A framework for object classification in farfield videos

Simple item page
dc.contributor.authorSetitra, Insaf
dc.contributor.authorLarabi, Slimane
dc.date.accessioned2014-12-03T07:59:51Z
dc.date.available2014-12-03T07:59:51Z
dc.date.issued2014-10-26
dc.description.abstractObject classification in videos is an important step in many applications such as abnormal event detection in video surveillance, traffic analysis is urban scenes and behavior control in crowded locations. In this work, propose a framework for moving object classification in farfield videos. Much works have been dedicated to accomplish this task. We overview existing works and combine several techniques to implement a real time object classifier with offline training phase. We follow three main steps to classify objects in steady background videos : background subtraction, object tracking and classification. We measure accuracy of our classifier by experiments done using the PETS 2009 dataset.fr_FR
dc.identifier.isrnCERIST-DSISM/RR--14-000000027--dzfr_FR
dc.identifier.urihttp://dl.cerist.dz/handle/CERIST/699
dc.publisherCERIST
dc.relation.ispartofRapports de recherche internes
dc.relation.placeAlger
dc.structureSystèmes et Documents Multimédia Structurés (SDMS)fr_FR
dc.subjectbackground subtractionfr_FR
dc.subjectfeature extractionfr_FR
dc.subjectobject trackingfr_FR
dc.subjectobject classificationfr_FR
dc.subjectvideo analysisfr_FR
dc.titleA framework for object classification in farfield videosfr_FR
dc.typeTechnical Report
Files
Collections
Research Reports