Open AccessA Fuzzy rule- based Abandoned Object Detection using Image Fusion for Intelligent Video Surveillance Systems
Author(s) -
K. G. Preetha
Publication year - 2021
Publication title -
türk bilgisayar ve matematik eğitimi dergisi
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.218
H-Index - 3
ISSN - 1309-4653
DOI - 10.17762/turcomat.v12i3.1652
Subject(s) - computer science , artificial intelligence , object (grammar) , face (sociological concept) , object detection , computer vision , process (computing) , fuzzy logic , fuzzy rule , constant false alarm rate , computer security , fuzzy set , pattern recognition (psychology) , social science , sociology , operating system
Abandoned object/luggage is a major threat in all public scenes like hospitals, railway stations, airports and shopping malls. Abandoned luggage may contain explosive, biological warfare or smuggled goods. Abandoned object detection is the process to identify the unattended strange object within a specific time. It is also crucial to identify the person who has abandoned the luggage in the scene. Video surveillance is one of the essential techniques for automatic video analysis to extract crucial information or relevant scenes. The main objectives of this work is the automatic detection of abandoned objects and related persons in public areas like airports, railway stations, shopping malls etc. Video enhancement techniques like residual dense networks are adopted to improve the quality of the image before applying it to detect the abandoned objects and related humans. The scenario of abandoned objects and related humans are identified through distance differencing methods. Once the scene is identified, the method is capable of producing alert messages or alarms in real-time through automated means. A fuzzy rule based threat assessment module is also incorporated in this work which reduces the false alarm rate. The related person is identified through reconstruction of the face through super-resolution techniques. Experiments are found to be appreciable in terms of the metrics in video enhancement, detection, fuzzification and face super-resolution.