Vehicle make and model recognition using sparse representation and symmetrical SURFs

作者：

Highlights：

• A novel idea is proposed to enrich the SURF scheme to detect symmetrical objects.

• A new detection scheme is proposed to detect vehicles from moving cameras.

• A novel sparse representation is proposed to represent and recognize vehicle makes and models.

• An HDC scheme is proposed to classify vehicles to various vehicle categories.

摘要

•A novel idea is proposed to enrich the SURF scheme to detect symmetrical objects.•A new detection scheme is proposed to detect vehicles from moving cameras.•A novel sparse representation is proposed to represent and recognize vehicle makes and models.•An HDC scheme is proposed to classify vehicles to various vehicle categories.

论文关键词：Symmetrical SURF,Sparse representation,Vehicle make and model recognition,Vehicle detection

论文评审过程：Received 8 January 2013, Revised 29 June 2013, Accepted 23 December 2014, Available online 14 January 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.12.018