Translator Disclaimer
17 March 2017 Real-time depth camera tracking with geometrically stable weight algorithm
Author Affiliations +
We present an approach for real-time camera tracking with depth stream. Existing methods are prone to drift in sceneries without sufficient geometric information. First, we propose a new weight method for an iterative closest point algorithm commonly used in real-time dense mapping and tracking systems. By detecting uncertainty in pose and increasing weight of points that constrain unstable transformations, our system achieves accurate and robust trajectory estimation results. Our pipeline can be fully parallelized with GPU and incorporated into the current real-time depth camera tracking system seamlessly. Second, we compare the state-of-the-art weight algorithms and propose a weight degradation algorithm according to the measurement characteristics of a consumer depth camera. Third, we use Nvidia Kepler Shuffle instructions during warp and block reduction to improve the efficiency of our system. Results on the public TUM RGB-D database benchmark demonstrate that our camera tracking system achieves state-of-the-art results both in accuracy and efficiency.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE) 0091-3286/2017/$25.00 © 2017 SPIE
Xingyin Fu, Feng Zhu, Feng Qi, and Mingming Wang "Real-time depth camera tracking with geometrically stable weight algorithm," Optical Engineering 56(3), 033104 (17 March 2017).
Received: 1 October 2016; Accepted: 1 March 2017; Published: 17 March 2017


Marker-less AR system based on line segment feature
Proceedings of SPIE (March 17 2015)
Real-time RGBD SLAM system
Proceedings of SPIE (September 11 2015)
Automatic stereoscopic system for person recognition
Proceedings of SPIE (June 22 1999)
Performance modeling of vote-based object recognition
Proceedings of SPIE (August 20 2003)

Back to Top