Author Login Editor-in-Chief Peer Review Editor Work Office Work

Computer Engineering ›› 2020, Vol. 46 ›› Issue (10): 1-17. doi: 10.19678/j.issn.1000-3428.0058018

• Hot Topics and Reviews • Previous Articles     Next Articles

Survey of Research in Image Semantic Segmentation Based on Deep Neural Network

JING Zhuangwei1a, GUAN Haiyan1b, PENG Daifeng1b, YU Yongtao2   

  1. 1a. School of Geographical Sciences;1b. School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China;
    2. School of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian, Jiangsu 223003, China
  • Received:2020-04-09 Revised:2020-05-26 Published:2020-06-02

基于深度神经网络的图像语义分割研究综述

景庄伟1a, 管海燕1b, 彭代峰1b, 于永涛2   

  1. 1. 南京信息工程大学 a. 地理科学学院;b. 遥感与测绘工程学院, 南京 210044;
    2. 淮阴工学院 计算机与软件工程学院, 江苏 淮安 223003
  • 作者简介:景庄伟(1996-),男,硕士研究生,主研方向为计算机视觉;管海燕(通信作者),教授、博士;彭代峰,博士;于永涛,副教授、博士。
  • 基金资助:
    国家自然科学基金(41671454,41971414)。

Abstract: With the rapid development of deep learning and its widespread applications in semantic segmentation,the quality of semantic segmentation has been significantly improved.This paper reviews and analyzes the mainstream deep neural network-based methods in semantic image segmentation.According to the ways of network training,the existing semantic image segmentation methods are categorized into fully supervised learning-based methods and weakly supervised learning-based methods.The performance,advantages and disadvantages of the representative algorithms of these two categories of semantic image segmentation methods are compared and analyzed.Then the paper systematically details the contributions of deep neural network to semantic segmentation.On this basis,the paper summarizes the current mainstream public datasets and remote sensing datasets,compares the segmentation performance of mainstream semantic image segmentation methods.Finally,the paper discusses the challenges faced with existing semantic segmentation techniques and the future development trends.

Key words: deep neural network, image semantic segmentation, computer vision, fully supervised learning, weakly supervised learning

摘要: 随着深度学习技术的快速发展及其在语义分割领域的广泛应用,语义分割效果得到显著提升。对基于深度神经网络的图像语义分割方法进行分析与总结,根据网络训练方式的不同,将现有的图像语义分割分为全监督学习图像语义分割和弱监督学习图像语义分割,对每种方法中代表性算法的效果以及优缺点进行对比与分析,并阐述深度神经网络对语义分割领域的贡献。在此基础上,归纳当前主流的公共数据集和遥感数据集,对比主要的图像语义分割方法的分割性能,探讨当前语义分割技术面临的挑战并对其未来的发展方向进行展望。

关键词: 深度神经网络, 图像语义分割, 计算机视觉, 全监督学习, 弱监督学习

CLC Number: