Object Bounding Transformed Network for End-to-End Semantic Segmentation

Kuan Chung Wang, Chien Yao Wang, Tzu Chiang Tai, Jia Ching Wang

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

Abstract

In recent years, numerous studies of the use of a Fully Convolutional Network (FCN) for image semantic segmentation have been published. This work introduces an end-to-end Object Bounding Transformed Network (OBTNet) which combines the advantages of the Object Boundary Guided (OBG) and Doman Transform (DT). OBG is an object boundary based approach that increases the integrity of object shape. Based on OBG, we propose an Object Boundary Network (OBN) as the object region and object boundary generator. In addition, our system achieves object region preserving and object boundary preserving by employing DT. The proposed system uses the pretrained multi-scale ResNet101 as the base network and uses multi-scale atrous convolution to preserve the dimensions of the feature map, increasing the accuracy of semantic segmentation. Experiments show that our system yielded a mean IOU of 77.74% and outperformed the baseline model on the VOC2012 test set.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PublisherIEEE Computer Society
Pages3217-3221
Number of pages5
ISBN (Electronic)9781538662496
DOIs
StatePublished - Sep 2019
Event26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan
Duration: 22 Sep 201925 Sep 2019

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2019-September
ISSN (Print)1522-4880

Conference

Conference26th IEEE International Conference on Image Processing, ICIP 2019
Country/TerritoryTaiwan
CityTaipei
Period22/09/1925/09/19

Keywords

  • Doman Transform Network
  • Object Boundary Guide
  • ResNet 101
  • image semantic segmentation

Fingerprint

Dive into the research topics of 'Object Bounding Transformed Network for End-to-End Semantic Segmentation'. Together they form a unique fingerprint.

Cite this