A local voting and refinement method for circle detection

Improving the accuracy of circle detection in images is important for feature detection in remote sensing imagery. The standard Hough transform detects circles from the whole image space, which inclines to be disturbed by noise and the imperfection of the edge information. In this paper, a method of voting and determining circles locally is proposed. This method improves the accuracy and stability of circle detection in images with noise, incomplete edge information and complex backgrounds. Synthetic and real satellite images are used to demonstrate the effectivity of circle detection of the proposed method.