Approximating a Single Viewpoint in Panoramic Imaging Devices
OMNIVIS '00 Proceedings of the IEEE Workshop on Omnidirectional Vision
Robot navigation using image sequences
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Landmark Real-Time Recognition and Positioning for Pedestrian Navigation
CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
3D real-time positioning for autonomous navigation using a nine-point landmark
Pattern Recognition
Environment topological structure recognition for robot navigation
ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
| Hi-index | 0.00 |
A vision based navigation system is presented for determininga mobile robotýs position and orientation usingpanoramic imagery. An omni-directional image sensormounted on the robot is useful in obtaining a 360° fieldof view, permitting navigational markers from all sides tobe viewed simultaneously. A robust marker-based systemis presented using vertically positioned linear markers aslandmarks. The markers consist of linearly encoded digitalpatterns, similar to a barcode but distinguishable with lesspixels. A set of patterns are orthogonal from one anotherand are readily recognized with any continous section visible.With a vertically posed panoramic image sensor, thesevertically mounted linear markers appear along radial lines.The panoramic image is pre-processed according to edge directionsto find candidate regions which are spatially sampledinto digital symbols. This extracted binary sequenceis examined to determine if it belongs in the marker patternset. This system is shown to be robust even with the lowresolution of a panoramic sensor with 800x800 active pixels.Experiments are shown with synthetic imagery and withthree real prototype systems.