GPO: Global Plane Optimization for Fast and Accurate Monocular SLAM Initialization

Autor:	Du, Sicong, Guo, Hengkai, Chen, Yao, Lin, Yilun, Meng, Xiangbing, Wen, Linfu, Wang, Fei-Yue
Rok vydání:	2020
Předmět:	Computer Science - Robotics Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Initialization is essential to monocular Simultaneous Localization and Mapping (SLAM) problems. This paper focuses on a novel initialization method for monocular SLAM based on planar features. The algorithm starts by homography estimation in a sliding window. It then proceeds to a global plane optimization (GPO) to obtain camera poses and the plane normal. 3D points can be recovered using planar constraints without triangulation. The proposed method fully exploits the plane information from multiple frames and avoids the ambiguities in homography decomposition. We validate our algorithm on the collected chessboard dataset against baseline implementations and present extensive analysis. Experimental results show that our method outperforms the fine-tuned baselines in both accuracy and real-time. Comment: Revised some minor errors. Accepted by ICRA 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2004.12051 Zobrazit plný text záznamu View this record from Arxiv