A Brief Survey on Semantic Segmentation based on Deep Neural Network

In recent years, semantic segmentation has become an important research topic in the field of machine vision. With the development of deep learning technology, image semantic segmentation based on deep neural networks has achieved remarkable results. Semantic segmentation is pixel-level image understanding, and each pixel in the image is assigned a category label. Semantic segmentation is widely applied in scenes such as autonomous driving, intelligent robots, human-computer interaction, etc. A large number of semantic segmentation methods have been proposed. In this paper, we introduce the background of semantic segmentation. Then, we divide the semantic segmentation methods based on deep learning into five categories and present the advantages and disadvantages of each class. Besides, we analyze publicly available datasets and evaluation metrics of semantic segmentation. Finally, this paper prospects the development trend of semantic segmentation.

關鍵字

Semantic Segmentation ； Deep Neural Network ； Weakly Supervised Methods ； RNN

參考文獻

G. E. Hinton and R. Salakhutdinov, "Reducing the Dimensionality of Data with Neural Networks," Science, vol. 313, pp. 504 - 507, 2006.

A. Garcia-Garcia, S. Orts, S. Oprea, V. Villena-Martinez, P. Martinez-Gonzalez, and J. Rodríguez, "A survey on deep learning techniques for image and video semantic segmentation," Appl. Soft Comput., vol. 70, pp. 41-65, 2018.

H. Yu et al., "Methods and datasets on semantic segmentation: A review," Neurocomputing, vol. 304, pp. 82-103, 2018.

E. Shelhamer, J. Long, and T. Darrell, "Fully Convolutional Networks for Semantic Segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, pp. 640-651, 2017.

O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," ArXiv, vol. abs/1505.04597, 2015.

國際替代計量

A Brief Survey on Semantic Segmentation based on Deep Neural Network

全文下載

主題瀏覽