Skip to main navigation Skip to search Skip to main content

Image semantic segmentation based on fully convolutional neural network and CRF

  • Huiyun Li*
  • , Xin Qian
  • , Wei Li
  • *Corresponding author for this work
  • Beihang University

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

Abstract

Image semantic segmentation is a popular research direction in the computer vision field. Semantic segmentation algorithms based on deep learning outperforms the traditional methods. Fully convolutional neural network (FCN) whose fully connected layers are transformed into convolution layers is a kind of convolutional neural network (CNN). In this paper, FCN is used to operate the image semantic segmentation, which could take input of arbitrary size image and implement end-to-end segmentation task. Due to the limited number of training images, some layers are fine-tuned from AlexNet and the dataset is enlarged by mirroring. The hierarchical feature maps from FCN are combined to improve the segmentation effect. Conditional random fields (CRF) is used on the segmentation result of FCN, which takes into account the positional relationship and color features between any two pixels. Experiments show that our method could refine the segmentation result of FCN, especially using CRF as post-processing.

Original languageEnglish
Title of host publicationGeo-Spatial Knowledge and Intelligence - 4th International Conference on Geo-Informatics in Resource Management and Sustainable Ecosystem, GRMSE 2016, Revised Selected Papers
EditorsHanning Yuan, Jing Geng, Fuling Bian
PublisherSpringer Verlag
Pages245-250
Number of pages6
ISBN (Print)9789811039652
DOIs
StatePublished - 2017
Event4th International Conference on Geo-Informatics in Resource Management and Sustainable Ecosystem, GRMSE 2016 - Kowloon, Hong Kong SAR
Duration: 18 Nov 201620 Nov 2016

Publication series

NameCommunications in Computer and Information Science
Volume698
ISSN (Print)1865-0929

Conference

Conference4th International Conference on Geo-Informatics in Resource Management and Sustainable Ecosystem, GRMSE 2016
Country/TerritoryHong Kong SAR
City Kowloon
Period18/11/1620/11/16

Keywords

  • CNN
  • CRF
  • FCN
  • Image semantic segmentation

Fingerprint

Dive into the research topics of 'Image semantic segmentation based on fully convolutional neural network and CRF'. Together they form a unique fingerprint.

Cite this