000052678 001__ 52678
000052678 005__ 20190316233501.0
000052678 037__ $$aREP_WORK
000052678 245__ $$aFixed Point Probability Field for Occlusion Handling
000052678 269__ $$a2004
000052678 260__ $$c2004
000052678 336__ $$aReports
000052678 520__ $$aIn this paper, we show that in a multi-camera context, we can effectively handle occlusions at each time frame independently, even when the only available data comes from the binary output of a fairly primitive motion detector. We start from occupancy probability estimates in a top view and rely on a generative model to yield probability images to be compared with the actual input images. We then refine the estimates so that the probability images match the binary input images as well as possible. We demonstrate the quality of our results on several sequences involving complex occlusions.
000052678 6531_ $$avisual surveillance
000052678 6531_ $$apeople detection
000052678 6531_ $$amulti-view environment
000052678 6531_ $$aocclusions
000052678 6531_ $$aprobabilistic framework.
000052678 700__ $$0240254$$g146262$$aFleuret, Francois
000052678 700__ $$aLengagne, Richard
000052678 700__ $$0240252$$aFua, Pascal$$g112366
000052678 8564_ $$uhttps://infoscience.epfl.ch/record/52678/files/IC_TECH_REPORT_200487.pdf$$zn/a$$s526327
000052678 909C0 $$xU10659$$0252087$$pCVLAB
000052678 909CO $$ooai:infoscience.tind.io:52678$$qGLOBAL_SET$$pIC$$preport
000052678 937__ $$aEPFL-REPORT-52678
000052678 970__ $$a200487/IC
000052678 973__ $$sPUBLISHED$$aEPFL
000052678 980__ $$aREPORT