Abnormal behavior detection is now a widely concerned research field, especially for crowded scenes. However, most traditional unsupervised approaches often suffered from the problem when the normal events in the scenario with large visual variety. This paper proposes a self-learning probabilistic Latent Semantic Analysis, which aims at taking full advantage of the high-level abnormal information to solve problems. We select the informative observations to construct the “reference events” from the training sets as a high-level guidance cue. Specifically, the training set is randomly divided into two separate subsets. One is used to learn this model, which is defined as the initialization sequence of “reference events”. The other aims to update this model and the the infrequent samples are chosen into the “reference events”. Finally, we define anomalies using events that are least similar to “reference events”. The experimental result demonstrates that the proposed model can detect anomalies accurately and robustly in the real-world crowd environment.
Shuoyan LIU
China Academy of Railway Sciences
Enze YANG
China Academy of Railway Sciences
Kai FANG
China Academy of Railway Sciences
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Shuoyan LIU, Enze YANG, Kai FANG, "Self-Learning pLSA Model for Abnormal Behavior Detection in Crowded Scenes" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 3, pp. 473-476, March 2021, doi: 10.1587/transinf.2020EDL8115.
Abstract: Abnormal behavior detection is now a widely concerned research field, especially for crowded scenes. However, most traditional unsupervised approaches often suffered from the problem when the normal events in the scenario with large visual variety. This paper proposes a self-learning probabilistic Latent Semantic Analysis, which aims at taking full advantage of the high-level abnormal information to solve problems. We select the informative observations to construct the “reference events” from the training sets as a high-level guidance cue. Specifically, the training set is randomly divided into two separate subsets. One is used to learn this model, which is defined as the initialization sequence of “reference events”. The other aims to update this model and the the infrequent samples are chosen into the “reference events”. Finally, we define anomalies using events that are least similar to “reference events”. The experimental result demonstrates that the proposed model can detect anomalies accurately and robustly in the real-world crowd environment.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDL8115/_p
Copy
@ARTICLE{e104-d_3_473,
author={Shuoyan LIU, Enze YANG, Kai FANG, },
journal={IEICE TRANSACTIONS on Information},
title={Self-Learning pLSA Model for Abnormal Behavior Detection in Crowded Scenes},
year={2021},
volume={E104-D},
number={3},
pages={473-476},
abstract={Abnormal behavior detection is now a widely concerned research field, especially for crowded scenes. However, most traditional unsupervised approaches often suffered from the problem when the normal events in the scenario with large visual variety. This paper proposes a self-learning probabilistic Latent Semantic Analysis, which aims at taking full advantage of the high-level abnormal information to solve problems. We select the informative observations to construct the “reference events” from the training sets as a high-level guidance cue. Specifically, the training set is randomly divided into two separate subsets. One is used to learn this model, which is defined as the initialization sequence of “reference events”. The other aims to update this model and the the infrequent samples are chosen into the “reference events”. Finally, we define anomalies using events that are least similar to “reference events”. The experimental result demonstrates that the proposed model can detect anomalies accurately and robustly in the real-world crowd environment.},
keywords={},
doi={10.1587/transinf.2020EDL8115},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Self-Learning pLSA Model for Abnormal Behavior Detection in Crowded Scenes
T2 - IEICE TRANSACTIONS on Information
SP - 473
EP - 476
AU - Shuoyan LIU
AU - Enze YANG
AU - Kai FANG
PY - 2021
DO - 10.1587/transinf.2020EDL8115
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2021
AB - Abnormal behavior detection is now a widely concerned research field, especially for crowded scenes. However, most traditional unsupervised approaches often suffered from the problem when the normal events in the scenario with large visual variety. This paper proposes a self-learning probabilistic Latent Semantic Analysis, which aims at taking full advantage of the high-level abnormal information to solve problems. We select the informative observations to construct the “reference events” from the training sets as a high-level guidance cue. Specifically, the training set is randomly divided into two separate subsets. One is used to learn this model, which is defined as the initialization sequence of “reference events”. The other aims to update this model and the the infrequent samples are chosen into the “reference events”. Finally, we define anomalies using events that are least similar to “reference events”. The experimental result demonstrates that the proposed model can detect anomalies accurately and robustly in the real-world crowd environment.
ER -