Improved semantic segmentation for robotic applications with hierarchical conditional random fields.
ICRA(2017)
摘要
Conventional approaches to semantic segmentation are inappropriate for robotic applications, as they focus on pixel-level performance and give little significance to spurious object detections. This paper presents a region-based conditional random field model for semantic segmentation that focuses on object-level performance, recognising that in a robotics context, false object detections can have costly consequences. We show how optimising at the semantic regionlevel results in significantly fewer false positive object detections than conventional approaches. We further show how both object and pixel-level performance can be improved over conventional methods by combining region random fields with dense pixel random fields in a hierarchical manner. An object-aware performance metric is introduced that heavily penalises false positive and false negative object detections, as appropriate for robotic applications. Our approach is evaluated on the challenging NYU v2 and Pascal VOC datasets, outperforming comparable conventional methods in terms of object and pixellevel performance.
更多查看译文
关键词
semantic segmentation,robotic applications,hierarchical conditional random fields,region-based conditional random field model,object-level performance,object detection,semantic region-level,pixel-level performance,object-aware performance metric
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络