Detecting pedestrians at very small scales

— This paper presents a novel image based detection method for pedestrians at very small scales (between 16 x 20 and 32 x 40). We propose a set of new distinctive image features based on collections of local image gradients grouped by a superpixel segmentation. Features are collected and classified using AdaBoost. The positive classified features then vote for potential hypotheses that are collected using a mean shift mode estimation approach. The presented method overcomes the common limitations of a sliding window approach as well as those of standard voting approaches based on interest points. Extensive tests have been produced on a dataset with more than 20000 images showing the potential of this approach.

• Type: Conference
• Year: 2009
• Where: IROS
• Authors: Luciano Spinello, A. Macho, Rudolph Triebel, Roland Siegwart
• Keywords: Distinctive Image Features, Image Based Detection, IROS 2009, Mode Estimation Approach, Robotics