Parameter calibration system of vehicle-mounted camera

Abstract

Disclosed is a parameter calibration method of a vehicle-mounted camera. The method includes steps of self-making a three-dimensional calibration board, and establishing a world coordinate system on the basis of the self-made three-dimensional calibration board; establishing a camera calibration model on the basis of the three-dimensional calibration board, acquiring world coordinates of chessboard corners of the three-dimensional calibration board, and extracting pixel coordinates of the chessboard corners on the basis of a corner detection algorithm; and using a least square method to calibrate inner and outer parameters of a camera in combination of the corner world coordinates and the pixel coordinates.

Description

technical field [0001] [01] The present invention relates to the field of intelligent transportation, and more specifically relates to the calibration of the internal and external parameters of the on-board camera in the assisted driving system of the vehicle. Background technique [0002] [02] In recent years, intelligent transportation has become a research hotspot, and the assisted driving system, as an important part of intelligent transportation, has attracted much attention. Among them, lane line detection, vehicle detection and tracking, and distance measurement are the key technologies of the assisted driving system. These technologies rely on the vehicle-mounted camera to collect the surrounding traffic environment, so it is of great significance to accurately calibrate the vehicle-mounted camera. [0003] [03] Camera calibration methods are divided into traditional camera calibration methods and self-calibration methods. Common calibration methods are: Tsai (trad...

AI Technical Summary

Problems solved by technology

The main problem of the existing vehicle camera calibration method is that it is relatively cumbersome to use a two-dimensional calibration board to calibrate, which is not conducive to the determination of the world coordinate system, and is not conducive to subsequent detection and ranging, etc.

[0006] [06] However, vehicle assisted driving technologies such as lane line detection, vehicle detection and tracking, and distance measurement in the prior art need to perform perspective transformation on the pictures taken by the on-board camera, so a fixed perspective transformation matrix is ​​required

Using a two-dimensional calibration board to calibrate the vehicle camera, a fixed world coordinate system cannot be obtained, and the perspective transformation matrix is ​​not fixed, which is inconvenient for subsequent perspective transformations

Many calibration methods that use auxiliary tools to determine the world coordinate system are also cumbersome, not simple enough, and relatively troublesome to operate

Images