Research On Semantic Segmentation Based on Deep Learning

Xiang Li ； Jiaye Wu ； Yujie Yang

《World Scientific Research Journal》 9卷12期 (2023/12) Pp. 244-252

https://doi.org/10.6911/WSRJ.202312_9(12).0031

摘要

With the development of deep learning technology, the integration of semantic segmentation and deep learning has made great technical breakthroughs. Image semantic segmentation has become one of the research hotspots in computer vision field. This technology has been widely used in medical image segmentation, remote sensing image detection, intelligent robot and other fields. This paper first describes the basic network model of semantic segmentation in detail, then introduces the application of semantic segmentation in different fields, and finally looks forward to the future research focus of semantic segmentation.

關鍵字

Semantic segmentation ； Computer vision ； Deep learning ； Convolutional neural network

參考文獻

Otsu N. A threshold selection method from gray-level histograms[J]. IEEE transactions on systems, man, and cybernetics, 1979, 9(1): 62-66.

WESZKA J S. A survey of threshold selection techniques[J]. Computer Graphics and Image Processing, 1978, 7 (2): 259-265. DOI: 10.1016/0146-664X(78) 90116-8

Adams R, Bischof L. Seeded region growing[J]. IEEE Transactions on pattern analysis and machine intelligence, 1994, 16(6): 641-647.

Shotton J, Johnson M, Cipolla R. Semantic texton forests for image categorization and segmentation[C]//2008 IEEE conference on computer vision and pattern recognition. IEEE, 2008: 1-8.

Mahapatra D. Analyzing training information from random forests for improved image segmentation[J]. IEEE Transactions on Image Processing, 2014, 23(4): 1504-1512.