Monocular camera external parameter calibration system and method

Abstract

The invention discloses a monocular camera external parameter calibration system and method, and belongs to the field of intelligent vehicles. A monocular camera external parameter calibration system comprises at least six targets, a camera, a total station and a calculation unit. The calculation unit analyzes the real pixel position of each target on the imaging plane of the camera, obtains the position of each target in a world coordinate system, obtains the position of a target vehicle in the world coordinate system, projects each target to the imaging plane of the camera at a hypothetical position, obtains a hypothetical pixel position of each target on the hypothetical imaging plane, compares the hypothetical pixel position with a real pixel position of each target, and calculates the pose of the camera in a vehicle coordinate system. The calibration center of the target vehicle can be accurately judged, the constraint of a calibration plate and a site is eliminated, the stop position and angle constraint of the target vehicle are liberated, the relative position and angle of the camera and the target vehicle are rapidly analyzed, and the detection sensitivity and accuracy are improved.

Description

technical field [0001] The invention belongs to the field of intelligent vehicles, and more particularly, relates to a system and method for calibrating external parameters of a monocular camera. Background technique [0002] The traditional camera external parameter calibration scheme generally uses a chess grid calibration board placed in front of the camera. Then use some open source software to calculate the positional relationship between the chess grid and the camera. Thereby, the spatial position and installation angle of the camera are calculated. This method is widely used in vehicle camera extrinsic parameter calibration. Whether it is a forward-looking camera or a surround-view camera, this method can be used to calibrate. Thereby, the position and angle relationship of the camera relative to the calibration plate is obtained. Then, according to the positional relationship between the calibration plate and the vehicle, the positional relationship between the c...

AI Technical Summary

Problems solved by technology

Generally, the size of the vehicle is known, and then the car is driven to a designated position, but it is also difficult to ensure that the vehicle can stop accurately, and it is difficult to observe the angle deviation

Therefore, even if the precise position and angle relationship between the camera and the calibration board is obtained through some open source software, large errors will still occur when calculating the angle relationship between the camera and the vehicle through the position and angle relationship between the calibration board and the vehicle, resulting in The measurement results are out of tolerance, and the rate of unqualified products remains high

[0006]2. Too dependent on the calibration board

There are too many restrictions on the site, and some enterprises cannot complete the work through the calibration board

[0007]3. The calibration plate must be flat

The surface is treated with alumina to ensure the accuracy of the surface, the manufacturing process is complicated, the cost is very high, and the service life is very short

Images