An efficient binary corner detector

摘要: Corner extraction is an important task in many computer vision systems. The quality of the corners and efficiency detection method are two very aspects that can greatly impact accuracy, robustness real-time performance corresponding corner-based system. In this paper we introduce a fast corner detector based on local binary-image regions. We verify proposed by measuring repeatability rate under various illumination, scale motion conditions. Our experimental results show while features comparable with other conventional methods, ours delivers faster performance.