Euclidean Path Modeling from Ground and Aerial Views

Weaddress the issue ofEuclideanpath mu& ling ina single camerafor activity monitoring in a multi-camera video surveillance system m e paperpmposes a novel linear solufwnro auto-calibrafeany camera observing pedestrians and uses these calibrated cameras to detect unusual object behaviot: The input rrajectories are metric rectified and #e inpur sequences are registered to rh sarellia imagery and prototype pa# models are constructed. During #e testing phase, using our simple yet eflcient similarity measures, we seek a relationbetween the input trajectories derivedfroma sequencea d h eprotorype path models. Real-world pedesrrian sequences are used ro demonstrate rhepracticality of h e proposed method

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Imran N. Junejo, Hassan Foroosh
• Keywords: Camera Observing Pedestrians, Computer Vision, CVPR 2007, Input Trajectories, Mu& Ling Ina, Multi-camera Video Surveillance, Real-world Pedesrrian Sequences