Visualization on colour based flow vector of thermal image for movement detection during interactive session

Ibrahim, Nabilah and Raman, Mohamad Nurazmi and Mahadi, Lina Farhana and Wan Zakaria, Wan Nurshazwani (2018) Visualization on colour based flow vector of thermal image for movement detection during interactive session. Journal of Physics: Conference Series, 1049. pp. 1-8. ISSN 1742-6588

[img] Text
AJ 2019 (70).pdf
Restricted to Registered users only

Download (558kB) | Request a copy

Abstract

Recently thermal imaging is exploited in applications such as motion and face detection. It has drawn attention many researchers to build such technology to improve lifestyle. This work proposed a technique to detect and identify a motion in sequence images for the application in security monitoring system or outdoor surveillance. Conventional system might cause false information with the present of shadow. Thus, methods employed in this work are Canny edge detector method, Lucas Kanade and Horn Shunck algorithms, to overcome the major problem when using thresholding method, which is only intensity or pixel magnitude is considered instead of relationships between the pixels. The results obtained could be observed in flow vector parameter and the segmentation colour based image for the time frame from 1 to 10 seconds. The visualization of both the parameters clarified the movement and changes of pixel intensity between two frames by the supportive colour segmentation, either in smooth or rough motion. Thus, this technique may contribute to others application such as biometrics, military system, and surveillance machine.

Item Type: Article
Uncontrolled Keywords: NIL
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions: Faculty of Electrical and Electronic Engineering > Department of Electronic Enngineering
Depositing User: Miss Afiqah Faiqah Mohd Hafiz
Date Deposited: 16 Nov 2021 04:15
Last Modified: 16 Nov 2021 04:15
URI: http://eprints.uthm.edu.my/id/eprint/2907

Actions (login required)

View Item View Item