Real-time depth range estimation and its application to mobile stereo camera

Hyoungchul Shin, Kwanghoon Sohn

Abstract: This paper proposes a real-time depth range estimation algorithm that produces a specialized depth map for mobile stereo camera and its applications. The proposed algorithm effectively controls the unwanted depth noise by using a simple depth fusion technique which is based-on the properties of different matching window size. Search range estimation used for the proposed algorithm improves both the algorithm efficiency and the accuracy of the proposed depth range map. In order to show the performance of the proposed algorithm, shooting guide functions such as auto-disparity control and comfortable zone indicator functions are implemented by using the proposed algorithm. Additionally, the out of focus images are represented as an image enhancement function. The proposed algorithm and the experimental results support that the proposed algorithm effectively controls the background artifacts and provide accurate dynamic range of depth with low computational complexity.