Real-Time Image Semantic Segmentation Based on Attention Mechanism and Multi-Label Classification

被引：0
|
作者：
Gao X. [1 ]
Li C. [1 ]
An J. [1 ]
机构：
[1] College of Information Sciences and Technology, Dalian Maritime University, Dalian
来源：
Li, Chungeng (li_chungeng@dlmu.edu.cn) | 1600年 / Institute of Computing Technology卷 / 33期
关键词：
Convolutional neural networks; Cross-level attention mechanism; Multi-label classification; Real-time semantic segmentation;
D O I：
10.3724/SP.J.1089.2021.18233
中图分类号：
学科分类号：
摘要：
Improving the accuracy is the goal in real-time semantic segmentation, especially for fuzzy boundary pixel segmentation. We proposed a high-precision and real-time semantic segmentation algorithm based on cross-level attention mechanism and multi-label classification. The procedure started with an optimization of DeepLabv3 to achieve real-time segmentation speed. Then, a cross-level attention module was added, so that the high-level features provided pixel-level attention for the low-level features, so as to inhibit the output of inaccurate semantic information in the low-level features. In the training phase, the multi-label classification loss function was introduced to assist the supervised training. The experimental results on Cityscapes dataset and CamVid dataset show that the segmentation accuracy is 68.1% and 74.1% respectively, and the segmentation speed is 42 frames/s and 89 frames/s respectively. It achieves a good balance between segmentation speed and accuracy, can optimize edge segmentation, and has strong robustness in complex scene segmentation. © 2021, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：59 / 67
页数：8
相关论文
共 26 条
  • [1] Csurka G, Perronnin F., An efficient approach to semantic segmentation, International Journal of Computer Vision, 95, 2, pp. 198-212, (2011)
  • [2] He Y H, Wang H, Zhang B., Color-based road detection in urban traffic scenes, IEEE Transactions on Intelligent Transportation Systems, 5, 4, pp. 309-318, (2004)
  • [3] An Zhe, Xu Xiping, Yang Jinhua, Et al., Design of augmented reality head-up display system based on image semantic segmentation, Acta Optica Sinica, 38, 7, pp. 77-83, (2018)
  • [4] Long J, Shelhamer E, Darrell T., Fully convolutional networks for semantic segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431-3440, (2015)
  • [5] Lin G S, Milan A, Shen C H, Et al., Refinenet: multi-path refinement networks for high-resolution semantic segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5168-5177, (2017)
  • [6] Ronneberger O, Fischer P, Brox T., U-Net: convolutional networks for biomedical image segmentation, Proceedings of Medical Image Computing and Computer Assisted Intervention, pp. 234-241, (2015)
  • [7] Chen L C, Papandreou G, Kokkinos I, Et al., Semantic image segmentation with deep convolutional nets and fully connected crfs, (2014)
  • [8] Chen L C, Papandreou G, Kokkinos I, Et al., DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs, IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 4, pp. 834-848, (2018)
  • [9] Chen L C, Papandreou G, Schroff F, Et al., Rethinking atrous convolution for semantic image segmentation
  • [10] Yue Shiyi, Image semantic segmentation based on hierarchical context information, Laser & Optoelectronics Progress, 56, 24, pp. 107-115, (2019)
123