Improving person detection using synthetic training data

Jie Yu, Dirk Farin, Christof Kruger, Bernt Schiele

Abstract

Person detection in complex real-world scenes is a challenging problem. State-of-the-art methods typically use supervised learning relying on significant amounts of training data to achieve good detection results. However, labeling training data is tedious, expensive, and error-prone. This paper presents a novel method to improve detection performance by supplementing real-world data with synthetically generated training data. We consider the case of detecting people in crowded scenes within an AdaBoost-framework employing Haar and Histogram-of-Oriented-Gradients (HOG) features. Our evaluations on real-world video sequences of crowded scenes with significant occlusions show that the combination of real and synthetic training data significantly improves overall detection results.
BibTeX
@inproceedings{yu2010improving,
  author = {Jie Yu and Dirk Farin and Christof Kruger and Bernt Schiele},
  title = {{Improving person detection using synthetic training data}},
  booktitle = {ICIP},
  year = {2010},
  doi = {10.1109/icip.2010.5650143},
}

Loading related content...

Figure