A visual sensor-based collision avoidance warning method for the inner wheel difference area of ​​a semi-trailer tractor

Abstract

This invention relates to a collision avoidance warning method for the inner wheel difference area of ​​a semi-trailer tractor based on visual sensors. An infrared camera is installed on each of the left and right sides of the tractor's cab to acquire environmental information on the corresponding side during the tractor's turn. The controller calculates the angle β between the tractor and trailer during the turn through image processing. The minimum turning radius of the semi-trailer tractor during the turn can be calculated using a preset model, predicting and simulating the inner wheel difference area. This information, combined with visual information, is presented to the driver in real time on the central control screen. Deep learning algorithms are used to perform semantic recognition on the image information. When people, vehicles, or objects are detected within the inner wheel difference area, the vehicle's audio system issues a warning to the driver, thus achieving the purpose of collision avoidance warning for the inner wheel difference area during the semi-trailer tractor's turn.

Description

Technical Field

[0001] This invention relates to the field of active safety technology in the field of heavy-duty truck intelligent driving technology, specifically to a collision avoidance warning method for the inner wheel difference area of ​​a semi-trailer tractor based on a visual sensor. Background Technology

[0002] When large vehicles turn (especially right), the turning radius of the front wheels differs from that of the rear wheels, causing their trajectories to not overlap and creating a difference in trajectory—the inner wheel difference. This creates a significant blind spot. This inner wheel difference greatly increases the risk of lateral collisions during vehicle movement. The inner wheel difference area formed by the front and rear wheels of a large semi-trailer is several times larger than that of a small car, further increasing the safety hazard and the likelihood of serious lateral collisions. To effectively monitor the inner wheel difference area generated during large vehicle turns, it is necessary to analyze the numerical value of the inner wheel difference and combine it with sensor data to achieve the goal of safety monitoring and early warning of the inner wheel difference area during vehicle turns. Summary of the Invention

[0003] To address the problems existing in the background technology, this invention aims to provide a collision avoidance warning method for the inner wheel difference area of ​​a semi-trailer tractor based on a visual sensor. The method utilizes a visual sensor to calculate and analyze the inner wheel difference value formed when the tractor and trailer turn, and uses its visualization mapping of the real scene, combined with semantic recognition by deep learning algorithms, to monitor and warn of the inner wheel difference area, thereby realizing the safety monitoring function of the inner wheel difference area when the semi-trailer tractor turns.

[0004] Solution for solving the problem

[0005] A visual sensor-based anti-collision warning system for the inner wheel difference area of ​​a semi-trailer tractor, the system comprising: an image data acquisition module, a controller module, a central control display module, and a warning module;

[0006] The image data acquisition module is used to acquire environmental image data and send it to the controller module;

[0007] The controller module is used to acquire real-time vehicle speed, steering wheel angle, and turn signal switch data. When the real-time vehicle speed is less than a set threshold and the steering wheel angle is greater than a set threshold, or when the turn signal switch is detected to be on, it acquires environmental image data, trailer vehicle parameters, tow pin distance from trailer, and wheel spacing data sent by the image data acquisition module. It processes the environmental image data, trailer vehicle parameters, tow pin distance from trailer, and wheel spacing data to identify the main trailer angle β and calculate and simulate the inner wheel difference area. It maps the simulated trajectory onto the environmental image data and sends it to the central control display module. At the same time, it identifies and judges whether there are obstacles in the environmental image data after the simulated trajectory is mapped. If there are obstacles, it sends a warning message to the warning module.

[0008] The central control display module is used to display the environmental image data after trajectory mapping sent by the controller module. The warning module is used to provide voice warnings for the warning information sent by the controller module.

[0009] Furthermore, the image data acquisition module employs infrared cameras, which are respectively positioned on the left and right sides of the tractor cab.

[0010] Furthermore, the controller module is pre-embedded with a trained Hough Transform image recognition algorithm model and a YOLOv5 image recognition algorithm model.

[0011] Furthermore, the Hough Transform image recognition algorithm model is used to perform angle information conversion processing on the environmental image data to obtain the angle β between the tractor and the trailer.

[0012] Furthermore, by combining the vehicle parameters of the trailer, the distance between the towing pin and the trailer, and the wheel spacing on both sides of the trailer, the inner wheel difference area is calculated and processed to obtain the minimum turning radius R of the trailer's rear wheel during the turning process of the semi-trailer tractor. Its trajectory is I, and the area between I and the vehicle is the inner wheel difference area.

[0013] Furthermore, the inner wheel difference region calculation process specifically includes:

[0014] The angle between the centerline of the tractor and the centerline of the trailer is ∠θ = 180° - ∠β, the distance between the trailer's last wheelbase and the towing pin is L, and the rear wheelbase is K.

[0015] Analyze the force relationship between the tractor and trailer during turning, assuming a virtual steering shaft AA exists at the trailer's towing pin position. ’ Virtual steering axis AA ’ Parallel to the other axles of the trailer, and in the same direction as the force on the towing pin, the force on the towing pin can be approximated as being in the same direction as the axis of the tractor, then ∠θ=∠α;

[0016]

[0017] Furthermore, the YOLOv5 image recognition algorithm model in the controller module is used to identify and determine whether there are obstacles in the environmental image data after the simulated trajectory mapping. If obstacles are found, a warning message is sent to the early warning module.

[0018] Beneficial effects:

[0019] The beneficial effects of the above technical solution are as follows:

[0020] This invention provides a collision avoidance warning system for the inner wheel difference area of ​​a semi-trailer tractor. It uses visual information to accurately, efficiently, and in real-time monitor the inner wheel difference area of ​​the semi-trailer tractor during turning, which can effectively prevent major lateral collision accidents during turning, protect people's lives and ensure the safety of the driver.

[0021] This invention has the advantages of small size, all-weather operation, convenient installation, reliable performance, simple use, and user-friendly design. It can achieve functions such as data collection, simulation, and monitoring using only visual information, and provide real-time feedback on road safety risks to drivers. Attached Figure Description

[0022] Figure 1 This is a system block diagram of the present invention;

[0023] Figure 2 This is a schematic diagram of the system equipment installation on a semi-trailer tractor;

[0024] Figure 3 This is a schematic diagram of the system operation of the present invention;

[0025] Figure 4 This is a schematic diagram of the trajectory simulation principle of the present invention;

[0026] Figure 5 This is a system workflow diagram of the present invention. Detailed Implementation

[0027] The specific implementation of the present invention is described below with reference to embodiments:

[0028] It should be noted that the structures, proportions, sizes, etc. shown in this specification are only used to complement the content disclosed in the specification for those skilled in the art to understand and read, and are not intended to limit the conditions under which the present invention can be implemented. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0029] Furthermore, the terms such as "upper," "lower," "left," "right," "middle," and "one" used in this specification are merely for clarity of description and are not intended to limit the scope of the invention. Any changes or adjustments to their relative relationships, without substantially altering the technical content, should also be considered within the scope of the invention.

[0030] Example 1:

[0031] like Figure 1 As shown, the present invention provides a collision avoidance warning method for the inner wheel difference area of ​​a semi-trailer tractor based on a visual sensor, characterized by including an infrared camera, a central control display screen (display module), a vehicle audio system (warning module), and a control module.

[0032] like Figure 2 As shown, two infrared cameras are respectively positioned at appropriate locations on the left and right sides of the tractor cab. The central control display screen and controller are located inside the vehicle cab. The system draws power from the vehicle's ACC as its operating power source.

[0033] like Figure 3 As shown, angle β is the angle between the tractor and trailer, I is the tire trajectory on the steering side of the trailer's rear axle, and R is the minimum turning radius of the trailer's rear wheels. The controller receives the corresponding side image information captured by the camera and uses the Hough Transform method to detect lines in the image. Because the Hough Transform can retain the angle information of the detected lines, only the required angle information needs to be converted to obtain the angle β between the tractor and trailer. Combined with the trailer's vehicle parameters, the distance between the towing pin and the trailer, and the wheel spacing on both sides of the trailer, the angle β between the tractor and trailer is calculated. Figure 4 The calculation model shown can determine the minimum turning radius R of the trailer's rear wheel during the turning process of the semi-trailer tractor. Its trajectory is I. The area between I and the vehicle is the inner wheel difference area. When judging the inner wheel difference warning during the turning process, it is only necessary to determine whether there is an obstacle in this area. By using the YOLOv5-based human and object detection technology, the images of the inner wheel difference area and its boundary collected by the camera are identified. If there is an obstacle, a warning message is issued.

[0034] like Figure 4 As shown, the control module calculates and analyzes the inner wheel difference of the tractor using known data. The specific analysis process is as follows:

[0035] The angle between the centerline of the tractor and the centerline of the trailer is ∠θ = 180° - ∠β. The distance between the trailer's last wheelbase and the towing pin is L, and the rear wheelbase is K.

[0036] The trailer is articulated to the tractor unit via a towing pin. It has no power of its own and relies on the tractor unit for towing. Furthermore, the trailer lacks a steering axle at its front end, making it impossible to directly represent the positional relationship of the trailer's front edge. Based on the analysis of the force relationship between the tractor unit and the trailer during turning, we now assume a virtual steering axle AA exists at the location of the trailer's towing pin. ’ Virtual steering axis AA ’ Parallel to the other axles of the trailer, and with the direction of force on the towing pin in the same direction, the direction of force on the towing pin can be approximated as being in the same direction as the axis of the tractor, then ∠θ=∠α.

[0037]

[0038] In practice, the calculated minimum turning radius R of the rear wheels can be appropriately reduced, leaving a certain safe distance as the threshold value for the collision avoidance warning of this system.

[0039] like Figure 5 As shown, the working process of the semi-trailer inner wheel difference area collision avoidance warning system of the present invention is as follows:

[0040] When the vehicle is traveling in a straight line, the system is in sleep mode. It activates when the vehicle speed is less than the set speed and the steering wheel angle is greater than the set angle, or when the turn signal switch is detected to be on. The steering side infrared camera begins collecting environmental information and transmits it to the controller. The controller processes the image information, identifies the main trailer angle, and calculates and simulates the inner wheel difference area. The trajectory is mapped onto the environmental information and displayed on the central control screen. When the controller detects an obstacle within the risk area through the image information, it issues a pre-set warning to the driver via audio, thus achieving the purpose of collision avoidance warning for the inner wheel difference area during semi-trailer tractor-trailer turning.

[0041] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0042] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0043] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

Claims

1. A visual sensor-based anti-collision warning system for the inner wheel difference area of ​​a semi-trailer tractor, characterized in that, The system includes: an image data acquisition module, a controller module, a central control display module, and an early warning module; The image data acquisition module is used to acquire environmental image data and send it to the controller module; The controller module is used to acquire real-time vehicle speed, steering wheel angle, and turn signal switch data. When the real-time vehicle speed is less than a set threshold and the steering wheel angle is greater than a set threshold, or when the turn signal switch is detected to be on, it acquires environmental image data sent by the image data acquisition module, as well as the trailer's final wheelbase towing pin distance and rear axle wheelbase. It processes the environmental image data, trailer's final wheelbase towing pin distance, and rear axle wheelbase to identify the angle β between the tractor and trailer and calculates and simulates the inner wheel difference area. It maps the simulated trajectory onto the environmental image data and sends it to the central control display module. At the same time, it identifies and judges whether there are obstacles in the environmental image data after the simulated trajectory is mapped. If there are obstacles, it sends a warning message to the warning module. The central control display module is used to display the environmental image data after trajectory mapping sent by the controller module. The warning module is used to provide voice alerts for the warning information sent by the controller module; The image data acquisition module uses infrared cameras, which are respectively arranged on the left and right sides of the tractor cab; The Hough Transform image recognition algorithm model is used to perform angle information conversion processing on the environmental image data to obtain the angle β between the tractor and the trailer. By combining the angle β between the tractor and the trailer, the distance between the trailer's last wheelbase and the towing pin, and the rear wheelbase, the inner wheel difference region is calculated and processed to obtain the minimum turning radius R of the trailer's rear wheel during the semi-trailer tractor's turning process. Its trajectory is I, and the area between I and the vehicle is the inner wheel difference region. The calculation and processing of the inner wheel difference region specifically includes: Angle between the centerline of the tractor and the centerline of the trailer The distance between the last wheelbase and the towing pin of the trailer is L, and the wheelbase of the rear axle is K; Analyze the force relationship between the tractor and trailer during turning, assuming a virtual steering shaft exists at the trailer's towing pin position. Virtual steering shaft Parallel to the other axles of the trailer and in the same direction as the force on the drawbar, the force on the drawbar can be approximated as being in the same direction as the axle direction of the tractor. ; 。 2. The visual sensor-based anti-collision warning system for the inner wheel difference area of ​​a semi-trailer tractor as described in claim 1, characterized in that, The controller module is pre-embedded with pre-trained Hough Transform image recognition algorithm models and YOLOv5 image recognition algorithm models.

3. The visual sensor-based anti-collision warning system for the inner wheel difference area of ​​a semi-trailer tractor as described in claim 2, characterized in that, The controller module uses the YOLOv5 image recognition algorithm model to identify and determine whether there are obstacles in the environmental image data after the simulated trajectory mapping. If obstacles are found, an alert message is sent to the warning module.

Images