Self-calibration method using the orientation- and scale-covariant features in planar scene

Qingkai Hou; Hu Chen; Zhiyun Zhuang; Fuyin Wang; Yanxin Ma; Qiong Yao; Shuidong Xiong

doi:10.1117/12.2575748

10 October 2020 Self-calibration method using the orientation- and scale-covariant features in planar scene

Qingkai Hou, Hu Chen, Zhiyun Zhuang, Fuyin Wang, Yanxin Ma, Qiong Yao, Shuidong Xiong

Proceedings Volume 11552, Optical Metrology and Inspection for Industrial Applications VII; 115521X (2020) https://doi.org/10.1117/12.2575748
Event: SPIE/COS Photonics Asia, 2020, Online Only

Conference Poster

Abstract

A self-calibration method for camera using two views of unknown-structure planar scene is introduced. The planar scene is common in the environment and can be easily identifiable outside the lab. Firstly, two orientation- and scale-covariant features, which can be provided by the SIFT feature detector, is used to estimate the homography of two views. Then the homography is decomposed into the camera parameters. A RANSAC scheme is adapted to cope with the outliers of SIFT correspondences. Finally, the camera parameters are optimized with a non-linear parameter optimization using the inliers of two views. This method calibrates the camera parameters and recovers the planar scenes simultaneously. Real scene data experiment demonstrates that the proposed method is easy to operate and provides the reliable calibration results for non-expert users.

Conference Presentation

Citation Download Citation

Qingkai Hou, Hu Chen, Zhiyun Zhuang, Fuyin Wang, Yanxin Ma, Qiong Yao, and Shuidong Xiong "Self-calibration method using the orientation- and scale-covariant features in planar scene", Proc. SPIE 11552, Optical Metrology and Inspection for Industrial Applications VII, 115521X (10 October 2020); https://doi.org/10.1117/12.2575748

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