Efficient and accurate set-based registration of time-separated aerial images
作者：
Highlights：
• Existing work limited to pair-wise or ad hoc extensions of pair-wise registrations.
• Quasi-invariant representation employed at the local (in image space) level.
• Coarse-to-fine approach used for increased accuracy and reliability.
• Constraints graph used to propagate local information across the image set.
• State-of-the-art significantly outperformed in accuracy, reliability, and speed.
摘要
Highlights•Existing work limited to pair-wise or ad hoc extensions of pair-wise registrations.•Quasi-invariant representation employed at the local (in image space) level.•Coarse-to-fine approach used for increased accuracy and reliability.•Constraints graph used to propagate local information across the image set.•State-of-the-art significantly outperformed in accuracy, reliability, and speed.
论文关键词：Remote,Sensing,Alignment,Map,Graph,Constraints
论文评审过程：Received 23 May 2014, Revised 25 March 2015, Accepted 8 April 2015, Available online 17 April 2015, Version of Record 16 July 2015.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.04.011
