Search

CN-117400860-B - CMS-based vehicle turning blind area compensation method and device and vehicle

CN117400860BCN 117400860 BCN117400860 BCN 117400860BCN-117400860-B

Abstract

The application provides a vehicle turning blind area compensation method based on CMS. The vehicle is subjected to blind supplement through a first camera and a left second camera which are symmetrically arranged on the right side of the vehicle head, and a third camera and a fourth camera which are respectively and symmetrically arranged on the left side and the right side of the hanging box. The method comprises the steps of enabling an image shot by a third camera to be used for blind compensation of a first camera when a vehicle turns right, enabling an image shot by a fourth camera to be used for blind compensation of a second camera when the vehicle turns left, and enabling the blind compensation process to involve technologies such as an edge detection algorithm, image processing, image stitching and image fusion. In addition, the application also provides a vehicle turning compensation device and a vehicle. The technical scheme of the application effectively solves the problem of blind areas caused by the fact that the vehicle body shields the view of the camera in the turning process of the large-sized vehicle.

Inventors

  • CHEN YIJUN
  • CHEN ANJUN

Assignees

  • 北京瞰瞰智能科技有限公司

Dates

Publication Date
20260512
Application Date
20230928

Claims (9)

  1. 1. The vehicle turning blind area compensation method based on the CMS is characterized by comprising a vehicle head, a hanging box connected to the vehicle head in a hanging mode, a first camera and a second camera which are symmetrically arranged on the right side and the left side of the vehicle head respectively, and a third camera and a fourth camera which are symmetrically arranged on the left side and the right side of the hanging box respectively, wherein the vehicle turning blind area compensation method based on the CMS comprises the following steps: When the vehicle turns right, acquiring a first image shot by the first camera and a third image shot by the third camera; When the vehicle turns left, acquiring a second image shot by the second camera and a fourth image shot by the fourth camera; performing blind area detection on the first image or the second image to obtain a first blind area or a second blind area; Determining a first region of interest in the region of the third image according to the first blind area, or determining a second region of interest in the region of the fourth image according to the second blind area, wherein the three-dimensional space conversion is carried out on the first blind area or the second blind area to obtain a 3D image of the first blind area or a 3D image of the second blind area; the method comprises the steps of splicing a first image with a first region of interest to obtain a first display picture or splicing a third image with a second region of interest to obtain a second display picture, wherein the first region of interest and the edge of a vehicle body in the first image are subjected to edge detection to obtain a first type splicing point, the second region of interest and the edge of the vehicle body in the second image are subjected to edge detection to obtain a second type splicing point, the first region of interest and the first image are spliced to obtain a first splicing picture or the second region of interest and the second image are spliced to obtain a second splicing picture according to the first type splicing point or the second type splicing point, and the first splicing picture is subjected to image fusion to obtain a first display picture or the second splicing picture is subjected to image fusion to obtain a second display picture.
  2. 2. The CMS-based vehicle turning blind area compensation method of claim 1, wherein the vehicle further comprises a display screen provided at a center console for a driver to view, and the vehicle turning blind area compensation method further comprises displaying the first display screen or the second display screen on the display screen.
  3. 3. The CMS-based vehicle turning blind zone compensation method of claim 1, wherein the blind zone detection of the first image or the third image to obtain the first blind zone or the second blind zone comprises: Performing marginalization processing on the first image or the second image to obtain the edge of the vehicle body of the vehicle; Identifying and marking a body edge of the vehicle in the first image or the second image; And obtaining a first blind area or a second blind area of the first image or the second image according to the edge of the vehicle body of the vehicle.
  4. 4. The CMS-based vehicle turning blind zone compensation method of claim 3, wherein the marginalizing the first image or the second image to obtain the vehicle body edge of the vehicle comprises: and carrying out edge processing on the first image or the second image to obtain the edge of the vehicle body of the vehicle by adopting an edge algorithm.
  5. 5. The CMS-based vehicle turn blind zone compensation method of claim 1, wherein the first image, the second image, the third image, and the fourth image are 2D images.
  6. 6. The CMS-based vehicle turning blind zone compensation method of claim 5, wherein the performing three-dimensional spatial conversion on the first blind zone or the second blind zone to obtain a 3D image of the first blind zone or the second blind zone 3D image comprises: establishing a mapping relation from a 2D image to a 3D image according to the internal parameters and the external parameters of the first camera; According to the mapping relation, performing three-dimensional space conversion on the first blind area to obtain a 3D image of the first blind area; Establishing a mapping relation from the 2D image to the 3D image according to the internal parameters and the external parameters of the second camera; and carrying out three-dimensional space conversion on the second blind area according to the mapping relation to obtain a 3D image of the second blind area.
  7. 7. The CMS-based vehicle turning blind zone compensation method of claim 1, wherein the image fusing the first stitched picture to obtain a first display picture or the image fusing the second stitched picture to obtain a second display picture comprises: And carrying out semitransparent treatment on the vehicle body area in the first spliced picture to obtain a first display picture or carrying out semitransparent treatment on the vehicle body area in the second spliced picture to obtain a second display picture.
  8. 8. The utility model provides a vehicle turn blind area compensation arrangement, the vehicle include the locomotive, articulate in the string case of locomotive, symmetry respectively set up first camera on locomotive right side and left second camera, and symmetry respectively set up the third camera and string case fourth camera of string case left and right sides, include: The acquisition module is used for acquiring a first image shot by the first camera and a third image shot by the third camera when the vehicle turns right and acquiring a second image shot by the second camera and a fourth image shot by the fourth camera when the vehicle turns left; The detection module is used for carrying out blind area detection on the first image or the third image to obtain a first blind area or a second blind area; The confirmation module is used for determining a first region of interest in the region of the second image according to the first blind region or determining a second region of interest in the region of the fourth image according to the second blind region, and comprises the steps of performing three-dimensional space conversion on the first blind region or the second blind region to obtain a 3D image of the first blind region or a 3D image of the second blind region, mapping the 3D image of the first blind region to the third image to obtain the first region of interest, or mapping the 3D image of the second blind region to the fourth image to obtain the second region of interest; The splicing module is used for splicing the first image and the first region of interest to obtain a first display picture or splicing the third image and the second region of interest to obtain a second display picture, and comprises the steps of detecting the edges of the first region of interest and the first image to obtain a first type of splicing point, detecting the edges of the second region of interest and the second image to obtain a second type of splicing point, splicing the first region of interest and the first image to obtain a first spliced picture according to the first type of splicing point or the second type of splicing point, or splicing the second region of interest and the second image to obtain a second spliced picture, and fusing the first spliced picture to obtain the first display picture or the second spliced picture to obtain the second display picture And the output module is used for outputting the first display picture or the second display picture.
  9. 9. A vehicle, comprising: the camera device comprises a first camera and a second camera which are arranged on the left side and the right side of the headstock, and a third camera and a fourth camera which are respectively and symmetrically arranged on the left side and the right side of the hanging box; Vehicle turn blind area compensation arrangement includes: A memory for storing program instructions of the CMS-based vehicle turning blind zone compensation method; a processor for executing program instructions of the CMS-based vehicle turning blind zone compensation method to implement the CMS-based vehicle turning blind zone compensation method of any one of claims 1 to 7.

Description

CMS-based vehicle turning blind area compensation method and device and vehicle Technical Field The application relates to the technical field of vehicle detection sensors, in particular to a vehicle turning blind area compensation method and device based on a CMS and a vehicle. Background With the development of science and technology, vehicles are visible everywhere in daily life, but with the increase of vehicles, blind areas are easy to form in the turning process of the vehicles. The resulting incidents are also increasing. In the prior art, the vehicle detects and complements blind areas when turning through a camera monitoring (Camera Monitor System, CMS) system, cameras are arranged on the left side and the right side of a driving position or the left side and the right side of a rearview mirror of the vehicle to shoot the left side and the right side of the vehicle, for a small-sized vehicle, the cameras on the two sides can shoot images on the left side and the right side of the vehicle in the turning process, the lateral blind areas can be eliminated to a certain extent, but for a large-sized vehicle, the box of the vehicle can shield the visual field of the cameras on the two sides in the turning process of the large-sized vehicle, so that visual field blind areas are generated, and the camera monitoring system cannot solve the problem of the blind areas caused by the shielding of the box of the vehicle. Disclosure of Invention The application provides a vehicle turning blind area compensation method and device based on a CMS (vehicle control system), and a vehicle, wherein the blind area can be avoided when the vehicle turns. In a first aspect, an embodiment of the present application provides a vehicle turning blind area compensation method based on CMS, which is characterized in that the vehicle includes a head, a hanging box connected to the head, a first camera and a second camera respectively symmetrically disposed on the right side and the left side of the head, and a third camera and a hanging box fourth camera respectively symmetrically disposed on the left side and the right side of the hanging box, the vehicle turning blind area compensation method based on CMS includes the steps of acquiring a first image captured by the first camera and a third image captured by the third camera when the vehicle turns right, acquiring a second image captured by the second camera and a fourth image captured by the fourth camera when the vehicle turns left, performing blind area detection on the first image or the second image to obtain a first blind area or a second blind area, determining a region of interest in the third image according to the first blind area, or the second determining a first region of interest in the third image, and displaying the first region of interest and the second region of interest by stitching the first image and the second image or the second region of interest, and displaying the first region of interest and the second region of interest. In a second aspect, an embodiment of the application provides a vehicle turning blind area compensation device, which comprises an acquisition module, a detection module, a confirmation module and an output module, wherein the acquisition module is used for acquiring a first image shot by a first camera and a third image shot by a third camera and acquiring a second image shot by a second camera and a fourth image shot by a fourth camera when a vehicle turns right, the detection module is used for carrying out blind area detection on the first image or the third image to obtain a first blind area or a second blind area, the confirmation module is used for determining the first blind area in the second image to obtain a first interested area or the second blind area to determine the second blind area in the fourth image to obtain a second interested area according to the first blind area, the splicing module is used for splicing the first image and the first interested area to obtain a first display picture or splicing the third image and the second interested area to obtain a second display picture, and the output module is used for outputting the first display picture or the second display picture. In a third aspect, an embodiment of the present application provides a vehicle, including a camera device including a first camera and a second camera disposed on left and right sides of the head, and a third camera and a fourth camera symmetrically disposed on left and right sides of the hanging box, respectively, a vehicle turning blind area compensation device including a memory for storing program instructions of the CMS-based vehicle turning blind area compensation method, and a processor for executing the program instructions of the CMS-based vehicle turning blind area compensation method to implement the CMS-based vehicle turning blind area compensation method according to the first aspect. According to the vehicle turning blind ar