6 July 2012 Causality-weighted active learning for abnormal event identification based on the topic model
Author Affiliations +
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.
© 2012 Society of Photo-Optical Instrumentation Engineers (SPIE)
Yawen Fan, Yawen Fan, Shibao Zheng, Shibao Zheng, Hua Yang, Hua Yang, Chongyang Zhang, Chongyang Zhang, Hang Su, Hang Su, } "Causality-weighted active learning for abnormal event identification based on the topic model," Optical Engineering 51(7), 077204 (6 July 2012). https://doi.org/10.1117/1.OE.51.7.077204 . Submission:
JOURNAL ARTICLE
13 PAGES


SHARE
RELATED CONTENT

Learning object models from few examples
Proceedings of SPIE (May 12 2016)
Imperfect learning for autonomous concept modeling
Proceedings of SPIE (January 16 2005)

Back to Top