Spatial contextual superpixel model for natural roadside vegetation classification

作者：

Highlights：

• A novel Spatial Contextual Superpixel Model (SCSM) for natural vegetation classification.

• A new reverse superpixel merging strategy to progressively merge superpixels.

• High performance on challenging natural datasets and Stanford background data.

摘要

•A novel Spatial Contextual Superpixel Model (SCSM) for natural vegetation classification.•A new reverse superpixel merging strategy to progressively merge superpixels.•High performance on challenging natural datasets and Stanford background data.

论文关键词：Feature extraction,Image segmentation,Classification algorithms,Object recognition,Artificial neural networks

论文评审过程：Received 15 July 2015, Revised 6 May 2016, Accepted 12 May 2016, Available online 20 May 2016, Version of Record 20 June 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.05.013