IA-SSLM: Irregularity-Aware Semi-Supervised Deep Learning Model for Analyzing Unusual Events in Crowds
Open Access
- 17 May 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 73327-73334
Abstract
Analyzing unusual events is significantly important for video surveillance to ensure people safety. These events are characterized by irregular patterns that do not conform to the expected behavior in the surveillance scenes. We present a novel irregularity-aware semi-supervised deep learning model (IA-SSLM) for detection of unusual events. While most existing works depend on the availability of large amount of labeled data for training, our proposed method utilizes a semi-supervised deep model to automatically learn feature representations from limited number of labeled data samples. Our method extracts meaningful information from both labeled and unlabeled data during the training stage to improve the performance. For this purpose, we explore the concept of consistency regularization and entropy minimization to output confident predictions on unlabeled data. For experimental analysis, we consider various standard and diverse datasets. The results show that our IA-SSLM method outperforms several reference methods using different performance metrics.Keywords
This publication has 29 references indexed in Scilit:
- Structured dictionary learning for abnormal event detection in crowded scenesPattern Recognition, 2018
- Automated unusual event detection in video surveillance2016
- Wide Residual Networks2016
- Trajectory‐based anomalous behaviour detection for intelligent traffic surveillanceIET Intelligent Transport Systems, 2015
- Video anomaly detection and localization using hierarchical feature representation and Gaussian process regression2015
- Unusual event detection in crowded scenes by trajectory analysis2015
- Violent flows: Real-time detection of violent crowd behavior2012
- Online detection of unusual events in videos via dynamic sparse coding2011
- Motion-based unusual event detection in human crowdsJournal of Visual Communication and Image Representation, 2011
- Deep, Big, Simple Neural Nets for Handwritten Digit RecognitionNeural Computation, 2010