A generalisable framework for saliency-based line segment detection
作者：
Highlights：
• A novel information-theoretic salient line segment detection framework is proposed.
• A saliency-based filtering formulation enables efficient salient line detection.
• The approach detects the most discriminative lines avoiding repetitive scene parts.
• The framework is generalisable as demonstrated by an extension to depth imagery.
• Superior repeatability is demonstrated compared to existing line detectors.
摘要
Highlights•A novel information-theoretic salient line segment detection framework is proposed.•A saliency-based filtering formulation enables efficient salient line detection.•The approach detects the most discriminative lines avoiding repetitive scene parts.•The framework is generalisable as demonstrated by an extension to depth imagery.•Superior repeatability is demonstrated compared to existing line detectors.
论文关键词：Line detection,Feature detection,Feature matching,Registration,Saliency
论文评审过程：Received 26 January 2015, Revised 14 May 2015, Accepted 25 June 2015, Available online 6 July 2015, Version of Record 19 August 2015.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.06.015
