Depth Estimation Using a Sliding Camera

Image-based 3D reconstruction technology is widely used in different fields. The conventional algorithms are mainly based on stereo matching between two or more fixed cameras, and high accuracy can only be achieved using a large camera array, which is very expensive and inconvenient in many applications. Another popular choice is utilizing structure-from-motion methods for arbitrarily placed camera(s). However, due to too many degrees of freedom, its computational cost is heavy and its accuracy is rather limited. In this paper, we propose a novel depth estimation algorithm using a sliding camera system. By analyzing the geometric properties of the camera system, we design a camera pose initialization algorithm that can work satisfyingly with only a small number of feature points and is robust to noise. For pixels corresponding to different depths, an adaptive iterative algorithm is proposed to choose optimal frames for stereo matching, which can take advantage of continuously pose-changing imaging and save the time consumption amazingly too. The proposed algorithm can also be easily extended to handle less constrained situations (such as using a camera mounted on a moving robot or vehicle). Experimental results on both synthetic and real-world data have illustrated the effectiveness of the proposed algorithm.