Surveillance video analysis for student action recognition and localization inside computer laboratories of a smart camp
- PDF / 3,221,633 Bytes
- 23 Pages / 439.642 x 666.49 pts Page_size
- 104 Downloads / 217 Views
Surveillance video analysis for student action recognition and localization inside computer laboratories of a smart campus M. Rashmi1 · T. S. Ashwin1
· Ram Mohana Reddy Guddeti1
Received: 5 August 2019 / Revised: 26 July 2020 / Accepted: 26 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In the era of smart campus, unobtrusive methods for students’ monitoring is a challenging task. The monitoring system must have the ability to recognize and detect the actions performed by the students. Recently many deep neural network based approaches have been proposed to automate Human Action Recognition (HAR) in different domains, but these are not explored in learning environments. HAR can be used in classrooms, laboratories, and libraries to make the teaching-learning process more effective. To make the learning process more effective in computer laboratories, in this study, we proposed a system for recognition and localization of student actions from still images extracted from (Closed Circuit Television) CCTV videos. The proposed method uses (You Only Look Once) YOLOv3, state-of-the-art real-time object detection technology, for localization, recognition of students’ actions. Further, the image template matching method is used to decrease the number of image frames and thus processing the video quickly. As actions performed by the humans are domain specific and since no standard dataset is available for students’ action recognition in smart computer laboratories, thus we created the STUDENT ACTION dataset using the image frames obtained from the CCTV cameras placed in the computer laboratory of a university campus. The proposed method recognizes various actions performed by students in different locations within an image frame. It shows excellent performance in identifying the actions with more samples compared to actions with fewer samples. Keywords Human action recognition · Smart campus · Object detection · Object localization · Neural networks · Computer enabled laboratories M. Rashmi
[email protected] T. S. Ashwin [email protected] Ram Mohana Reddy Guddeti [email protected] 1
Department of Information Technology, National Institute of Technology Karnataka Surathkal, Mangalore, 575025, India
Multimedia Tools and Applications
1 Introduction Incorporating the human ability to recognize another person’s actions to a machine is one of the challenging scientific research area in computer vision and machine learning. Automated video analysis systems can detect events related to human actions or human behavior and thus play an essential role in surveillance systems. Many researchers have worked on image and video analysis for the past several years to tackle different problems like object detection and localization, action recognition, and event recognition. HAR is a process in which the model interprets the action performed by a human, such as eating, smiling, cycling, etc. Automated video analysis systems that can interpret the events related to human actio
Data Loading...
