NAVE	Networked Augmented Virtual Environment (NAVE) Group

Publication:Feihu Yan, Zhaoxin Li, Zhong Zhou. Robust and Efficient Edge-based Visual Odometry[J]. Computational Visual Media. 2022, 8:467–481 (SCI, IF:2.2) pdf         Visual odometry, which aims to estimate relative camera motion between sequential video frames, has been widely used in the fields of augmented reality, virtual reality, and autonomous driving. However, it is still quite challenging for state-of-the-art approaches to handle low-texture scenes. In this paper, we propose a robust and efficient visual odometry algorithm that directly utilizes edge pixels to track camera pose. In contrast to direct methods, we choose reprojection error to construct the optimization energy, which can effectively cope with illumination changes. The distance transform map built upon  edge detection for each frame is used to improve  tracking efficiency. A novel weighted edge alignment method together with  sliding window optimization is proposed to further improve the accuracy. Experiments on public datasets  show that the  method is comparable to  state-of-the-art methods in terms of tracking accuracy, while being faster and more robust. create by admin at 2021-11-23 16:33:19