Title :
Appearance-based place recognition for topological localization
Author :
Ulrich, Iwan ; Nourbakhsh, Illah
Author_Institution :
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
This paper presents a new appearance-based place recognition system for topological localization. The method uses a panoramic vision system to sense the environment. Color images are classified in real-time based on nearest-neighbor learning, image histogram matching, and a simple voting scheme. The system has been evaluated with eight cross-sequence tests in four unmodified environments, three indoors and one outdoors. In all eight cases, the system successfully tracked the mobile robot´s position. The system correctly classified between 87% and 98% of the input color images. For the remaining images, the system was either momentarily confused or uncertain, but never classified an image incorrectly
Keywords :
image classification; image matching; learning (artificial intelligence); mobile robots; real-time systems; robot vision; topology; appearance-based place recognition; cross-sequence tests; image histogram matching; mobile robot position tracking; nearest-neighbor learning; panoramic vision system; real-time color image classification; topological localization; voting scheme; Color; Histograms; Machine vision; Mobile robots; Robot kinematics; Robot sensing systems; Sensor systems; System testing; Uncertainty; Voting;
Conference_Titel :
Robotics and Automation, 2000. Proceedings. ICRA '00. IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-5886-4
DOI :
10.1109/ROBOT.2000.844734
