Obstacle recognition method, obstacle recognition system and storage medium
An obstacle identification and obstacle technology, applied in the field of vehicle safety, can solve the problems of reducing the driving speed of the mixer truck and affecting the production efficiency, and achieve the effect of increasing the driving speed, improving the production efficiency and avoiding traffic accidents.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0062] Such as figure 1 As shown, Embodiment 1 provides an obstacle identification method for agitating vehicles, where multiple fisheye cameras are arranged on the agitating vehicle, and the obstacle identification method includes:
[0063] Step 102, establishing a calibration scene according to the parking position of the mixing vehicle;
[0064] Step 104, calibrate the working position of any fisheye camera in the calibration scene;
[0065] Step 106, according to the working position of any fisheye camera in the calibration scene, determine the camera parameters and distortion parameters of any fisheye camera;
[0066] Step 108, according to the camera internal parameters and distortion parameters of any fisheye camera, correct the original image taken by any fisheye camera when the stirring vehicle is walking, so as to obtain the undistorted image of any fisheye camera;
[0067] Step 110, according to the undistorted image of any fisheye camera, generate a panoramic bir...
Embodiment 2
[0082] On the basis of any of the above-mentioned embodiments, according to the undistorted image of any fisheye camera, the step of generating a panoramic bird's-eye view image when the stirring vehicle is walking specifically includes: determining any The top-view transformation matrix between the undistorted image of a fisheye camera and the first bird's-eye view image; according to the top-view transformation matrix, the undistorted image of any fisheye camera is converted into the first bird's-eye view image; for the first bird's-eye view image of any fisheye camera A bird's-eye view image is subjected to blurred image restoration processing to generate a second bird's-eye view image; according to the second bird's-eye view image of any fisheye camera, a panoramic bird's-eye view image of the stirring vehicle is generated when it is walking.
[0083] In a specific embodiment, such as figure 2 As shown, the obstacle recognition methods include:
[0084] Step 202, accordi...
Embodiment 3
[0090] On the basis of any of the above embodiments, the step of performing blurred image restoration processing on the first bird's-eye view image of any fisheye camera to generate the second bird's-eye view image specifically includes: obtaining the blurred image stored in association with any fisheye camera Kernel; according to the first bird's-eye view image of any fish-eye camera and the blur kernel, perform blurred image restoration processing on the first bird's-eye view image of any fish-eye camera to generate a second bird's-eye view image.
[0091] In this embodiment, by determining the blur kernel stored in association with the fisheye camera as the blur kernel of the first bird's-eye view image corresponding to the fisheye camera, by performing RL on the first bird's-eye view image and the blur kernel of the first bird's-eye view image Algorithm deconvolution to remove blur for the first bird's-eye view image, and then generate a clear second bird's-eye view image. ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


