Learning discriminated and correlated patches for multi-view object detection using sparse coding

作者：

Highlights：

• We propose a novel method for multi-view object detection in this work.

• View-characteristic discriminated patches are learned for each view.

• Hough decision tree and sparse coding representation are explored for detection.

• Cross-view discriminative patches are related to assist object detection.

摘要

•We propose a novel method for multi-view object detection in this work.•View-characteristic discriminated patches are learned for each view.•Hough decision tree and sparse coding representation are explored for detection.•Cross-view discriminative patches are related to assist object detection.

论文关键词：Multi-view object detection,Hough decision tree,Transfer vote,Sparse coding

论文评审过程：Received 20 July 2015, Revised 11 February 2017, Accepted 25 March 2017, Available online 30 March 2017, Version of Record 8 April 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.03.033