Rearview mirror detection method and device and intelligent driving equipment

Abstract

The invention discloses a rearview mirror detection method and device and intelligent driving equipment, and the method comprises the steps: obtaining a first image and a second image which are images of a first rearview mirror containing a target vehicle and collected at different angles; according to the first image and the second image, the position of the first rearview mirror on the target vehicle is determined; and controlling the intelligent driving equipment according to the position of the first rearview mirror on the target vehicle. The technical scheme can be applied to the field of intelligent vehicles such as electric vehicles and new energy vehicles, the detection precision of the root position of the rearview mirror can be improved through the images of the first rearview mirror containing the target vehicle collected at different angles, and the detection accuracy of the root position of the rearview mirror can be improved in the automatic parking process. The precision of planning the path according to the position of the root of the rearview mirror of the vehicle can be improved, the probability that the rearview mirror of the vehicle rubs the rearview mirror of the target vehicle is reduced, and the parking efficiency and safety can be improved.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicles, and more specifically, to a rearview mirror detection method, apparatus, and intelligent driving device. Background Art

[0002] With the rapid development of the automotive industry, many assisted driving and autonomous driving technologies have emerged, which can reduce driving stress, improve safety, and traffic efficiency. Auto parking (AP) is a widely used assisted driving technology. AP refers to the vehicle automatically parking in a parking space, that is, the autonomous driving system can semi-automatically or fully automatically help the user park the vehicle in a parking space. Auto parking can include auto parking assist (APA), remote parking assist (RPA), and auto valet parking (AVP), etc.

[0003] During the auto parking process, especially when parking into a narrow or extremely narrow parking space, accurately detecting the position of the rearview mirror of other vehicles is a key factor in ensuring parking safety. Therefore, a rearview mirror detection solution that can accurately detect the position of the rearview mirror of other vehicles is urgently needed to be developed. Summary of the Invention

[0004] This application provides a rearview mirror detection method, apparatus, and intelligent driving device, which can improve the detection accuracy of the position of the rearview mirror of other vehicles, and thus contribute to improving the efficiency and safety when parking into a narrow or extremely narrow parking space.

[0005] In a first aspect, a rearview mirror detection method is provided. This method can be executed by an intelligent driving device, or by a computing platform of the intelligent driving device, or by a chip or circuit provided in the computing platform.

[0006] The method includes: obtaining a first image and a second image, where the first image and the second image are images of a first rearview mirror of a target vehicle collected from different angles; determining the position of the first rearview mirror on the target vehicle according to the first image and the second image; and controlling the intelligent driving device according to the position of the first rearview mirror on the target vehicle.

[0007] In some implementation manners, the position of the target vehicle when the first image is obtained is the same as the position of the target vehicle when the second image is obtained.

[0008] Wherein, the position of the first rearview mirror on the target vehicle can be understood as the position of the root of the first rearview mirror on the target vehicle.

[0009] It should be noted that the above-mentioned acquisition of images from different angles can be understood as: the included angle between the line connecting the optical center of the imaging device for acquiring the first image and the first rearview mirror, and the line connecting the optical center of the imaging device for acquiring the second image and the first rearview mirror is not 0.

[0010] In the above technical solution, the images of the first rearview mirror of the target vehicle acquired from different angles help to improve the detection accuracy of the position of the root of the rearview mirror. During the automatic parking process of the intelligent driving device, it can improve the accuracy of the intelligent driving device to plan the path according to the position of the root of the rearview mirror, reduce the probability of the intelligent driving device rubbing against the rearview mirror of the target vehicle, and help to improve the parking efficiency and safety.

[0011] Combined with the first aspect, in some implementation manners of the first aspect, the first image is acquired at a first moment, the second image is acquired at a second moment, and determining the position of the first rearview mirror on the target vehicle includes: determining a first straight line according to the first image, where the first straight line is the straight line where the first area of the intelligent driving device and the root of the first rearview mirror are located at the first moment; determining a second straight line according to the second image, where the second straight line is the straight line where the second area of the intelligent driving device and the root of the first rearview mirror are located at the second moment; determining the position of the root of the first rearview mirror on the target vehicle according to the intersection point of the first straight line and the outer contour of the target vehicle, and the intersection point of the second straight line and the outer contour of the target vehicle.

[0012] In some implementation manners, the first moment and the second moment are the same moment, and the first area and the second area are different areas. Or, the first moment and the second moment are different moments, and the first area and the second area are the same area.

[0013] Exemplarily, determine the first straight line according to the pixel position of the first rearview mirror in the first image, and this first straight line indicates the direction in which the optical center of the imaging device for acquiring the first image points to the first rearview mirror. Determine the second straight line according to the pixel position of the first rearview mirror in the second image, and this second straight line indicates the direction in which the optical center of the imaging device for acquiring the second image points to the first rearview mirror.

[0014] Combined with the first aspect, in some implementation manners of the first aspect, the intelligent driving device includes a first imaging device and a second imaging device, the first image is acquired by the first imaging device at a first moment, and the second image is acquired by the second imaging device at a second moment; the first area is the area on the intelligent driving device where the first imaging device is set, and the second area is the area on the intelligent driving device where the second imaging device is set.

[0015] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: when the first rearview mirror is in the retracted state, determining the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a first compensation amount; or, when the first rearview mirror is in the unfolded state, determining the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a second compensation amount; wherein, the first compensation amount is less than or equal to the second compensation amount.

[0016] In the above technical solution, providing different compensation amounts for the outer contour of the rearview mirror according to the state of the rearview mirror of the target vehicle helps to further improve the detection accuracy of the position of the rearview mirror. When parking in an extremely narrow parking space caused by the target vehicle or driving in an extremely narrow aisle caused by the target vehicle, performing path planning according to the position of the outer contour of the rearview mirror after the above compensation helps to further improve the parking or driving efficiency.

[0017] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: determining the first compensation amount and / or the second compensation amount according to the vehicle model of the target vehicle.

[0018] In the above technical solution, determining different compensation amounts according to different vehicle models can provide compensation for different vehicles more accurately, and then determine the position of the outer contour of the rearview mirror more accurately.

[0019] In combination with the first aspect, in certain implementations of the first aspect, the target vehicle is located on one side of the first position area, and the first rearview mirror is close to the first position area; wherein, the first position area is the target parking area of the intelligent driving device, or the first position area is the area passed by the intelligent driving device when driving to the destination.

[0020] In the above technical solution, when the target vehicle is located next to the target parking area of the intelligent driving device or the target vehicle is located in the driving path of the intelligent driving device, the position of the first rearview mirror of the target vehicle is detected. That is, when another vehicle is located in other areas, such as far from the target parking area of the intelligent driving device, the position of the rearview mirror of that vehicle is not detected, which can reduce the computational complexity of the intelligent driving device and help save energy consumption.

[0021] In combination with the first aspect, in certain implementations of the first aspect, the drivable width of the first position area is less than or equal to the width threshold.

[0022] In the above technical solution, when the width of the first position area is relatively narrow, detecting the position of the first rearview mirror of the target vehicle helps to further reduce the computational complexity and save energy consumption.

[0023] In combination with the first aspect, in some implementations of the first aspect, controlling an intelligent driving device includes: controlling the intelligent driving device to drive into a first position area according to the position of a first rearview mirror on a target vehicle.

[0024] Exemplarily, determine a path for the intelligent driving device to drive into or past the first position area according to the position of the first rearview mirror on the target vehicle, and control the intelligent driving device to travel along this path.

[0025] In the above technical solution, during automatic parking or autonomous driving, it is possible to improve the accuracy of the intelligent driving device in planning a path according to the position of the root of the rearview mirror, reduce the probability of the intelligent driving device rubbing against the rearview mirror of the target vehicle, and contribute to improving the parking efficiency and safety.

[0026] In combination with the first aspect, in some implementations of the first aspect, controlling an intelligent driving device includes: controlling a display device of the intelligent driving device to display the position of the first rearview mirror on the target vehicle.

[0027] In the above technical solution, when the intelligent driving device is in the human driving mode, by displaying the more accurate position of the first rearview mirror on the target vehicle through the display device, it is possible to reduce the probability of the own vehicle rubbing against other vehicles in the human driving mode, and thus improve the driving safety.

[0028] In a second aspect, a rearview mirror detection device is provided. The device includes: an acquisition unit configured to acquire a first image and a second image, where the first image and the second image are images of a first rearview mirror of a target vehicle acquired from different angles; a processing unit configured to determine the position of the first rearview mirror on the target vehicle according to the first image and the second image; and the processing unit is further configured to: control the intelligent driving device according to the position of the first rearview mirror on the target vehicle.

[0029] In combination with the second aspect, in some implementations of the second aspect, the first image is acquired at a first moment, the second image is acquired at a second moment, and the processing unit is configured to: determine a first straight line according to the first image, where the first straight line is the straight line where a first area of the intelligent driving device and the root of the first rearview mirror are located at the first moment; determine a second straight line according to the second image, where the second straight line is the straight line where a second area of the intelligent driving device and the root of the first rearview mirror are located at the second moment; and determine the position of the root of the first rearview mirror on the target vehicle according to the intersection point of the first straight line and the outer contour of the target vehicle and the intersection point of the second straight line and the outer contour of the target vehicle.

[0030] In combination with the second aspect, in some implementations of the second aspect, the intelligent driving device includes a first imaging device and a second imaging device. The first image is captured by the first imaging device at a first moment, and the second image is captured by the second imaging device at a second moment. The first area is the area on the intelligent driving device where the first imaging device is disposed, and the second area is the area on the intelligent driving device where the second imaging device is disposed.

[0031] In combination with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: when the first rearview mirror is in the retracted state, determine the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a first compensation amount; or, when the first rearview mirror is in the opened state, determine the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a second compensation amount; wherein, the first compensation amount is less than or equal to the second compensation amount.

[0032] In combination with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: determine the first compensation amount and / or the second compensation amount according to the vehicle model of the target vehicle.

[0033] In combination with the second aspect, in some implementations of the second aspect, the target vehicle is located on one side of a first position area, and the first rearview mirror is close to the first position area; wherein, the first position area is the target parking area of the intelligent driving device, or, the first position area is the area passed by the intelligent driving device when traveling towards the destination.

[0034] In combination with the second aspect, in some implementations of the second aspect, the drivable width of the first position area is less than or equal to a width threshold.

[0035] In combination with the second aspect, in some implementations of the second aspect, the processing unit is configured to: control the intelligent driving device to drive into the first position area according to the position of the first rearview mirror on the target vehicle.

[0036] In combination with the second aspect, in some implementations of the second aspect, the processing unit is configured to: control the display device of the intelligent driving device to display the position of the first rearview mirror on the target vehicle.

[0037] In a third aspect, a rearview mirror detection device is provided. The device includes: a memory for storing a computer program; a processor for executing the computer program stored in the memory so that the device executes the method in any possible implementation manner of the first aspect.

[0038] In a fourth aspect, an intelligent driving device is provided. The intelligent driving device includes the device in any possible implementation manner of the second aspect or the third aspect.

[0039] In combination with the fourth aspect, in some implementation manners of the fourth aspect, the intelligent driving device is a vehicle.

[0040] In a fifth aspect, a computer program product is provided. The computer program product includes computer program code which, when running on a computer, causes the computer to execute the method in any one of the possible implementation manners of the first aspect.

[0041] It should be noted that the above computer program code can be stored in whole or in part on a first storage medium, where the first storage medium can be packaged together with the processor or separately packaged from the processor.

[0042] In a sixth aspect, a computer-readable medium is provided. The computer-readable medium stores instructions which, when executed by a processor, cause the processor to implement the method in any one of the possible implementation manners of the first aspect.

[0043] In a seventh aspect, a chip is provided. The chip includes a circuit which is used to execute the method in any one of the possible implementation manners of the first aspect. Description of the Drawings

[0044] Figure 1 is a functional schematic diagram of the intelligent driving device provided by an embodiment of the present application;

[0045] Figure 2 is a schematic block diagram of the rearview mirror detection system provided by an embodiment of the present application;

[0046] Figure 3 is a schematic diagram of the installation position of the imaging device provided by an embodiment of the present application;

[0047] Figure 4 is a schematic flowchart of the rearview mirror detection method provided by an embodiment of the present application;

[0048] Figure 5 is a schematic diagram of the application scenario of the rearview mirror detection method provided by an embodiment of the present application;

[0049] Figure 6 is another schematic diagram of the application scenario of the rearview mirror detection method provided by an embodiment of the present application;

[0050] Figure 7 is yet another schematic diagram of the application scenario of the rearview mirror detection method provided by an embodiment of the present application;

[0051] Figure 8 is another schematic flowchart of the rearview mirror detection method provided by an embodiment of the present application;

[0052] Figure 9It is a schematic block diagram of the rearview mirror detection device provided by an embodiment of the present application;

[0053] Figure 10 It is another schematic block diagram of the rearview mirror detection device provided by an embodiment of the present application. Specific embodiments

[0054] To facilitate the understanding of the solution of the embodiment of the present application, the concepts involved in the present application are introduced below:

[0055] 1. Root of the rearview mirror: The area where the exterior rearview mirror is connected to the vehicle body.

[0056] 2. Tip of the rearview mirror: The place where the exterior rearview mirror is farthest from the vehicle body, or the outer contour of the rearview mirror.

[0057] 3. Retracted state or opened state of the rearview mirror: Taking a flip-type rearview mirror as an example, the flip angle of the rearview mirror is the included angle between the outer tangent planes of the rearview mirror housing (upper housing or lower housing) when the rearview mirror is unfolded and when the rearview mirror is folded to the extreme position. Among them, the extreme position can be understood as the position where the included angle between the rearview mirror and the vehicle body supported by the steering gear of the rearview mirror is the smallest. The flip angle can be decomposed into a horizontal flip angle and a vertical flip angle. Taking a four-wheel vehicle as an example, the horizontal flip angle can be the angle at which the rearview mirror flips within the plane where the four tires of the vehicle are located, and the vertical flip angle can be the angle at which the rearview mirror flips perpendicular to the plane where the four tires of the vehicle are located. It can be understood that both the horizontal flip angle and the vertical flip angle of the rearview mirror are greater than or equal to zero. When the rearview mirror is folded to the extreme position, both the horizontal flip angle and the vertical flip angle of the rearview mirror are zero. The state when the rearview mirror is folded to the extreme position is the retracted state, and the state when the horizontal flip angle of the rearview mirror is not zero is the opened state.

[0058] Next, the technical solutions in the present application will be described with reference to the accompanying drawings.

[0059] Figure 1 It is a schematic functional block diagram of an intelligent driving device provided by an embodiment of the present application. As Figure 1As shown, the intelligent driving device 100 may include a perception system 120 and a computing platform 150. Among them, the perception system 120 may include several sensors for sensing information about the environment around the intelligent driving device 100. For example, the perception system 120 may further include a positioning system, which may be a global positioning system (GPS), or a Beidou system or other positioning systems. Also for example, the perception system 120 may further include one or more of an inertial measurement unit (IMU), a lidar, a millimeter wave radar, an ultrasonic radar, and a camera device. In this application, the camera device may include, but is not limited to, a fish-eye camera and a wide-angle camera. The camera device may include a red, green and blue / infrared (RGB / IR) camera, or may also include a depth camera, such as a time of flight (TOF) camera, a binocular camera, a structured light camera, etc.

[0060] Some or all functions of the intelligent driving device 100 can be controlled by the computing platform 150. The computing platform 150 may include processors 151 to 15n. A processor is a circuit with signal processing capabilities. In one implementation, a processor can be a circuit with the ability to read and execute instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a type of microprocessor), or a digital signal processor (DSP), etc.; in another implementation, a processor can achieve certain functions through the logical relationship of a hardware circuit, and the logical relationship of this hardware circuit is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of a processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of a processor loading instructions to implement the functions of some or all of the above units. In addition, a processor can also be a hardware circuit designed for artificial intelligence, which can be understood as a type of ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include a memory for storing instructions, and some or all of the processors 151 to 15n can call the instructions in the memory to implement corresponding functions.

[0061] The intelligent driving device 100 may include an advanced driving assistant system (ADAS). The ADAS uses various sensors on the intelligent driving device (including but not limited to: lidar, millimeter-wave radar, camera device, ultrasonic sensor, global positioning system, inertial measurement unit) to obtain information from the surroundings of the intelligent driving device, and analyzes and processes the obtained information to achieve functions such as obstacle perception, target recognition, intelligent driving device positioning, path planning, driver monitoring / reminder, etc., thereby improving the safety, automation level, and comfort of the intelligent driving device.

[0062] In terms of logical functions, the ADAS system generally includes three main functional modules: a perception module, a decision-making module, and an execution module. The perception module senses the surrounding environment of the vehicle body through sensors and inputs corresponding real-time data to the decision-making center for processing. The perception module mainly includes on-vehicle cameras / ultrasonic radars / millimeter-wave radars / lidar, etc.; the decision-making module makes corresponding decisions using computing devices and algorithms based on the information obtained by the perception module; after receiving the decision signal from the decision-making module, the execution module takes corresponding actions, such as driving, lane changing, steering, braking, warning, etc.

[0063] Under different levels of autonomous driving (L0 - L5), based on the information obtained by artificial intelligence algorithms and multi-sensors, ADAS can achieve different levels of autonomous driving assistance. The above levels of autonomous driving (L0 - L5) are based on the grading standards of the Society of Automotive Engineers (SAE). Among them, L0 is no automation; L1 is driving assistance; L2 is partial automation; L3 is conditional automation; L4 is highly automated; L5 is fully automated. For the tasks of monitoring road conditions and making responses at levels L1 to L3, they are jointly completed by the driver and the system, and the driver needs to take over the dynamic driving tasks. At levels L4 and L5, the driver can completely transform into the role of a passenger. Currently, the functions that ADAS can achieve mainly include but are not limited to: adaptive cruise control, automatic emergency braking, automatic parking, blind spot monitoring, traffic warning / braking at the front intersection, traffic warning / braking at the rear intersection, forward collision warning, lane departure warning, lane keeping assistance, rear collision warning for the vehicle ahead, traffic sign recognition, traffic congestion assistance, highway assistance, etc. It should be understood that: the above various functions can have specific modes under different levels of autonomous driving (L0 - L5), and the higher the level of autonomous driving, the more intelligent the corresponding mode. For example, automatic parking can include APA, RPA, and AVP, etc. For APA, the driver does not need to operate the steering wheel, but still needs the driver to monitor the status of the intelligent driving device in real time on the intelligent driving device; for RPA, the driver can use a terminal (such as a mobile phone) to remotely control the parking of the intelligent driving device outside the intelligent driving device; for AVP, the intelligent driving device can complete parking without the driver. In terms of the corresponding levels of autonomous driving, APA is approximately at the level of L2, RPA is approximately at the level of L2 - L3, and AVP is approximately at the level of L4.

[0064] In the embodiment of the present application, the computing platform 150 can determine the tip position of the rearview mirror of the other vehicle according to the image of the other vehicle obtained by the perception system 120. The computing platform 150 can also perform parking path planning according to the determined tip position of the rearview mirror of the other vehicle to reduce the probability of the own vehicle rubbing against the rearview mirror of the other vehicle during parking.

[0065] The intelligent driving devices involved in the embodiments of the present application may include road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, the intelligent driving device may be a vehicle, which is a vehicle in a broad sense and can be a transportation vehicle (such as a commercial vehicle, a passenger vehicle, a motorcycle, a flying vehicle, a train, etc.), an industrial vehicle (such as a forklift, a trailer, a tractor, etc.), an engineering vehicle (such as an excavator, a bulldozer, a crane, etc.), an agricultural equipment (such as a lawn mower, a harvester, etc.), a recreational equipment, a toy vehicle, etc. The embodiments of the present application do not specifically limit the type of the vehicle.

[0066] Figure 2 The schematic diagram of the rearview mirror detection system architecture provided by the embodiments of the present application is shown. As Figure 2 shown, the system includes a perception module 210, a detection module 220, a planning and control module 230, and an actuator 240. Among them, the perception module 210 may include Figure 1 one or more sensors in the perception system 120 as shown. For example, the perception module 210 includes a camera device 211. The detection module 220 and the planning and control module 230 may be Figure 1 one or more processors in the computing platform 150 as shown.

[0067] More specifically, the detection module 220 includes a root determination module 221 and a tip determination module 222. The root determination module 221 determines the root position of the target rearview mirror of the target vehicle according to the images of the target rearview mirror of the target vehicle collected by the camera device 211 from at least two angles. The tip determination module 222 is used to determine the opening and closing state of the target rearview mirror according to the image of the target rearview mirror collected by the camera device 211, and then determine the tip compensation amount according to the opening and closing state of the target rearview mirror, and then determine the tip position of the target rearview mirror according to the root position and the tip compensation amount. Among them, the target vehicle may be located on the path that the intelligent driving device needs to pass through when driving to the target position, and the target rearview mirror may be the rearview mirror on one side of the target vehicle close to the path that the intelligent driving device needs to pass through when driving to the target position.

[0068] Further, the detection module 220 sends the information of the determined tip position of the rearview mirror to the planning and control module 230. When the planning and control module 230 plans the path for the intelligent driving device to drive to the target position, it plans the path for the intelligent driving device to pass by the target vehicle according to the tip position of the rearview mirror. The planning and control module 230 calculates the corresponding control amount according to the planned path and outputs the above control amount to the actuator 240. When the actuator 240 executes the control amount, it controls the vehicle to drive according to the planned path. In some possible implementation manners, the actuator may include the steering and braking control systems in the intelligent driving device 100.

[0069] It should be understood that the above modules are only examples. In actual applications, the above modules may be added or deleted according to actual needs. For example, Figure 2 in the system architecture shown in, the root determination module 221 and the tip determination module 222 can be combined into one module. For another example, Figure 2 the system architecture shown may further include a prompt module. The prompt module is used to prompt the tip position of the target rearview mirror of the target vehicle, or the prompt module is used to prompt the relationship between the tip position of the target rearview mirror and the planned path of the intelligent driving device, such as the distance between the tip position of the target rearview mirror and the outer contour of the intelligent driving device when the intelligent driving device is driving on the planned path.

[0070] Taking the intelligent driving device as a vehicle as an example, Figure 3 shows a schematic diagram of the arrangement position of the camera device in the vehicle in the above embodiment. As Figure 3 shown, the camera device can be arranged at the front of the vehicle (such as position ①), for example, a front-view camera arranged under the front license plate frame; the camera device can also be arranged at the rear of the vehicle (such as position ④), for example, a rear-view camera arranged above the rear license plate frame; the camera device can also be arranged on the side of the vehicle (such as positions ② and ③), for example, side cameras arranged at the left and right rearview mirrors of the vehicle.

[0071] It should be understood that Figure 3 the arrangement positions of the camera devices shown are only for illustrative purposes. In actual implementation, the camera devices can also be arranged at other positions outside the vehicle.

[0072] The above Figures 1 to 3 introduced the rearview mirror detection system provided by this application. The following details the rearview mirror detection method provided by this application.

[0073] Figure 4 shows a schematic flowchart of the rearview mirror detection method provided by an embodiment of this application. Figure 4 The method 400 shown can be executed by Figure 1 the intelligent driving device 100 shown, for example, executed by the computing platform 150 of the intelligent driving device 100. Or the method 400 can also be executed by Figure 2 the system shown, for example, executed by the detection module 220. Specifically, the method 400 may include S410 and S420.

[0074] S410, obtain a first image and a second image, where the first image and the second image are images of the first rearview mirror of the target vehicle collected from different angles respectively.

[0075] Exemplarily, the first image and the second image can be captured by the same imaging device at different times. For example, if the target vehicle is located on the right side of the intelligent driving device, the above imaging device can be a side view camera arranged at Figure 3 the position ③ shown. Alternatively, the first image and the second image can also be captured by different imaging devices at the same time. For example, if the target vehicle is located in the front right of the intelligent driving device, the above different imaging devices can be a front view camera arranged at Figure 3 the position ① shown, and a side view camera arranged at Figure 3 the position ③ shown. Alternatively, the first image and the second image can also be captured by different imaging devices at different times. For example, during the driving process of the intelligent driving device, at the first time, the first image is captured by a front view camera arranged at Figure 3 the position ① shown, and at the second time, the second image is captured by a side view camera arranged at Figure 3 the position ③ shown.

[0076] Exemplarily, the target vehicle can be stationary. Alternatively, the speed of the target vehicle is less than or equal to the speed threshold. Exemplarily, the speed threshold can be 1 meter per second (m / s), or it can also be 0.5 m / s, or it can also be other values. More specifically, if the first image and the second image are captured by the same imaging device at different times, the position of the target vehicle between these two different times can be the same; if the first image and the second image are captured by different imaging devices at the same time, the speed of the target vehicle can be less than or equal to the speed threshold.

[0077] In some implementation manners, the target vehicle can be a vehicle that affects the driving of the intelligent driving device. Exemplarily, the target vehicle is located on one side of the first position area, and the first rearview mirror is close to the first position area. Wherein, the first position area is the target parking area of the intelligent driving device, or the first position area is the area passed by the intelligent driving device when driving towards the destination. As Figure 5As shown, vehicle 501 is taken as an example of an intelligent driving device. In one example, when vehicle 501 is moving forward, it needs to pass through area a. Since there is vehicle 502 on one side of area a and the presence of vehicle 502 may affect the smoothness of vehicle 501's driving (for example, when the pose of vehicle 501 is inappropriate, it may rub against the convex part of the outer contour of vehicle 502), vehicle 501 can detect the position of the convex part (such as rearview mirror 5021) on the side of vehicle 502 close to area a, and plan the driving path in area a according to the position of the convex part of vehicle 502, so as to avoid rubbing between the host vehicle and vehicle 502. In another example, vehicle 501 selects area b as the parking area. Since there is vehicle 505 on one side of area b and the presence of vehicle 505 may affect the parking pose of vehicle 501, vehicle 501 can detect the position of the convex part (such as rearview mirror 5051) on the side of vehicle 505 close to area b, and plan the parking pose in area b and the driving path when parking into area b according to the position of the convex part of vehicle 505, so as to avoid rubbing between the host vehicle and vehicle 505, and / or avoid inconvenience for the right-side passengers to get on and off after the host vehicle parks in area b.

[0078] In some implementation manners, when the drivable width of the first position area is less than or equal to the width threshold, detect the position of the rearview mirror of the vehicle on one side of the first position area close to the first position area. For example, due to the restrictions of vehicle 502, vehicle 503, and vehicle 504, the width of area a in the direction perpendicular to the driving direction of vehicle 501 is too narrow, resulting in vehicle 501 may rub against at least one of vehicle 502, vehicle 503, and vehicle 504 when passing through area a. Then vehicle 501 can detect the position of rearview mirror 5021 of vehicle 502, and plan the driving path of the host vehicle in area a according to the position of rearview mirror 5021. Exemplarily, the width threshold can be 2.3 meters, or it can also be 2.5 meters, or it can also be other values. For example, the width threshold is determined according to the width of the host vehicle, and a preset width is added to the width of the host vehicle to obtain the width threshold. Among them, the preset width can be 30 centimeters, or 40 centimeters, or it can also be other values.

[0079] It can be understood that the above vehicle 502 and vehicle 505 can be regarded as some examples of the target vehicle, area a and area b can be regarded as some examples of the first position area, and rearview mirror 5021 and rearview mirror 5051 can be regarded as some examples of the first rearview mirror.

[0080] S420. Determine the position of the first rearview mirror on the target vehicle according to the first image and the second image.

[0081] Exemplarily, the position of the first rearview mirror on the target vehicle includes the position of the first rearview mirror in the longitudinal direction of the target vehicle, or may further include the position of the first rearview mirror in the height direction of the target vehicle. Herein, the longitudinal direction refers to the direction parallel to the vehicle center line, and the height direction refers to the direction perpendicular to the plane where the four wheels of the vehicle are located. In addition, the position of the first rearview mirror on the target vehicle can be understood as the position of the root of the first rearview mirror on the outer contour of the target vehicle.

[0082] In some implementation manners, determining the position of the first rearview mirror on the target vehicle according to the first image and the second image includes: determining a first straight line according to the first image, where the first straight line is the straight line where the first area of the intelligent driving device and the root of the first rearview mirror are located at the first moment; determining a second straight line according to the second image, where the second straight line is the straight line where the second area of the intelligent driving device and the root of the first rearview mirror are located at the second moment; determining the position of the root of the first rearview mirror on the outer contour of the target vehicle according to the intersection point of the first straight line and the outer contour of the target vehicle, and the intersection point of the second straight line and the outer contour of the target vehicle.

[0083] Wherein, the first straight line is determined according to the pixel position corresponding to the first rearview mirror in the first image, and the first straight line indicates the direction in which the optical center of the imaging device that acquires the first image points to the first rearview mirror. The second straight line is determined according to the pixel position corresponding to the first rearview mirror in the second image, and the second straight line indicates the direction in which the optical center of the imaging device that acquires the second image points to the first rearview mirror.

[0084] As Figure 6 shown in (a) of Figure 6As shown in (b) thereof, where the contour 601 is the outer contour of the vehicle 610 sensed by the radar sensor, and the contour 602 is the outer contour of the vehicle 610 determined by fusing the sensing results of multiple sensors (such as radar sensors, camera devices, etc.). The arrow 603 can be understood as the direction in which the optical center of the camera device 1 of the host vehicle points to the root of the rearview mirror 611 when the camera device 1 is at position 1; the arrow 604 can be understood as the direction in which the optical center of the camera device 2 of the host vehicle points to the root of the rearview mirror 611 when the camera device 2 is at position 2. Among them, the camera device 1 and the camera device 2 can be the same camera device. When the camera device 1 and the camera device 2 are the same camera device, position 1 and position 2 are different positions of the camera device respectively. Further, according to the intersection point of the arrow 603 and the contour 602 (hereinafter referred to as intersection point a), and the intersection point of the arrow 604 and the contour 602 (hereinafter referred to as intersection point b), the position 605 is determined, and this position 605 indicates the position of the root of the rearview mirror 611 on the vehicle 610. Exemplarily, the position 605 can be determined according to the different weights of the position indicated by the intersection point a and the position indicated by the intersection point b. For example, when determining the position 605, the weights of the position indicated by the intersection point a and the position indicated by the intersection point b are each 0.5, or the weights of the position indicated by the intersection point a and the position indicated by the intersection point b are 0.4 and 0.6 respectively. This application does not make specific limitations on this. In actual implementation, the weights of the position indicated by the intersection point a and the position indicated by the intersection point b can be determined according to the positions of the camera device 1 and the camera device 2 in the host vehicle; or, the weights of the position indicated by the intersection point a and the position indicated by the intersection point b can also be determined according to the angle between the arrow 603 (or 604) and the central axis of the host vehicle; or, the weights of the position indicated by the intersection point a and the position indicated by the intersection point b can also be determined by other methods.

[0085] It can be understood that the straight line where the arrow 603 is located can be regarded as an example of the above-mentioned first straight line; the straight line where the arrow 604 is located can be regarded as an example of the above-mentioned second straight line.

[0086] In some implementation manners, after executing S420, the method 400 further includes: determining the position of the first rearview mirror in the lateral direction of the target vehicle. Among them, the lateral direction refers to the direction parallel to the plane where the four wheels of the vehicle are located and perpendicular to the vehicle center line. The position of the first rearview mirror in the lateral direction can include the position of the tip of the first rearview mirror.

[0087] Exemplarily, a lateral distance can be added to the root position of the first rearview mirror in a direction parallel to the lateral direction of the target vehicle to obtain the tip position of the first rearview mirror. For example, if the coordinates of the root position of the first rearview mirror in the xoy plane of the vehicle coordinate system are (x, y), then the coordinates of the tip position of the first rearview mirror in the xoy plane of the vehicle coordinate system can be (x, y + Δy). Here, the x-axis is parallel to the longitudinal direction of the target vehicle, the y-axis is parallel to the lateral direction of the target vehicle and the positive direction of the y-axis is the direction from the vehicle center to the first rearview mirror, and Δy represents the above-mentioned lateral distance. Exemplarily, the lateral distance can be 12 cm, or 15 cm, or it can also be other values. For example, the lateral distance can be determined according to the model of the target vehicle.

[0088] In some implementation manners, before or after executing S420, or while executing S420, method 400 further includes: determining the opening and closing state of the first rearview mirror, that is, the first rearview mirror is in a retracted state or an open state. When the first rearview mirror is in the retracted state, determining the position of the outer contour of the first rearview mirror according to the outer contour of the target vehicle and the first compensation amount; or, when the first rearview mirror is in the open state, determining the position of the outer contour of the first rearview mirror according to the outer contour of the target vehicle and the second compensation amount; where the first compensation amount is less than or equal to the second compensation amount.

[0089] Exemplarily, when the root position of the first rearview mirror has been determined, determining the position of the outer contour of the first rearview mirror according to the outer contour of the target vehicle and the first compensation amount (or the second compensation amount) may include: determining the tip position of the first rearview mirror according to the position of the root of the first rearview mirror on the outer contour of the target vehicle and the first compensation amount (or the second compensation amount). As Figure 7 shown, the outer contour line of vehicle 610 is 701, and position 702 is the position of the root of rearview mirror 611 on the outer contour of the vehicle. More specifically, as Figure 7 (a) in shows, if the rearview mirror 611 is in the retracted state, then adding the first compensation amount to 702 to obtain the outer contour position 703 of the first rearview mirror; as Figure 7 (b) in shows, if the rearview mirror 611 is in the open state, then adding the second compensation amount to 702 to obtain the outer contour position 704 of the first rearview mirror.

[0090] Exemplarily, the first compensation amount can be 8 cm, or 10 cm, or it can also be other values; the second compensation amount can be 12 cm, or 15 cm, or it can also be other values.

[0091] In specific implementation, the opening and closing state of the first rearview mirror can be determined based on multiple images collected within a period of time, or alternatively, the opening and closing state of the first rearview mirror can be determined in combination with the driving state of the target vehicle. Among them, the multiple images can include the first image and / or the second image, or can also be other images other than the first image and the second image. In one example, a neural network can be used to process the multiple images to determine the opening and closing state of the first rearview mirror. If it is determined that the first rearview mirror is retracted after sequentially processing the multiple images, the first rearview mirror is in the retracted state; if it is determined that the first rearview mirror is open after sequentially processing the multiple images, the first rearview mirror is in the open state. In another example, if the target vehicle is in a driving state, it can be determined that the first rearview mirror is in the open state. Among them, the neural network can be Visual Geometry Group (VGG) 16, VGG19, Residual Networks (ResNet) 50, etc.

[0092] In some implementation manners, method 400 further includes: determining a first compensation amount and / or a second compensation amount according to the vehicle type of the target vehicle. Among them, the vehicle type of the target vehicle indicates that the target vehicle is one of a sedan, a passenger car (such as a mini, light, medium, large, extra-large), or a truck (such as a mini, light, medium, heavy). It should be understood that the above vehicle types are only exemplary descriptions, and in actual implementation, the vehicle types of vehicles can also include more or fewer vehicle types.

[0093] Exemplarily, the vehicle type of the target vehicle can be determined by processing the image collected by the imaging device through an image processing method; or alternatively, it can also be received through vehicle-to-everything (V2X) communication or vehicle-to-vehicle (V2V) communication, etc.

[0094] S430, control the intelligent driving device according to the position of the first rearview mirror on the target vehicle.

[0095] In some implementation manners, controlling the intelligent driving device includes: controlling the intelligent driving device to drive into the first position area according to the position of the first rearview mirror on the target vehicle; and / or controlling the display device of the intelligent driving device to display the position of the first rearview mirror on the target vehicle.

[0096] The rearview mirror detection method provided by the embodiments of the present application can improve the accuracy of detecting the position of the rearview mirror of other vehicles. Further, when meeting a vehicle in a narrow position or parking in a narrow parking position, the accurate detection of the rearview mirror position helps to improve the rationality and safety of the driving path planned for the own vehicle, improve the vehicle passing rate, and reduce the probability of scratching between the own vehicle and other vehicles.

[0097] Figure 8 Fig. 8 shows another schematic flowchart of the rearview mirror detection method provided by the embodiments of the present application. The method 800 can be regarded as an extension or further explanation of the method 400. Specifically, the method 800 includes S801 to S806.

[0098] S801, obtaining a plurality of images collected by a camera device and including the vehicle 1.

[0099] Wherein, the vehicle 1 can be an example of the above target vehicle.

[0100] S802, determining the outline of the vehicle 1 according to one or more of the plurality of images.

[0101] Exemplarily, the outline of the vehicle 1 can be determined by a post - fusion method. For example, after processing the data collected by the camera device and the data sensed by the radar respectively, through post - fusion methods such as Kalman filtering, extended Kalman filter (EKF), and Hungarian matching, the processing result of the data collected by the camera device and the data result of the radar sensing are fused to determine the outline of the vehicle 1.

[0102] S803, determining the pixel positions of the rearview mirror 1 in each of at least two images including the rearview mirror 1 of the vehicle 1 in the plurality of images.

[0103] Wherein, the rearview mirror 1 is an example of the above first rearview mirror.

[0104] S804, determining the opening and closing state of the rearview mirror 1 according to at least one image including the rearview mirror 1 of the vehicle 1 in the plurality of images.

[0105] S805, determining the position of the rearview mirror 1 in the longitudinal direction of the vehicle 1 according to the pixel positions and the outline of the vehicle 1.

[0106] Wherein, the position of the rearview mirror 1 in the longitudinal direction of the vehicle 1 can be understood as: the intersection point of the root position of the rearview mirror 1 in the direction parallel to the central axis of the vehicle 1 and the outline of the vehicle 1.

[0107] Exemplarily, the method for determining the longitudinal position of the rearview mirror 1 in the vehicle 1 according to the pixel positions and the outline of the vehicle 1 can refer to the description in the method 400, which will not be elaborated here.

[0108] S806, determining the tip position of the rearview mirror 1 according to the position of the rearview mirror 1 in the longitudinal direction of the vehicle 1 and the opening and closing state of the rearview mirror 1.

[0109] Exemplarily, the implementation method for determining the tip position of the rearview mirror 1 can refer to the description in method 400, which will not be elaborated here.

[0110] In actual implementation, some steps among S801 to S806 can be executed. For example, S804 and S806 can be not executed. After determining the root position of the rearview mirror 1 (i.e., the position in the longitudinal direction of the vehicle 1), the tip position of the rearview mirror 1 can be determined based on compensating a preset value in the lateral direction of the vehicle 1 with respect to the root position. Among them, the preset value can be 15 cm, or 20 cm, or can also be other values.

[0111] In various embodiments of the present application, if there is no special description and logical conflict, the terms and / or descriptions among the various embodiments are consistent and can be referenced mutually. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0112] In the foregoing text, in combination with Figures 1 to 8 the rearview mirror detection method provided by the embodiments of the present application is described in detail. Next, in combination with Figure 9 and Figure 10 the rearview mirror detection device provided by the embodiments of the present application will be described in detail. It should be understood that the description of the device embodiments corresponds to the description of the method embodiments. Therefore, the content not described in detail can refer to the foregoing method embodiments. For the sake of brevity, it will not be elaborated here.

[0113] Figure 9 Fig. shows a schematic block diagram of a rearview mirror detection device 2000 provided by an embodiment of the present application. The device 2000 may include units for executing method 400 or method 800. Moreover, each unit in the device 2000 is for implementing the corresponding processes in the embodiments of method 400 and method 800.

[0114] Specifically, the device 2000 includes an acquisition unit 2010 and a processing unit 2020. When the device 2000 is used to execute method 400, the acquisition unit 2010 is used to: acquire a first image and a second image, where the first image and the second image are images of a first rearview mirror of a target vehicle acquired from different angles; the processing unit 2020 is used to: determine the position of the first rearview mirror on the target vehicle according to the first image and the second image; the processing unit 2020 is further used to: control an intelligent driving device according to the position of the first rearview mirror on the target vehicle.

[0115] In some implementations, the first image is captured at a first moment, and the second image is captured at a second moment. The processing unit 2020 is configured to: determine a first straight line according to the first image, where the first straight line is the straight line where the first area of the intelligent driving device and the root of the first rearview mirror are located at the first moment; determine a second straight line according to the second image, where the second straight line is the straight line where the second area of the intelligent driving device and the root of the first rearview mirror are located at the second moment; and determine the position of the root of the first rearview mirror on the target vehicle according to the intersection point of the first straight line and the outer contour of the target vehicle and the intersection point of the second straight line and the outer contour of the target vehicle.

[0116] In some implementations, the intelligent driving device includes a first imaging device and a second imaging device. The first image is captured by the first imaging device at a first moment, and the second image is captured by the second imaging device at a second moment; the first area is the area on the intelligent driving device where the first imaging device is disposed, and the second area is the area on the intelligent driving device where the second imaging device is disposed.

[0117] In some implementations, the processing unit 2020 is further configured to: when the first rearview mirror is in a retracted state, determine the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a first compensation amount; or, when the first rearview mirror is in an open state, determine the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a second compensation amount; where the first compensation amount is less than or equal to the second compensation amount.

[0118] In some implementations, the processing unit 2020 is further configured to: determine the first compensation amount and / or the second compensation amount according to the vehicle model of the target vehicle.

[0119] In some implementations, the target vehicle is located on one side of a first position area, and the first rearview mirror is close to the first position area; where the first position area is the target parking area of the intelligent driving device, or the first position area is the area during the journey when the intelligent driving device travels towards the destination

[0120] In some implementations, the drivable width of the first position area is less than or equal to a width threshold.

[0121] In some implementations, the processing unit 2020 is configured to: control the intelligent driving device to drive into the first position area according to the position of the first rearview mirror on the target vehicle.

[0122] In some implementations, the processing unit 2020 is configured to: control the display device of the intelligent driving device to display the position of the first rearview mirror on the target vehicle.

[0123] Exemplarily, the acquisition unit 2010 and the processing unit 2020 can be disposed in Figure 2In the system shown, more specifically, the above-mentioned acquisition unit 2010 can be arranged in the planning module 220, and the processing unit 2020 can be arranged in the control module 230. Exemplarily, the operations performed by the above-mentioned acquisition unit 2010 and processing unit 2020 can be executed by one processor, or can also be executed by different processors. In a specific implementation process, the above one or more processors can be processors arranged in Figure 1 the intelligent driving device 100 shown; or, the above device 2000 can be a chip arranged in the intelligent driving device 100.

[0124] In a specific implementation process, each unit in the above device can be integrated in whole or in part, or can also be independently implemented. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0125] Figure 10 It is another schematic block diagram of the rearview mirror detection device provided by an embodiment of the present application. Figure 10 The rearview mirror detection device 2100 shown can include: a processor 2110, a transceiver 2120, and a memory 2130. Among them, the processor 2110, the transceiver 2120, and the memory 2130 are connected through an internal connection path. The memory 2130 is used to store instructions, and the processor 2110 is used to execute the instructions stored in the memory 2130 to implement the methods in the above embodiments. Optionally, the memory 2130 can be coupled to the processor 2110 through an interface, or can also be integrated with the processor 2110.

[0126] It should be noted that the above transceiver 2120 can include, but is not limited to, transceiver devices such as input / output interfaces to implement communication between the device 2100 and other devices or communication networks.

[0127] The memory 2130 can be a volatile memory and / or a non-volatile memory. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM). For example, the RAM can be used as an external cache. By way of example and not limitation, the RAM includes the following various forms: static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0128] The transceiver 2120 uses a transceiver device such as, but not limited to, a transceiver to implement communication between the device 2110 and other devices or a communication network, so as to receive / send data / information for implementing the methods in the above various embodiments.

[0129] An embodiment of the present application further provides a computing platform, which includes the rearview mirror detection device 2000 or the rearview mirror detection device 2100 in the above embodiments.

[0130] An embodiment of the present application further provides an intelligent driving device, which includes the computing platform in the above embodiments; or, the intelligent driving device includes the rearview mirror detection device 2000 or the rearview mirror detection device 2100 in the above embodiments.

[0131] An embodiment of the present application further provides a computer program product, which includes computer program code. When the computer program code runs on a computer, it causes the computer to implement the methods in the above various embodiments of the present application.

[0132] An embodiment of the present application also provides a computer-readable storage medium storing computer instructions, which, when running on a computer, cause the computer to implement the methods in the above various embodiments of the present application.

[0133] An embodiment of the present application also provides a chip including circuitry for executing the methods in the above various embodiments of the present application.

[0134] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0135] In the description of the embodiments of the present application, unless otherwise specified, " / " means "or". For example, A / B may represent A or B; herein, "and / or" is a relationship describing associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In the present application, "at least one" means one or more, and "a plurality" means two or more. "At least one (item)" or its similar expression means any combination of these items, including any combination of single (item) or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, c can be single or multiple.

[0136] In the embodiments of the present application, prefix words such as "first" and "second" are only used to distinguish different described objects and have no restrictive effect on the position, order, priority, quantity, content, etc. of the described objects. In the embodiments of the present application, the use of ordinal numbers and other prefix words for distinguishing described objects does not constitute a limitation on the described objects. The description of the described objects refers to the description in the context of the claims or embodiments, and no redundant limitation should be formed due to the use of such prefix words.

[0137] In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0138] In various embodiments of the present application, without special instructions and logical conflicts, the terms and / or descriptions among the various embodiments are consistent and can be cross-referenced. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0139] The unit described as a separate component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] In addition, in each embodiment of the present application, each functional unit may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

[0141] As mentioned above, the above are only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A rearview mirror detection method, characterized in that, Applied to an intelligent driving device, including: Obtain a first image and a second image, where the first image and the second image are images of the first rearview mirror of the target vehicle collected from different angles respectively; Determine the position of the first rearview mirror on the target vehicle according to the first image and the second image; Control the intelligent driving device according to the position of the first rearview mirror on the target vehicle.

2. The method according to claim 1, wherein The first image is collected at a first moment, and the second image is collected at a second moment. Determining the position of the first rearview mirror on the target vehicle includes: Determine a first straight line according to the first image, where the first straight line is the straight line where the first area of the intelligent driving device and the root of the first rearview mirror are located at the first moment; Determine a second straight line according to the second image, where the second straight line is the straight line where the second area of the intelligent driving device and the root of the first rearview mirror are located at the second moment; Determine the position of the root of the first rearview mirror on the target vehicle according to the intersection point of the first straight line and the outer contour of the target vehicle, and the intersection point of the second straight line and the outer contour of the target vehicle.

3. The method according to claim 2, characterized in that, The intelligent driving device includes a first imaging device and a second imaging device. The first image is collected by the first imaging device at the first moment, and the second image is collected by the second imaging device at the second moment; the first area is the area where the first imaging device is arranged on the intelligent driving device, and the second area is the area where the second imaging device is arranged on the intelligent driving device.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: When the first rearview mirror is in the retracted state, determine the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a first compensation amount; or, When the first rearview mirror is in the unfolded state, determine the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a second compensation amount; Wherein, the first compensation amount is less than or equal to the second compensation amount.

5. The method according to claim 4, characterized in that The method further includes: Determine the first compensation amount and / or the second compensation amount according to the vehicle model of the target vehicle.

6. The method according to any one of claims 1 to 5, characterized in that, The target vehicle is located on one side of a first position area, and the first rearview mirror is close to the first position area; wherein, the first position area is the target parking area of the intelligent driving device, or the first position area is the area passed by the intelligent driving device when driving towards the destination.

7. The method according to claim 6, characterized in that, The drivable width of the first position area is less than or equal to a width threshold.

8. The method according to claim 6 or 7, characterized in that, Controlling the intelligent driving device includes: Control the intelligent driving device to drive into the first position area according to the position of the first rearview mirror on the target vehicle.

9. The method according to any one of claims 1 to 8, characterized in that Controlling the intelligent driving device includes: Control the display device of the intelligent driving device to display the position of the first rearview mirror on the target vehicle.

10. A rearview mirror detection device, characterized in that, Including: An acquisition unit for acquiring a first image and a second image, where the first image and the second image are images of the first rearview mirror of the target vehicle collected from different angles respectively; A processing unit for determining the position of the first rearview mirror on the target vehicle based on the first image and the second image; The processing unit is further configured to: control the intelligent driving device according to the position of the first rearview mirror on the target vehicle.

11. The device according to claim 10, characterized in that, The first image is acquired at a first moment, and the second image is acquired at a second moment. The processing unit is configured to: Determine a first straight line according to the first image, where the first straight line is the straight line where the first area of the intelligent driving device and the root of the first rearview mirror are located at the first moment; Determine a second straight line according to the second image, where the second straight line is the straight line where the second area of the intelligent driving device and the root of the first rearview mirror are located at the second moment; Determine the position of the root of the first rearview mirror on the target vehicle according to the intersection point of the first straight line and the outer contour of the target vehicle, and the intersection point of the second straight line and the outer contour of the target vehicle.

12. The device according to claim 11, wherein The intelligent driving device includes a first imaging device and a second imaging device. The first image is acquired by the first imaging device at the first moment, and the second image is acquired by the second imaging device at the second moment; the first area is the area on the intelligent driving device where the first imaging device is disposed, and the second area is the area on the intelligent driving device where the second imaging device is disposed.

13. The device according to any one of claims 10 to 12, characterized in that, The processing unit is further configured to: When the first rearview mirror is in a retracted state, determine the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a first compensation amount; or, When the first rearview mirror is in an open state, determine the position of the outer contour of the first rearview mirror according to the position of the first rearview mirror on the target vehicle and a second compensation amount; Wherein, the first compensation amount is less than or equal to the second compensation amount.

14. The device according to claim 13, characterized in that, The processing unit is further configured to: Determine the first compensation amount and / or the second compensation amount according to the vehicle model of the target vehicle.

15. The device according to any one of claims 10 to 14, characterized in that The target vehicle is located on one side of a first position area, and the first rearview mirror is close to the first position area; wherein, the first position area is the target parking area of the intelligent driving device, or the first position area is the area passed by the intelligent driving device when driving to the destination.

16. The device according to claim 15, characterized in that, The drivable width of the first position area is less than or equal to a width threshold.

17. The device according to claim 15 or 16, characterized in that, The processing unit is further configured to: Control the intelligent driving device to drive into the first position area according to the position of the first rearview mirror on the target vehicle.

18. The device according to any one of claims 10 to 17, characterized in that The processing unit is further configured to: Control the display device of the intelligent driving device to display the position of the first rearview mirror on the target vehicle.

19. A rearview mirror detection device, characterized in that, Including: A memory for storing a computer program; A processor for executing the computer program stored in the memory, so that the device executes the method according to any one of claims 1 to 9.

20. An intelligent driving device, characterized in that, The intelligent driving device includes the device according to any one of claims 10 to 19.

21. A computer-readable storage medium, characterized in that, Instructions are stored thereon, and when the instructions are executed by a processor, the processor is caused to implement the method according to any one of claims 1 to 9.

22. A chip, characterized in that, The chip includes a circuit for performing the method according to any one of claims 1 to 9.

Images