Vehicle verification between two nonoverlapped views using sparse representation

作者：

Highlights：

• The proposed system can be applied to vehicle verification under non-overlapped views of which the shapes and illuminations of vehicles are different.

• Propose a novel sparse dictionary learning approach, Boost K-SVD, for vehicle verification.

• The generated dictionary provides good RIP and sparser representation for samples.

• The better dictionary, the better pair verification can be promised.

• An adaptive dictionary size estimation is proposed to estimate optimal sizes for different datasets.

摘要

•The proposed system can be applied to vehicle verification under non-overlapped views of which the shapes and illuminations of vehicles are different.•Propose a novel sparse dictionary learning approach, Boost K-SVD, for vehicle verification.•The generated dictionary provides good RIP and sparser representation for samples.•The better dictionary, the better pair verification can be promised.•An adaptive dictionary size estimation is proposed to estimate optimal sizes for different datasets.

论文关键词：Boost K-SVD,K-SVD,Vehicle verification,Atom initializing,Restricted isometry property (RIP)

论文评审过程：Received 1 March 2017, Revised 7 February 2018, Accepted 25 February 2018, Available online 7 March 2018, Version of Record 9 April 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.02.031