On the representation and estimation of spatial uncertainly
International Journal of Robotics Research
Video Google: A Text Retrieval Approach to Object Matching in Videos
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Scalable Recognition with a Vocabulary Tree
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Self-localization in non-stationary environments using omni-directional vision
Robotics and Autonomous Systems
Machine learning for high-speed corner detection
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
FrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping
IEEE Transactions on Robotics
LESS-mapping: Online environment segmentation based on spectral mapping
Robotics and Autonomous Systems
Information-theoretic compression of pose graphs for laser-based SLAM
International Journal of Robotics Research
Spatio-temporal feature-based keyframe detection from video shots using spectral clustering
Pattern Recognition Letters
Real-time 6-DOF multi-session visual SLAM over large-scale environments
Robotics and Autonomous Systems
Long-term mapping and localization using feature stability histograms
Robotics and Autonomous Systems
Lifelong localization in changing environments
International Journal of Robotics Research
Self-help: Seeking out perplexing images for ever improving topological mapping
International Journal of Robotics Research
Robust loop closing over time for pose graph SLAM
International Journal of Robotics Research
| Hi-index | 0.00 |
The typical SLAM mapping system assumes a static environment and constructs a map that is then used without regard for ongoing changes. Most SLAM systems, such as FastSLAM, also require a single connected run to create a map. In this paper we present a system of visual mapping, using only input from a stereo camera, that continually updates an optimized metric map in large indoor spaces with movable objects: people, furniture, partitions, etc. The system can be stopped and restarted at arbitrary disconnected points, is robust to occlusion and localization failures, and efficiently maintains alternative views of a dynamic environment. It operates completely online at a 30 Hz frame rate.