Method and device for tracking non-motorized vehicle lane blind area during right steering at vehicle intersection

By installing a blind spot camera on the right side of the vehicle and dynamically adjusting the gimbal corner, the problem of real-time observation of blind spots in non-motor lanes when the vehicle turns right is solved, effectively covering the blind spots and improving traffic safety is achieved.

CN119550918AActive Publication Date: 2025-03-04ANHUI POLYTECHNIC UNIV
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411966089.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-30
Publication Date
2025-03-04
Estimated Expiration
2044-12-30

AI Technical Summary

Technical Problem

When the vehicle turns right, it is difficult for the driver to observe the traffic conditions of the non-motorized vehicle lane on the right in real time, resulting in blind spots in the field of vision and increasing the risk of traffic accidents.

Method used

By installing a blind spot camera on the right side of the vehicle and dynamically adjusting the angle β of the gimbal, the image images of the non-motorized vehicle lane are obtained in real time, the center coordinates of the blind spots are calculated, and the viewing direction of the camera is dynamically adjusted to cover the blind spots.

Benefits of technology

It effectively reduces the blind spots of the non-motorized vehicle lanes when turning, improves the driver's real-time observation of traffic conditions on the right, and reduces the incidence of traffic accidents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119550918A_ABST
    Figure CN119550918A_ABST
Patent Text Reader

Abstract

The invention relates to the field of vehicle safety, in particular to a method for tracking a non-motorized vehicle lane blind area in right steering at a vehicle intersection, and a corresponding device and system thereof. The method comprises the steps that S1, the steering wheel rotation angle of a vehicle is obtained in real time, and the vehicle rotation angle is calculated according to the steering wheel rotation angle and vehicle body parameters of the vehicle; and S2, acquiring an image picture of a non-motorized vehicle lane on the right side through a blind area camera mounted on the vehicle body, calculating a center coordinate of a blind area position according to the image picture, and representing the center coordinate as a parameter related to a vehicle turning angle. S3, based on the center coordinates of the blind area, the rotation relation between the holder rotation angle of the blind area camera and the vehicle rotation angle is obtained; and dynamically adjusting the rotation angle of the holder of the blind area camera so as to enable the optical center direction of the blind area camera to coincide with the center coordinate of the blind area. The problem that in the prior art, it is difficult to observe the traffic condition of the non-motor vehicle on the right side in real time during right turning is solved, and then the traffic safety accident rate is effectively reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle safety, and in particular to a method for tracking a blind spot of a non-motor vehicle lane during a right turn at an intersection, a blind spot tracking device for a non-motor vehicle lane, and a right turn blind spot safety auxiliary driving system for a vehicle. Background Art

[0002] During turning, the A-pillar, B-pillar and other structural parts of the vehicle body can easily block the driver's line of sight, causing blind spots in the driver's field of vision. The rearview mirror has a fixed angle and can only observe a fixed area on the side and rear of the vehicle. When the vehicle angle is adjusted, only part of the non-motorized vehicle lane can be observed through the rearview mirror or window. The traffic dynamics in the blind spot are unknown, which is not conducive to the driver's control of the vehicle and poses a threat to traffic safety.

[0003] Some vehicles install cameras to obtain image data from the outside of the vehicle, thereby helping users observe traffic conditions in blind spots to reduce the incidence of traffic accidents and improve driving safety. However, in actual situations, the installed cameras can usually only observe images from a fixed perspective. For drivers, it is not necessary to pay attention to traffic conditions at a specific perspective, but rather to traffic conditions at certain specific locations. For example, when a vehicle turns right, it is usually necessary to pay attention to traffic conditions on non-motor vehicles on the right. Therefore, how to dynamically track areas with safety risks during vehicle driving is an important issue that technicians need to solve. Summary of the invention

[0004] In order to solve the problem that it is difficult to realize real-time observation of the traffic conditions of non-motor vehicles on the right side when turning right in the prior art, the present invention provides a method, device and system for tracking the blind spot of non-motor vehicles when turning right at an intersection.

[0005] The technical solution provided by the present invention includes the following contents:

[0006] A method for tracking a blind spot of a non-motor vehicle lane during a right turn at a vehicle intersection, which is used to dynamically adjust a pan / tilt angle β of a blind spot camera installed on the right side of the vehicle when the vehicle turns right, and comprises the following steps:

[0007] S1: Get the vehicle's steering wheel angle θ in real time sw , and calculate the vehicle turning angle θ based on the steering wheel angle and the current vehicle body parameters.

[0008] S2: Obtain the image of the right non-motorized vehicle lane through the blind spot camera installed on the vehicle body, and calculate the center coordinates of the blind spot position (C x , C y ) and express it as a parameter related to the vehicle turning angle; the process is as follows:

[0009] S21: A vehicle coordinate system is established with the position of the right side B-pillar of the vehicle as the origin, the vehicle forward direction as the Y-axis, and the vehicle width direction as the X-axis.

[0010] S22: Identify a dangerous area at the intersection of the non-motorized vehicle lane appearing in the image, define the area as a blind spot, and determine the boundary of the blind spot.

[0011] S23: Define that the distance between the intersection of the far long side of the blind spot and the Y axis and the origin is A; the distance between the intersection of the near short side of the blind spot and the Y axis and the origin is B.

[0012] S24: Obtain the values ​​of A, B, and θ in real time, and calculate the center coordinates of the blind spot (C x , C y ):

[0013]

[0014] In the above formula, d represents the width of the non-motorized vehicle lane;

[0015] S3: Based on the center coordinates of the blind area (C x , C y ), obtain the rotation relationship between the pan-tilt angle β of the blind spot camera and the vehicle angle θ; dynamically adjust the pan-tilt angle β of the blind spot camera so that the optical center direction of the blind spot camera coincides with the center coordinates of the blind spot.

[0016] In the present invention, the blind spot is defined as a rectangular area with a width of the non-motor vehicle as the width and a length of 30m. The pedestrian crossing line at the blind spot intersection is the front boundary of the short side of the blind spot.

[0017] As a further improvement of the present invention, in step S1, the calculation formula of the vehicle turning angle θ is as follows:

[0018]

[0019] In the above formula, δ represents the transmission ratio of the vehicle; v represents the driving speed of the vehicle; and L represents the length of the vehicle body.

[0020] As a further improvement of the present invention, in step S3, the rotation relationship between the pan / tilt angle β and the vehicle angle θ is as follows:

[0021]

[0022] In the above formula, D represents the distance from the right rearview mirror of the vehicle to the B-pillar.

[0023] As a further improvement of the present invention, a steering wheel angle threshold θ0 is preset, and the real-time vehicle steering wheel angle θ swAfter exceeding the safety zone (-θ0, θ0), the right-turn non-motor vehicle lane tracking function is triggered.

[0024] As a further improvement of the present invention, a delay time T0 is preset; after the right-turn non-motor vehicle lane tracking function of the vehicle is triggered, when the time for the vehicle steering wheel to return to the center reaches the preset delay time T0, the right-turn non-motor vehicle lane tracking function of the vehicle is turned off and the camera's pan / tilt is restored to its initial position.

[0025] As a further improvement of the present invention, the positioning and navigation information of the vehicle is obtained in real time, and the following decisions are made:

[0026] (1) When the vehicle reaches the intersection and the vehicle steering wheel angle θ sw After exceeding the safety zone (-θ0, θ0), the right-turn non-motor vehicle lane tracking function is triggered.

[0027] (2) After the vehicle leaves the intersection and the time it takes for the vehicle's steering wheel to return to the center position reaches a preset delay time T0, the right-turn non-motor vehicle lane tracking function of the vehicle is turned off.

[0028] As a further improvement of the present invention, the image data collected by the blind spot camera is displayed in real time inside the vehicle, the moving targets in the blind spot in the video image are identified, and a reminder is issued to the driver when there is an approaching moving target in the blind spot.

[0029] The present invention also includes a blind spot tracking device for non-motor vehicle intersections, which includes: a memory, a processor, and a computer program stored in the memory and running in the processor. When the processor executes the computer program, the video data collected by the blind spot camera and the vehicle turning angle θ are acquired in real time; then the blind spot tracking method for non-motor vehicle lanes during right turns at vehicle intersections as described above is used to dynamically adjust the pan / tilt turning angle β of the blind spot camera.

[0030] The present invention also includes a right-turn blind spot safety auxiliary driving system for a vehicle, which includes a blind spot camera and a blind spot tracking device for a non-motor vehicle intersection. The blind spot camera is installed on the right side of the vehicle to obtain an image of the right rear. The blind spot camera also includes a pan / tilt for adjusting its own framing direction.

[0031] The blind spot tracking device at the non-motor vehicle intersection is electrically connected to the vehicle's control system and the blind spot camera; the blind spot tracking device at the non-motor vehicle intersection is used to, after triggering the vehicle's right-turn non-motor vehicle lane tracking function, adopt the aforementioned non-motor vehicle lane blind spot tracking method during the right turn of the vehicle at the intersection, to dynamically adjust the pan-tilt angle β of the blind spot camera, and display the image data collected by the blind spot camera in real time on the vehicle's on-board system.

[0032] The technical solution provided by the present invention has the following beneficial effects:

[0033] This aspect provides a technical solution for rotating and adjusting the angle of a blind spot camera gimbal installed on a vehicle according to the steering angle of the vehicle. When the vehicle drives to an intersection and turns right, the solution can use the blind spot camera to track and observe high-risk areas on the non-motorized vehicle lane in the same direction, thereby providing guidance for the user's driving decision. The solution of the present invention can reduce the blind spot of the non-motorized vehicle road when the vehicle turns, ensuring the recognition and property safety of other vehicles and pedestrians on the road.

[0034] In addition, the scheme of the present invention has simple logic, strong practicality, low deployment cost and broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of the steps of a method for tracking a blind spot in a non-motor vehicle lane during a right turn at an intersection provided in Example 1 of the present invention.

[0036] Figure 2 This is the spatial distribution map of the blind spot when the vehicle turns right at an intersection.

[0037] Figure 3 A schematic diagram of the dynamic coordinate system of the blind spot camera rotation control process established based on the vehicle.

[0038] Figure 4 This is a schematic diagram of the operating principle of the blind spot tracking device for non-motor vehicle intersections provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "or / and" used herein includes any and all combinations of one or more of the related listed items.

[0041] Example 1

[0042] When a motor vehicle turns right at an intersection, due to the blind spots caused by the vehicle's body structure such as the B-pillar and the user's driving skills, the driver will not be able to fully observe the vehicle conditions on the right non-motorized vehicle lane, which can easily cause traffic accidents. In order to reduce the incidence of such accidents, existing traffic regulations require vehicles to slow down when turning, turn on the turn signal in advance, and use the rearview mirror to observe the road conditions. However, the field of view of the rearview mirror will change when the vehicle turns, and it cannot help the driver to fully observe risk areas such as the non-motorized vehicle lane at the intersection. In response to this problem, this embodiment provides a method for tracking the blind spot of the non-motorized vehicle lane when the vehicle turns right at an intersection. The method is used to start the blind spot camera installed on the right side of the vehicle when the vehicle arrives at the intersection and turns right, and dynamically adjust the pan-tilt angle β of the blind spot camera, and use the blind spot camera to track the corresponding position of the non-motorized vehicle lane, and then provide guidance for the user's driving decision through the image collected by the blind spot camera.

[0043] Specifically, Figure 1 As shown, the method for tracking the blind spot of a non-motor vehicle lane during a right turn at an intersection provided by this embodiment includes the following steps:

[0044] S1: Get the vehicle's steering wheel angle θ in real time sw , and calculate the vehicle turning angle θ according to the steering wheel angle and the current vehicle body parameters; the calculation process is as follows:

[0045] (1) First, calculate the wheel angle θ of the vehicle's steering wheel based on the steering wheel angle wh :

[0046]

[0047] In the above formula, δ represents the transmission ratio of the vehicle.

[0048] (2) According to the wheel angle θ wh Calculate the turning radius r of the vehicle:

[0049]

[0050] In the above formula, L represents the body length of the vehicle.

[0051] (3) The vehicle turning angle θ is calculated based on the vehicle's driving speed v and turning radius r:

[0052]

[0053] S2: Obtain the image of the right non-motorized vehicle lane through the blind spot camera installed on the vehicle body, and calculate the center coordinates of the blind spot position (C x , C y). In the solution of this embodiment, in order to track the blind spot, the blind spot camera needs to determine the center coordinates of the blind spot. This embodiment determines the center coordinates of the blind spot position (C x , C y ) process is as follows:

[0054] S21: Figure 2 As shown, a vehicle coordinate system is established with the position of the right side B-pillar of the vehicle as the origin, the vehicle forward direction as the Y-axis, and the vehicle width direction as the X-axis.

[0055] S22: Identify a dangerous area at the intersection of the non-motorized vehicle lane appearing in the image, define the area as a blind spot, and determine the boundary of the blind spot.

[0056] In this embodiment, the blind spot is defined as a rectangular area with a width of non-motor vehicles and a length of 30m. Among them, the crosswalk line at the intersection of the blind spot is the front boundary of the short side of the blind spot. That is, starting from the boundary of the crosswalk on the side of the oncoming vehicle at the intersection, the area of ​​the crosswalk totaling 30m is the blind spot that the blind spot camera in this embodiment needs to track. In actual application, the area can be identified by an image recognition algorithm, and the boundary of the blind spot can be marked.

[0057] S23: Define that the distance between the intersection of the far long side of the blind spot and the Y axis and the origin is A; the distance between the intersection of the near short side of the blind spot and the Y axis and the origin is B.

[0058] In this embodiment, if Figure 3 As shown, the blind spot on the non-motorized vehicle lane is a quadrilateral, and the four corner points of the quadrilateral are recorded as P1, P2, P3, and P4 respectively; then P1P2 intersects the Y axis at point E; P2P3 intersects the Y axis at point F. At this time, A=|OF|, B=|OE|. On this basis, considering that the reference of the coordinate system is constantly changing when the vehicle moves, the coordinates of the blind spot can be converted into a dynamic coordinate system related to the vehicle turning angle θ. For example, in the dynamic coordinate system, combined with the values ​​of A and B, the vehicle turning angle θ, and the width d of the non-motorized vehicle lane, the four corner points of the blind spot can be expressed as follows:

[0059] Coordinates of P1:

[0060]

[0061] Coordinates of P2:

[0062]

[0063] Coordinates of P3:

[0064]

[0065] P4's coordinates:

[0066]

[0067] S24: Obtain the values ​​of A, B, and θ in real time, and calculate the center coordinates of the blind spot (C x , C y ) and express it as a parameter related to the vehicle turning angle; the process is as follows:

[0068] (1) The relationship between the coordinates of the center of the blind spot and other corner points satisfies the following formula:

[0069]

[0070] (2) Substituting the coordinates of P1 and P3 into the above formula, the center coordinates of the blind spot can be obtained as follows:

[0071]

[0072] In the above formula, d represents the width of the non-motorized vehicle lane.

[0073] S3: Based on the center coordinates of the blind area (C x , C y ), obtain the rotation relationship between the pan-tilt angle β of the blind spot camera and the vehicle angle θ; dynamically adjust the pan-tilt angle β of the blind spot camera so that the optical center direction of the blind spot camera coincides with the center coordinates of the blind spot.

[0074] In this embodiment, the calculation formula of the pan / tilt angle β that satisfies the tracking effect is as follows:

[0075]

[0076] In the above formula, D represents the distance from the right rearview mirror of the vehicle to the B-pillar.

[0077] Furthermore, the center coordinates of the blind area (C x , C y ) is substituted into the above formula, the rotation relationship between the pan-tilt angle β and the vehicle angle θ can be obtained. In this embodiment, the rotation relationship between the pan-tilt angle β and the vehicle angle θ is as follows:

[0078]

[0079] In the above formula, D represents the distance from the right rearview mirror of the vehicle to the B-pillar.

[0080] The tracking method for the non-motor vehicle lane blind spot during a right turn at an intersection provided in this embodiment is mainly applied to the vehicle control system, which can collect the vehicle's steering information in real time, and then trigger the corresponding non-motor vehicle lane tracking function as needed, and then dynamically adjust the pan / tilt angle β of the vehicle blind spot camera when necessary. In actual application, the rules for triggering the non-motor vehicle lane tracking function designed in this embodiment are:

[0081] A steering wheel angle threshold θ0 is preset, and the real-time vehicle steering wheel angle θ sw After exceeding the safety zone (-θ0, θ0), the right-turn non-motor vehicle lane tracking function is triggered.

[0082] As is known to all, the steering type of a vehicle can be identified based on the steering wheel angle of the vehicle. For example, when θ sw is less than 0, indicating that the vehicle is turning left, and when θ sw If it is greater than 0, it means that the vehicle is turning right. Generally speaking, users will also use the steering wheel to correct the direction and change lanes during driving. In order to distinguish between conventional direction correction and lane change operations, this embodiment sets a steering wheel angle threshold θ0; the threshold value can be set to 5-15° as needed. sw If the value is exceeded, it is usually considered that the vehicle is turning and the corresponding function needs to be triggered when turning right. Otherwise, it is considered that the vehicle is changing lanes or correcting direction, and there is no need to trigger the right-turn non-motor vehicle lane tracking function.

[0083] Correspondingly, the exit mechanism of the right-turn non-motor vehicle lane tracking function designed in the technical solution provided by this embodiment is: a delay time T0 is preset; after the right-turn non-motor vehicle lane tracking function of the vehicle is triggered, when the vehicle steering wheel returns to the right position for a preset delay time T0, the right-turn non-motor vehicle lane tracking function of the vehicle is turned off and the camera pan / tilt is restored to the initial position. In a typical solution, T0 = 3S.

[0084] Generally speaking, after the vehicle completes the right turn and enters the straight lane of the corresponding road, the driver will gradually correct the direction until it returns to the straight lane. During this process, the vehicle has already left the intersection. Therefore, there is no need to continue to observe the non-motorized vehicle lane on the previous road. At this time, this embodiment chooses to exit the corresponding function after the vehicle returns to the straight lane, and restores the pan / tilt of the blind spot camera to the initial position, waiting for the next trigger.

[0085] In a more optimized solution of this embodiment, the positioning and navigation information of the vehicle is obtained in real time, so as to more accurately identify the turning behavior of the vehicle at the intersection, and make trigger conditions for executing and exiting the right-turn non-motor vehicle lane tracking function of the vehicle. Specifically, the decision-making process of the optimized solution of this embodiment is as follows:

[0086] (1) When the vehicle reaches the intersection and the vehicle steering wheel angle θ sw After exceeding the safety zone (-θ0, θ0), the right-turn non-motor vehicle lane tracking function is triggered.

[0087] (2) After the vehicle leaves the intersection and the time it takes for the vehicle's steering wheel to return to the center position reaches a preset delay time T0, the right-turn non-motor vehicle lane tracking function of the vehicle is turned off.

[0088] In addition, this embodiment displays the image data collected by the blind spot camera in real time inside the vehicle. The image screen is displayed on the central control screen of the vehicle, or other external display devices for assisted driving. On the displayed image screen of the blind spot camera, the moving targets appearing in the blind spot can also be identified through image recognition and target tracking technology, and the driver can be reminded when there are approaching moving targets in the blind spot. For example, when a non-motor vehicle that may intrude into the vehicle's driving route appears in the blind spot during a vehicle turn, an alarm is issued to the user, reminding the user to slow down or take other risk avoidance measures.

[0089] Example 2

[0090] Based on the scheme of embodiment 1, this embodiment also includes a blind spot tracking device for non-motor vehicle intersections, which includes: it includes a memory, a processor, and a computer program stored in the memory and running in the processor. When the processor executes the computer program, the video data collected by the blind spot camera and the vehicle turning angle θ are acquired in real time; then the tracking method of the blind spot of the non-motor vehicle lane during the right turn at the vehicle intersection as described above is used to dynamically adjust the pan / tilt turning angle β of the blind spot camera.

[0091] The non-motor vehicle road intersection blind spot tracking device provided in this embodiment is essentially a computer device used to implement the solution in embodiment 1. Figure 4 As shown, the computer device can be an embedded device installed in each vehicle or a computing device independent of the vehicle. After it is connected to the vehicle's control system, it can recognize the scene in combination with the vehicle's basic information and operating parameters, and drive the blind spot camera's pan / tilt to rotate with the steering wheel angle when turning right at the intersection.

[0092] In practical applications, the computer device in this embodiment can adopt an intelligent terminal, a tablet computer, a laptop computer, a desktop computer, a rack server, a blade server, a tower server or a cabinet server (including an independent server, or a server cluster composed of multiple servers) that can execute programs. The computer device pointed out in this embodiment at least includes but is not limited to: a memory and a processor that can be connected to each other through a system bus. Among them, the memory (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory can be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory may also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the memory is usually used to store the operating system and various application software installed on the computer device. In addition, the memory may also be used to temporarily store various data that have been output or are to be output.

[0093] The processor may be a central processing unit (CPU), a graphics processing unit (GPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor is generally used to control the overall operation of a computer device. In this embodiment, the processor is used to run program codes stored in a memory or process data.

[0094] Example 3

[0095] Based on Embodiments 1 and 2, this embodiment provides a right-turn blind spot safety assisted driving system for a vehicle, which includes a blind spot camera and a blind spot tracking device for a non-motor vehicle intersection. The blind spot camera is installed on the right side of the vehicle to obtain an image of the right rear. The blind spot camera also includes a pan / tilt for adjusting its own framing direction.

[0096] The blind spot tracking device at the non-motor vehicle intersection is electrically connected to the vehicle's control system and the blind spot camera; the blind spot tracking device at the non-motor vehicle intersection is used to, after triggering the vehicle's right-turn non-motor vehicle lane tracking function, adopt the aforementioned non-motor vehicle lane blind spot tracking method during the right turn of the vehicle at the intersection, to dynamically adjust the pan-tilt angle β of the blind spot camera, and display the image data collected by the blind spot camera in real time on the vehicle's on-board system.

[0097] The above-described embodiment only expresses one implementation mode of the present invention, and its description is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the attached claims.

Claims

1. A method for tracking the blind spot of a non-motor vehicle lane when a vehicle turns right at an intersection, characterized in that: It is used to dynamically adjust the pan / tilt angle β of the blind spot camera installed on the right side of the vehicle when the vehicle turns right, and includes the following steps: S1: Get the vehicle's steering wheel angle θ in real time sw , and calculate the vehicle turning angle θ according to the steering wheel angle and the current vehicle body parameters; S2: Obtain the image of the right non-motorized vehicle lane through the blind spot camera installed on the vehicle body, and calculate the center coordinates of the blind spot position (C x , C y ) and express it as a parameter related to the vehicle turning angle; the process is as follows: S21: Establish a vehicle coordinate system with the position of the right side B-pillar of the vehicle as the origin, the vehicle forward direction as the Y axis, and the vehicle width direction as the X axis; S22: Identify a dangerous area at the intersection of a non-motor vehicle lane appearing in the image, define the area as a blind spot, and determine the boundary of the blind spot; S23: Define that the distance between the intersection of the far long side of the blind spot and the Y axis and the origin is A; the distance between the near short side and the corner of the Y axis and the origin is B; S24: Obtain the values ​​of A, B, and θ in real time, and calculate the center coordinates of the blind spot (C x , C y ): In the above formula, d represents the width of the non-motorized vehicle lane; S3: Based on the center coordinates of the blind area (C x , C y ), obtain the rotation relationship between the pan-tilt angle β of the blind spot camera and the vehicle angle θ; dynamically adjust the pan-tilt angle β of the blind spot camera so that the optical center direction of the blind spot camera coincides with the center coordinates of the blind spot.

2. The method for tracking the blind spot of a non-motor vehicle lane during a right turn at an intersection according to claim 1, characterized in that: The blind spot is defined as a rectangular area with a width of a non-motor vehicle and a length of 30m; the crosswalk at the blind spot intersection is the front boundary on the short side of the blind spot.

3. The method for tracking the blind spot of a non-motor vehicle lane during a right turn at an intersection according to claim 2, characterized in that: In step S1, the calculation formula of the vehicle turning angle θ is as follows: In the above formula, δ represents the transmission ratio of the vehicle; v represents the driving speed of the vehicle; and L represents the length of the vehicle body.

4. The method for tracking the blind spot of a non-motor vehicle lane during a right turn at an intersection according to claim 3, characterized in that: In step S3, the rotation relationship between the pan / tilt angle β and the vehicle angle θ is as follows: In the above formula, D represents the distance from the right rearview mirror of the vehicle to the B-pillar.

5. The method for tracking the blind spot of a non-motor vehicle lane during a right turn at an intersection according to claim 1, characterized in that: A steering wheel angle threshold θ0 is preset, and the real-time vehicle steering wheel angle θ sw After exceeding the safety zone (-θ0, θ0), the right-turn non-motor vehicle lane tracking function is triggered.

6. The method for tracking the blind spot of a non-motor vehicle lane during a right turn at an intersection according to claim 5, characterized in that: A delay time T0 is preset; after the right-turn non-motor vehicle lane tracking function of the vehicle is triggered, when the time for the vehicle steering wheel to return to the center reaches the preset delay time T0, the right-turn non-motor vehicle lane tracking function of the vehicle is turned off.

7. The method for tracking the blind spot of a non-motor vehicle lane during a right turn at an intersection according to claim 6, characterized in that: Obtain the vehicle's positioning and navigation information in real time, and then make the following decisions: (1) When the vehicle reaches the intersection and the vehicle steering wheel angle θ sw After exceeding the safety zone (-θ0, θ0), the right-turn non-motor vehicle lane tracking function is triggered; (2) After the vehicle leaves the intersection and the time it takes for the vehicle's steering wheel to return to the center position reaches a preset delay time T0, the right-turn non-motor vehicle lane tracking function of the vehicle is turned off.

8. The method for tracking the blind spot of a non-motor vehicle lane during a right turn at an intersection according to claim 1, characterized in that: The image data collected by the blind spot camera is displayed in real time inside the vehicle, the moving targets in the blind spot in the video image are identified, and a reminder is issued to the driver when there is an approaching moving target in the blind spot.

9. A blind spot tracking device for non-motor vehicle intersections, characterized in that: It includes: It includes a memory, a processor, and a computer program stored in the memory and running in the processor, characterized in that: when the processor executes the computer program, the video data collected by the blind spot camera and the vehicle turning angle θ are acquired in real time; then the tracking method for the blind spot of the non-motor vehicle lane during the right turn at the vehicle intersection as described in any one of claims 1 to 8 is used to dynamically adjust the pan / tilt turning angle β of the blind spot camera.

10. A vehicle right turn blind spot safety auxiliary driving system, characterized in that: It includes: A blind spot camera is installed on the right side of the vehicle to obtain an image of the right rear; the blind spot camera also includes a pan / tilt for adjusting its own framing direction; The blind spot tracking device for non-motor vehicle intersections as described in claim 9 is electrically connected to the control system of the vehicle and the blind spot camera; the blind spot tracking device for non-motor vehicle intersections is used to, after triggering the right-turn non-motor vehicle lane tracking function of the vehicle, adopt the tracking method for the blind spot of the non-motor vehicle lane during the right turn of the vehicle at the intersection as described in any one of claims 1-8 to achieve dynamic adjustment of the pan-tilt angle β of the blind spot camera, and display the image data collected by the blind spot camera in real time on the vehicle's on-board system.

Citation Information

Patent Citations

  • Camera calibration apparatus

    CN102194226A

  • Back sight image cognition based on-vehicle blind area early warning system and method

    CN102632839A

  • Method and device for calibrating a camera of a vehicle

    CN110176038A

  • KR20200102564A