A Vision Based Approach for Anomaly Detection in Smart Environments Using Thermal Images
Harsh Motka1, Latha Parameswaran2
1Harsh Motka, Department of Computer Science and Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore (Tamil Nadu), India.
2Latha Parameswaran, Department of Computer Science and Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore (Tamil Nadu), India.
Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 2838-2844 | Volume-8 Issue-7, May 2019 | Retrieval Number: G5973058719/19©BEIESP
Open Access | Ethics and 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: A process of identifying, accumulating the infrared heat radiation into a form of visible images which in turn forms a thermal images. These thermal images are useful for anomaly detection in critical applications. Infrared radiations from the objects vary from each other considering the environmental conditions. Heat maps can be generated based on the amount of heat radiation collected. Those generated heat maps can be analyzed using image processing approaches. In this paper, an attempt has been made to identify or predict possible outbreak of fire due to very high heat emission by objects using thermal images for any environment. Required features from the acquired thermal images are extracted using image processing algorithm for analyzation. Using extracted features, decision tree classification is used to detect anomaly. Experimental results show promising direction to detect anomaly towards disaster management. Using the proposed method 91% of accuracy was obtained in detecting possible fire break out.
Keyword: Decision Tree, Feature Extraction, Thermal Infrared Imaging.
Scope of the Article: Search-Based Software Engineering