Skip to main navigation Skip to search Skip to main content

Learning contextual information for indoor semantic segmentation

  • Jianhua Wang
  • , Chuanxia Zheng*
  • , Weihai Chen
  • , Xingming Wu
  • *Corresponding author for this work
  • Beihang University

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

Abstract

Deep Convolutional Neural Networks(DCNNs) have recently shown great performance in many high-level vision tasks, such as image classification, object detection and more recently outdoor semantic segmentation. However, the convolutional layer only process the local regions in the image, ignoring the global context information. To overcome this poor localization property of Convolutional Neural Networks(CNNs), a new form of model that combine conditional random field(CRF) to CNNs is proposed. Hence, we train the CNNs to learn local pixel-wise information and then combine the CRF based on probabilistic graph model that are connected to global pixel. The experiment results on the public indoor NYUD v2 dataset demonstrate the proposed model outperform the existing state-of-the-art methods on a challenging 40 classes task, yielding a higher class average accuracy of 47.1% and pixel average accuracy of 66.4%.

Original languageEnglish
Title of host publicationProceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1639-1644
Number of pages6
ISBN (Electronic)9781509026050
DOIs
StatePublished - 19 Oct 2016
Event11th IEEE Conference on Industrial Electronics and Applications, ICIEA 2016 - Hefei, China
Duration: 5 Jun 20167 Jun 2016

Publication series

NameProceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016

Conference

Conference11th IEEE Conference on Industrial Electronics and Applications, ICIEA 2016
Country/TerritoryChina
CityHefei
Period5/06/167/06/16

Fingerprint

Dive into the research topics of 'Learning contextual information for indoor semantic segmentation'. Together they form a unique fingerprint.

Cite this