Efficient hundreds-baseline stereo by counting interest points for moving omni-directional multi-camera system

In this article, we propose an efficient method for estimating a depth map from long-baseline image sequences captured by a calibrated moving multi-camera system. Our concept for estimating a depth map is very simple; we integrate the counting of the total number of interest points (TNIP) in images with the original framework of multiple baseline stereo. Even by using a simple algorithm, the depth can be determined without computing similarity measures such as SSD (sum of squared differences) and NCC (normalized cross correlation) that have been used for conventional stereo matching. The proposed stereo algorithm is computationally efficient and robust for distortions and occlusions and has high affinity with omni-directional and multi-camera imaging. Although expected trade-off between accuracy and efficiency is confirmed for a naive TNIP-based method, a hybrid approach that uses both TNIP and SSD improve this with realizing high accurate and efficient depth estimation. We have experimentally verified the validity and feasibility of the TNIP-based stereo algorithm for both synthetic and real outdoor scenes.