Automobile collision avoidance control method and device

Abstract

The application relates to an automobile anti-collision control method, which comprises the following steps: firstly controlling a camera module to acquire current image information, acquiring surrounding environment information through the current image information, and judging whether the surrounding environment information meets the operation condition of a laser radar; if the surrounding environment information meets the operation condition of the laser radar, the laser radar is preferentially used for anti-collision detection; if the surrounding environment information does not meet the operation condition of the laser radar, the camera module is used for anti-collision detection; meanwhile, the laser radar at a corresponding position can be accurately turned on or turned off through sensing the self movement of a vehicle, so that the camera module and the laser radar can be accurately and quickly used in cooperation.

Description

Technical Field

[0001] This application relates to the field of collision avoidance technology, and in particular to a method and device for automobile collision avoidance control. Background Technology

[0002] Crash buffer vehicles are primarily used in highway construction, tunnel construction, and road construction. They minimize the safety risks to construction vehicles, maintenance personnel, and traffic police handling accidents during urban road and highway maintenance. The crash buffer energy absorption module of the crash buffer vehicle mainly consists of an onboard crash buffer pad and a guide sign frame, acting as a buffer guardian behind construction vehicles. In the event of a rear-end collision, it can create a buffer zone between the offending vehicle and the construction work area ahead, absorbing the impact energy through structural deformation of the equipment, minimizing the probability of collision damage to personnel and equipment.

[0003] With the advancement of technology, most vehicles have incorporated automatic collision avoidance systems to enhance driving safety. The principle of active collision avoidance is to use high-tech methods such as onboard sensors, high-precision maps, and computer algorithms to enable the vehicle to perceive its environment, make judgments, and execute control functions, thereby achieving the goal of collision avoidance.

[0004] With the popularization of vehicle collision avoidance technology, lidar or camera systems used for vehicle collision avoidance are becoming more and more common. However, the use of lidar can damage the electronic components in the camera modules in the surrounding environment, causing the camera modules in the surrounding environment to malfunction. Summary of the Invention

[0005] Therefore, it is necessary to provide a vehicle collision avoidance control method to address the problem that the use of traditional LiDAR can damage the electronic components in the camera modules in the surrounding environment, causing the camera modules in the surrounding environment to malfunction.

[0006] This application provides a vehicle collision avoidance control method, including:

[0007] Control the camera module to acquire current image information;

[0008] Analyze the current image information to obtain the current surrounding environment information;

[0009] Determine whether the current surrounding environment information meets the conditions for lidar operation;

[0010] If the current surrounding environment information meets the conditions for lidar operation, then the lidar will be activated.

[0011] Analyze the lidar to obtain its data;

[0012] Based on the current vehicle operation data, determine whether the lidar data meets the braking conditions;

[0013] If the lidar data meets the braking conditions, then control the vehicle to brake;

[0014] If the current surrounding environment information does not meet the conditions for the operation of the lidar, the camera module will be activated;

[0015] Analyze the camera module to obtain its data;

[0016] Based on the current vehicle operation data, determine whether the camera module data meets the braking conditions;

[0017] If the data from the camera module meets the braking conditions, the vehicle will be controlled to brake.

[0018] Furthermore, the step of parsing the current image information to obtain the current surrounding environment information includes:

[0019] Preprocess the current image information to obtain the preprocessed current image information;

[0020] Feature extraction is performed on the preprocessed current image information to obtain multiple features;

[0021] Determine whether the obtained multiple features include a camera;

[0022] If the obtained multiple features include the camera, then the features containing the camera are extracted to obtain the extracted features.

[0023] By preprocessing the images contained in the current image information, and then extracting features from the preprocessed images, the success rate and accuracy of subsequent feature extraction can be increased.

[0024] Furthermore, if the obtained multiple features include a camera, then the features containing the camera are extracted to obtain the extracted features, and the process further includes:

[0025] Select one of the extracted features;

[0026] The extracted features are analyzed to obtain the camera's shooting range information from the extracted features;

[0027] Obtain the scanning range information of the lidar;

[0028] Determine if there is any overlap between the camera's shooting range information and the LiDAR's scanning range information;

[0029] If the camera's shooting range information and the lidar's scanning range information overlap, then the current surrounding environment information does not meet the conditions for lidar operation.

[0030] If the camera's shooting range information and the LiDAR's scanning range information do not overlap, then return to the step of selecting an extracted feature;

[0031] If the camera's shooting range information and the LiDAR's scanning range information in each extracted feature do not overlap, then the current surrounding environment information meets the conditions for LiDAR operation.

[0032] By comparing the shooting range information of multiple cameras in the acquired surrounding environment information with the scanning range information of the LiDAR one by one, if the shooting range information of multiple cameras intersects with the scanning range information of the LiDAR, the current surrounding environment information does not meet the conditions for LiDAR operation. Only when none of the shooting range information of multiple cameras intersects with the scanning range information of the LiDAR, the current surrounding environment information meets the conditions for LiDAR operation.

[0033] Furthermore, the step of parsing the extracted features to obtain the camera's shooting range information from the extracted features includes:

[0034] A three-dimensional coordinate system is established with the camera module as the origin;

[0035] The extracted features are analyzed to obtain the coordinate information of the camera in three-dimensional coordinates and the tilt angle of the camera.

[0036] The camera is analyzed to obtain its shooting range, which includes the horizontal shooting angle range and the vertical shooting angle range of the camera.

[0037] The horizontal and vertical shooting angle ranges of the camera are integrated into the three-dimensional coordinate system to obtain the first updated three-dimensional coordinate system.

[0038] By first establishing a three-dimensional coordinate system with the camera module as the origin, and then fusing the camera's shooting range from the extracted features into the three-dimensional coordinate system, we can obtain stereo data based on the camera's position and shooting range in the current state.

[0039] Furthermore, obtaining the scanning range information of the lidar includes:

[0040] The scanning range of the lidar is obtained, which includes the horizontal scanning angle range and the vertical scanning angle range of the lidar;

[0041] The horizontal and vertical scanning angle ranges of the lidar are incorporated into the three-dimensional coordinate system after the first update to obtain the three-dimensional coordinate system after the second update.

[0042] The installation locations of the LiDAR and the camera module on the vehicle are known. By fusing the scanning range of the LiDAR into a three-dimensional coordinate system, the scanning range of the LiDAR and the shooting range of the camera can be compared in the same dimension.

[0043] Furthermore, determining whether there is any overlap between the camera's shooting range information and the LiDAR's scanning range information includes:

[0044] The second updated 3D coordinate system is analyzed to obtain the coordinate information of the camera and its shooting range, as well as the coordinate information and scanning range of the LiDAR.

[0045] If the coordinates of the camera are within the scanning range of the LiDAR, and the coordinates of the LiDAR are within the shooting range of the camera, then the shooting range information of the camera and the scanning range information of the LiDAR overlap.

[0046] If the coordinates of the camera are within the scanning range of the LiDAR, but the coordinates of the LiDAR are not within the shooting range of the camera, then the shooting range information of the camera and the scanning range information of the LiDAR do not overlap.

[0047] If the camera's coordinates are not within the LiDAR's scanning range, but the LiDAR's coordinates are within the camera's field of view, then the camera's field of view information and the LiDAR's scanning range information do not overlap.

[0048] By comparing the coordinate information of the camera with that of the LiDAR, and the shooting range of the camera with the scanning range of the LiDAR, it is determined whether there is any overlap between the shooting range information of the camera and the scanning range information of the LiDAR.

[0049] Simultaneously, by acquiring specific coverage data from cameras and lidar, and by monitoring changes in that data, it is possible to control lidar in other locations to turn on or off in advance.

[0050] Furthermore, determining whether the lidar data meets the braking conditions based on the current vehicle operating data includes:

[0051] Obtain current vehicle operation data;

[0052] Analyze the current vehicle operation data to obtain the current vehicle speed, the minimum braking distance at the current vehicle speed, and the direction of travel;

[0053] Analyze the lidar data to obtain the distance to the nearest obstacle and the position and direction of the nearest obstacle relative to the current vehicle.

[0054] Determine whether the vehicle has reached the braking condition;

[0055] If the driving direction is the same as the position of the nearest obstacle relative to the current vehicle, and the distance of the nearest obstacle is close to the minimum braking distance of the current vehicle's driving speed, then the current vehicle has reached the braking condition.

[0056] By analyzing the real-time changes in current vehicle operating data, it is possible to determine whether the LiDAR data meets the current vehicle braking conditions. Furthermore, it is possible to predict the LiDAR data for the next moment based on the current vehicle operating data, and then analyze or control the LiDAR operation for the next moment.

[0057] Furthermore, determining whether the camera module data meets the braking conditions based on the current vehicle operating data includes:

[0058] Obtain current vehicle operation data;

[0059] Analyze the current vehicle operation data to obtain the current vehicle speed, the minimum braking distance at the current vehicle speed, and the direction of travel;

[0060] Analyze the data from the camera module to obtain the distance to the nearest obstacle and the position and direction of the nearest obstacle relative to the current vehicle.

[0061] Determine whether the vehicle has reached the braking condition;

[0062] If the driving direction is the same as the position of the nearest obstacle relative to the current vehicle, and the distance of the nearest obstacle is close to the minimum braking distance of the current vehicle's driving speed, then the current vehicle has reached the braking condition.

[0063] By analyzing the camera module data, the distance between the camera module and surrounding objects can be obtained. Based on the current vehicle operation data, it can be determined whether the distance between the camera module and surrounding objects meets the current vehicle braking conditions. At the same time, the vehicle's operating state in the next moment can be predicted based on the current vehicle operating state. This prediction can be assisted by acquiring steering wheel data, brake data, and throttle data. When the vehicle operating state in the next moment is obtained, the corresponding distance between the camera module and surrounding objects in the next moment can be obtained, which makes it easier to determine whether the braking conditions for the vehicle will be met in the future.

[0064] This application also provides a collision avoidance device, including:

[0065] Vehicle body;

[0066] Multiple detection devices are provided, each of which is fixedly connected to the vehicle body and arranged around the vehicle body. The detection devices are used to detect surrounding environmental information and also to detect obstacle information.

[0067] A processing device is fixedly connected to the vehicle body, and multiple detection devices are communicatively connected to the processing device. The processing device is used to execute the vehicle collision avoidance control method as described above.

[0068] Multiple detection devices acquire real-time information about the surrounding environment and obstacles around the vehicle. The acquired information is then analyzed and processed by a processing device to determine the specific control method for the detection devices and the determination of whether the vehicle should brake.

[0069] Furthermore, the detection device includes:

[0070] A camera module is fixedly connected to the vehicle body, and the camera module is used to acquire image information;

[0071] A lidar is positioned close to the camera module and is fixedly connected to the camera module. The lidar is used to acquire obstacle information.

[0072] The image information acquired by the camera module is used not only to determine the vehicle braking conditions, but also to determine the conditions for activating the lidar, while the obstacle information acquired by the lidar is only used to determine the vehicle braking conditions.

[0073] This application relates to a vehicle collision avoidance control method. It first controls a camera module to acquire current image information, then uses this image information to acquire surrounding environmental information, and determines whether the surrounding environmental information meets the conditions for lidar operation. If the surrounding environmental information meets the lidar operation conditions, the lidar is used preferentially for collision avoidance detection. If the surrounding environmental information does not meet the lidar operation conditions, the camera module is used for collision avoidance detection. Simultaneously, the method can also sense the vehicle's own movement to precisely activate or deactivate lidar at corresponding locations, achieving precise and rapid coordination between the camera module and the lidar. Attached Figure Description

[0074] Figure 1 This is a schematic flowchart of an embodiment of the vehicle collision avoidance control method provided in this application.

[0075] Figure 2 This is a schematic diagram of the anti-collision device provided in one embodiment of this application.

[0076] Figure 3This is a schematic diagram showing the positional relationship between the camera module and the lidar in an anti-collision device provided in an embodiment of this application.

[0077] Figure label:

[0078] 11. Vehicle body; 12. Detection device; 121. Camera module; 122. LiDAR; 13. Processing device. Detailed Implementation

[0079] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0080] like Figure 1 As shown, in one embodiment of this application, the vehicle collision avoidance control method includes the following steps S001 to S011:

[0081] S001, control the camera module to acquire current image information.

[0082] Specifically, controlling the camera module to acquire current image information means taking an image from the current installation angle of the camera module. The camera module in this step can also capture real-time video, and further obtain current image information by performing image analysis on the obtained real-time video.

[0083] S002, parse the current image information to obtain the current surrounding environment information.

[0084] Specifically, the current surrounding environment information refers to the information in the image acquired by the camera module, such as pedestrians, guardrails, trees, walls, crash barriers, buses, transport vehicles, and cameras.

[0085] S003, determine whether the current surrounding environment information meets the conditions for lidar operation.

[0086] Specifically, the conditions for the operation of lidar are established based on the premise of not damaging the cameras within the lidar's working range.

[0087] S004. If the current surrounding environment information meets the conditions for the operation of the lidar, then the lidar is activated.

[0088] S005, analyze the lidar and obtain the lidar data.

[0089] Specifically, this lidar data is the real-time data obtained by the lidar at the current moment for detecting surrounding obstacles.

[0090] S006, Based on the current vehicle operation data, determine whether the lidar data meets the braking conditions.

[0091] Specifically, the current vehicle operation data refers to the vehicle's driving data, which can be obtained through the vehicle's own sensors.

[0092] S007, if the lidar data meets the braking conditions, then control the vehicle to brake.

[0093] Specifically, the braking conditions are set based on the current vehicle operating data and with the aim of preventing a collision.

[0094] S008, if the current surrounding environment information does not meet the conditions for the operation of the lidar, then the camera module is activated.

[0095] S009, parse the camera module to obtain the camera module data.

[0096] S010, Based on the current vehicle operation data, determine whether the camera module data meets the braking conditions.

[0097] S011, if the data from the camera module meets the braking conditions, then control the vehicle to brake.

[0098] In this embodiment, the camera module is first controlled to acquire current image information, and then the surrounding environment information is acquired through the current image information. It is then determined whether the surrounding environment information meets the conditions for the operation of the lidar. If the surrounding environment information meets the conditions for the operation of the lidar, the lidar is used first for collision avoidance detection. If the surrounding environment information does not meet the conditions for the operation of the lidar, the camera module is used for collision avoidance detection. At the same time, the lidar at the corresponding position can be precisely turned on or off by sensing the movement of the vehicle itself, so as to achieve precise and rapid cooperation between the camera module and the lidar.

[0099] In one embodiment of this application, the step of parsing the current image information to obtain the current surrounding environment information includes the following steps S002a to S002d:

[0100] S002a, preprocess the current image information to obtain the preprocessed current image information;

[0101] Specifically, the current image information includes the current image. Preprocessing the current image information includes denoising the current image to obtain the denoised current image. Then, feature enhancement processing is performed on the denoised current image to obtain the preprocessed current image.

[0102] S002b, Perform feature extraction on the preprocessed current image information to obtain multiple features;

[0103] S002c, determine whether the obtained multiple features include a camera;

[0104] S002d, if the obtained multiple features include the camera, then the features containing the camera are extracted to obtain the extracted features.

[0105] In this embodiment, the image contained in the current image information is preprocessed, and then features are extracted from the preprocessed image. Preprocessing the image can increase the success rate and accuracy of subsequent feature extraction.

[0106] In one embodiment of this application, if the obtained multiple features include a camera, the features containing the camera are extracted to obtain the extracted features, and then the following steps are further included: S002e to S002k:

[0107] S002e, select one of the extracted features.

[0108] S002f, parse the extracted features to obtain the camera's shooting range information from the extracted features.

[0109] Specifically, the camera's shooting range information in the extracted features can be obtained by first obtaining the camera's brand information from the extracted features, and then retrieving the corresponding shooting range information; if the camera's brand information cannot be obtained, the application scenario of the camera is analyzed, and the conventional usage specifications of that scenario are used as the camera's shooting range information.

[0110] S002g, obtain the scanning range information of the LiDAR.

[0111] S002h determines whether there is any overlap between the camera's shooting range information and the LiDAR's scanning range information.

[0112] S002i, if the camera's shooting range information and the lidar's scanning range information overlap, then the current surrounding environment information does not meet the conditions for lidar operation.

[0113] S002j, if the camera's shooting range information and the lidar's scanning range information do not overlap, then return to the step of selecting an extracted feature.

[0114] S002k, if the camera's shooting range information and the LiDAR's scanning range information in each extracted feature do not overlap, then the current surrounding environment information meets the conditions for LiDAR operation.

[0115] In this embodiment, the shooting range information of multiple cameras in the acquired surrounding environment information is compared one by one with the scanning range information of the LiDAR. When one of the shooting range information of multiple cameras intersects with the scanning range information of the LiDAR, the current surrounding environment information does not meet the conditions for LiDAR operation. Only when none of the shooting range information of multiple cameras intersects with the scanning range information of the LiDAR, the current surrounding environment information meets the conditions for LiDAR operation.

[0116] In one embodiment of this application, the step of parsing the extracted features to obtain the camera's shooting range information from the extracted features includes the following steps S003f to S006f:

[0117] S003f establishes a three-dimensional coordinate system with the camera module as the origin.

[0118] S004f, analyze the extracted features to obtain the coordinate information of the camera in three-dimensional coordinates and the tilt angle of the camera in the extracted features.

[0119] S005f, Analyze the camera to obtain the camera's shooting range, which includes the camera's horizontal shooting angle range and vertical shooting angle range.

[0120] S006f integrates the horizontal and vertical shooting angle ranges of the camera into the three-dimensional coordinate system to obtain the first updated three-dimensional coordinate system.

[0121] Specifically, the extracted features are compared with the preprocessed image, and the camera's coordinates in three-dimensional coordinates and the camera's tilt angle can be obtained through two-dimensional to three-dimensional transformation.

[0122] In this embodiment, a three-dimensional coordinate system is first established with the camera module as the origin, and then the shooting range of the camera in the extracted features is fused into the three-dimensional coordinate system, thereby obtaining stereo data based on the camera position and shooting range in the current state.

[0123] In one embodiment of this application, obtaining the scanning range information of the lidar includes the following steps S003g to S004g:

[0124] S003g, obtain the scanning range of the lidar, wherein the scanning range of the lidar includes the horizontal scanning angle range and the vertical scanning angle range of the lidar.

[0125] S004g integrates the horizontal and vertical scanning angle ranges of the lidar into the three-dimensional coordinate system after the first update, resulting in the three-dimensional coordinate system after the second update.

[0126] Specifically, the scanning range of a lidar can be obtained by analyzing the lidar's configuration parameters.

[0127] In this embodiment, the installation positions of the LiDAR and the camera module on the vehicle are known. By fusing the scanning range of the LiDAR into the three-dimensional coordinate system again, the scanning range of the LiDAR and the shooting range of the camera can be compared in the same dimension.

[0128] In one embodiment of this application, determining whether there is an overlap between the camera's shooting range information and the lidar's scanning range information includes the following steps S003h to S006h:

[0129] S003h, analyze the updated 3D coordinate system to obtain the camera's coordinate information and shooting range in the updated 3D coordinate system; the lidar's coordinate information and scanning range.

[0130] S004h, if the coordinate information of the camera is within the scanning range of the LiDAR, and the coordinate information of the LiDAR is within the shooting range of the camera, then the shooting range information of the camera and the scanning range information of the LiDAR have an overlap.

[0131] S005h, if the coordinate information of the camera is within the scanning range of the LiDAR, but the coordinate information of the LiDAR is not within the shooting range of the camera, then the shooting range information of the camera and the scanning range information of the LiDAR do not overlap.

[0132] S006h, if the coordinate information of the camera is not within the scanning range of the LiDAR, but the coordinate information of the LiDAR is within the shooting range of the camera, then the shooting range information of the camera and the scanning range information of the LiDAR do not overlap.

[0133] Specifically, the scanning range of a LiDAR includes the coordinate information of the LiDAR, the scanning range information of the LiDAR, and the scanning distance information of the LiDAR. The scanning distance information of the LiDAR is the distance beyond which the LiDAR will no longer cause damage to the camera.

[0134] In this embodiment, the camera's shooting range information and the LiDAR's scanning range information are compared to determine whether there is any overlap between them.

[0135] Simultaneously, by acquiring specific coverage data from cameras and lidar, and by monitoring changes in that data, it is possible to control lidar in other locations to turn on or off in advance.

[0136] In one embodiment of this application, determining whether the lidar data meets the braking conditions based on the current vehicle operating data includes the following steps S006a to S006e:

[0137] S006a, Obtain current vehicle operation data.

[0138] S006b, parse the current vehicle operation data to obtain the current vehicle speed, the minimum braking distance at the current vehicle speed, and the driving direction.

[0139] S006c, parse the lidar data to obtain the distance to the nearest obstacle and the position and direction of the nearest obstacle relative to the current vehicle.

[0140] S006d, determine whether the current vehicle has reached the braking condition.

[0141] S006e, if the driving direction is consistent with the position direction of the nearest obstacle relative to the current vehicle, and the distance of the nearest obstacle is close to the minimum braking distance of the current vehicle's driving speed, then the vehicle in front has reached the braking condition.

[0142] Specifically, the vehicle's operating data changes in real time, which in turn causes the lidar data to change in real time as well.

[0143] In this embodiment, by analyzing the real-time changes in the current vehicle operation data, it is possible to determine whether the LiDAR data meets the current vehicle braking conditions. At the same time, it is also possible to predict the LiDAR data at the next moment based on the current vehicle operation data, such as the predicted range that the LiDAR will scan at the next moment. This allows for the analysis of the LiDAR data at the next moment or the control of the LiDAR operation at the next moment, thereby achieving advance control of the LiDAR.

[0144] In one embodiment of this application, determining whether the camera module data meets the braking conditions based on the current vehicle operating data includes the following steps S010a to S010e:

[0145] S010a, Obtain current vehicle operation data.

[0146] S010b, parse the current vehicle operation data to obtain the current vehicle speed, the minimum braking distance at the current vehicle speed, and the driving direction.

[0147] S010c, parse the camera module data to obtain the distance to the nearest obstacle and the position and direction of the nearest obstacle relative to the current vehicle in the camera module data.

[0148] S010d determines whether the current vehicle has reached the braking condition.

[0149] S010e, if the driving direction is consistent with the position direction of the nearest obstacle relative to the current vehicle, and the distance of the nearest obstacle is close to the minimum braking distance of the current vehicle's driving speed, then the current vehicle meets the braking conditions.

[0150] Specifically, the type of obstacle in the camera module data can be identified by feature extraction. When the obstacle is a stationary object such as a wall, crash barrier, or tree, the minimum braking distance of the current vehicle is compared with the distance between the vehicle and the nearest obstacle in real time. An alarm is issued when the distance between the vehicle and the nearest obstacle is close to the minimum braking distance of the current vehicle.

[0151] When a vehicle loses control for unknown reasons and its speed cannot be reduced or controlled by human intervention, feasible safety impact plans can be obtained by acquiring real-time camera module data. For example, if a vehicle loses control, feature analysis of the camera module data can be performed to identify features in the vehicle's direction of travel, such as crash barriers, trees, and walls. By analyzing the energy absorption capacity of each feature, these features can be ranked, and the crash barrier with the highest energy absorption capacity can be used as the highest-level target for collision deceleration of the out-of-control vehicle.

[0152] In this embodiment, by parsing the camera module data, the distance between the camera module and surrounding objects is obtained. Based on the current vehicle operation data, it is determined whether the distance between the camera module and surrounding objects meets the current vehicle braking conditions. At the same time, the vehicle operation state at the next moment can be predicted based on the current vehicle operation state. This prediction can be assisted by acquiring steering wheel data, brake data, and throttle data. When the vehicle operation state at the next moment is obtained, the corresponding distance between the camera module and surrounding objects at the next moment can be obtained, which facilitates the determination of whether the braking conditions for the vehicle will be met in the future.

[0153] like Figure 2 As shown, in one embodiment of this application, a collision avoidance device is provided, including a vehicle body 11, a plurality of detection devices 12 and a processing device 13.

[0154] Multiple detection devices 12 are configured. Each detection device 12 is fixedly connected to the vehicle body 11. The multiple detection devices 12 are arranged around the vehicle body 11. The detection devices 12 are used to detect surrounding environmental information. The detection devices 12 are also used to detect obstacle information.

[0155] The processing device 13 is fixedly connected to the vehicle body 11. Multiple detection devices 12 are communicatively connected to the processing device 13. The processing device 13 is used to execute the vehicle collision avoidance control method as described above.

[0156] Specifically, the processing device 13 is used to process the surrounding environment information and obstacle information obtained from the detection device 12, and through analysis and judgment of the surrounding environment information and obstacle information, it issues control commands to the detection device 12.

[0157] In this embodiment, multiple detection devices 12 acquire real-time information about the surrounding environment and obstacles around the vehicle body 11, and the processing device 13 analyzes and processes the acquired information about the surrounding environment and obstacles to obtain a method for specifically controlling the detection devices 12 and a judgment result on whether the vehicle should brake.

[0158] like Figure 3 As shown, in one embodiment of this application, the detection device 12 includes a camera module 121 and a lidar 122.

[0159] The camera module 121 is fixedly connected to the vehicle body 11. The camera module 121 is used to acquire image information.

[0160] The lidar 122 is positioned close to the camera module 121. The lidar 122 is fixedly connected to the camera module 121. The lidar 122 is used to acquire obstacle information.

[0161] Specifically, the position of the camera module 121 in the same detection device 12 can be approximately the same as the position of the lidar 122, so as to reduce the data calculation and improve the data processing time and processing speed.

[0162] In this embodiment, the image information acquired by the camera module 121 is used not only to determine the vehicle braking conditions, but also to determine the conditions for the LiDAR 122 to be activated, while the obstacle information acquired by the LiDAR 122 is used to determine the vehicle braking conditions.

[0163] The technical features of the above embodiments can be combined arbitrarily, and the execution order of the method steps is not restricted. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0164] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An automobile collision avoidance control method characterized by comprising: The automobile anti-collision control method comprises the following steps: controlling a camera module to obtain current image information; analyzing the current image information to obtain current surrounding environment information; determining whether the current surrounding environment information meets the condition for laser radar operation; if the current surrounding environment information meets the condition for laser radar operation, the laser radar is enabled; analyzing the laser radar to obtain laser radar data; based on current vehicle operation data, it is determined whether the laser radar data meets a braking condition; if the laser radar data meets the braking condition, the vehicle is controlled to brake; if the current surrounding environment information does not meet the condition for laser radar operation, the camera module is analyzed to obtain camera module data; based on current vehicle operation data, it is determined whether the camera module data meets the braking condition; if the camera module data meets the braking condition, the vehicle is controlled to brake. The step of analyzing the current image information to obtain current surrounding environment information comprises the following steps: pre-processing the current image information to obtain pre-processed current image information; performing feature extraction on the pre-processed current image information to obtain a plurality of features; determining whether the obtained plurality of features contain a camera; if the obtained plurality of features contain a camera, the feature containing the camera is extracted to obtain an extracted feature. If the obtained plurality of features contain a camera, the feature containing the camera is extracted to obtain an extracted feature, and then the following steps are further included: selecting an extracted feature; analyzing the extracted feature to obtain shooting range information of the camera in the extracted feature; obtaining scanning range information of the laser radar; determining whether the shooting range information of the camera and the scanning range information of the laser radar have an intersection; if the shooting range information of the camera and the scanning range information of the laser radar have an intersection, the current surrounding environment information does not meet the condition for laser radar operation; if the shooting range information of the camera and the scanning range information of the laser radar do not have an intersection, the step of selecting an extracted feature is returned; if the shooting range information of the camera and the scanning range information of the laser radar in each extracted feature do not have an intersection, the current surrounding environment information meets the condition for laser radar operation.

2. The automobile collision avoidance control method according to claim 1, characterized by, The step of analyzing the extracted feature to obtain shooting range information of the camera in the extracted feature comprises the following steps: establishing a three-dimensional coordinate system with the camera module as the origin; analyzing the extracted feature to obtain coordinate information of the camera in the three-dimensional coordinate and an inclination angle of the camera; analyzing the camera to obtain a shooting range of the camera, wherein the shooting range of the camera comprises a horizontal shooting angle range and a vertical shooting angle range of the camera; and integrating the horizontal shooting angle range and the vertical shooting angle range of the camera into the three-dimensional coordinate system to obtain a first updated three-dimensional coordinate system.

3. The automobile collision avoidance control method according to claim 2, characterized by, The acquisition of the scanning range information of the laser radar comprises: acquiring the scanning range of the laser radar, the scanning range of the laser radar comprising a horizontal scanning angle range and a vertical scanning angle range of the laser radar; and integrating the horizontal scanning angle range and the vertical scanning angle range of the laser radar into the first updated three-dimensional coordinate system to obtain the second updated three-dimensional coordinate system.

4. The automobile collision avoidance control method according to claim 3, characterized by, The judgment of whether the shooting range information of the camera and the scanning range information of the laser radar have an intersection comprises: analyzing the second updated three-dimensional coordinate system to obtain the coordinate information of the camera in the second updated three-dimensional coordinate system and the shooting range of the camera, the coordinate information of the laser radar and the scanning range of the laser radar; if the coordinate information of the camera is located within the scanning range of the laser radar and the coordinate information of the laser radar is located within the shooting range of the camera, the shooting range information of the camera and the scanning range information of the laser radar have an intersection; if the coordinate information of the camera is located within the scanning range of the laser radar but the coordinate information of the laser radar is not located within the shooting range of the camera, the shooting range information of the camera and the scanning range information of the laser radar have no intersection; and if the coordinate information of the camera is not located within the scanning range of the laser radar but the coordinate information of the laser radar is located within the shooting range of the camera, the shooting range information of the camera and the scanning range information of the laser radar have no intersection.

5. The automobile collision avoidance control method according to claim 4, characterized by, The judgment of whether the camera module data reaches the braking condition based on the current vehicle operation data comprises: acquiring the current vehicle operation data; analyzing the current vehicle operation data to obtain the driving speed of the current vehicle, the minimum braking distance of the driving speed of the current vehicle and the driving direction; analyzing the camera module data to obtain the distance of the nearest obstacle in the camera module data and the position direction of the nearest obstacle relative to the current vehicle; and judging whether the current vehicle reaches the braking condition; if the driving direction is consistent with the position direction of the nearest obstacle relative to the current vehicle and the distance of the nearest obstacle is close to the minimum braking distance of the driving speed of the current vehicle, the current vehicle reaches the braking condition.

6. The automobile collision avoidance control method according to claim 5, characterized by, The judgment of whether the camera module data reaches the braking condition based on the current vehicle operation data comprises: acquiring the current vehicle operation data; analyzing the current vehicle operation data to obtain the driving speed of the current vehicle, the minimum braking distance of the driving speed of the current vehicle and the driving direction; analyzing the camera module data to obtain the distance of the nearest obstacle in the camera module data and the position direction of the nearest obstacle relative to the current vehicle; and judging whether the current vehicle reaches the braking condition; if the driving direction is consistent with the position direction of the nearest obstacle relative to the current vehicle and the distance of the nearest obstacle is close to the minimum braking distance of the driving speed of the current vehicle, the current vehicle reaches the braking condition.

7. A crash avoidance device characterized by It comprises: a vehicle body; The detection device is arranged in multiple, each of which is fixedly connected with the vehicle body, and is arranged around the vehicle body. The detection device is used for detecting surrounding environment information and obstacle information. The processing device is fixedly connected with the vehicle body, and each of the detection devices is in communication connection with the processing device. The processing device is used for executing the automobile anti-collision control method according to any one of claims 1 to 6.

8. A crash avoidance device according to claim 7, characterised in that The detection device comprises a camera module fixedly connected with the vehicle body, which is used for acquiring image information; and a laser radar arranged close to the camera module, which is fixedly connected with the camera module and used for acquiring obstacle information.

Images