Real-time Image Semantic Segmentation Based on Block Adaptive Feature Fusion

被引：0
|
作者：
Huang T.-H. [1 ]
Nie Z.-Y. [1 ]
Wang Q.-G. [2 ]
Li S. [3 ]
Yan L.-C. [1 ]
Guo D.-S. [1 ]
机构：
[1] College of Information Science and Engineering, National Huaqiao University, Xiamen
[2] Institute for Intelligent Systems, University of Johannesburg, Johannesburg
[3] the Hong Kong Polytechnic University, Hong Kong
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2021年 / 47卷 / 05期
基金：
中国国家自然科学基金;
关键词：
Block adaptive feature fusion (BAFF); Deep learning; Real-time semantic segmentation network; SkipNet;
D O I：
10.16383/j.aas.c180645
中图分类号：
学科分类号：
摘要：
Recently, image semantic segmentation has made great progress with deep learning, which benefits robotics and automatic driving vehicle. This paper proposes a real-time semantic segmentation algorithm based on block adaptive feature fusion (BAFF). Under the framework of a light convolutional network, a block adaptive feature fusion algorithm is proposed in the context-embedding module, to improve the accuracy of real-time semantic segmentation. First, the problem caused by the different size of receptive field in layers is analyzed, and a feature fusion mechanism with block weight is presented on SkipNet. Then, layers' feature integration is carried on by three-dimension convolution. The feature- weights are calculated by an additional network with depthwise-separable-convolutions (DSC). Finally, the features are fused under adaptive weights. Experiments show that this method obtains excellent segmentation results with a good balance between rapidity and accuracy and owns robustness on segmentation of complex scenes. Copyright © 2021 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：1137 / 1148
页数：11
相关论文
共 30 条
  • [1] Rother C, Kolmogorov V, Blake A., GrabCut-interactive foreground extraction using iterated graph cuts, ACM Trans Graphics, 23, 3, pp. 309-314, (2004)
  • [2] Xia Jian-Feng, Segmentation and recognition of cancer cells based on mathematical morphology, Electronic Science and Technology, 29, 10, pp. 36-38, (2016)
  • [3] He X, Zemel R S, Ray D., Learning and incorporating top- down cues in image segmentation, Proceedings of the 9th European Conference on Computer Vision, pp. 338-351, (2006)
  • [4] Ravi D, Bober M, Farinella G M, Guarnera M, Battiato S., Semantic segmentation of images exploiting DCT based features and random forest, Pattern Recognition, 52, 3, pp. 260-273, (2016)
  • [5] Hinton G E, Salakhutdinov R R., Reducing the dimensionality of data with neural networks, Science, 313, 5786, pp. 504-507, (2006)
  • [6] Long J, Shelhamer E, Darrell T., Fully convolutional net- works for semantic segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 4, pp. 640-651, (2017)
  • [7] Zeiler M D, Krishnan D, Taylor G W, Fergus R., Deconvolutional networks, Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2528-2535, (2010)
  • [8] Kirkland E J., Bilinear Interpolation, Advanced Computing in Electron Microscopy, pp. 261-263, (2010)
  • [9] Zhang X Y, Zhou X Y, Lin M X, Sun J., ShuffleNet: An extremely efficient convolutional neural network for mobile devices, Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848-6856, (2018)
  • [10] Howard A G, Zhu M L, Chen B, Kalenichenko D, Wang W J, Weyand T, Andreetto M, Adam H., MobileNets: Efficient convolutional neural networks for mobile vision applications, (2017)
123