Robust uncalibrated stereo rectification with constrained geometric distortions (USR-CGD)
作者：
Highlights：
• Uncalibrated stereo rectification with constrained geometric distortions is proposed.
• It provides a balanced performance between rectification and geometric errors.
• The generalized homography is proposed to reduce the rectification model error.
• The novel optimization scheme with geometric regularization terms is proposed.
• The superiority of the proposed method is proved by extensive experimental results.
摘要
•Uncalibrated stereo rectification with constrained geometric distortions is proposed.•It provides a balanced performance between rectification and geometric errors.•The generalized homography is proposed to reduce the rectification model error.•The novel optimization scheme with geometric regularization terms is proposed.•The superiority of the proposed method is proved by extensive experimental results.
论文关键词：Projective rectification,Regularization,Homography,Epipolar geometry,Fundamental matrix,Geometric distortion,Constrained optimization
论文评审过程：Received 5 May 2016, Revised 12 October 2016, Accepted 2 January 2017, Available online 9 January 2017, Version of Record 22 March 2017.
论文官网地址：https://doi.org/10.1016/j.imavis.2017.01.001
