ウェーブレット処理とSVMを用いたMHIによる不審動作監視

Bibliographic Information

Other Title
  • Unusual behavior monitoring method using MHI by wavelet preprocessing and support vector machine
  • ウェーブレット ショリ ト SVM オ モチイタ MHI ニヨル フシンドウサ カンシ

Search this article

Abstract

This paper prescribes an approach for providing a method of detecting unusual human behavior from video images processed by Motion History Image (MHI) method. The video input data are pre- processed by Gabor filter or Haar wavelet transform and formulate MHI which are classified by SVM learning examples of usual and unusual behaviors. The four types characteristic features derived from MHI data are evaluated.

Journal

Related Projects

See more

Details 詳細情報について

Report a problem

Back to top