ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

A Real Time Abandoned Object Detection and Addressing using IoT

Journal: International Journal of Computational Engineering Research(IJCER) (Vol.07, No. 05)

Publication Date:

Authors : ; ;

Page : 24-28

Keywords : Abandoned object detection; Object detection and tracking; SVM classifier; Visual surveillance.;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Most of the bomb blast were done with the help of abandoned objects. So, effective and efficient detection and Real time localization of abandoned objects is very important to prevent attacks. This paper gives an algorithm for detection with less complexity. For foreground detection two background short term and long term are constructed and updated continuously in real time. For change detection Mean-ratio and Log-ratio operators are used. To achieve higher accuracy fusion and fuzzy clustering can be applied on both outputs. Motion based criteria needs to be applied for static and moving object detection. SMV classifier is used to recognize the left-baggage. Proposed method in this paper can figure out very small abandoned objects with low quality video frames, and it is also vigorous the varying illuminations and dynamic background. It is most important to develop a system with careful control of false alarm.

Last modified: 2017-05-10 19:09:11