Real-time and scalable incremental segmentation on dense SLAM
Tateno K, Tombari F, Navab N (2015)
Publication Type: Conference contribution
Publication year: 2015
Journal
Publisher: Institute of Electrical and Electronics Engineers Inc.
Book Volume: 2015-December
Pages Range: 4465-4472
Conference Proceedings Title: IEEE International Conference on Intelligent Robots and Systems
Event location: Hamburg, DEU
ISBN: 9781479999941
DOI: 10.1109/IROS.2015.7354011
Abstract
This work proposes a real-time segmentation method for 3D point clouds obtained via Simultaneous Localization And Mapping (SLAM). The proposed method incrementally merges segments obtained from each input depth image in a unified global model using a SLAM framework. Differently from all other approaches, our method is able to yield segmentation of scenes reconstructed from multiple views in real-time, with a complexity that does not depend on the size of the global model. At the same time, it is also general, as it can be deployed with any frame-wise segmentation approach as well as any SLAM algorithm. We validate our proposal by a comparison with the state of the art in terms of computational efficiency and accuracy on a benchmark dataset, as well as by showing how our method can enable real-time segmentation from reconstructions of diverse real indoor environments.
Involved external institutions
Germany (DE)How to cite
APA:
Tateno, K., Tombari, F., & Navab, N. (2015). Real-time and scalable incremental segmentation on dense SLAM. In IEEE International Conference on Intelligent Robots and Systems (pp. 4465-4472). Hamburg, DEU: Institute of Electrical and Electronics Engineers Inc..
MLA:
Tateno, Keisuke, Federico Tombari, and Nassir Navab. "Real-time and scalable incremental segmentation on dense SLAM." Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015, Hamburg, DEU Institute of Electrical and Electronics Engineers Inc., 2015. 4465-4472.
BibTeX: Download