Journal of Frontiers of Computer Science and Technology ›› 2021, Vol. 15 ›› Issue (1): 47-59.DOI: 10.3778/j.issn.1673-9418.2004039

• Surveys and Frontiers • Previous Articles     Next Articles

Survey of Image Semantic Segmentation Methods Based on Deep Neural Network

XU Hui, ZHU Yuhua, ZHEN Tong, LI Zhihui   

  1. 1. Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Edu-cation, Zhengzhou 450001, China
    2. College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China
    3. Yellow River Conservancy Technical Institute, Kaifeng, Henan 475000, China
  • Online:2021-01-01 Published:2021-01-07



  1. 1. 粮食信息处理与控制教育部重点实验室(河南工业大学),郑州 450001
    2. 河南工业大学 信息科学与工程学院,郑州 450001
    3. 黄河水利职业技术学院,河南 开封 475000


Image semantic segmentation is a hot research topic in the field of computer vision in recent years. With the rise of deep learning technology, image semantic segmentation and deep learning technology are integrated and developed, which has made significant progress. It is widely used in practical scenarios such as unmanned driving, intelligent security, intelligent robot, human-computer interaction. Firstly, several deep neural network models for image semantic segmentation are introduced, and then the existing mainstream deep neural network-based image semantic segmentation methods are introduced. According to the differences of implementation technologies, image semantic segmentation methods are classified, and the technical characteristics, advantages and disadvantages of representative algorithms are analyzed and summarized. After that, the common datasets and performance evaluation indexes of image semantic segmentation are summarized, and the experimental results of classic semantic segmentation methods are compared on this basis. Finally, the future feasible research directions in the field of semantic segmentation are prospected.

Key words: computer vision, image semantic segmentation, deep neural network



关键词: 计算机视觉, 图像语义分割, 深度神经网络