Robust automatic multi-camera viewpoint stabilization using Harris laplace corner detection and spanning tree

Bhuiyan, Sharif Shah Newaj and Khalifa, Othman Omran (2018) Robust automatic multi-camera viewpoint stabilization using Harris laplace corner detection and spanning tree. In: 2018 7th International Conference on Computer and Communication Engineering (ICCCE), 19th-20th September 2018, Kuala Lumpur.

	PDF - Published Version Restricted to Registered users only Download (944kB) | Request a copy
	PDF (SCOPUS) - Published Version Restricted to Repository staff only Download (594kB) | Request a copy

Abstract

In this paper, an algorithm to improve image stabilization process in 3D for multiple camera viewpoints from different angle is developed. It can automatically simplify the region of interest with unique key-points matching. Harris Laplace corner detection has been used to find accurate matching key points for different photometric changes, scaling in images. Spanning tree has been used to improve the connectivity of correct matching pairs by minimizing the global error value. Spanning tree is the key for stabilized randomly positioned camera viewpoints. It always gives successful stabilization output. This process doesn’t need to analyze the key-points twice. The results show that the proposed algorithm can process more than 120 camera viewpoints in less than two (<2) seconds. It shows a great consistency for different image sets for different viewpoints of cameras.

Item Type:	Conference or Workshop Item (Plenary Papers)
Additional Information:	4119/68113
Uncontrolled Keywords:	Video stabilization, 3D video, Multi-camera system, feature extraction, Video processing
Subjects:	T Technology > T Technology (General) > T10.5 Communication of technical information
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering Kulliyyah of Engineering > Department of Electrical and Computer Engineering
Depositing User:	Prof. Dr Othman O. Khalifa
Date Deposited:	12 Dec 2018 09:27
Last Modified:	13 Feb 2019 19:03
URI:	http://irep.iium.edu.my/id/eprint/68113

Actions (login required)

View Item