Anomalous Human Activity Recognition in Surveillance Videos
Raksha S1, B G Prasad2
1Raksha S, Department of Computer Science and Engineering, B.M.S College of Engineering, Bangalore (Karnataka), India.
2Dr. B G Prasad, Department of Computer Science and Engineering, B.M.S College of Engineering, Bangalore (Karnataka), India.
Manuscript received on 04 August 2019 | Revised Manuscript received on 27 August 2019 | Manuscript Published on 05 September 2019 | PP: 350-355 | Volume-8 Issue-2S7 July 2019 | Retrieval Number: B10640782S719/2019©BEIESP | DOI: 10.35940/ijrte.B1064.0782S719
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper is a survey on different approaches for Human Activity recognition which has utmost significance in pervasive computing due to its many applications in real-life. Human-oriented problems such as security can be easily taken care of by detecting abnormal behavior. Accurate human activity recognition in real-time is challenging because human activities are complicated and extremely diverse in nature. The traditional Closed-circuit Television (CCTV) system requires to be monitored all the time by a human being, which is inefficient and costly. Therefore, there is a need for a system which can recognize human activity effectively in real-time. It is time-consuming to determine the activity from a surveillance video, due to its size, hence there is a need to compress the video using adaptive compression approaches. Adaptive video compression is a technique that compresses only those parts of the video in which there is least focus, and the rest is not compressed. The objective of the discussion is to be able to implement an automated anomalous human activity recognition system which uses surveillance video to capture the occurrence of an unusual event and caution the user in real-time. So, the paper has two parts that include adaptive video compression approaches of the surveillance videos and providing that compressed video as the input to detect anomalous human activity.
Keywords: Human Activity Recognition, Adaptive Video Compression, Vision-based Human Activity Recognition, Anomaly Detection.
Scope of the Article: Pattern Recognition