The electronic image stabilization technology research based on improved optical-flow motion vector estimation

Chao Wang; Ming Ji; Ying Zhang; Wentao Jiang; Xiaoyan Lu; Jiaoying Wang; Heng Yang

doi:10.1117/12.2229882

26 January 2016 The electronic image stabilization technology research based on improved optical-flow motion vector estimation

Chao Wang, Ming Ji, Ying Zhang, Wentao Jiang, Xiaoyan Lu, Jiaoying Wang, Heng Yang

Author Affiliations +

Proceedings Volume 9796, Selected Papers of the Photoelectronic Technology Committee Conferences held November 2015; 97962U (2016) https://doi.org/10.1117/12.2229882
Event: Selected Proceedings of the Chinese Society for Optical Engineering Conferences held November 2015, 2015, Various, China

Abstract

The electronic image stabilization technology based on improved optical-flow motion vector estimation technique can effectively improve the non normal shift, such as jitter, rotation and so on. Firstly, the ORB features are extracted from the image, a set of regions are built on these features; Secondly, the optical-flow vector is computed in the feature regions, in order to reduce the computational complexity, the multi resolution strategy of Pyramid is used to calculate the motion vector of the frame; Finally, qualitative and quantitative analysis of the effect of the algorithm is carried out. The results show that the proposed algorithm has better stability compared with image stabilization based on the traditional optical-flow motion vector estimation method.

Citation Download Citation

Chao Wang, Ming Ji, Ying Zhang, Wentao Jiang, Xiaoyan Lu, Jiaoying Wang, and Heng Yang "The electronic image stabilization technology research based on improved optical-flow motion vector estimation", Proc. SPIE 9796, Selected Papers of the Photoelectronic Technology Committee Conferences held November 2015, 97962U (26 January 2016); https://doi.org/10.1117/12.2229882

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available