Recognizing in the depth: Selective 3D Spatial Pyramid Matching Kernel for object and scene categorization

作者：

Highlights：

• We introduce the 3DSPMK for object and scene recognition in depth images.

• Our model repeatedly subdivides a cube inscribed in the point cloud.

• Then, a weighted sum of histogram of visual word occurrences is computed.

• Results on publicly available benchmarks have been reported.

摘要

•We introduce the 3DSPMK for object and scene recognition in depth images.•Our model repeatedly subdivides a cube inscribed in the point cloud.•Then, a weighted sum of histogram of visual word occurrences is computed.•Results on publicly available benchmarks have been reported.

论文关键词：3D Spatial Pyramid Matching Kernel,Object recognition,Scene classification,Point clouds,Depth images

论文评审过程：Received 10 January 2014, Revised 12 May 2014, Accepted 24 August 2014, Available online 1 September 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.08.007