A novel framework for detection of motion and appearance-based Anomaly using ensemble learning and LSTMs. (15th April 2022)

• Record Type: Journal Article
• Authors: Sabih, Mohammad; Vishwakarma, Dinesh Kumar
• Is Part Of: Expert systems with applications. Volume 192(2022)
• Publication Date: 2022-04-15
• Subjects: Optical flow -- Bidirectional LSTM -- Ensemble learning -- Weighted loss; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.116394
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A novel supervised methodology to detect motion and appearance-based Anomaly. An ensemble learning strategy to boost the models' performance. Weighted loss is used to encounter the heavy data imbalance. Abstract: The variable time-dependent densities in crowd motion and several occlusions in real scenarios make the task of spotting anomalies very laborious. Also, an anomalous entity can be perceived to be non-anomalous from a different angle of perception. The proposed methodology introduces a novel framework for crowd anomaly detection at a patch level by integrating a thread of bi-directional LSTM for motion-based Anomaly and a thread of ensemble learning which uses pre-trained CONV-nets to learn appearance-based anomalies. A novel post-processing step to address the underlying false predictions using a threshold comparator system is also introduced. The proposed methodology is tested on the benchmark datasets, namely UCSD PED-1, PED-2, and UMN dataset, and it performs comparably with the other existing methods in the literature.