Sie sind nicht angemeldet Anmelden | Anmelden
max planck institut
» Home » Departments »

New Features and Insights for Pedestrian Detection

New Features and Insights for Pedestrian Detection

Stefan Walk, Nikodem Majer, Konrad Schindler and Bernt Schiele
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010), June 13-18, 2010, San Francisco, California, USA

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.







For further information and questions please contact Stefan Walk, Nikodem Majer, Konrad Schindler or Bernt Schiele.



alte website