The Community for Technology Leaders
2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) (2018)
San Diego, CA, USA
July 23, 2018 to July 27, 2018
ISBN: 978-1-5386-4196-5
pp: 1-6
Kun Zhao , School of Information Science and Technology, University of Science and Technology of China Key Laboratory of Electromagnetic Space Information the Chinese Academy of Sciences
Bin Liu , School of Information Science and Technology, University of Science and Technology of China Key Laboratory of Electromagnetic Space Information the Chinese Academy of Sciences
Weihai Li , School of Information Science and Technology, University of Science and Technology of China Key Laboratory of Electromagnetic Space Information the Chinese Academy of Sciences
Nenghai Yu , School of Information Science and Technology, University of Science and Technology of China Key Laboratory of Electromagnetic Space Information the Chinese Academy of Sciences
Zhiqiang Liu , School of Information Science and Technology, University of Science and Technology of China Key Laboratory of Electromagnetic Space Information the Chinese Academy of Sciences
ABSTRACT
Detecting and locating anomalies defined as unusual and irregular behaviors are important for public security in surveillance videos. In this paper, we propose a novel feature called Point Trajectory-based Histogram of Optical Flow (PT-HOF) to better capture the fine-grained spatial and temporal information along the point trajectory in crowd scenes. By encoding the extracted features through an unsupervised autoencoder network, the high-level representation features are used to build a Gaussian Mixture Model for estimating the anomaly likelihood of each trajectory. Furthermore, the consistency motion object (CMO) is constructed by clustering similar point trajectories in a local region to analyze the spatial structure of trajectories, which can improve the accuracy of anomaly localization. Experiments on two benchmark datasets demonstrate the advantage of the proposed algorithm by comparing with state-of-the-art methods.
INDEX TERMS
Anomaly detection, PT-HOF, consistency motion object
CITATION

K. Zhao, B. Liu, W. Li, N. Yu and Z. Liu, "Anomaly Detection and Localization: A Novel Two-Phase Framework Based on Trajectory-Level Characteristics," 2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), San Diego, CA, USA, 2018, pp. 1-6.
doi:10.1109/ICMEW.2018.8551517
339 ms
(Ver 3.3 (11022016))