Share Email Print

Optical Engineering

Causality-weighted active learning for abnormal event identification based on the topic model
Author(s): Yawen Fan; Shibao Zheng; Hua Yang; Chongyang Zhang; Hang Su
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Abnormal event identification in crowded scenes is a fundamental task for video surveillance. However, it is still challenging for most current approaches because of the general insufficiency of labeled data for training, particularly for abnormal data. We propose a novel active-supervised joint topic model for learning activity and training sample collection. First, a multi-class topic model is constructed based on the initial training data. Then the remaining unlabeled data stream is surveyed. The system actively decides whether it can label a new sample by itself or if it has to ask a human annotator. After each query, the current model is incrementally updated. To alleviate class imbalance, causality-weighted method is applied to both likelihood and uncertainty sampling for active learning. Furthermore, a combination of a new measure termed query entropy and the overall classification accuracy is used for assessing the model performance. Experimental results on two real-world traffic videos for abnormal event identification tasks demonstrate the effectiveness of the proposed method.

Paper Details

Date Published: 6 July 2012
PDF: 13 pages
Opt. Eng. 51(7) 077204 doi: 10.1117/1.OE.51.7.077204
Published in: Optical Engineering Volume 51, Issue 7
Show Author Affiliations
Yawen Fan, Shanghai Jiao Tong Univ. (China)
Shibao Zheng, Shanghai Jiao Tong Univ. (China)
Hua Yang, Shanghai Jiao Tong Univ. (China)
Chongyang Zhang, Shanghai Jiao Tong Univ. (China)
Hang Su, Shanghai Jiao Tong Univ. (China)

© SPIE. Terms of Use
Back to Top