Share Email Print

Proceedings Paper

Video-based violence detection by human action analysis with neural network
Author(s): Yunqing Zhao; Wilton W. T. Fok; C. W. Chan
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In recent years, human action analysis is a focal point in video processing, especially on action recognition and safety surveillance. It always performs as an auxiliary tool to minimize the manpower-resource on special tasks. This paper explores the human action analysis in a specified situation, based on the human posture extraction by pose-estimation algorithm. Deep neural network (DNN) methods was used, composed of residual learning blocks for feature extraction and recurrent neural network for time-series data learning. All these modules can be applied on real-time videos, classifying different security levels of actions between two people, with 91.8% accuracy on test set. Meanwhile, some other classical network structures were compared as baselines. After forward inference process of the neural network model, a logic enhancement algorithm was raised and applied in this paper, due to the prediction error between two classes. Experiments were conducted on real-time videos, achieving satisfying performance.

Paper Details

Date Published: 27 November 2019
PDF: 8 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113212N (27 November 2019); doi: 10.1117/12.2543564
Show Author Affiliations
Yunqing Zhao, The Univ. of Hong Kong (Hong Kong, China)
Wilton W. T. Fok, The Univ. of Hong Kong (Hong Kong, China)
C. W. Chan, The Univ. of Hong Kong (Hong Kong, China)

Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?