Efficient anomaly recognition using surveillance videos

Gulshan Saleem; Usama Ijaz Bajwa; Rana Hammad Raza; Fayez Hussain Alqahtani; Amr Tolba; Feng Xia

doi:10.7717/peerj-cs.1117

Efficient anomaly recognition using surveillance videos

PeerJ Comput Sci. 2022 Oct 14:8:e1117. doi: 10.7717/peerj-cs.1117. eCollection 2022.

Authors

Gulshan Saleem¹, Usama Ijaz Bajwa¹, Rana Hammad Raza², Fayez Hussain Alqahtani³, Amr Tolba⁴, Feng Xia⁵

Affiliations

¹ Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Lahore, Pakistan.
² Electronics and Power Engineering Department, Pakistan Navy Engineering College (PNEC), National University of Sciences and Technology (NUST), Karachi, Pakistan.
³ Software Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia.
⁴ Computer Science Department, Community College, King Saud University, Riyadh, Saudi Arabia.
⁵ School of Engineering, IT and Physical Sciences, Federation University Australia, Ballarat, Australia.

Abstract

Smart surveillance is a difficult task that is gaining popularity due to its direct link to human safety. Today, many indoor and outdoor surveillance systems are in use at public places and smart cities. Because these systems are expensive to deploy, these are out of reach for the vast majority of the public and private sectors. Due to the lack of a precise definition of an anomaly, automated surveillance is a challenging task, especially when large amounts of data, such as 24/7 CCTV footage, must be processed. When implementing such systems in real-time environments, the high computational resource requirements for automated surveillance becomes a major bottleneck. Another challenge is to recognize anomalies accurately as achieving high accuracy while reducing computational cost is more challenging. To address these challenge, this research is based on the developing a system that is both efficient and cost effective. Although 3D convolutional neural networks have proven to be accurate, they are prohibitively expensive for practical use, particularly in real-time surveillance. In this article, we present two contributions: a resource-efficient framework for anomaly recognition problems and two-class and multi-class anomaly recognition on spatially augmented surveillance videos. This research aims to address the problem of computation overhead while maintaining recognition accuracy. The proposed Temporal based Anomaly Recognizer (TAR) framework combines a partial shift strategy with a 2D convolutional architecture-based model, namely MobileNetV2. Extensive experiments were carried out to evaluate the model's performance on the UCF Crime dataset, with MobileNetV2 as the baseline architecture; it achieved an accuracy of 88% which is 2.47% increased performance than available state-of-the-art. The proposed framework achieves 52.7% accuracy for multiclass anomaly recognition on the UCF Crime2Local dataset. The proposed model has been tested in real-time camera stream settings and can handle six streams simultaneously without the need for additional resources.

Keywords: Anomaly recognition; Crime detection; Deep learning; Video analysis; Video surveillance.

Grants and funding

Gulshan Saleem, Usama Ijaz Bajwa, and Rana Hammad Raza received support for this study from the National Center of Big Data and Cloud Computing (NCBC) and the HEC of Pakistan. Fayez Hussain Alqahtani and Amr Tolba received funding for this work from the Researchers Supporting Project No. (RSP2022R509) at King Saud University, Riyadh, Saudi Arabia. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.