Two-View Monocular Depth Estimation by Optic-Flow-Weighted Fusion

Abstract

Depth estimation with monocular cameras is a cheap and promising solution for autonomous vehicles and robots. Even though there are many approaches in the literature, the issue of estimating depth of objects with low optic flow (low parallax) still remains. This work proposes a new two-view monocular depth estimation method that estimates depths with only a monocular camera using two optic flow directions based on the Flat Surface Model, fusing them with optic flow as weights. The proposed method achieves an average depth estimation error of 3.68 m and a maximum error of 107.34 m, which are smaller than those obtained by traditional techniques (22.90 and 9815.44 m, respectively).