期刊文献+

基于深度神经网络的图像语义分割研究综述 被引量:47

Survey of Research in Image Semantic Segmentation Based on Deep Neural Network
下载PDF
导出
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。 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.
作者 景庄伟 管海燕 彭代峰 于永涛 JING Zhuangwei;GUAN Haiyan;PENG Daifeng;YU Yongtao(School of Geographical Sciences,Nanjing University of Information Science and Technology,Nanjing 210044,China;School of Remote Sensing and Geomatics Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China;School of Computer and Software Engineering,Huaiyin Institute of Technology,Huaian,Jiangsu 223003,China)
出处 《计算机工程》 CAS CSCD 北大核心 2020年第10期1-17,共17页 Computer Engineering
基金 国家自然科学基金(41671454,41971414)。
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 deep neural network image semantic segmentation computer vision fully supervised learning weakly supervised learning
  • 相关文献

参考文献3

二级参考文献26

  • 1刘健庄,栗文青.灰度图象的二维Otsu自动阈值分割法[J].自动化学报,1993,19(1):101-105. 被引量:356
  • 2Sonka M,Hlavac V,Boyle R.Image Processing:Analysis and Machine Vision.Beijing:Posts & Telecom Press,2003 被引量:1
  • 3Otsu N.A threshold selection method from gray-level histograms.IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):919-926 被引量:1
  • 4Sahoo P K.A survey of threshold techniques.Computer Vision Graphic,Image Process,1988,41(2):233-260 被引量:1
  • 5Wu S,Amin A.Automatic thresholding of gray-level using multi-stage approach.In:Proceedings of IEEE International Conference on Document Analysis and Recognition.IEEE,2003.1238-1242 被引量:1
  • 6Tsai D M.A fast thresholding selection procedure for multimodal and unimodal histograms.Pattern Recognition Letters,1995,16(6):653-666 被引量:1
  • 7Yin P Y,Chen L H.A new method for multilevel thresholding using symmetry and duality of the histogram.In:Proceedings of 1994 International Symposium on Speech,Image Processing and Neural Networks.IEEE,1994.1:45-48 被引量:1
  • 8David J E,Albert T A,Chenoweth D L.Two-dimensional entropic segmentation.Pattern Recognition Letters,1999,20(3):329-336 被引量:1
  • 9Albuquerque M P,Esquef I A,Gesualdi M A R.Image thresholding using Tsallis entropy.Pattern Recognition Letters,2004,25(9):1059-1065 被引量:1
  • 10Sahoo P K,Arara G.A thresholding method based on two-dimensional Renyi's entropy.Pattern Recognition,2004,37(6):1149-1161 被引量:1

共引文献382

同被引文献351

引证文献47

二级引证文献205

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部