Back to articles
Articles
Volume: 30 | Article ID: art00016
Image
Person Segmentation Using Convolutional Neural Networks With Dilated Convolutions
  DOI :  10.2352/ISSN.2470-1173.2018.10.IMAWM-455  Published OnlineJanuary 2018
Abstract

Semantic segmentation, classifying each pixel in an image to a set of various objects, is an important and necessary problem to understand images. In recent years, convolutional neural networks trained with public datasets enable to segment objects and understand images. However, it is still challenging to segment objects with high accuracy on a simple and small network. In this work, we describe convolutional neural networks with dilated convolutions to segment person accurately especially near boundary using data augmentation technique. Additionally, we develop a smaller network which can run each frame in webcam video faster without degrading segmentation performance. Our method both numerically and visually outperforms other segmentation techniques.

Subject Areas :
Views 18
Downloads 3
 articleview.views 18
 articleview.downloads 3
  Cite this article 

David Joon Ho, Qian Lin, "Person Segmentation Using Convolutional Neural Networks With Dilated Convolutionsin Proc. IS&T Int’l. Symp. on Electronic Imaging: Imaging and Multimedia Analytics in a Web and Mobile World,  2018,  pp 455-1 - 455-7,  https://doi.org/10.2352/ISSN.2470-1173.2018.10.IMAWM-455

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2018
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology