Fast Adaptive Depth Estimation Algorithm Based on K-means Segmentation

A fast depth estimation algorithm based on the K-means image segmentation is proposed in this paper. Traditional global-based depth estimation methods using graph-cuts made good performance on the depth map estimation, however, the time cost is a big problem for real time application. A fast segment-based method was discussed in this paper, aiming to reduce time cost and at the same time maintain or even improve the performance of depth map estimation. Firstly, the reference image is segmented by K-means method and then mark each segment as different types. Secondly, apply different matching methods for each kind of segment to get the initial matching cost. Thirdly, correct the depth values of unreliable pixels in each segments Finally, depth values of each segments are determined by using the final matching cost. The experience results demonstrate the superior performance of the proposed algorithm.(2)