Dense Disparity Estimation in Ego-motion Reduced Search Space

TL;DR

This paper introduces a method that leverages ego-motion and previous frame data to improve depth estimation accuracy and computational efficiency in stereo vision, validated on KITTI data.

Contribution

It proposes transforming previous disparity maps using ego-motion to reduce search space and enhance depth estimation accuracy with Kalman filtering.

Findings

Increased depth estimation accuracy on KITTI benchmark

Reduced disparity search space and flickering

Lower computational complexity

Abstract

Depth estimation from stereo images remains a challenge even though studied for decades. The KITTI benchmark shows that the state-of-the-art solutions offer accurate depth estimation, but are still computationally complex and often require a GPU or FPGA implementation. In this paper we aim at increasing the accuracy of depth map estimation and reducing the computational complexity by using information from previous frames. We propose to transform the disparity map of the previous frame into the current frame, relying on the estimated ego-motion, and use this map as the prediction for the Kalman filter in the disparity space. Then, we update the predicted disparity map using the newly matched one. This way we reduce disparity search space and flickering between consecutive frames, thus increasing the computational efficiency of the algorithm. In the end, we validate the proposed approach on real-world data from the KITTI benchmark suite and show that the proposed algorithm yields more accurate results, while at the same time reducing the disparity search space.