RGB-D dense mapping with feature-based method

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 光电信息技术研究室

	RGB-D dense mapping with feature-based method
	Fu XY(付兴银)1,2,3,4 ; Lu RR(鲁荣荣)1,2,3,4 ; Wu QX(吴清潇)o 1,2,4; Zhu F(朱枫)1,2,4
	2018
会议日期	May 22-24, 2018
会议地点	Beijing, China
关键词	dense SLAM RGB-D camera TSDF reconstruction real-time
页码	1-10
英文摘要	Simultaneous Localization and Mapping (SLAM) plays an important role in navigation and augmented reality (AR) systems. While feature-based visual SLAM has reached a pre-mature stage, RGB-D-based dense SLAM becomes popular since the birth of consumer RGB-D cameras. Different with the feature-based visual SLAM systems, RGB-D-based dense SLAM systems, for example, KinectFusion, calculate camera poses by registering the current frame with the images raycasted from the global model and produce a dense surface by fusing the RGB-D stream. In this paper, we propose a novel reconstruction system. Our system is built on ORB-SLAM2. To generate the dense surface in real-time, we first propose to use truncated signed distance function (TSDF) to fuse the RGB-D frames. Because camera tracking drift is inevitable, it is unwise to represent the entire reconstruction space with a TSDF model or utilize the voxel hashing approach to represent the entire measured surface. We use moving volume proposed in Kintinuous to represent the reconstruction region around the current frame frustum. Different with Kintinuous which corrects the points with embedded deformation graph after pose graph optimization, we re-fuse the images with the optimized camera poses and produce the dense surface again after the user ends the scanning. Second, we use the reconstructed dense map to filter out the outliers of the features in the sparse feature map. The depth maps of the keyframes are raycasted from the TSDF volume according to the camera pose. The feature points in the local map are projected into the nearest keyframe. If the discrepancy between depth values of the feature and the corresponding point in the depth map exceeds the threshold, the feature is considered as an outlier and removed from the feature map. The discrepancy value is also combined with feature pyramid layer to calculate the information matrix when minimizing the reprojection error. The features in the sparse map reconstructed near the produced dense surface will impose large influence in camera tracking. We compare the accuracy of the produced camera trajectories as well as the 3D models to the state-of-the-art systems on the TUM and ICL-NIUM RGB-D benchmark datasets. Experimental results show our system achieves state-of-the-art results. © 2018 SPIE.
源文献作者	Chinese Society for Optical Engineering (CSOE) ; Division of Information and Electronic Engineering of Chinese Academy of Engineering
产权排序	1
会议录	Proceedings of SPIE 10845, Optical Sensing and Imaging Technologies and Applications
会议录出版者	SPIE
会议录出版地	Bellingham, USA
语种	英语
ISSN号	0277-786X
ISBN号	978-1-5106-2333-0
WOS记录号	WOS:000455327800019
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/23951]
专题	沈阳自动化研究所_光电信息技术研究室
通讯作者	Fu XY(付兴银)
作者单位	1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 2.Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang 110016, China 3.University of Chinese Academy of Sciences, Beijing 100049, China 4.Key Lab of Image Understanding and Computer Vision, Liaoning Province, Shenyang 110016, China
推荐引用方式 GB/T 7714	Fu XY,Lu RR,Wu QX,et al. RGB-D dense mapping with feature-based method[C]. 见:. Beijing, China. May 22-24, 2018.