in a memory 404 to implement the method for estimating the size of a target object described in detail above. Examples of the processor 402 may include a central processing unit (CPU), a microcontroller, and the like. The memory 404 includes various forms of memory, such as DRAM. The device 400 may also include an input interface 410 and an output interface 412. The input interface 410 is used to receive input signals and data from an input device (such as a mouse, a keyboard coupled to a computing device, a sensor device coupled to an ECU, etc.). The output interface 412 is used to send output signals and data to an output device (such as a display). In addition, the device 400 may also include a non-volatile storage device 406 for tangibly storing computer program instructions and data.

[0034] The various methods, steps, operations, units, modules, components, models, and networks described in conjunction with the present disclosure may be implemented as hardware, software executed by a processor, firmware, or any combination thereof. According to one or more aspects of the present disclosure, a computer program product for estimating the size of a target object may include a computer program for implementing the above-mentioned reference Figure 3 A processor may execute computer instructions for one or more of the methods or steps described. According to other aspects of the present disclosure, a computer readable medium may store computer instructions for estimating the size of a target object, and when the instructions are executed by a processor, the processor may execute the above-mentioned reference Figure 3 One or more of the methods or steps described. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. Any connection can be properly referred to as a computer-readable medium.

[0035] In addition to the description herein, various modifications may be made to the embodiments and implementations of the present disclosure without departing from the scope of the embodiments and implementations of the present disclosure. Therefore, the descriptions and examples herein should be interpreted as illustrative rather than limiting. The scope of the present disclosure should be measured only by reference to the claims.

Claims

1. A method for estimating the size of a target object, comprising: Obtaining roadside perception data and vehicle-side perception data, wherein the roadside perception data is determined based on radar sensing signals from one or more roadside perception devices, and the vehicle-side perception data is determined based on radar sensing signals from one or more vehicle-side perception devices; Based on the roadside perception data and the vehicle-side perception data, determining one or more target objects associated with the roadside perception data and the vehicle-side perception data; and Based on the roadside perception data and the vehicle-side perception data, a target object size of at least one target object among the one or more target objects is estimated.

2. The method according to claim 1, wherein: The roadside sensing device and the vehicle-side sensing device respectively include one or more of the following: millimeter wave radar and laser radar.

3. The method according to claim 1, wherein: The roadside perception data and the vehicle-side perception data include radar point cloud data.

4. The method according to claim 1, wherein: The one or more target objects are further determined based on the image signal from the image sensor.

5. The method according to claim 3, wherein: The one or more target objects are determined based on the relative position and / or relative speed between the radar point cloud associated with the roadside perception data and the radar point cloud associated with the vehicle-side perception data.

6. The method according to claim 5, wherein: The relative position and / or relative speed between the radar point cloud associated with the roadside perception data and the radar point cloud associated with the vehicle-side perception data are determined through coordinate system conversion.

7. A device for estimating the size of a target object, comprising: Memory; A processor is coupled to the memory, wherein the processor is configured to execute the method according to any one of claims 1 to 6.

8. A computer readable medium storing a computer program comprising instructions which, when executed by a processor, cause the processor to be configured to perform the method according to any one of claims 1 to 6.

9. An apparatus for estimating the size of a target object, comprising means for executing the method according to any one of claims 1-6.

Images