Trailer and blind spot target detection method and apparatus

Abstract

The present application relates to the technical field of vehicles, and provides a trailer and a blind area target detection method and device. The trailer detection method comprises the following steps: acquiring image information from a set range behind a vehicle; performing edge point processing on the image information to obtain an edge line of a target in the set range; and determining whether any edge line of any target is in a preset trailer area, and if so, determining that the target is a trailer. The trailer detection method of the present application can identify a trailer without needing to additionally configure a trailer module, thereby saving the cost of the trailer module, and without needing to calibrate the size of the trailer in the trailer identification process, and being easy to implement.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method and apparatus for detecting trailers and blind spot targets. Background Technology

[0002] Currently, many vehicles are equipped with blind spot detection systems. These systems mainly rely on millimeter-wave radars installed on both sides of the rear of the vehicle to detect vehicles in adjacent lanes. If a vehicle in an adjacent lane enters the blind spot of the vehicle's rearview mirror, it will remind the driver to pay attention to driving safety.

[0003] However, if a vehicle is equipped with a trailer, the trailer can interfere with the radar signal emitted by the millimeter-wave radar, causing false alarms in the blind spot detection system. Therefore, identifying trailers becomes particularly important, and existing trailer identification methods mainly fall into two categories:

[0004] One approach is to install a trailer hitchhiking module on the vehicle. This module, upon detecting a trailer, sends a signal to the blind spot detection system to disable the blind spot detection function. However, this solution requires the additional installation of the trailer hitchhiking module, increasing the overall weight and cost of the vehicle.

[0005] Secondly, it relies solely on millimeter-wave radar to calibrate the trailer size. This method filters out false targets based on the magnitude of the reflected energy of the detected target, greatly increasing the difficulty of trailer calibration.

[0006] Therefore, it is clear that existing trailer identification methods have limitations in terms of cost and performance. Summary of the Invention

[0007] In view of this, the present invention aims to provide a trailer inspection method to at least partially solve the above-mentioned technical problems.

[0008] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0009] A trailer detection method includes: acquiring image information within a predetermined range behind a vehicle; performing edge point processing on the image information to obtain the edge lines of targets within the predetermined range; and determining whether any edge line of any target is within a preset trailer area, and if so, determining that the target is a trailer.

[0010] Furthermore, the trailer detection method also includes setting the trailer area, comprising: determining a plurality of calibration points for calibrating the trailer area, wherein the attribute parameters of the plurality of calibration points include the longitudinal distance, lateral distance, azimuth angle, and trailer height of the trailer relative to the rear of the vehicle; adjusting the range of the attribute parameters of the plurality of calibration points according to the outline information of the trailer, the connection method between the trailer and the vehicle, and / or the driving state of the vehicle; and determining the trailer area based on the adjusted attribute parameters of the plurality of calibration points.

[0011] Furthermore, determining whether any edge line of any target is within a preset trailer area includes: obtaining attribute parameters of the edge point on the edge line, the attribute parameters including the longitudinal distance, lateral distance, and azimuth angle of the edge point relative to the rear of the vehicle, as well as the height information at the edge point; and within a preset continuous observation period, if the attribute parameters of the edge point on any edge line fall within the range corresponding to the calibration point of the trailer area, then the target corresponding to the edge line is determined to be a trailer.

[0012] Compared with existing technologies, the trailer detection method of the present invention obtains the edge line of the target by performing edge point processing on the image information, and determines whether the target is a trailer by determining whether the edge line enters the preset trailer area. It can identify trailers without the need for additional trailer module configuration, saving the cost of trailer module. Moreover, it does not require the trailer size to be calibrated during the trailer identification process, making it easy to implement.

[0013] Another objective of this invention is to propose a blind zone target detection method to at least partially solve the above-mentioned technical problems.

[0014] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0015] A blind spot target detection method is applied to a vehicle that detects blind spots using millimeter-wave radar. The method includes: acquiring image information within the vehicle's blind spot area; performing edge point processing on the image information to obtain the edge lines of targets within the blind spot area; determining whether any edge line of any target is within a preset trailer area; if so, identifying the target as a trailer and acquiring trailer outline information expressed in edge point form; and after determining the existence of the trailer, performing the following processing on targets other than the trailer:

[0016] Obtain the location information of the target detected by the millimeter-wave radar;

[0017] The location information of the target is compared with its corresponding edge line. If they match, the target is determined to be a real target.

[0018] Furthermore, the blind spot target detection method also includes setting the trailer area, comprising: determining a plurality of calibration points for calibrating the trailer area, wherein the attribute parameters of the plurality of calibration points include the longitudinal distance, lateral distance, azimuth angle, and trailer height of the trailer relative to the rear of the vehicle; adjusting the range of the attribute parameters of the plurality of calibration points according to the outline information of the trailer, the connection method between the trailer and the vehicle, and / or the driving state of the vehicle; and determining the trailer area based on the adjusted attribute parameters of the plurality of calibration points.

[0019] Furthermore, determining whether any edge line of any target is within a preset trailer area includes: obtaining attribute parameters of the edge point on the edge line, the attribute parameters including the longitudinal distance, lateral distance, and azimuth angle of the edge point relative to the rear of the vehicle, as well as the height information at the edge point; and within a preset continuous observation period, if the attribute parameters of the edge point on any edge line fall within the range corresponding to the calibration point of the trailer area, then the target corresponding to the edge line is determined to be a trailer.

[0020] Furthermore, acquiring image information within the blind spot range of the vehicle includes acquiring image information within the blind spot range of the vehicle using a camera installed on the vehicle.

[0021] Compared to existing technologies, the blind spot target detection method of this invention integrates image information about the target with the location information detected by millimeter-wave radar. This ensures both the detection of trailers and the differentiation between real targets and false targets caused by trailer interference. As a result, when a trailer is detected, the vehicle's blind spot detection function does not need to be turned off to avoid false alarms caused by trailer interference, thus ensuring driving safety and driving experience.

[0022] Another object of the present invention is to provide a trailer inspection device to at least partially solve the above-mentioned technical problems.

[0023] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0024] A trailer inspection device includes a controller, wherein the controller is used to perform the trailer inspection method described above.

[0025] Furthermore, the trailer detection device also includes a camera that communicates with the controller to capture image information within a set range behind the vehicle and transmit it to the controller.

[0026] The trailer detection device and the trailer detection method described above have the same advantages over the prior art, and will not be repeated here.

[0027] Another object of the present invention is to provide a blind zone target detection device to at least partially solve the above-mentioned technical problems.

[0028] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0029] A blind spot target detection device includes a controller, wherein the controller is used to perform the blind spot target detection method described above.

[0030] Furthermore, the blind spot target detection device also includes: a camera, communicating with the controller, for capturing image information within the blind spot range of the vehicle and transmitting it to the controller; and a millimeter-wave radar, communicating with the controller, for detecting the position information of targets within the blind spot range and transmitting it to the controller.

[0031] The blind spot target detection device and the aforementioned blind spot target detection method have the same advantages over the prior art, and will not be repeated here.

[0032] Another object of the present invention is to provide a machine-readable storage medium to at least partially solve the above-mentioned technical problems.

[0033] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0034] A machine-readable storage medium storing instructions for causing a machine to perform the aforementioned trailer detection method and the aforementioned blind spot target detection method.

[0035] The machine-readable storage medium has the same advantages over the prior art as the aforementioned trailer detection method and blind spot target detection method, and will not be repeated here.

[0036] Other features and advantages of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0037] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0038] In the attached diagram:

[0039] Figure 1 This is a flowchart illustrating the trailer inspection method according to Embodiment 1 of the present invention;

[0040] Figure 2 This is a schematic diagram of the process for setting up the trailer area in a preferred embodiment of the present invention;

[0041] Figure 3This is a schematic diagram of the positional relationship between the vehicle and the trailer in an embodiment of the present invention;

[0042] Figure 4 This is a flowchart illustrating the blind zone target detection method according to Embodiment 2 of the present invention;

[0043] Figure 5 This is a schematic diagram illustrating the principle of combining millimeter-wave radar with a camera to determine the real target in an example of an embodiment of the present invention;

[0044] Figure 6 This is a system architecture diagram of the trailer detection device according to Embodiment 3 of the present invention; and

[0045] Figure 7 This is a system architecture diagram of the blind zone target detection device according to Embodiment 4 of the present invention.

[0046] Explanation of reference numerals in the attached figures:

[0047] 610, 710 Central Control Module

[0048] 620 and 720 cameras

[0049] 630 and 730 related components

[0050] 740 mmWave Radar

[0051] 750 Human-Computer Interaction Module Detailed Implementation

[0052] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other.

[0053] It should be noted that, in this embodiment of the invention, the vehicle equipped with the trailer is referred to as a "self-propelled vehicle".

[0054] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0055] Example 1

[0056] Figure 1 This is a flowchart illustrating the trailer inspection method according to Embodiment 1 of the present invention. Figure 1 As shown, the trailer inspection method may include the following steps:

[0057] Step S110: Obtain image information within a set range behind the vehicle.

[0058] This setting range can be, for example, the blind zone range defined by the ISO 17387 standard.

[0059] Preferably, the image information can be obtained by taking pictures using a camera. The image information output by the camera reflects, to some extent, the vehicle's free space, i.e., the space in which the vehicle can drive, and is defined as the road surface segmented by the edges of the shoulder, static targets, and moving targets.

[0060] Step S120: Perform edge point processing on the image information to obtain the edge line of the target within the set range.

[0061] Edge point processing to extract edge points, edge lines, and even target contours is a common image processing technique. For example, by judging the differences between pixels to be detected in the image (left-right and top-bottom), it is determined whether the pixel is an edge point. An ID information for the edge point is then set, and consecutive edge points are selected and connected sequentially according to the ID information to form an edge line. The target contour or even free space is then drawn using multiple edge lines. Furthermore, since real vehicles are symmetrical about their central axis, the symmetry of the vehicle target can be used to simplify the target contour drawing process when the target is a vehicle. Other symmetrical targets can also be processed in the same way.

[0062] Step S130: Determine whether any edge line of any target is within the preset trailer area. If so, determine that the target is a trailer.

[0063] In a preferred embodiment, the trailer detection method may further include setting up the trailer area. Figure 2 This is a schematic diagram of the process for setting up the trailer area in a preferred embodiment of the present invention, such as... Figure 2 As shown, the following steps may be included:

[0064] Step S210: Determine multiple calibration points for calibrating the trailer area.

[0065] Figure 3 This is a schematic diagram illustrating the positional relationship between the vehicle and the trailer in an embodiment of the present invention. It shows that the trailer area can be described by the longitudinal distance dx, the lateral distance dy, and the azimuth angle r relative to the rear of the vehicle. Furthermore, considering the size of the trailer itself, it should also include... Figure 3 The trailer height dz is not shown (it is easy to see that dx, dy, and dz are mutually perpendicular). Based on this, the attribute parameters of the plurality of calibration points may include the longitudinal distance dx, the lateral distance dy, the azimuth angle r, and the trailer height dz relative to the rear of the vehicle.

[0066] Step S220: Adjust the range of attribute parameters of the multiple calibration points according to the outline information of the trailer, the connection method between the trailer and the vehicle, and / or the driving status of the vehicle.

[0067] The trailer's outline information can be, for example, the dimensions of a conventional trailer. The range of attribute parameters for each calibration point can be empirically determined based on the dimensions of a conventional trailer, such as the range of the trailer height dz. The connection method between the trailer and the vehicle includes a soft connection and a hard connection. A hard connection refers to a connection where the distance between the trailer and the vehicle is completely fixed, while a soft connection refers to a connection where the distance between the trailer and the vehicle may change during driving. Considering the existence of soft connections, during driving, the vehicle's driving states such as constant speed, acceleration, turning, or braking will cause changes in its longitudinal distance, lateral distance, and azimuth angle with the trailer. Therefore, this embodiment of the invention can also adjust the range of attribute parameters of the multiple calibration points according to the driving state of the vehicle.

[0068] Step S230: Determine the trailer area based on the adjusted attribute parameters of the plurality of calibration points.

[0069] For example, by adjusting the attribute parameters of the calibration point, the trailer area can be determined as the region formed by dx = [0, -a] meters, r = [b, -c] degrees, dy = [e, -f], and dz = [g + Δg]. This region is set to take into account various practical scenarios, so targets entering this region are generally trailers. Here, a, b, c, e, f, g, and Δg are all calibration values.

[0070] Furthermore, after determining the trailer area, in a preferred embodiment, step S130 may further include:

[0071] Step S131: Obtain the attribute parameters of the edge points on the edge line.

[0072] The attribute parameters of the edge point include the longitudinal distance, lateral distance, and azimuth angle of the edge point relative to the rear of the vehicle, as well as the height information at the edge point. Similarly, in the example, these four attribute parameters can be represented as longitudinal distance dx, lateral distance dy, azimuth angle r, and trailer height dz, respectively.

[0073] Step S132: Within a preset continuous observation period, if the attribute parameters of any edge point on an edge line fall within the range corresponding to the calibration point of the trailer area, then the target corresponding to that edge line is determined to be a trailer.

[0074] For example, corresponding to the above example regarding the trailer area dx = [0, -a] meters, r = [b, -c] degrees, dy = [e, -f], dz = [g + Δg], within a continuous observation period t, if the edge points of a certain edge line of the rear target continuously exist in an area of ​​dx = [0, -a] meters, r = [b, -c] degrees, dy = [e, -f], and the height of each edge point is within the range of dz = [g + Δg] meters, then it indicates that the edge line of the rear target has entered the preset trailer area, and thus the rear target is considered to be a trailer.

[0075] Accordingly, Embodiment 1 of the present invention obtains the edge line of the target by performing edge point processing on the image information, and determines whether the target is a trailer by determining whether the edge line enters the preset trailer area. It can identify trailers without the need for additional trailer module configuration, saving the cost of trailer module, and does not require trailer size calibration during trailer identification, making it easy to implement.

[0076] Example 2

[0077] As mentioned in the background section, trailers can interfere with the radar signals emitted by millimeter-wave radar, causing false alarms in blind spot detection systems. This interference mainly manifests as trailers blocking part of the radar's detection range and potentially causing radar wave reflections, creating false targets. To address this issue, solutions using trailer modules send a signal to the blind spot detection system to disable the blind spot detection function after detecting a trailer, thus preventing false alarms. However, disabling the blind spot detection function obviously prevents the vehicle from detecting targets in the blind spot, increasing the risk of collisions between the target and the vehicle or trailer, which is detrimental to driving safety.

[0078] In response, Embodiment 2 of the present invention provides a blind zone target detection method based on Embodiment 1. Figure 4 This is a flowchart illustrating the blind spot target detection method according to Embodiment 2 of the present invention. This blind spot detection method is applied to vehicles whose blind spots are detected by millimeter-wave radar. Figure 4 As shown, the blind spot detection method may include the following steps:

[0079] Step S410: Obtain image information within the blind spot area of ​​the vehicle.

[0080] The blind zone range can be defined with reference to the ISO 17387 standard.

[0081] In a preferred embodiment, image information within the blind spot area of ​​the vehicle can be captured using a camera installed on the vehicle. The camera can be installed, for example, in the center of the rear of the vehicle, on the roof, or a 360-degree surround-view camera can be used to ensure that it can capture images of the entire blind spot area.

[0082] Step S420: Perform edge point processing on the image information to obtain the edge line of the target within the blind zone.

[0083] The specific edge point processing procedure can be found in Implementation Example 1, and will not be repeated here.

[0084] Step S430: Determine whether any edge line of any target is within a preset trailer area. If so, determine that the target is a trailer and obtain trailer outline information expressed in the form of edge points.

[0085] The process of setting up the trailer area and determining the specific trailer can also be referred to in Embodiment 1, and will not be repeated here. It should be noted that the edge points of the trailer were obtained during the process of determining the trailer using the method of Embodiment 1, and these edge points can be used to describe the outline of the trailer.

[0086] Step S440: After determining the existence of the trailer, the targets other than the trailer are processed to determine whether they are real targets.

[0087] Specifically, step S440, which determines whether a target is a real target, may include: acquiring the position information of the target detected by the millimeter-wave radar; and comparing the position information of the target with its corresponding edge line. If the two match, the target is determined to be a real target.

[0088] For example, Figure 5 This is a schematic diagram illustrating the principle of combining millimeter-wave radar with a camera to determine the real target, as shown in an embodiment of the present invention. Figure 5 As shown, the arc-shaped area represents the detection range of the millimeter-wave radar, while the area formed by the irregular lines represents the detection range of the camera (i.e., the camera's free space). Comparing the position information detected by the millimeter-wave radar with the free space formed by the target's edge lines detected by the camera, it can be seen that the position of target 1 determined by the millimeter-wave radar matches the edge line of target 1 determined by the camera. Therefore, target 1 is a real target. Target 2, however, is within the camera's free space and has no obvious edge line; therefore, target 1 is likely a false target.

[0089] In a preferred embodiment, an alarm can also be triggered after the real target is determined, for example, by combining the TTC (Time To Collision) information output by the millimeter-wave radar to trigger an alarm for target 1.

[0090] The second embodiment of the present invention actually performs information fusion processing on the image information of the target and the location information detected by the millimeter-wave radar. This ensures that the trailer can be detected and that the real target can be distinguished from the false target caused by the trailer interference. This allows the vehicle's blind spot detection function to be turned off when the trailer is detected, thus avoiding false alarms caused by trailer interference and ensuring driving safety and driving experience.

[0091] It should be noted that, in the preferred embodiment, in addition to image information collected by cameras and other means and location information detected by millimeter-wave radar, information collected by other sensors or information such as the target's RCS (Radar-Cross Section) and size can be combined to further improve the detection strategy for targets in the blind zone, thereby improving detection accuracy.

[0092] Other implementation details and effects of this second embodiment can be found in the first embodiment described above, and will not be repeated here.

[0093] Example 3

[0094] Embodiment 3 of the present invention provides a trailer detection device, which is equipped with a controller, wherein the controller is used to execute the trailer detection method described in Embodiment 1.

[0095] Figure 6 This is a system architecture diagram of the trailer detection device according to Embodiment 3 of the present invention. Figure 6 The trailer detection device described in this example is equipped with a controller, such as a central control module 610, which is responsible for executing the trailer detection method of Embodiment 1. Preferably, the trailer detection device may also include a camera 620, the main function of which is, for example, to capture image information within a set range behind the vehicle as described in Embodiment 1, and transmit it to the central control module 610 for image processing. The trailer detection device 600 may also include an association component 630, such as an association sensor and an association actuator, such as a steering wheel angle sensor, a yaw angle acceleration sensor, and an electronic stability system. The association component 630 communicates with the central control module 610, thereby obtaining image information captured by the camera 620 and information obtained after image processing by the central control module 610, to assist vehicle operation. For example, the electronic stability system may obtain the azimuth angle r from the central control module 610 for trailer stability control. The associated component 630 can also provide the information collected by its sensors to the central control module 610 to enrich the trailer detection strategy, such as transmitting steering wheel angle and yaw acceleration to the central control module 610 to help determine the vehicle's driving status.

[0096] Other implementation details and effects of this embodiment three can be found in the above embodiment one, and will not be repeated here.

[0097] Example 4

[0098] Embodiment 4 of the present invention provides a blind spot target detection device, which is equipped with a controller, wherein the controller is used to execute the blind spot target detection method described in Embodiment 2.

[0099] Figure 7 This is a system architecture diagram of the blind zone target detection device according to Embodiment 4 of the present invention. Figure 7 The blind spot target detection device described in this example is configured with a controller, such as a central control module 710, which is responsible for executing the blind spot target detection method of Embodiment 2. Preferably, the blind spot target detection device may also include a camera 720 and a millimeter-wave radar 740. The main function of the camera 720 is, for example, to capture image information within the blind spot range of the vehicle as described in Embodiment 2, and transmit it to the central control module 710 for image processing. The main function of the millimeter-wave radar 740 is, for example, to detect the position information of targets within the blind spot range as described in Embodiment 2, and transmit it to the central control module 710 for comparison of the target's position information with the edge line. The blind spot target detection device 700 may also include an association component 730, whose function is the same as in Embodiment 3, and will not be described again here. In addition, the blind spot target detection device 700 may also include a human-machine interaction module 750, which communicates with the central control module 710. It can be used to receive an alarm from the central control module 710 for detecting a real target in the blind spot, and can also be used to send a function to the central control module 710 to turn off the blind spot detection system in response to driver operation.

[0100] Other implementation details and effects of this embodiment four can be found in the above embodiment two, and will not be repeated here.

[0101] This invention also provides a machine-readable storage medium storing instructions that cause a machine to execute the trailer detection method of Embodiment 1 or the blind spot target detection method of Embodiment 2.

[0102] This invention also provides a processor for running a program, wherein the program executes the trailer detection method of Embodiment 1 or the blind spot target detection method of Embodiment 2.

[0103] This invention also provides a computer program product that, when executed on vehicle-related components, is suitable for executing an initialization program with the following method steps: the trailer detection method of Embodiment 1 or the blind spot target detection method of Embodiment 2.

[0104] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of the present invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0106] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0107] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0108] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0109] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0110] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0111] It should also be noted that the term "comprising," or any other variation thereof, is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A trailer inspection method, characterized in that, The trailer detection method is implemented solely through a camera and includes: Acquire image information within a set range behind the vehicle, wherein the image information is obtained by taking pictures using the camera; Edge point processing is performed on the image information to obtain the edge line of the target within the set range; and Determine whether any edge line of any target is within a preset trailer area. If so, the target is determined to be a trailer. The trailer area is described by the longitudinal distance, lateral distance, azimuth angle, and trailer height of the trailer relative to the rear of the vehicle. The trailer inspection method further includes setting up the trailer area without needing to calibrate the trailer dimensions. The trailer area is the space between the rear of the vehicle and the trailer. This space varies depending on the connection method between the trailer and the vehicle and / or the vehicle's driving state. The connection method includes a flexible connection, and the driving state includes constant speed driving, acceleration, turning, or braking. The provision of the trailer area includes: Determine multiple calibration points for calibrating the trailer area, wherein the attribute parameters of the multiple calibration points include the longitudinal distance, lateral distance, azimuth angle, and trailer height of the trailer relative to the rear of the vehicle; Based on the trailer's outline information, the connection method between the trailer and the vehicle, and / or the vehicle's driving status, adjust the range of attribute parameters for the multiple calibration points; and The trailer area is determined based on the adjusted attribute parameters of the multiple calibration points.

2. The trailer inspection method according to claim 1, characterized in that, The determination of whether any edge line of any target is within the preset trailer area includes: Obtain the attribute parameters of the edge points on the edge line, including the longitudinal distance, lateral distance, and azimuth angle of the edge point relative to the rear of the vehicle, as well as the height information at the edge point; and Within a preset continuous observation period, if the attribute parameters of any edge point on an edge line fall within the range corresponding to the calibration point of the trailer area, then the target corresponding to that edge line is determined to be a trailer.

3. A blind spot target detection method, applied to vehicles whose blind spots are detected by millimeter-wave radar, characterized in that, The blind zone target detection method includes: Acquire image information within the blind spot area of ​​the vehicle, wherein the image information is obtained by taking pictures using a camera; Edge point processing is performed on the image information to obtain the edge line of the target within the blind zone; Determine whether any edge line of any target lies within a preset trailer area. If so, identify the target as a trailer and obtain trailer outline information in the form of edge points. The trailer area is described by the longitudinal distance, lateral distance, azimuth angle, and height of the trailer relative to the rear of the vehicle. After confirming the presence of the trailer, the blind spot detection function of the vehicle remains active. For targets other than the trailer, the following steps are performed: acquire the position information of the target detected by the millimeter-wave radar; compare the position information of the target with its corresponding edge line; if they match, the target is determined to be a real target; if the target does not have a corresponding edge line in the free space of the camera, the target is determined to be a false target generated by interference from the trailer. The blind spot target detection method further includes: setting up the trailer area without needing to calibrate the trailer size. The trailer area is the space between the rear of the vehicle and the trailer. This space varies depending on the connection method between the trailer and the vehicle and / or the vehicle's driving state. The connection method includes a flexible connection, and the driving state includes constant speed driving, acceleration, turning, or braking. The provision of the trailer area includes: Determine multiple calibration points for calibrating the trailer area, wherein the attribute parameters of the multiple calibration points include the longitudinal distance, lateral distance, azimuth angle, and trailer height of the trailer relative to the rear of the vehicle; Based on the trailer's outline information, the connection method between the trailer and the vehicle, and / or the vehicle's driving status, adjust the range of attribute parameters for the multiple calibration points; and The trailer area is determined based on the adjusted attribute parameters of the multiple calibration points.

4. The blind zone target detection method according to claim 3, characterized in that, The determination of whether any edge line of any target is within the preset trailer area includes: Obtain the attribute parameters of the edge points on the edge line, including the longitudinal distance, lateral distance, and azimuth angle of the edge point relative to the rear of the vehicle, as well as the height information at the edge point; and Within a preset continuous observation period, if the attribute parameters of any edge point on an edge line fall within the range corresponding to the calibration point of the trailer area, then the target corresponding to that edge line is determined to be a trailer.

5. The blind zone target detection method according to claim 3 or 4, characterized in that, The image information acquired within the blind spot area of ​​the vehicle includes: The system uses cameras installed on the vehicle to obtain image information within the vehicle's blind spot area.

6. A trailer detection device, characterized in that, The trailer detection device includes a controller, wherein the controller is used to perform the trailer detection method as described in claim 1 or 2.

7. The trailer detection device according to claim 6, characterized in that, The trailer detection device also includes: The camera communicates with the controller to capture image information within a set range behind the vehicle and transmit it to the controller.

8. A blind zone target detection device, characterized in that, The blind spot target detection device includes a controller, wherein the controller is used to execute the blind spot target detection method as described in any one of claims 3 to 5.

9. The blind zone target detection device according to claim 8, characterized in that, The blind zone target detection device also includes: A camera, communicating with the controller, is used to capture image information within the vehicle's blind spot area and transmit it to the controller; and A millimeter-wave radar communicates with the controller to detect the location information of targets within the blind zone and transmits it to the controller.

10. A machine-readable storage medium storing instructions for causing a machine to perform the trailer detection method of claim 1 or 2 or the blind spot target detection method of any one of claims 3 to 5.

Images