An improved statistical approach for moving object detection in thermal video frames

In a video surveillance system, background modeling is assumed to be a fundamental technique for moving object detection. The surveillance system based on thermal video overcomes many challenges, such as background variations, varying light intensity, external illumination source, and so on. This pa...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2022-03, Vol.81 (7), p.9289-9311
Main Authors: Rai, Mritunjay, Sharma, Rohit, Satapathy, Suresh Chandra, Yadav, Dileep Kumar, Maity, Tanmoy, Yadav, R. K.
Format: Article
Language:English
Subjects:
1212: Deep Learning Techniques for Infrared Image/Video Understanding
Classification
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Frames (data processing)
Luminous intensity
Modelling
Moving object recognition
Multimedia Information Systems
Special Purpose and Application-Based Systems
Subtraction
Surveillance
Video data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In a video surveillance system, background modeling is assumed to be a fundamental technique for moving object detection. The surveillance system based on thermal video overcomes many challenges, such as background variations, varying light intensity, external illumination source, and so on. This paper presents a new method for background modeling and background subtraction. The method utilizes the combined approach of Fisher's Linear Discriminant and Relative Entropy for pixel based classification and detection of moving objects in thermal video frames. The experimental results show the higher average value of various performance indicators like Accuracy, ROC, and F-measure. In contrast, the percentage of false classification and total error is minimum and also has lesser execution time. The method outperforms when compared with the other existing methods.
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-021-11548-x