REALIZATION OF REALTIME AUTOMATIC SYSTEM TO DETECT CIRCULAR OBJECT USING LINE SEGMENT BASED RANDOMIZED HOUGH TRANSFORM IN CAMERA IMAGE

摘要

A method for realizing a real-time automatic circular object detecting system by using a line segment-based RHT of a camera image is provided to reduce the repetitive performance time required for the oval detection by introducing an MPM(Merging Probability Map). To obtain a edge line from an image, the edge detection and thinning process are performed(110,120). An edge is separated into edge line segments(130). Segments which are not yet separated are separated into edge line segments. An MPM is defined. Through the MPM, it is determined whether to perform the merging of the edge line segments(140). An RHT is applied to the merged line segments. By using the RHT, the whole circular object within an input image is accurately detected(150).