Joint occlusion boundary detection and figure/ground assignment by extracting common-fate fragments in a back-projection scheme

作者：

Highlights：

• Occlusion boundary and figure/ground segmentation are studied in a Gestalt-based, low-level approach.

• Experiments on occlusion boundary benchmarks demonstrate the power of this mid-level, non-learning-based approach.

摘要

•Occlusion boundary and figure/ground segmentation are studied in a Gestalt-based, low-level approach.•Experiments on occlusion boundary benchmarks demonstrate the power of this mid-level, non-learning-based approach.

论文关键词：

论文评审过程：Received 15 June 2016, Revised 23 September 2016, Accepted 10 October 2016, Available online 20 October 2016, Version of Record 28 October 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.10.013