Abstract
Obtaining an optimal tradeoff between accuracy and efficiency in ellipse detection is a significant challenge. In this paper, we propose a fast, high-precision ellipse detection method that utilizes arc selection and grouping strategies to significantly reduce the computation amount. A fast corner detection algorithm is also proposed. In the proposed method, to generate ellipse candidates comprehensively, both grouped and ungrouped-salient arcs are fitted. Further, the salient ellipse candidates are selected as final detections that are subject to the selection strategy, which realizes both validation and de-redundancy (clustering) functions. A complexity analysis of the method revealed that the detection time is linearly related to the number of edge points. The results of extensive experiments conducted on three public datasets demonstrate that the proposed method is approximately 75% faster than state-of-the-art methods with comparable or higher precision, and its detection time is less than 30 ms in most cases.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have