Open AccessUnusual Event Detection using Mean Feature Point Matching Algorithm
Author(s) -
Chitra Hegde,
Shakti Singh Chundawat,
S N Divya
Publication year - 2016
Publication title -
international journal of electrical and computer engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.277
H-Index - 22
ISSN - 2088-8708
DOI - 10.11591/ijece.v6i4.pp1595-1601
Subject(s) - computer science , feature (linguistics) , matching (statistics) , artificial intelligence , pattern recognition (psychology) , similarity (geometry) , domain (mathematical analysis) , feature extraction , event (particle physics) , point (geometry) , task (project management) , image (mathematics) , data mining , mathematics , statistics , mathematical analysis , philosophy , linguistics , physics , geometry , quantum mechanics , management , economics
Analysis and detection of unusual events in public and private surveillance system is a complex task. Detecting unusual events in surveillance video requires the appropriate definition of similarity between events. The key goal of the proposed system is to detect behaviours or actions that can be considered as anomalies. Since suspicious events differ from domain to domain, it remains a challenge to detect those events in major domains such as airport, super malls, educational institutions etc. The proposed Mean Feature Point Matching (MFPM) algorithm is used for detecting unusual events. The Speeded-Up Robust Features (SURF) method is used for feature extraction. The MFPM algorithm compares the feature points of the input image with the mean feature points of trained dataset. The experimental result shows that the proposed system is efficient and accurate for wide variety of surveillance videos.