Pedestrian detection on CAVIAR dataset using a movement feature space

Abstract

This work develops a pedestrian detection system using a feature space based on level lines, called Movement Feature Space (MFS). Besides detecting the movement in the scene, this feature space defines the descriptors used by the classifiers to identify pedestrians. Locations hypotheses of pedestrian are performed by a cascade of boosted classifiers. The validation of these regions of interest is carried out by a Support Vector Machine classifier. Results rise to 81 % of good detection rate, having 0.6 false alarms per image on average on the FRONT VIEW CAVIAR dataset.