IoT-based crowd monitoring system: Using SSD with transfer learning. (July 2021)

• Record Type: Journal Article
• Authors: Ahmed, Imran; Ahmad, Misbah; Ahmad, Awais; Jeon, Gwanggil
• Is Part Of: Computers & electrical engineering. Volume 93(2021)
• Publication Date: 2021-07
• Subjects: Internet of Things -- Crowd monitoring -- People detection -- People counting -- Overhead view -- Deep learning; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107226
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: The constantly developing urbanization and the emergence of smart cities require better security surveillance and crowd monitoring systems. The growing availability of the Internet of Things (IoT) devices in public and private organizations also provide intelligent and secure surveillance solutions for real-time monitoring in public spaces. This article introduces an IoT-based crowd surveillance system that uses a deep learning model to detect and count people using an overhead view perspective. The Single Shot Multibox Detector (SSD) model with Mobilenetv2 as the basic network is used for the detection of people. The detection model's accuracy is enhanced with a transfer learning approach. Two virtual lines are defined to count how many people are leaving and entering the scene. In order to assess performance, experiments are performed using different video clips. Results indicate that transfer learning increases the overall detection performance of the system with an accuracy of 95%. Graphical abstract: Highlights: This paper presents an IoT-based crowd monitoring system for the detection and counting of people. SSD Mobilenetv2 architecture is used for the detection of people in an overhead view scene. Transfer learning is applied to improve the detection performance of the model. The developed system is also capable of counting people, leaving, and entering the scene using virtual lines. Performance of the system is assessed with both pre-trained and trained learning models using an overhead view data set.