Multi-baseline stereo by maximizing total number of interest points
Tomokazu Sato, Naokazu Yokoya · 2007
This paper proposes a novel method for estimating depth without similarity measures such as SSD and NCC. Our idea for estimating a depth map is very simple; only counting interest points in images is integrated with the framework of multi-baseline stereo. Even by a simple algorithm, depth can be determined without computing similarity measures such as SSD and NCC that have been used for conventional stereo matching. The proposed method realizes robust depth estimation against occlusions with lower computational cost. Through a naive TNIP based method can realize fast and robust depth estimation, the accuracy of estimated depth is lower than one by SSSD based method because TNIP uses sparse data. In this paper, we also show that accuracy of depth estimation can be increased by combining TNIP based methos and SSSD based method. In experiments, the validity and feasibility of our algorithm are demonstrated for both synthetic and real outdoor scenes.