In this paper we propose a real-time solution to localize the surgical instruments in an eye surgery simulator, Eye Si. The hardware consists of three synchronized cameras that capture the movements of the instruments, and an FPGA card for grabbing and preprocessing the images. The surgical instruments are localized using the method of Hough transform combined with the technique of stereo vision. The proposed method is robust to noise and low quality camera images. A fast algorithm of voting in Hough transform is also proposed.
Dieser Eintrag ist Teil der Universitätsbibliographie.
Search Authors in