Abnormal Event Detection Based on Deep Autoencoder Fusing Optical Flow

Meina Qiao, Tian Wang, Jiakun Li, Ce Li, Zhiwei Lin, Hichem Snoussi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)
189 Downloads (Pure)

Abstract

As an important research topic in computer vision, abnormal detection has gained more and more attention. In order to detect abnormal events effectively, we propose a novel method using optical flow and deep autoencoder. In our model, optical flow of the original video sequence is calculated and visualized as optical flow image, which is then fed into a deep autoencoder. Then the deep autoencoder extract features from the training samples which are compressed to low dimension vectors. Finally, the normal and abnormal samples gather separately in the coordinate axis. In the evaluation, we show that our approach outperforms the existing methods in different scenes, in terms of accuracy.
Original languageEnglish
Title of host publicationUnknown Host Publication
PublisherIEEE
Pages11098-11103
Number of pages6
ISBN (Print)978-988-15639-3-4
Publication statusE-pub ahead of print - 11 Sep 2017
EventThe Chinese Control Conference 2017 - Dalian, China
Duration: 11 Sep 2017 → …

Conference

ConferenceThe Chinese Control Conference 2017
Period11/09/17 → …

    Fingerprint

Keywords

  • Abnormal detection
  • Deep autoencoder
  • Optical flow

Cite this

Qiao, M., Wang, T., Li, J., Li, C., Lin, Z., & Snoussi, H. (2017). Abnormal Event Detection Based on Deep Autoencoder Fusing Optical Flow. In Unknown Host Publication (pp. 11098-11103). IEEE.