Safe auxiliary driving device based on Beidou

By installing Beidou-based safety assisted driving devices on large mining trucks, using Beidou navigation, front-view module and radar module for lane line, vehicle and obstacle detection, combined with Bayesian network for early warning, the open-pit mines was solved The problem of low driving safety of large mining trucks has significantly improved driving safety.

CN118915112AInactive Publication Date: 2024-11-08NORTH REC (ANHUI) TECH CO LTD
View PDF 12 Cites 0 Cited by

Patent Information

Application Number
CN202411038869.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The driving safety of medium and large mining trucks in open-pit mines is low, especially in the case of unstable geology and insufficient night light, which poses a high risk.

Method used

The Beidou-based safety assisted driving device is adopted, which includes the Beidou navigation and positioning module, the front view module and the radar module. The lane line detection, vehicle detection and obstacle detection are carried out through the signal processing module, and early warning is carried out using the Bayesian network.

Benefits of technology

It improves the driving safety of medium and large mining trucks in the mine, ensures the safety of drivers and mine resources, and reduces the risk of collision through real-time monitoring and early warning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915112A_ABST
    Figure CN118915112A_ABST
Patent Text Reader

Abstract

The invention discloses a Beidou-based safe auxiliary driving device, and the device is characterized in that the device comprises a Beidou navigation positioning module which is used for monitoring the information of a vehicle; the foresight module is used for acquiring road information in front of the vehicle; the radar module is used for transmitting fan-shaped wave beams to the front of the vehicle and determining obstacle information according to echo signals; and the signal processing module is used for carrying out lane line detection, vehicle detection and obstacle detection according to the vehicle information, the road information and the obstacle information. The driving safety of large mining trucks in a mine field can be improved, and the safety of drivers and resources in the mine field is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of safe assisted driving, and in particular relates to a Beidou-based safe assisted driving device. Background Art

[0002] In the production process of open-pit mines, large mining trucks are usually used to undertake the transportation work of the mines. Large mining trucks bring higher efficiency and lower costs to mine production.

[0003] The roads in open-pit mines are geologically unstable due to factors such as mining and blasting, and road rolling occurs from time to time. In addition, the light in the mine is weak at night and the operation time is long. The safe driving of large mining trucks can only rely on the driver, but there are risks.

[0004] Therefore, how to improve the driving safety of large mining trucks in mines and ensure the safety of drivers and resources in mines is a technical problem to be solved by technical personnel in this field. Summary of the invention

[0005] The purpose of the invention is to solve the technical problem in the prior art that large mining trucks have low driving safety in open-pit mines.

[0006] In order to achieve the above technical objectives, the present invention provides a Beidou-based safety auxiliary driving device, which includes:

[0007] Beidou navigation and positioning module, used to monitor the vehicle's own information;

[0008] A front-view module is used to obtain road information in front of the vehicle;

[0009] The radar module is used to emit a fan-shaped beam in front of the vehicle and determine obstacle information based on the echo signal;

[0010] The signal processing module is used to perform lane detection, vehicle detection and obstacle detection based on the vehicle's own information, road information and obstacle information.

[0011] Furthermore, the Beidou navigation and positioning module includes an antenna submodule and a host submodule, the antenna submodule includes a Beidou antenna, a 4G main antenna and a 4G secondary antenna, and the host submodule includes a Beidou module, a CPU processor, an MCU circuit, a USB interface, a LAN interface, a CAN bus transceiver and a CAN interface.

[0012] Furthermore, the signal processing module performs lane line detection specifically including:

[0013] Acquire road image information through a camera;

[0014] Segmenting the road image information to obtain an initial lane line feature vector;

[0015] The lane line is determined after the initial lane line feature vector is processed to obtain the target lane line feature vector.

[0016] Furthermore, after acquiring the road image information, the method further includes performing noise reduction and contrast enhancement on the road image information and then converting the road image information from a pixel coordinate system to a parameter coordinate system.

[0017] Furthermore, the segmentation process of the road image information to obtain the initial lane line feature vector specifically includes detecting the parameters of the straight line in the parameter space of the segmented image through Hough transform, and then filtering and predicting the parameters of the straight line through a Kalman filter to extract the initial lane line feature vector.

[0018] Furthermore, the device also includes an early warning device, which is specifically used to:

[0019] Obtaining traffic information, the traffic information including vehicle speed, vehicle position, lane line, and preset vehicle distance;

[0020] Inputting the traffic information into a Bayesian network to obtain a prediction result;

[0021] An early warning is issued based on the prediction result.

[0022] Furthermore, the signal processing module performs vehicle detection, specifically including:

[0023] Grayscale the road information to obtain a grayscale image;

[0024] Extracting a binary image containing the shadow area at the bottom of the vehicle from the grayscale image by an image segmentation method;

[0025] Performing morphological filtering on the binary image to locate the vehicle area to be confirmed;

[0026] The outline of the vehicle area to be confirmed is extracted to confirm whether there is a vehicle.

[0027] Furthermore, the signal processing module is also used to determine the road width, specifically including:

[0028] Segmenting the road information into a road surface image and a non-road surface image;

[0029] Connecting edge pixels in the road surface image to form a road boundary;

[0030] Extracting vertical lines in the road boundary by Hough transformation, and taking the line with the smallest X value of the coordinate position among the vertical lines as the first boundary of the road width, and taking the line with the largest X value of the coordinate position among the vertical lines as the second boundary of the road width;

[0031] The difference between the coordinate X values ​​of the first boundary and the second boundary is taken as the road width.

[0032] The present invention provides a Beidou-based safety auxiliary driving device. Compared with the prior art, the device includes: a Beidou navigation and positioning module for monitoring vehicle information; a forward-looking module for obtaining road information in front of the vehicle; a radar module for emitting a fan-shaped beam in front of the vehicle and determining obstacle information according to the echo signal; and a signal processing module for performing lane line detection, vehicle detection, and obstacle detection according to the vehicle information, road information, and obstacle information. The device can improve the driving safety of large and medium-sized mining trucks in a mine and ensure the safety of drivers and resources in the mine. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 The figure is a schematic diagram of the structure of a Beidou-based safety auxiliary driving device provided in an embodiment of this specification;

[0035] Figure 2 The figure is a schematic diagram of a process of determining whether a vehicle exists in an embodiment of this specification;

[0036] Figure 3 The figure shows a schematic diagram of the structure of the Beidou navigation and positioning module in the embodiment of this specification. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0038] like Figure 1The structure diagram of the Beidou-based safety assisted driving device provided by the embodiment of this specification is shown. Although this specification provides the method operation steps or device structure shown in the following embodiments or drawings, more or fewer operation steps or module units can be included in the method or device based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure is applied in an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiment or drawings (for example, a parallel processor or multi-threaded processing environment, or even a distributed processing, server cluster implementation environment).

[0039] The structure of the Beidou-based safety auxiliary driving device provided in the present embodiment is as follows: Figure 1 As shown, the device comprises:

[0040] Beidou navigation and positioning module, used to monitor the vehicle's own information;

[0041] A front-view module is used to obtain road information in front of the vehicle;

[0042] The radar module is used to emit a fan-shaped beam in front of the vehicle and determine obstacle information based on the echo signal;

[0043] The signal processing module is used to perform lane detection, vehicle detection and obstacle detection based on the vehicle's own information, road information and obstacle information.

[0044] Specifically, the forward-looking system is developed based on a megapixel high-definition color camera and a high-performance SoC embedded platform. By rationally utilizing multi-core heterogeneous and accelerator resources, it meets the computing requirements of deep learning and realizes high-performance visual products based on deep learning. The product adopts a number of high-tech technologies such as image recognition, tracking, and dangerous behavior assessment to achieve a variety of applications based on lane line detection, vehicle detection, pedestrians and cyclists, etc., changing the traditional deficiency of relying mainly on visual judgment of the environment. The main process is as follows: Use image recognition technology through high-definition cameras to collect road-related information.

[0045] The radar uses an automotive anti-collision radar, which emits a fan-shaped beam straight ahead and processes the echo signal to report the relative distance, speed and angle between the obstacle in front and the radar. It is a core component of the collision warning system and safety assisted driving. Compared with traditional GNSS positioning, it can more reliably warn the surrounding environment.

[0046] The information processing module is used to perform lane line detection, vehicle detection and obstacle detection based on the vehicle's own information, road information and obstacle information. It can also process environmental information and vehicle information in real time, mainly including two parts: risk level assessment and optimal braking deceleration estimation. The risk assessment algorithm of the safety assisted driving system adopts a distance discrimination method, which mainly includes three distances, namely, the first part is the warning distance (the distance within the driver's reaction time); the second part is the braking distance (using the formula derived from Newton kinematics to characterize the system deceleration distance); the third part is the prefabricated safety distance (the safety distance reserved between the vehicle and the vehicle in front after braking, which can be looked up in the table through the vehicle's speed or relative speed). The optimal braking deceleration estimation of safety assisted driving takes into account the smoothness and comfort of braking, and the estimation formula is as follows:

[0047] A optim =V rel 2 / (D dis -D safe ) / 2*K a

[0048] In the above formula, K a is the deceleration gain, A optim is the optimal braking deceleration, V rel 2 is the relative vehicle speed, D dis is the preset distance, D safe The braking safety distance is calculated based on the real-time braking deceleration estimation, and median filtering and empirical coefficient control are performed to ensure the smoothness and monotonic increase of the braking deceleration during the braking assistance process.

[0049] In the embodiment of the present application, the Beidou navigation and positioning module includes an antenna submodule and a host submodule, the antenna submodule includes a Beidou antenna, a 4G main antenna and a 4G secondary antenna, and the host submodule includes a Beidou module, a CPU processor, an MCU circuit, a USB interface, a LAN interface, a CAN bus transceiver and a CAN interface. Figure 3 Shown is a schematic diagram of the structure of the Beidou navigation and positioning module.

[0050] The Beidou module is connected to the Beidou antenna and obtains enhanced data solution through the mobile Internet, achieving higher Beidou positioning accuracy compared to traditional methods; the CAN transceiver is connected to the vehicle through a dedicated CAN bus interface to read vehicle sensor data; the 4G module is connected to the 4G main and auxiliary antennas to achieve 4G network communication, and users can monitor the vehicle's position, speed and vehicle sensor parameters in real time through the 4G network. External interfaces include USB interface, LAN interface and CAN bus interface to achieve AUTOSAR network management and CAN-based UDS diagnosis.

[0051] In the embodiment of the present application, the signal processing module performs lane line detection specifically including:

[0052] Acquire road image information through a camera;

[0053] Segmenting the road image information to obtain an initial lane line feature vector;

[0054] The lane line is determined after the initial lane line feature vector is processed to obtain the target lane line feature vector.

[0055] In the embodiment of the present application, after acquiring the road image information, it also includes performing noise reduction and contrast enhancement on the road image information and then converting it from a pixel coordinate system to a parameter coordinate system.

[0056] In an embodiment of the present application, the road image information is segmented to obtain an initial lane line feature vector, specifically including detecting the parameters of a straight line in a parameter space in the segmented image through a Hough transform, and then filtering and predicting the parameters of the straight line through a Kalman filter to extract the initial lane line feature vector.

[0057] Specifically, the acquired image is preprocessed, including noise reduction, contrast enhancement and other operations, to improve the image quality. Then, the original image is transformed using the inverse perspective transform, and the pixel coordinate system is converted into a parameter coordinate system, which helps with subsequent straight line fitting and lane line detection. Next, the Hough transform is used to detect the straight line in the parameter space. Through the Hough transform, the parameters of all the straight lines in the image can be found, including their slopes and intercepts. Then, the Kalman filter is used to filter and predict these parameters to reduce the influence of noise and outliers. Finally, the lane line is extracted based on the filtered straight line parameters.

[0058] The above method has good stability and high accuracy in the process of lane line detection. The device then transmits the analyzed data to the vehicle-road cooperative system, and the vehicle-road cooperative system transmits the received data to the data processing unit and compares and analyzes the data set for vehicle collision warning, pedestrian collision warning, lane departure warning, vehicle distance keeping warning, emergency braking, speeding warning, speed limit / height limit prompt, and blind spot monitoring warning in the warning device. When the data exceeds the warning value, the device will issue a warning prompt on the sound and dashboard. When the data exceeds the alarm value, the device will issue a rapid and high-pitched sound alarm, and when the data is about to reach the critical value, emergency measures will be taken to ensure the driver's life safety.

[0059] Specifically, traffic information is obtained, the traffic information including vehicle speed, vehicle position, lane line, and preset vehicle distance; the traffic information is input into a Bayesian network to obtain a prediction result; and an early warning is issued based on the prediction result.

[0060] Bayesian network prediction includes the following steps:

[0061] 1. Define the loss function: The mean square error loss function is used to measure the difference between the predicted result and the actual result. According to the existing data set, it contains the input feature X and the corresponding target value y (the feature value X is the traffic road information such as vehicle speed, vehicle position, lane line and reasonable vehicle distance, and the target value is the set vehicle distance warning value. That is, after continuous training and learning through a large amount of sample data, the corresponding model obtained by regression modeling only needs to input the feature value and set a reasonable warning threshold in advance. The Bayesian network prediction will invert the error between the predicted value and the actual value according to the model. When the corresponding threshold is exceeded, the terminal will issue an alarm prompt.). For each sample point (x, y), the predicted value of the regression model is f(x), then the MSE (root mean square error) loss function can be defined as:

[0062] MSE=1 / N∑(f(x)-y)^2

[0063] Here, N is the number of samples in the dataset.

[0064] 2. Calculate the gradient: After defining the loss function, the gradient needs to be calculated to determine the direction and magnitude of the parameter update. In Bayesian networks, mathematical tools such as the chain rule can be used to calculate the gradient. The loss function is represented in a composite form, where the input feature is g(x), the corresponding target value is f(x), and the derivative of g(x) is g'(x). Then the derivative of f(g(x)) can be calculated by the following steps: first calculate the value of g(x), then take the derivative of g(x), and finally substitute g'(x) into the derivative of f(x).

[0065] 3. Update parameters: Based on the calculated gradient, use the gradient descent method to update the parameters of the model.

[0066] 4. Iterative optimization: Repeat steps 2 and 3 until the preset number of iterations is reached or the loss function reaches the preset threshold, that is, the calculated MSE root mean square error reaches the ideal accuracy requirement. During the iteration process, it is necessary to continuously evaluate the prediction results and adjust the parameters to obtain the optimal solution.

[0067] 5. Predict new data: Finally, use the optimized Bayesian network model to predict new data.

[0068] In the embodiment of the present application, the signal processing module performs vehicle detection, specifically including:

[0069] Grayscale the road information to obtain a grayscale image;

[0070] Extracting a binary image containing the shadow area at the bottom of the vehicle from the grayscale image by an image segmentation method;

[0071] Performing morphological filtering on the binary image to locate the vehicle area to be confirmed;

[0072] The outline of the vehicle area to be confirmed is extracted to confirm whether there is a vehicle.

[0073] Specifically, the weighted average method is used to grayscale the image collected by the camera to obtain a grayscale image; the grayscale image is processed by an image segmentation method based on the grayscale of the road surface, the shadow area at the bottom of the vehicle is extracted from the environmental background, and a binary image containing the shadow area at the bottom of the vehicle is obtained; the obtained binary image is subjected to morphological filtering operation to make the shadow area at the bottom of the vehicle present more obvious matrix-like features, and based on the shadow features at the bottom of the vehicle, a rectangular area filtering threshold and a rectangular aspect ratio filtering threshold are set to accurately locate the rectangular area of ​​the shadow at the bottom of the vehicle, and a rectangular width and height magnification coefficient of the shadow area is set to generate a vehicle ROI area, that is, the vehicle area to be confirmed; based on the symmetry features of the vehicle contour, the Canny operator is used to extract the contour of the vehicle ROI area, and the contour existence judgment and symmetry judgment methods are used to determine whether there is a vehicle in the vehicle ROI area.

[0074] Specifically, Figure 2 The figure shows a flow chart of detecting whether a vehicle exists. The video frame to be detected is determined through the video captured by the camera. Then step one: preprocessing, specifically graying and image segmentation of the video frame to be detected in sequence; step two: generating a vehicle ROI area, specifically performing image morphological filtering and vehicle ROI positioning on the segmented image in sequence; step three: vehicle existence judgment: edge detection and vehicle existence verification are performed on the vehicle ROI area; finally, the detection result is output.

[0075] In the embodiment of the present application, the signal processing module is also used to determine the road width, specifically including:

[0076] Segmenting the road information into a road surface image and a non-road surface image;

[0077] Connecting edge pixels in the road surface image to form a road boundary;

[0078] Extracting vertical lines in the road boundary by Hough transformation, and taking the line with the smallest X value of the coordinate position among the vertical lines as the first boundary of the road width, and taking the line with the largest X value of the coordinate position among the vertical lines as the second boundary of the road width;

[0079] The difference between the coordinate X values ​​of the first boundary and the second boundary is taken as the road width.

[0080] Specifically, a method based on color image segmentation is used. According to the different characteristics of the image in each area, the road information is segmented on the boundary or area to extract useful information. According to the difference between the red, green and blue components of the front road image and the roadside surrounding environment components on the image, the non-road image and the road image in the road image are divided.

[0081] Then, the edge pixels in the road image are determined, and then these pixels are connected together to form the required road boundary. The vertical straight lines in the edge detection are extracted using Hough transform. The straight line L1 with the smallest X value in the vertically detected straight lines is taken as the left boundary of the road width identification, and the straight line L2 with the largest X value is taken as the right boundary. Finally, the length information L of the road width is obtained through the X coordinate difference (X2-X1) between the left and right boundaries.

[0082] The embodiments of this specification are not limited to complying with industry communication standards, standard computer resource data update and data storage rules, or the situations described in one or more embodiments of this specification. Certain industry standards or slightly modified implementation plans based on the implementation described in the custom method or embodiment can also achieve the same, equivalent or similar, or predictable implementation effects after deformation of the above-mentioned embodiments. The embodiments obtained by using these modified or deformed data acquisition, storage, judgment, processing methods, etc. can still fall within the scope of the optional implementation plans of the embodiments of this specification.

[0083] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a computer-readable medium such as a microprocessor or processor and a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, ATMEL AT91SAM, MICROCHIP PIC18F26K20, and SILICONE LABS C8051F320. The memory controller can also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0084] The device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. There may be other divisions in actual implementation, such as multiple units or plug-ins may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, indirect coupling or communication connection of the device or unit, which may be electrical, mechanical or other forms.

[0085] These computer program instructions can also be loaded onto a computer or other programmable resource data updating device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0086] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0087] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A Beidou-based safety auxiliary driving device, characterized in that: The device comprises: Beidou navigation and positioning module, used to monitor the vehicle's own information; A front-view module is used to obtain road information in front of the vehicle; The radar module is used to emit a fan-shaped beam in front of the vehicle and determine obstacle information based on the echo signal; The signal processing module is used to perform lane detection, vehicle detection and obstacle detection based on the vehicle's own information, road information and obstacle information.

2. The Beidou-based safety assisted driving device according to claim 1, characterized in that: The Beidou navigation and positioning module includes an antenna submodule and a host submodule. The antenna submodule includes a Beidou antenna, a 4G main antenna and a 4G secondary antenna. The host submodule includes a Beidou module, a CPU processor, an MCU circuit, a USB interface, a LAN interface, a CAN bus transceiver and a CAN interface.

3. The Beidou-based safety assisted driving device according to claim 1, characterized in that: The signal processing module performs lane line detection specifically including: Acquire road image information through a camera; Segmenting the road image information to obtain an initial lane line feature vector; The lane line is determined after the initial lane line feature vector is processed to obtain the target lane line feature vector.

4. The Beidou-based safety assisted driving device as claimed in claim 3, characterized in that: After acquiring the road image information, the method further includes performing noise reduction and contrast enhancement on the road image information and converting the road image information from a pixel coordinate system to a parameter coordinate system.

5. The Beidou-based safety auxiliary driving device as claimed in claim 4, characterized in that: The segmentation process of the road image information to obtain the initial lane line feature vector specifically includes detecting the parameters of the straight line in the parameter space of the segmented image through Hough transform, and then filtering and predicting the parameters of the straight line through a Kalman filter to extract the initial lane line feature vector.

6. The Beidou-based safety auxiliary driving device according to claim 1, characterized in that: The device also includes an early warning device, which is specifically used for: Obtaining traffic information, the traffic information including vehicle speed, vehicle position, lane line, and preset vehicle distance; Inputting the traffic information into a Bayesian network to obtain a prediction result; An early warning is issued based on the prediction result.

7. The Beidou-based safety auxiliary driving device according to claim 1, characterized in that: The signal processing module performs vehicle detection, specifically including: Grayscale the road information to obtain a grayscale image; Extracting a binary image containing the shadow area at the bottom of the vehicle from the grayscale image by an image segmentation method; Performing morphological filtering on the binary image to locate the vehicle area to be confirmed; The outline of the vehicle area to be confirmed is extracted to confirm whether there is a vehicle.

8. The Beidou-based safety auxiliary driving device according to claim 1, characterized in that: The signal processing module is also used to determine the road width, specifically including: Segmenting the road information into a road surface image and a non-road surface image; Connecting edge pixels in the road surface image to form a road boundary; Extracting vertical lines in the road boundary by Hough transformation, and taking the line with the smallest X value of the coordinate position among the vertical lines as the first boundary of the road width, and taking the line with the largest X value of the coordinate position among the vertical lines as the second boundary of the road width; The difference between the coordinate X values ​​of the first boundary and the second boundary is taken as the road width.

Citation Information

Patent Citations

  • Auxiliary driving device based on image sensor and working method thereof

    CN101804813A

  • Video-based method for rapidly detecting transit vehicles

    CN101872546A

  • Vehicle line walking method and system based on machine vision

    CN103389733A

  • Lane departure warning system based on monocular vision

    CN108438004A

  • Lane line extraction and recognition method based on machine vision

    CN109993099A