Research of method in human detection based on bandelet transform

Hong Han, Xing Wu, Licheng Jiao, Lichuan YueProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2009 · DOI

Abstract

Based on the geometric flow of images and the second generation bandelet transform, a new feature extraction method was proposed and used to detect human in images. In this paper, bandelet coefficients and their statistical values were extracted as the feature of human images, combined with linear SVM classifier to classify and detect human in images. In the proposed algorithm, some general statistical values of the bandelet coefficients were computed to enhance the classification capacity. The results of human detection experiments indicate that the proposed method can describe human characteristics and improve the performance of classifier effectively. It is very suitable for human detection in images.
BibTeX
@inproceedings{han2009research,
  author = {Hong Han and Xing Wu and Licheng Jiao and Lichuan Yue},
  title = {{Research of method in human detection based on bandelet transform}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2009},
  doi = {10.1117/12.832905},
}

Loading related content...

Figure