Detecting pedestrians at very small scales

Luciano Spinello, A. Macho, Rudolph Triebel, Roland SiegwartIROS 2009 · OpenReview

Abstract

This paper presents a novel image based detection method for pedestrians at very small scales (between 16 × 20 and 32 × 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.
BibTeX
@inproceedings{spinello2009detecting,
  author = {Luciano Spinello and A. Macho and Rudolph Triebel and Roland Siegwart},
  title = {{Detecting pedestrians at very small scales}},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  year = {2009},
  url = {https://openreview.net/forum?id=eyoW4KEFVa},
}

Loading related content...

Figure