European Conference on Computer Vision

ECCV 2014: Computer Vision – ECCV 2014 pp 472-487

Deep Learning of Scene-Specific Classifier for Pedestrian Detection

  • Xingyu Zeng
  • Wanli Ouyang
  • Meng Wang
  • Xiaogang Wang
Conference paper

DOI: 10.1007/978-3-319-10578-9_31

Volume 8691 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Zeng X., Ouyang W., Wang M., Wang X. (2014) Deep Learning of Scene-Specific Classifier for Pedestrian Detection. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8691. Springer, Cham

Abstract

The performance of a detector depends much on its training dataset and drops significantly when the detector is applied to a new scene due to the large variations between the source training dataset and the target scene. In order to bridge this appearance gap, we propose a deep model to automatically learn scene-specific features and visual patterns in static video surveillance without any manual labels from the target scene. It jointly learns a scene-specific classifier and the distribution of the target samples. Both tasks share multi-scale feature representations with both discriminative and representative power. We also propose a cluster layer in the deep model that utilizes the scene-specific visual patterns for pedestrian detection. Our specifically designed objective function not only incorporates the confidence scores of target training samples but also automatically weights the importance of source training samples by fitting the marginal distributions of target samples. It significantly improves the detection rates at 1 FPPI by 10% compared with the state-of-the-art domain adaptation methods on MIT Traffic Dataset and CUHK Square Dataset.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Xingyu Zeng
    • 1
  • Wanli Ouyang
    • 1
  • Meng Wang
    • 1
  • Xiaogang Wang
    • 1
    • 2
  1. 1.The Chinese University of Hong KongShatinHong Kong
  2. 2.Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesChina