The use of depth information, such as that provided by a stereo system, can potentially enhance the robustness of motion detection algorithms with regards to typical factors such as sudden illumination variations, shadows and camouflage. In this paper we propose and compare two change detection strategies based on two views which exploits 2D and 3D information in order to deal with typical change detection issues. Preliminary experimental results provided using two different stereo matching algorithms on real stereo sequences show the usefulness of the proposed approach in the considered scenario
F. Tombari, S. Mattoccia, L. Di Stefano, F. Tonelli (2007). Detecting motion by means of 2D and 3D information. TOKYO : Asian Federation of Computer Vision.
Detecting motion by means of 2D and 3D information
TOMBARI, FEDERICO;MATTOCCIA, STEFANO;DI STEFANO, LUIGI;
2007
Abstract
The use of depth information, such as that provided by a stereo system, can potentially enhance the robustness of motion detection algorithms with regards to typical factors such as sudden illumination variations, shadows and camouflage. In this paper we propose and compare two change detection strategies based on two views which exploits 2D and 3D information in order to deal with typical change detection issues. Preliminary experimental results provided using two different stereo matching algorithms on real stereo sequences show the usefulness of the proposed approach in the considered scenarioI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
