Improved semantic segmentation for robotic applications with hierarchical conditional random fields

Benjamin J. Meyer, Tom Drummond

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

4 Citations (Scopus)


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.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Robotics and Automation (ICRA 2017)
EditorsHaoyong Yu, Zhidong Wang
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages8
ISBN (Electronic)9781509046331
ISBN (Print)9781509046338
Publication statusPublished - 21 Jul 2017
EventIEEE International Conference on Robotics and Automation 2017 - Sands Expo and Convention Centre, Singapore, Singapore
Duration: 29 May 20173 Jun 2017 (Proceedings)


ConferenceIEEE International Conference on Robotics and Automation 2017
Abbreviated titleICRA 2017
Internet address

Cite this