6 Papers
17 Citations
Xin Li is an academic researcher from National University of Defense Technology. The author has contributed to research in topics: Pose & Rotation (mathematics). The author has an hindex of 3, co-authored 5 publications.
Chat about Author
Papers
Simplified mirror-based camera pose computation via rotation averaging
Gucan Long,Laurent Kneip,Xin Li,Xiaohu Zhang,Qifeng Yu +4 more
- 07 Jun 2015
TL;DR: A novel approach to compute the camera pose with respect to a reference object given only mirrored views, which enables mirror-based pose estimation in closed-form under the chordal L2-metric, or in an outlier-robust way by employing iterative L1-norm averaging.
Airborne vision-aided landing navigation system for fixed-wing UAV
Pengyu Guo,Xin Li,Yang Gui,Xiang Zhou,Zhang Hongliang,Xiaohu Zhang +5 more
- 01 Oct 2014
TL;DR: In order to achieve accurate automatic recovery of fixed-wing UAV at the known landing site, an airborne aided landing navigation system based on machine vision is designed and realized, and the key algorithms of the system are investigated.
15
Accurate mirror-based camera pose estimation with explicit geometric meanings
TL;DR: An accurate closed form solution is proposed to estimate camera pose by several mirrored reference object images acquired via a planar mirror under different unknown poses that is more accurate when there are more than three images and has explicit geometric meanings.
5
Adaptive and accelerated tracking-learning-detection
Pengyu Guo,Xin Li,Shaowen Ding,Zunhua Tian,Xiaohu Zhang +4 more
- 21 Aug 2013
TL;DR: An improved online long-term visual tracking algorithm, named adaptive and accelerated TLD (AA-TLD) based on Tracking-Learning-Detection (TLD), which is a novel tracking framework which can be used in the field of video surveillance to meet the need of real-time video tracking.
5
Non-Intervisible Pose Estimation Based on Plannar Mirror
Jin Bo Liu,Gu Can Long,Xin Li +2 more
TL;DR: This article proposes an unattached and linear approach to solve and optimize transformation of camera-to-body without any prior information of planar mirror configuration and presents a number of simulations and experiments to prove that the formulation significantly improves accuracy and robust.