Fully Convolutional Neural Network with Augmented Atrous Spatial Pyramid Pool and Fully Connected Fusion Path for High Resolution Remote Sensing Image Segmentation
Source abstract
Abstract
Recent developments in Convolutional Neural Networks (CNNs) have allowed for the achievement of solid advances in semantic segmentation of high-resolution remote sensing (HRRS) images. Nevertheless, the problems of poor classification of small objects and unclear boundaries caused by the characteristics of the HRRS image data have not been fully considered by previous works. To tackle these challenging problems, we propose an improved semantic segmentation neural network, which adopts dilated convolution, a fully connected (FC) fusion path and pre-trained encoder for the semantic segmentation task of HRRS imagery. The network is built with the computationally-efficient DeepLabv3 architecture, with added Augmented Atrous Spatial Pyramid Pool and FC Fusion Path layers. Dilated convolution enlarges the receptive field of feature points without decreasing the feature map resolution. The improved neural network architecture enhances HRRS image segmentation, reaching the classification accuracy of 91%, and the precision of recognition of small objects is improved. The applicability of the improved model to the remote sensing image segmentation task is verified.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Advanced Image Fusion Techniques · Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information Science and Technology, North East Forest University, Harbin 150040, China
College of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China
Institute of Mathematics, Silesian University of Technology, 44-100 Gliwice, Poland
Department of Software Engineering, Kaunas University of Technology, 51386 Kaunas, Lithuania
Funding
National key R&D Program of China · Key Research and Development Program of Shaanxi Province · Scientific Research Program Funded by Shaanxi Provincial Education Department · China Postdoctoral Science Foundation · Specialized Research Fund for the Doctoral Program of Higher Education of China
References (48)
Show source-provided references
1. Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks10.1016/j.isprsjprs.2019.02.006 ↗
2. Road segmentation in SAR satellite images with deep fully convolutional neural networks10.1109/LGRS.2018.2864342 ↗
3. Road segmentation based on hybrid convolutional network for high-resolution visible remote sensing image10.1109/LGRS.2018.2878771 ↗
4. Deep learning classification of land cover and crop types using remote sensing data10.1109/LGRS.2017.2681128 ↗
5. Zhang, C., Gao, S., Yang, X., Li, F., Yue, M., Han, Y., and Fan, K. (2018). Convolutional neural network-based remote sensing images segmentation method for extracting winter wheat spatial distribution. Appl. Sci., 8.10.3390/app8101981 ↗
6. Buscombe, D., and Ritchie, A.C. (2018). Landscape classification with deep neural networks. Geosciences, 8.10.31223/OSF.IO/5MX3C ↗
7. SeNet: Structured edge network for sea-land segmentation10.1109/LGRS.2016.2637439 ↗
8. Azimi, S.M., Fischer, P., Korner, M., and Reinartz, P. (2018). Aerial LaneNet: Lane-marking semantic segmentation in aerial imagery using wavelet-enhanced cost-sensitive symmetric fully convolutional neural networks. IEEE Trans. Geosci. Remote Sens., 1–19.10.1109/TGRS.2018.2878510 ↗
9. Using satellite remote sensing and numerical modelling for the monitoring of suspended particulate matter concentration during reclamation construction at Dalian offshore airport in China10.1080/22797254.2018.1498301 ↗
10. Salzano, R., Salvatori, R., Valt, M., Giuliani, G., Chatenoux, B., and Ioppi, L. (2019). Automated Classification of Terrestrial Images: The Contribution to the Remote Sensing of Snow Cover. Geosciences, 9.10.3390/geosciences9020097 ↗
11. Wei, W., Polap, D., Li, X., Woźniak, M., and Liu, J. (2018, January 18–21). Study on remote sensing image vegetation classification method based on decision tree classifier. Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI), Bangalore, India.10.1109/SSCI.2018.8628721 ↗
12. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
13. Robust Autodual Morphological Profiles for the Classification of High-Resolution Satellite Images10.1109/TGRS.2013.2251468 ↗
14. An Automatic Framework for Detecting and Characterizing the Performance Degradation of Software Systems10.1109/TR.2014.2338255 ↗
15. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). ImageNet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada.
16. Guo, Z., Shao, X., Xu, Y., Miyazaki, H., Ohira, W., and Shibasaki, R. (2016). Identification of Village Building via Google Earth Images and Supervised Machine Learning Methods. Remote Sens., 8.10.3390/rs8040271 ↗
17. Fully Convolutional Networks for Semantic Segmentation10.1109/TPAMI.2016.2572683 ↗
18. Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks
19. Yuan, J. (2016). Automatic Building Extraction in Aerial Scenes Using Convolutional Networks. arXiv.
20. Convolutional Neural Networks for Large-Scale Remote Sensing Image Classification10.1109/TGRS.2016.2612821 ↗
21. Mboga, N., Georganos, S., Grippa, T., Lennert, M., Vanhuysse, S., and Wolff, E. (2019). Fully Convolutional Networks and Geographic Object-Based Image Analysis for the Classification of VHR Imagery. Remote Sens., 11.10.3390/rs11050597 ↗
22. Fu, G., Liu, C., Zhou, R., Sun, T., and Zhang, Q. (2017). Classification for High Resolution Remote Sensing Imagery Using a Fully Convolutional Network. Remote Sens., 9.10.3390/rs9050498 ↗
23. Kulikajevas, A., Maskeliūnas, R., Damaševičius, R., and Misra, S. (2019). Reconstruction of 3D Object Shape Using Hybrid Modular Neural Network Architecture Trained on 3D Models from ShapeNetCore Dataset. Sensors, 19.10.3390/s19071553 ↗
24. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Scene Segmentation10.1109/TPAMI.2016.2644615 ↗
25. U-Net: Convolutional Networks for Biomedical Image Segmentation
26. DeepUNet: A deep fully convolutional network for pixel-level sea-land segmentation10.1109/JSTARS.2018.2833382 ↗
27. A Y-net deep learning method for road segmentation using high-resolution visible remote sensing images10.1080/2150704X.2018.1557791 ↗
28. Chen, L.C., Papandreou, G., Schroff, F., and Hartwig, A. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv.
29. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs10.1109/TPAMI.2017.2699184 ↗
30. Deng, J., Dong, W., Socher, R., Li, L., Li, K., and Fei-Fei, L. (2009, January 20–25). ImageNet: A large-scale hierarchical image database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
31. Hu, P., and Ramanan, D. (2017, January 21–26). Finding Tiny Faces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.166 ↗
32. Combined energy minimization for image reconstruction from few views10.1155/2012/154630 ↗
33. Big Data Analytics Enabled by Feature Extraction Based on Partial Independence10.1016/j.neucom.2017.07.072 ↗
34. Semantic segmentation for high spatial resolution remote sensing images based on convolution neural network and pyramid pooling module10.1109/JSTARS.2018.2860989 ↗
35. Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., and Sang, N. (2018). Learning a Discriminative Feature Network for Semantic Segmentation. arXiv.10.1109/CVPR.2018.00199 ↗
36. Peng, C., Zhang, X., Yu, G., Luo, G., and Sun, J. (2017, January 21–26). Large kernel matters—Improve semantic segmentation by global convolutional network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.189 ↗
37. Fully Convolutional Networks for Semantic Segmentation of Very High Resolution Remotely Sensed Images Combined With DSM10.1109/LGRS.2018.2795531 ↗
38. Multi-threaded learning control mechanism for neural networks10.1016/j.future.2018.04.050 ↗
39. Wang, H., Wang, Y., Zhang, Q., Xiang, S., and Pan, C. (2017). Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images. Remote Sens., 9.10.3390/rs9050446 ↗
40. CoinNet: Copy initialization network for multispectral imagery semantic segmentation10.1109/LGRS.2018.2880756 ↗
41. Yan, J., Wang, H., Yan, M., Diao, W., Sun, X., and Li, H. (2019). IoU-adaptive deformable R-CNN: Make full use of IoU for multi-class object detection in remote sensing imagery. Remote Sens., 11.10.3390/rs11030286 ↗
42. Ren, Y., Zhu, C., and Xiao, S. (2018). Deformable Faster R-CNN with Aggregating Multi-Layer Features for Partially Occluded Object Detection in Optical Remote Sensing Images. Remote Sens., 10.10.3390/rs10091470 ↗
43. Very high resolution remote sensing image classification with SEEDS-CNN and scale effect analysis for superpixel CNN classification10.1080/01431161.2018.1513666 ↗
44. Ji, S., Wei, S., and Lu, M. (2018). A scale robust convolutional neural network for automatic building extraction from aerial and satellite imagery. Int. J. Remote Sens., 3308–3322.10.1080/01431161.2018.1528024 ↗
45. Panboonyuen, T., Jitkajornwanich, K., Lawawirojwong, S., Srestasathiern, P., and Vateekul, P. (2019). Semantic Segmentation on Remotely Sensed Images Using an Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning. Remote Sens., 11.10.20944/preprints201812.0090.v3 ↗
46. Shrestha, S., and Vanneschi, L. (2018). Improved Fully Convolutional Network with Conditional Random Fields for Building Extraction. Remote Sens., 10.10.3390/rs10071135 ↗
47. Xu, Z., Xu, X., Wang, L., Yang, R., and Pu, F. (2017). Deformable ConvNet with Aspect Ratio Constrained NMS for Object Detection in Remote Sensing Imagery. Remote Sens., 9.10.3390/rs9121312 ↗
48. Zhao, W., Zhang, H., Yan, Y., Fu, Y., and Wang, H. (2018). A Semantic Segmentation Algorithm Using FCN with Combination of BSLIC. Appl. Sci., 8.10.3390/app8040500 ↗