Real-Time RGB-D Camera Relocalization via Randomized Ferns for Keyframe Encoding
Visualization and Computer Graphics, IEEE Transactions (2015)
摘要
Recovery from tracking failure is essential in any simultaneous localization and tracking system. In this context, we explore an efficient keyframe-based relocalization method based on frame encoding using randomized ferns. The method enables automatic discovery of keyframes through online harvesting in tracking mode, and fast retrieval of pose candidates in the case when tracking is lost. Frame encoding is achieved by applying simple binary feature tests which are stored in the nodes of an ensemble of randomized ferns. The concatenation of small block codes generated by each fern yields a global compact representation of camera frames. Based on those representations we define the frame dissimilarity as the block-wise hamming distance (BlockHD). Dissimilarities between an incoming query frame and a large set of keyframes can be efficiently evaluated by simply traversing the nodes of the ferns and counting image co-occurrences in corresponding code tables. In tracking mode, those dissimilarities decide whether a frame/pose pair is considered as a novel keyframe. For tracking recovery, poses of the most similar keyframes are retrieved and used for reinitialization of the tracking algorithm. The integration of our relocalization method into a hand-held KinectFusion system allows seamless continuation of mapping even when tracking is frequently lost.
更多查看译文
关键词
slam (robots),cameras,image coding,image colour analysis,image representation,image retrieval,object tracking,pose estimation,blockhd,automatic keyframe discovery,binary feature tests,block code concatenation,block-wise hamming distance,code tables,frame dissimilarity,frame-pose pair,global compact camera frame representation,hand-held kinectfusion system,image co-occurrences,incoming query frame,keyframe encoding,keyframe-based relocalization method,node traversal,online harvesting,pose retrieval,randomized ferns,real-time rgb-d camera relocalization,simultaneous localization and tracking system,tracking algorithm reinitialization,tracking failure recovery,tracking mode,camera relocalization,dense tracking and mapping,marker-free augmented reality,tracking recovery,pipelines,simultaneous localization and mapping,encoding,image reconstruction,real time systems
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络