FSD-SLAM: a fast semi-direct SLAM algorithm

doi:10.1007/s40747-021-00323-y

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进机器人控制团队

	FSD-SLAM: a fast semi-direct SLAM algorithm
	Dong, Xiang 2; Cheng, Long 1,3; Peng, Hu 2; Li, Teng 2
刊名	COMPLEX & INTELLIGENT SYSTEMS
	2021-03-15
页码	12
关键词	SLAM Feature enhancement Pose estimation Incremental dynamic covariance scaling Point cloud integration
ISSN号	2199-4536
DOI	10.1007/s40747-021-00323-y
通讯作者	Cheng, Long(long.cheng@ia.ac.cn) ; Li, Teng(liteng@ahu.edu.cn)
英文摘要	Current visual-based simultaneous localization and mapping(SLAM) system suffers from feature loss caused by fast motion and unstructured scene in complex environments. Addressing this problem, a fast semi-direct SLAM algorithm is proposed in this paper. The main idea of this method is to combine the feature point method with the direct method in order to improve the robustness of the system in the environment of scarce visual features and low texture. First, the feature enhancement module based on subgraph is developed to extract image feature points more stably. Second, an apparent shape weighted fusion method is proposed for camera pose estimation, which can still work robustly in the absence of feature points. Third, an incremental dynamic covariance scaling algorithm is studied for optimizing the error of camera pose estimation. Finally, based on the optimized camera pose, a face element model is designed to estimate and fuse the point cloud pose, and obtain an ideal three-dimensional point cloud map. The proposed algorithm has been tested extensively on the benchmark TUM dataset and the real environment. The results show that the algorithm has better performance than existing visual based SLAM algorithms.
资助项目	National Key Research and Development Project Intelligent Robot Special Program[2018YFB1305804] ; National Natural Science Foundation of China[62025307] ; National Natural Science Foundation of China[61873268] ; National Natural Science Foundation of China[U1913209] ; Beijing Natural Science Foundation[JQ19020] ; Anhui University Cooperative Innovation Project[GXXT-2019-003]
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER HEIDELBERG
WOS记录号	WOS:000629072000001
资助机构	National Key Research and Development Project Intelligent Robot Special Program ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Anhui University Cooperative Innovation Project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/44009]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队
通讯作者	Cheng, Long; Li, Teng
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Iaboratory Management & Control Complex, Beijing 100190, Peoples R China 2.Anhui Univ, Sch Elect Engn & Automat, Hefei 230601, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Dong, Xiang,Cheng, Long,Peng, Hu,et al. FSD-SLAM: a fast semi-direct SLAM algorithm[J]. COMPLEX & INTELLIGENT SYSTEMS,2021:12.
APA	Dong, Xiang,Cheng, Long,Peng, Hu,&Li, Teng.(2021).FSD-SLAM: a fast semi-direct SLAM algorithm.COMPLEX & INTELLIGENT SYSTEMS,12.
MLA	Dong, Xiang,et al."FSD-SLAM: a fast semi-direct SLAM algorithm".COMPLEX & INTELLIGENT SYSTEMS (2021):12.