Event-based depth estimation with dense occlusion

• Kangrui Zhou, Taihang Lei, Guan Banglei, and Qifeng Yu
• received 02/22/2024; accepted 05/13/2024; posted 05/13/2024; Doc. ID 521988
• Abstract: Occlusions pose a significant challenge to depth estimation in various fields, including automatic driving, remote sensing observation, and video surveillance. In this Letter, we propose a novel depth estimation method for dense occlusion to estimate the depth behind occlusions. We design a comprehensive procedure using an event camera that consists of two steps: rough estimation and precise estimation. In the rough estimation, we reconstruct two segments of the event stream to remove occlusions and subsequently employ binocular intersection measurement to estimate the rough depth. In the precise estimation, we propose a criterion that the maximum total length of edges of reconstructed images corresponds to the actual depth and search for the precise depth around the rough depth. The experimental results demonstrate that our method is implemented with relative errors of depth estimation below 1.05%.