Sciweavers

Share
CVPR
2010
IEEE

New Features and Insights for Pedestrian Detection

10 years 8 months ago
New Features and Insights for Pedestrian Detection
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...
Stefan Walk, Nikodem Majer, Konrad Schindler, Bern
Added 04 Apr 2010
Updated 08 Sep 2010
Type Conference
Year 2010
Where CVPR
Authors Stefan Walk, Nikodem Majer, Konrad Schindler, Bernt Schiele
Comments (0)
books