Keypoints-based background model and foreground pedestrian extraction for future smart cameras

Omar Hamdoun (1) , Fabien Moutarde (1)

1 CAOR - Centre de Robotique

In this paper, we present a method for background modeling using only keypoints, and detection of foreground moving pedestrians using background keypoints substraction followed by adaBoost classification of foreground keypoints. A first experimental evaluation shows very promising detection performances in real-time.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Omar Hamdoun, Fabien Moutarde. Keypoints-based background model and foreground pedestrian extraction for future smart cameras. 3rd ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC'2009), Aug 2009, Como, Italy. ⟨hal-00435678⟩