Method and device for detecting target object, controller, vehicle and medium

Abstract

The embodiment of the invention relates to a method and device for detecting a target object, a controller, a vehicle and a medium. The method includes acquiring radar data and image data related to a target object. The method further includes determining whether the radar data is abnormal data based on a height of the target object determined by the radar data. In addition, the method also includes, in response to the radar data being abnormal data, detecting the target object using the image data, and discarding the radar data. According to the scheme for detecting the target object provided by the embodiment of the invention, whether the radar data is the abnormal data or not can be determined in the target object detection, and after the radar data is determined to be the abnormal data, target object detection can be carried out only by using the image data instead of using the radar data, so that the target object detection efficiency is improved. And detection errors caused by abnormal data are avoided, so that the target object detection effect can be improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computers, and more particularly, to methods, devices, controllers, vehicles, and media for detecting target objects. Background Art

[0002] Target detection technology is widely used in all walks of life and has become one of the key technologies in today's technology field. It plays a crucial role in fields such as assisted driving and autonomous driving. The rapid development of target detection not only provides more intelligent and efficient solutions for various industries, but also brings great convenience to people's lives and work.

[0003] In target detection technology, image data and radar data are usually used for joint analysis. Image data provides rich visual information, which helps to accurately identify the appearance and shape features of the target. Radar data, on the other hand, provides information such as distance, speed, and direction by emitting radio waves and measuring the signals reflected back. Summary of the Invention

[0004] Embodiments of the present disclosure provide methods, devices, controllers, vehicles, and media for detecting target objects.

[0005] According to a first aspect of the present disclosure, there is provided a method for detecting a target object. The method includes obtaining radar data and image data related to the target object. The method further includes determining whether the radar data is abnormal data based on the height of the target object determined from the radar data. Additionally, the method includes, in response to the radar data being abnormal data, using the image data to detect the target object while discarding the radar data.

[0006] According to a second aspect of the present disclosure, there is provided a device for detecting a target object. The device includes a target data acquisition unit configured to obtain radar data and image data related to the target object. The device further includes an abnormal data determination unit configured to determine whether the radar data is abnormal data based on the height of the target object determined from the radar data. Additionally, the device includes a target object detection unit configured to, in response to the radar data being abnormal data, use the image data to detect the target object while discarding the radar data.

[0007] According to a third aspect of the present disclosure, there is provided a controller. The controller includes at least one processor; and a memory coupled to the at least one processor and having instructions stored thereon that, when executed by the at least one processor, cause the controller to perform the steps of the method in the first aspect of the present disclosure.

[0008] According to a fourth aspect of the present disclosure, there is provided a vehicle that includes the controller in the third aspect of the present disclosure.

[0009] According to a fifth aspect of the present disclosure, a machine-readable storage medium is provided. Machine-executable instructions are stored on the machine-readable storage medium, and the machine-executable instructions are executed by a processor to implement the steps of the method in the first aspect of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] By describing the exemplary embodiments of the present disclosure in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present disclosure will become more apparent. Among them, in the exemplary embodiments of the present disclosure, the same reference numerals generally represent the same components.

[0011] Figure 1 A schematic diagram showing an example environment in which the device and / or method according to the embodiments of the present disclosure may be implemented;

[0012] Figure 2 A flowchart showing a method for detecting a target object according to an embodiment of the present disclosure;

[0013] Figure 3 A schematic diagram showing a coordinate system for fusing image data and radar data according to an embodiment of the present disclosure;

[0014] Figure 4 A schematic diagram showing a process for detecting a target object according to an embodiment of the present disclosure;

[0015] Figure 5 A schematic diagram showing a device for detecting a target object according to an embodiment of the present disclosure; and

[0016] Figure 6 A schematic block diagram showing an example device suitable for implementing the embodiments of the present disclosure.

[0017] In each of the drawings, the same or corresponding reference numerals indicate the same or corresponding parts. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure.

[0019] As described above, in object detection, image data and radar data are usually used for joint analysis. Fusing image data and radar data can effectively make up for their respective limitations and enhance the robustness and adaptability of object detection. However, in some cases, the radar will return abnormal data. Conventional object detection techniques do not judge the returned radar data, but directly fuse the radar data with the image data. When the radar data is abnormal data, it will lead to poor object detection effects.

[0020] To this end, an embodiment of the present disclosure proposes a solution for detecting a target object. The solution first obtains radar data and image data related to the target object, and then determines whether the radar data is abnormal data according to the height information determined by the radar data. When it is determined that the radar data is abnormal data, only the image data is used for detecting the target object, and the radar data is not used. Through the solution for detecting a target object proposed by the embodiment of the present disclosure, it is possible to first determine whether the radar data is abnormal data during the detection of the target object, and after determining that the radar data is abnormal data, only the image data can be used instead of the radar data for detecting the target object, avoiding detection errors caused by abnormal data, and thus improving the effect of target object detection.

[0021] The embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings, where Figure 1 shows an example environment 100 in which the devices and / or methods of the embodiments of the present disclosure can be implemented.

[0022] As Figure 1 shown, the example environment 100 includes a host vehicle 110, a traffic light pole 120, and a target vehicle 130. The host vehicle 110 may include a vision sensor 112, a radar sensor 114, and a computing device 116. In some embodiments, the vision sensor 112 may be installed on the top of the host vehicle 110. It should be understood that the vision sensor 112 may also be located at other positions of the host vehicle 110, and the present disclosure does not limit this. The vision sensor 112 may include, but is not limited to, a driving recorder, a camera, a video camera device, a camera, or other devices with a video recording function. It mainly includes optical lenses (including optical lenses, filter films, protective films, etc.), image sensors, image signal processors ISP, serializers, and connectors, etc.

[0023] The vision sensor 112 can acquire image data, which includes picture data and video data. For example, the vision sensor 112 can acquire the picture data and video data of the target vehicle 130. In addition, the vision sensor can also acquire the picture data and video data of the traffic light pole 120. Compared with the radar sensor 114, the vision sensor 112 can perform target recognition and classification, while the radar sensor 114 can only detect whether there is an obstacle ahead and cannot accurately identify the category of the obstacle. In some embodiments, various lane line recognition, traffic light recognition, traffic sign recognition, etc. can also be performed using the vision sensor 112.

[0024] Continue to refer to Figure 1 , a radar sensor 114 can be deployed in front of the ego vehicle 110. It should be understood that the radar sensor 114 can also be deployed at other positions of the ego vehicle 110, and the present disclosure does not limit this. The radar sensor 114 can include, but is not limited to, millimeter-wave radar, ultrasonic radar, and lidar. In some embodiments, the radar sensor 114 can be a millimeter-wave radar, which is a radar sensor device that uses electromagnetic waves with a wavelength in the millimeter range to measure distance, angle, and speed. Generally, millimeter waves refer to electromagnetic waves in the frequency range of 30 - 300 GHz (wavelength of 1 - 10 mm). The wavelength of millimeter waves is between centimeter waves and light waves, so millimeter waves have the advantages of both microwave guidance and optoelectronic guidance. In some embodiments, the radar sensor 114 can acquire millimeter-wave radar point cloud data related to the traffic light pole 120. In addition, in some embodiments, the radar sensor 114 can acquire millimeter-wave radar point cloud data related to the target vehicle 130.

[0025] As Figure 1 shown, Example 100 shows a fusion system composed of the vision sensor 112 and the radar sensor 114. However, the ego vehicle 112 can include one or more vision sensors and one or more radar sensors, and the present disclosure does not limit this. In some embodiments, the vision sensor 112 can be a front-view camera, and the radar sensor 112 can be a millimeter-wave radar, and the two form a 1R1V system (R: millimeter-wave radar, V: front-view camera). In the 1R1V system, both the image data and the millimeter-wave radar data can be used to construct the environment model of the ego vehicle, and there are two fusion methods for the image data and the millimeter-wave radar data. The first fusion method can create target objects from the input of the image data and associate them with the millimeter-wave radar data. The second fusion method can create target objects based on the millimeter-wave radar data and associate them with the image data input. The embodiments of the present disclosure are mainly described with the first fusion method, but the embodiments of the present disclosure are equally applicable to the second fusion method.

[0026] Continue to refer to Figure 1, in the first fusion method, the visual sensor 112 is used as the main sensor because the resolution of the visual sensor 112 is higher than that of the radar sensor 114, and it can obtain sufficient environmental details to help the host vehicle 110 recognize the environment. The visual sensor 112 can depict the appearance and shape of objects, read signs, etc. However, it should be understood that the visual sensor 112 is greatly affected by environmental factors and external factors, such as insufficient light in tunnels, driving at night, and reduced visibility caused by foggy weather. Therefore, it is necessary to fuse the radar data of the radar sensor 114 for target detection. Compared with the visual sensor 112, the detection performance of the radar sensor 114 is less affected by extreme weather and light, can work all-weather, and requires lower computing power for information processing, and the distance and radial velocity estimation are more accurate. In some embodiments, the radar sensor 114 is a millimeter-wave radar. Compared with lidar, the millimeter-wave radar has a lower cost and stronger anti-interference ability. Lidar detects by emitting light beams and cannot be turned on in bad weather such as rain, snow, haze, and sandstorms, while millimeter waves have a strong ability to penetrate fog, smoke, and dust, so it can detect in bad weather.

[0027] As Figure 1 shown, the exemplary environment 100 may further include a traffic light pole 120. It should be understood that there may be more traffic light poles and other non-target vehicle objects in the actual environment. As mentioned above, the visual sensor 112 can obtain the image data of the traffic light pole 120, such as picture data and video data. In addition, as mentioned above, since the image data can be used for target recognition and classification, the category of the object in the obtained image data can be determined through the image data. For example, it can be determined through an object classification model that the object in the image data is a traffic light pole rather than other vehicles. It should be understood that in assisted driving or autonomous driving, the focus of target recognition and detection should be on other vehicles or obstacles on the road, rather than stationary objects such as traffic light poles around the road. In addition, as mentioned above, the radar sensor 114 can obtain the radar point cloud data of the traffic light pole 120, but it is impossible to determine through the radar point cloud data that the object in front is the traffic light pole 120 rather than the target vehicle 130. Therefore, when target detection of the target vehicle 130 is required to adjust the assisted driving or autonomous driving strategy of the host vehicle 110, the radar point cloud data of the traffic light pole 120 may be regarded as the radar point cloud data of the target vehicle 130, thus interfering with the target detection of the target vehicle 130.

[0028] Continue to refer to Figure 1, the example environment 100 may further include a target vehicle 130. It should be understood that more other target vehicles may be included in the actual environment. By acquiring image data and radar data, the host vehicle 110 can perform target detection on the target vehicle 130 to adjust the assisted driving or autonomous driving strategy of the host vehicle 110. For example, when the host vehicle 110 activates the Adaptive Cruise Control (ACC) function, target detection of the target vehicle 130 is required to determine parameters such as the distance from the target vehicle 130 to the host vehicle 110, so as to judge whether it is necessary to adjust the speed of the host vehicle 110 or directly brake. In some embodiments, the target vehicle 130 may be stationary, and since the traffic light pole 120 is also stationary, it is impossible to judge whether the acquired radar data comes from the traffic light pole 120 or the target vehicle 130 based on the speed information determined by the radar data. In this case, if the image data and radar data are directly fused to determine the distance from the target vehicle 130 to the host vehicle 110, it may lead to abnormal distance determination (for example, closer than the actual distance), resulting in the host vehicle suddenly decelerating or braking emergently when the ACC function is activated, bringing an uncomfortable experience to the driver. For example, referring to Figure 1 , the actual distance from the traffic light pole 120 to the host vehicle 110 is 140. However, since the radar data may come from the traffic light pole 140, the actual distance from the target vehicle 130 to the host vehicle 110 may be 142. Therefore, if it is not judged whether the radar data comes from the traffic light pole 120 or the target vehicle 130, and the radar data and image data are directly fused to perform target detection on the target vehicle 130, it will result in the determined distance from the target vehicle 130 to the host vehicle 110 being less than the actual distance.

[0029] Therefore, when performing target detection on the target vehicle 130, it is necessary to judge whether the acquired radar data is abnormal data. If the radar data is abnormal data, the radar data needs to be discarded and the image data is used for target detection. If the radar data is normal data, then the image data and radar data can be fused to perform target detection.

[0030] Such as Figure 1As shown, the host vehicle 110 in the example environment 100 may further include a computing device 116. In some embodiments, after acquiring radar data and image data related to the target vehicle 130, target detection may be performed to determine relevant parameters of the target vehicle 130, such as size, speed, and distance to the host vehicle 110, etc. The process of target detection may be executed on the computing device 116. In addition, the process of target detection may also be executed on the computing unit of the vision sensor 112 or the computing unit of the radar sensor 114. The present disclosure places no restrictions on this. In practical applications, the computing device 116 may be deployed on the host vehicle 110 for use, or may be deployed separately. The computing device 116 may include, but is not limited to, any one of the following: mobile phone, tablet computer, personal digital assistant, mobile Internet device, wearable device, in-vehicle device, and other devices supporting network communication, etc. It should be noted that the scenarios applicable to the present invention include, but are not limited to, the field of assisted driving, the field of autonomous driving, the field of obstacle detection, and any other scenarios where target detection is required.

[0031] The foregoing has been described in conjunction with Figure 1 the example environment 100 in which the embodiments of the present disclosure can be implemented. The following will be described in conjunction with Figure 2 a flowchart of a method 200 for detecting a target object according to an embodiment of the present disclosure.

[0032] As Figure 2 shown, at block 202, radar data and image data related to the target object may be acquired. For example, referring to Figure 1 , radar data and image data related to the target vehicle 130 may be acquired, where the image data may be acquired by the vision sensor 112 and the radar data may be acquired by the radar sensor 114.

[0033] At block 204, based on the height of the target object determined from the radar data, it may be determined whether the radar data is abnormal data. For example, the height of the target object may be determined from the radar data to determine whether the radar data is abnormal data. Referring to Figure 1 , as described above, the radar sensor 114 may acquire the radar data of the target vehicle 130, but may also acquire the radar data of the traffic light pole 120. When performing target detection on the target vehicle 130, it is necessary to determine that the radar data comes from the target vehicle 130 rather than the traffic light pole 120. If the radar data comes from the traffic light pole 120, it is abnormal data. Since the height of the traffic light pole 120 is usually relatively high and the height of the target vehicle 130 is lower than that of the traffic light pole 120, the height information determined from the radar data may be used to determine whether the radar data is abnormal data.

[0034] At block 206, in response to the radar data being abnormal data, the image data can be used to detect the target object while discarding the radar data. For example, referring to Figure 1 , when it is determined that the radar data is abnormal data, the image data can be used to detect the target vehicle 130 to determine relevant information about the target vehicle 130. As described above, although in general, fusing image data and radar data for target detection can achieve better detection effects, if the radar data is not judged whether it is abnormal data and the abnormal radar data is used for target detection, it will lead to errors in target detection. For example, the distance from the target vehicle 130 to the host vehicle 110 is incorrectly calculated, resulting in a poor driving experience for the driver or even a safety accident.

[0035] Thus, through the method 200 for detecting a target object according to the embodiments of the present disclosure, it is possible to determine whether the radar data is abnormal data before performing target object detection, and after determining that the radar data is abnormal data, only the image data can be used instead of the radar data for target object detection, avoiding detection errors caused by abnormal data, thereby improving the effect of target object detection.

[0036] Figure 3 FIG. shows a schematic diagram of a coordinate system 300 that fuses image data and radar data according to an embodiment of the present disclosure. The image data and the radar data each have different coordinate systems and different acquisition frequencies. Therefore, it is necessary to convert the data of different coordinate systems to the same coordinate system and perform time registration to achieve data fusion. Therefore, joint calibration of the image data and the radar data is required to determine the conversion relationship between the image data and the radar data, that is, to find the corresponding pixel points in the radar point cloud data and the image data at the same moment. When performing coordinate system conversion, the radar coordinate system can be first converted to the camera coordinate system, then it can be converted from the camera coordinate system to the image coordinate system, and finally it can be converted from the image coordinate system to the pixel coordinate system to achieve the fusion of the image data and the radar data.

[0037] As Figure 3 shown, the coordinate system 300 includes an image target 302 determined by the image data. Since target recognition and classification can be performed through the image data, it can be determined that the image target 302 is the image data of the target vehicle, and it can be known from the image target 302 that the distance from the target vehicle to the host vehicle is 79 meters. In addition, for reference, the coordinate system 300 also includes the actual positions 304, 306, 308, 310, and 312 of the target vehicle changing with time. As Figure 3As shown, there is a certain error between the position of the image target 302 determined from the image data of the target vehicle and the actual position of the target vehicle. This is because there is a certain error in the vision sensor when the distance from the vehicle is relatively far (for example, more than 50 meters). As the host vehicle approaches the target vehicle, this error will gradually decrease.

[0038] In addition, the coordinate system 300 further includes a radar target 314 determined from the radar data of an object other than the target vehicle (for example, a traffic light pole). As mentioned above, since target classification cannot be performed through radar data, it is impossible to determine whether the acquired radar data is from the target vehicle or the traffic light pole. In this case, if the image target 302 and the radar target 314 are directly fused, a large error will occur in the target detection of the target vehicle because the radar target actually comes from the traffic light pole rather than the target vehicle. Therefore, it is necessary to judge the radar data. When it is determined that the radar data is abnormal data, the radar data is discarded and the image data is used to detect the target vehicle. In some embodiments, the height value determined from the radar data can be used to judge the radar data. If the height value is greater than a predetermined height threshold, the radar data can be determined to be abnormal data. For example, if the height determined from the radar data is 5 meters, it can be determined that the radar data comes from an object other than the target vehicle because the height of the target vehicle is lower than 5 meters. In some embodiments, the height value determined from the radar data can be compared with the height value determined from the image data. If the difference between the two is greater than a predetermined threshold, the radar data can be determined to be abnormal data.

[0039] Figure 4 The figure shows a schematic diagram of a process 400 for detecting a target object according to an embodiment of the present disclosure. As Figure 4 shown, at block 402, image data can be acquired using a vision sensor. For example, referring to Figure 1 , the vision sensor 112 can be used to acquire image data. At block 404, radar data can be acquired using a radar sensor. For example, referring to Figure 1 , the radar sensor 114 can be used to acquire radar data. At block 406, the image data and the radar data are converted into the same coordinate system. For example, as Figure 3 described, the image data and the radar data can be converted into a pixel coordinate system.

[0040] At block 408, it can be determined whether the radar data is abnormal data. For example, the height value determined from the radar data can be used to determine whether the radar data is abnormal data. If the height value is greater than a predetermined height threshold, the radar data is abnormal data. If the height value is less than or equal to the predetermined threshold, the radar data is not abnormal data. When it is determined that the radar data is abnormal data, proceed to block 410, and only the image data is used without using the radar data to detect the target vehicle, that is, the radar data is discarded.

[0041] At block 408, when it is determined that the radar data is not abnormal data, proceed to block 412 to determine whether the position difference between the first position determined from the image data and the second position determined from the radar data is greater than or equal to a predetermined position difference threshold. If the position difference is greater than or equal to the predetermined position difference threshold, proceed to block 410 to detect the target vehicle using only the image data without using the radar data. Since the image data and the radar data are compared, abnormal radar data can be avoided from affecting target detection. If the position determined by the radar data has a large gap from the position determined by the image data, the radar data can be discarded and only the image data is used to detect the target object. In some embodiments, since the image data and the radar data have been converted to the same coordinate system, the first position can be determined by the first coordinate information corresponding to the image data, and the second position can be determined by the second coordinate information corresponding to the radar data.

[0042] At block 412, when it is determined that the position difference is less than the predetermined position difference threshold, proceed to block 414. At block 414, determine whether the speed difference between the first speed determined from the image data and the second speed determined from the radar data is greater than or equal to a predetermined speed difference threshold. If the speed difference is greater than or equal to the predetermined speed difference threshold, proceed to block 410 to detect the target vehicle using only the image data without using the radar data. Since the image data and the radar data are compared, abnormal radar data can be avoided from affecting target detection. If the speed determined by the radar data has a large gap from the speed determined by the image data, the radar data can be discarded and only the image data is used to detect the target object. At block 414, when it is determined that the speed difference is less than the predetermined speed difference threshold, proceed to block 416 to detect the target object using the image data and the radar data.

[0043] Through the process 400 of the embodiments of the present disclosure, it can be determined whether the radar data is abnormal data. When it is determined that the radar data is abnormal data, only the image data is used to detect the target object, whereby parameter information related to the target object can be determined, and the assisted driving strategy and / or the autonomous driving strategy related to the host vehicle can be adjusted based on the determined parameter information.

[0044] Figure 5The figure shows a schematic diagram of a device 500 for detecting a target object according to an embodiment of the present disclosure. The device 500 includes a target data acquisition unit 502, an abnormal data determination unit 504, and a target object detection unit 506. The target data acquisition unit 502 is configured to acquire radar data and image data related to the target object. The abnormal data determination unit 504 is configured to determine whether the radar data is abnormal data based on the height of the target object determined from the radar data. In addition, the target object detection unit 506 is configured to, in response to the radar data being abnormal data, use the image data to detect the target object and discard the radar data.

[0045] In some embodiments, the abnormal data determination unit 504 includes: a height threshold judgment unit configured to determine whether the height is greater than a height threshold; and an abnormal data second determination unit configured to, in response to the height of the target object being greater than the height threshold, determine that the radar data is the abnormal data.

[0046] In some embodiments, the device 500 further includes: a target object second detection unit configured to, in response to the radar data not being the abnormal data, use the image data and the radar data to detect the target object.

[0047] In some embodiments, the image data is acquired by a vision sensor mounted on the vehicle itself, and the radar data is acquired by a radar sensor mounted on the vehicle itself.

[0048] In some embodiments, the target object detection unit 506 includes: a target distance determination unit configured to use the image data and the radar data to determine the distance from the target object to the vehicle itself.

[0049] In some embodiments, the target distance determination unit includes: a first position information determination unit configured to determine the first position information of the target object based on the image data; a second position information determination unit configured to determine the second position information of the target object based on the radar data; a position difference determination unit configured to determine the position difference between the first position information and the second position information; and a target distance second determination unit configured to, in response to determining that the position difference is less than a position difference threshold, use the image data and the radar data to determine the distance from the target object to the vehicle itself.

[0050] In some embodiments, the target distance determination unit further includes: a target distance third determination unit configured to, in response to determining that the position difference is greater than or equal to the position difference threshold, use the image data to determine the distance from the target object to the vehicle itself and discard the radar data.

[0051] In some embodiments, the position difference determination unit includes: a first coordinate determination unit configured to determine a first coordinate value of the target object in a coordinate system based on the image data; a second coordinate determination unit configured to determine a second coordinate value of the target object in the coordinate system based on the radar data; and a second position difference determination unit configured to determine the position difference based on the first coordinate value and the second coordinate value.

[0052] In some embodiments, the target distance determination unit includes: a first speed determination unit configured to determine first speed information of the target object based on the image data; a second speed determination unit configured to determine second speed information of the target object based on the radar data; a speed difference determination unit configured to determine a speed difference between the first speed information and the second speed information; and a fourth target distance determination unit configured to, in response to determining that the speed difference is less than a speed difference threshold, determine the distance from the target object to the host vehicle using the image data and the radar data.

[0053] In some embodiments, the target distance determination unit further includes: a fifth target distance determination unit configured to, in response to the speed difference being less than the speed difference threshold, determine the distance of the target object using the image data and discard the radar data.

[0054] In some embodiments, the apparatus 500 further includes: an assisted driving determination unit configured to adjust the assisted driving strategy of the host vehicle by detecting the target object using the image data.

[0055] Figure 6 FIG. shows a schematic block diagram of an exemplary device 600 suitable for implementing the embodiments of the present disclosure. As shown, the device 600 includes a processor 601, which can execute various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 602 and loaded into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0056] Each of the methods and processes described above can be executed by the processor 601. For example, in some embodiments, each of the methods and processes described above can be implemented as a computer software program tangibly embodied in a machine-readable medium. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602. When the computer program is loaded into the RAM 603 and executed by the processor 601, one or more actions of the methods and processes described above can be performed.

[0057] The present disclosure can be a method, apparatus, system, and / or computer program product. The computer program product can include a computer-readable storage medium having thereon computer-readable program instructions for performing various aspects of the present disclosure.

[0058] The computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer-readable storage medium can be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), and any suitable combination of the foregoing. The computer-readable storage medium as used herein is not to be construed as a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0059] The computer-readable program instructions described herein can be downloaded to each computing / processing device from the computer-readable storage medium, or can be downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. The network adapter or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0060] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0061] Aspects of the present disclosure are described herein with reference to the flowchart and / or block diagram of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer - readable program instructions.

[0062] These computer - readable program instructions can be provided to a processing unit of a general - purpose computer, a special - purpose computer, or other programmable data - processing apparatus to produce a machine such that, when the instructions are executed by the processing unit of the computer or other programmable data - processing apparatus, a device is created that implements the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, which causes a computer, a programmable data - processing apparatus, and / or other devices to operate in a particular manner. Thus, the computer - readable medium storing the instructions includes a manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0063] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other devices to generate a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0064] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions.

[0065] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A method for detecting a target object, comprising: Obtaining radar data and image data related to the target object; Determining whether the radar data is abnormal data based on the height of the target object determined from the radar data; And In response to the radar data being the abnormal data, using the image data to detect the target object and discarding the radar data.

2. The method according to claim 1, wherein determining whether the radar data is the abnormal data comprises: Determining whether the height is greater than a height threshold; And In response to the height being greater than the height threshold, determining that the radar data is the abnormal data.

3. The method according to claim 1, further comprising: In response to the radar data not being the abnormal data, using the image data and the radar data to detect the target object.

4. The method according to claim 3, wherein the image data is obtained by a vision sensor mounted on the vehicle itself, and the radar data is obtained by a radar sensor mounted on the vehicle itself.

5. The method according to claim 4, wherein using the image data and the radar data to detect the target object comprises: Using the image data and the radar data to determine the distance from the target object to the vehicle itself.

6. The method according to claim 5, wherein determining the distance from the target object to the vehicle itself comprises: Based on the image data, determining first position information of the target object; Based on the radar data, determining second position information of the target object; Determining a position difference between the first position information and the second position information; And In response to determining that the position difference is less than a position difference threshold, using the image data and the radar data to determine the distance from the target object to the vehicle itself.

7. The method according to claim 6, further comprising: In response to determining that the position difference is greater than or equal to the position difference threshold, using the image data to determine the distance from the target object to the vehicle itself and discarding the radar data.

8. The method according to claim 7, wherein determining the position difference between the first position information and the second position information comprises: Based on the image data, determining a first coordinate value of the target object in a coordinate system; Based on the radar data, determining a second coordinate value of the target object in the coordinate system; And Based on the first coordinate value and the second coordinate value, determining the position difference.

9. The method according to claim 5, wherein determining the distance from the target object to the vehicle itself comprises: Based on the image data, determining first speed information of the target object; Based on the radar data, determining second speed information of the target object; Determining a speed difference between the first speed information and the second speed information; And In response to determining that the speed difference is less than a speed difference threshold, using the image data and the radar data to determine the distance from the target object to the vehicle itself.

10. The method according to claim 9 further comprises: In response to the speed difference being greater than or equal to the speed difference threshold, determining the distance of the target object by using the image data and discarding the radar data.

11. The method according to claim 1 further comprises: Adjusting the assisted driving strategy of the host vehicle by detecting the target object by using the image data.

12. A device for detecting a target object, comprising: A target data acquisition unit configured to acquire radar data and image data related to the target object; An abnormal data determination unit configured to determine whether the radar data is abnormal data based on the height of the target object determined from the radar data; And A target object detection unit configured to, in response to the radar data being the abnormal data, detect the target object by using the image data and discard the radar data.

13. A controller, comprising: At least one processor; And A memory coupled to the at least one processor and having instructions stored thereon, the instructions, when executed by the at least one processor, cause the controller to execute the method according to any one of claims 1-11.

14. A vehicle, comprising the controller according to claim 13.

15. A machine-readable storage medium having machine-executable instructions stored thereon, wherein the machine-executable instructions are executed by a processor to implement the method according to any one of claims 1 to 11.

Images