3D-Convolutional Neural Network with Generative Adversarial Network and Autoencoder for Robust Anomaly Detection in Video Surveillance.

Journal: International journal of neural systems
PMID:

Abstract

As the surveillance devices proliferate, various machine learning approaches for video anomaly detection have been attempted. We propose a hybrid deep learning model composed of a video feature extractor trained by generative adversarial network with deficient anomaly data and an anomaly detector boosted by transferring the extractor. Experiments with UCSD pedestrian dataset show that it achieves 94.4% recall and 86.4% precision, which is the competitive performance in video anomaly detection.

Authors

  • Wonsup Shin
    Department of Computer Science, Yonsei University, 50 Yonsei-ro, Sudaemoon-gu, Seoul 03722, South Korea.
  • Seok-Jun Bu
    Department of Computer Science, Yonsei University, 50 Yonsei-ro, Sudaemoon-gu, Seoul 03722, South Korea.
  • Sung-Bae Cho
    Department of Computer Science, Yonsei University, Seoul, South Korea. Electronic address: sbcho@cs.yonsei.ac.kr.