New features and insights for pedestrian detection
Top Cited Papers
- 1 June 2010
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1030-1037
- https://doi.org/10.1109/cvpr.2010.5540102
Abstract
Despite impressive progress in people detection the performance on challenging datasets like Caltech Pedestrians or TUD-Brussels is still unsatisfactory. In this work we show that motion features derived from optic flow yield substantial improvements on image sequences, if implemented correctly - even in the case of low-quality video and consequently degraded flow fields. Furthermore, we introduce a new feature, self-similarity on color channels, which consistently improves detection performance both for static images and for video sequences, across different datasets. In combination with HOG, these two features outperform the state-of-the-art by up to 20%. Finally, we report two insights concerning detector evaluations, which apply to classifier-based object detection in general. First, we show that a commonly under-estimated detail of training, the number of bootstrapping rounds, has a drastic influence on the relative (and absolute) performance of different feature/classifier combinations. Second, we discuss important intricacies of detector evaluation and show that current benchmarking protocols lack crucial details, which can distort evaluations.Keywords
This publication has 20 references indexed in Scilit:
- Human detection using partial least squares analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Implicit color segmentation features for pedestrian and object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Multi-cue onboard pedestrian detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A discriminatively trained, multiscale, deformable part modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Classification using intersection kernel support vector machines is efficientPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Detecting Pedestrians by Learning Shapelet FeaturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part DetectorsInternational Journal of Computer Vision, 2007
- Multi-cue Pedestrian Detection and Tracking from a Moving VehicleInternational Journal of Computer Vision, 2006
- Pedestrian detection for driving assistance systems: single-frame classification and system level performancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- A Trainable System for Object DetectionInternational Journal of Computer Vision, 2000