Title :
Egomotion estimation on a topological space
Author :
Silva, Cesar ; Santos-Victor, Jose
Author_Institution :
Inst. de Sistemas e Robotica, Inst. Superior Tecnico, Lisbon, Portugal
Abstract :
We present an egomotion estimation method for a monocular observer moving with arbitrary motion. The method is uniquely based on the normal flow field and the estimation problem is defined in a particular topological space-the L-space-to allow the use of global data for the final estimates. Additionally, robust statistics methods are used for motion model selection, and provide improved robustness to image noise and data outliers
Keywords :
image sequences; least mean squares methods; motion estimation; observers; parameter estimation; statistical analysis; topology; bidimensional regression; data outliers; egomotion estimation; flow field; image noise; least means squares; monocular observer; motion model selection; spatiotemporal image; statistics methods; topological space; Cameras; Electrical capacitance tomography; Image matching; Image motion analysis; Layout; Motion estimation; Optical computing; Optical noise; Postal services; Statistics;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.711080
