Show simple item record

Detecting and tracking multiple interacting objects without class-specific models

dc.date.accessioned2006-04-25T13:33:26Z
dc.date.accessioned2018-11-24T10:24:49Z
dc.date.available2006-04-25T13:33:26Z
dc.date.available2018-11-24T10:24:49Z
dc.date.issued2006-04-25
dc.identifier.urihttp://hdl.handle.net/1721.1/32536
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/32536
dc.description.abstractWe propose a framework for detecting and tracking multiple interacting objects from a single, static, uncalibrated camera. The number of objects is variable and unknown, and object-class-specific models are not available. We use background subtraction results as measurements for object detection and tracking. Given these constraints, the main challenge is to associate pixel measurements with (possibly interacting) object targets. We first track clusters of pixels, and note when they merge or split. We then build an inference graph, representing relations between the tracked clusters. Using this graph and a generic object model based on spatial connectedness and coherent motion, we label the tracked clusters as whole objects, fragments of objects or groups of interacting objects. The outputs of our algorithm are entire tracks of objects, which may include corresponding tracks from groups of objects during interactions. Experimental results on multiple video sequences are shown.
dc.format.extent19 p.
dc.format.extent80453528 bytes
dc.format.extent1840042 bytes
dc.language.isoen_US
dc.subjectvisual surveillance
dc.subjectmulti-target tracking
dc.subjectbackground subtraction
dc.subjectgroup tracking
dc.titleDetecting and tracking multiple interacting objects without class-specific models


Files in this item

FilesSizeFormatView
MIT-CSAIL-TR-2006-027.pdf1.840Mbapplication/pdfView/Open
MIT-CSAIL-TR-2006-027.ps80.45Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record