Abstract
This paper presents a high precision calibration method based on genetic algorithm (GA) for binocular vision system, involving the problems of the GA optimization and the camera modeling. For the GA optimization, both the binary-code and the real-code are considered. The binary-code makes the feasible solution approach to the optimal solution rapidly, and then the accuracy of GA is further improved by using the real-code. Furthermore, in order to improve the convergence rate of the algorithm, the parameters of the two cameras are calculated separately, and the target function is selected by the forward mapping relationship between the world coordinates and the image coordinates. The experimental results demonstrate the effectiveness of the proposed approach.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
