MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images
Source abstract
Abstract
Semantic segmentation of remote sensing images is an important technique for spatial analysis and geocomputation. It has important applications in the fields of military reconnaissance, urban planning, resource utilization and environmental monitoring. In order to accurately perform semantic segmentation of remote sensing images, we proposed a novel multi-scale deep features fusion and cost-sensitive loss function based segmentation network, named MFCSNet. To acquire the information of different levels in remote sensing images, we design a multi-scale feature encoding and decoding structure, which can fuse the low-level and high-level semantic information. Then a max-pooling indices up-sampling structure is designed to improve the recognition rate of the object edge and location information in the remote sensing image. In addition, the cost-sensitive loss function is designed to improve the classification accuracy of objects with fewer samples. The penalty coefficient of misclassification is designed to improve the robustness of the network model, and the batch normalization layer is also added to make the network converge faster. The experimental results show that the classification performance of MFCSNet outperforms U-Net and SegNet in classification accuracy, object details and prediction consistency.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote-Sensing Image Classification · Advanced Image Fusion Techniques · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Optical Electrical Image Processing, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
Department of Electrical and Information Engineering, Hebei Jiaotong Vocational and Technical College, Shijiazhuang 050000, China
State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China
College of Information Science and Engineering, Northeastern University, Shenyang 110819, China
Funding
Natural Science Young Foundation of Hebei Provincial Department of Education
References (35)
Show source-provided references
1. Overview of Remote Sensing Image Classification Methods
2. Fusing Landsat and MODIS Data for Vegetation Monitoring10.1109/MGRS.2015.2434351 ↗
3. Satellite remote sensing in support of an integrated ocean observing system10.1109/MGRS.2013.2289656 ↗
4. Qiong, Y., and Wei, L. (2016, January 11–12). Geological Exploration Scheme Based on Remote Sensing Image Processing Technology. Proceedings of the 2016 IEEE International Conference on Smart Grid & Electrical Automation, Zhangjiajie, China.10.1109/ICSGEA.2016.79 ↗
5. A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: General guidelines for practitioners and future research10.1016/j.rse.2016.02.028 ↗
6. Gaussian Process Approach to Remote Sensing Image Classification10.1109/TGRS.2009.2023983 ↗
7. Remote sensing of transpiration and heat fluxes using multi-angle observations10.1016/j.rse.2013.05.023 ↗
8. An INSPIRE-Based Vocabulary for the Publication of Agricultural Linked Data10.1007/978-3-319-33245-1_13 ↗
9. Řezník, T., Lukas, V., Charvát, K., Křivánek, Z., Kepka, M., Herman, L., and Řezníková, H. (2017). Disaster Risk Reduction in Agriculture through Geospatial (Big) Data Processing. ISPRS Int. J. Geo-Inf., 6.10.3390/ijgi6080238 ↗
10. Multi-level Building Detection Framework in Remote Sensing Images Based on Convolutional Neural Networks10.1109/JSTARS.2018.2866284 ↗
11. RoadNet: Learning to Comprehensively Analyze Road Networks in Complex Urban Scenes From High-Resolution Remotely Sensed Images10.1109/TGRS.2018.2870871 ↗
12. Bag-of-Visual-Words Scene Classifier With Local and Global Features for High Spatial Resolution Remote Sensing Imagery10.1109/LGRS.2015.2513443 ↗
13. Sood, A.K., and Wechsler, H. (1992). Indexing via Color Histograms. Active Perception and Robot Vision, Springer.10.1007/978-3-642-77225-2 ↗
14. Unsupervised Ship Detection Based on Saliency and S-HOG Descriptor from Optical Satellite Images10.1109/LGRS.2015.2408355 ↗
15. Distinctive Image Features from Scale-Invariant Keypoints10.1023/B:VISI.0000029664.99615.94 ↗
16. Self-Supervised Low-Rank Representation (SSLRR) for Hyperspectral Image Classification
17. Multi-source Remote Sensing Image Classification of CART Automatic Decision Tree Based on ENVI—Taking Beijing as an Example
18. Réjichi, S., and Chaabane, F. (2015, January 26–31). Feature extraction using PCA for VHR satellite image time series spatio-temporal classification. Proceedings of the IEEE Geoscience and Remote Sensing Symposium 2015, Milan, Italy.10.1109/IGARSS.2015.7325806 ↗
19. Application of Improved K-means Algorithm in Remote Sensing Image Classification
20. Reducing the dimensionality of data with neural networks10.1126/science.1127647 ↗
21. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
22. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–8). ImageNet classification with deep convolutional neural networks. Proceedings of the International Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, NV, USA.
23. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
24. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
25. Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7–12). Faster R-CNN: Towards real-time object detection with region proposal networks. Proceedings of the International Conference on Neural Information Processing Systems (NIPS), Montreal, QC, Canada.
26. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 8–16). SSD: Single Shot MultiBox Detector. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
27. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (July, January 26). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
28. Shelhamer, E., Long, J., and Darrell, T. (2015, January 7–12). Fully Convolutional Networks for Semantic Segmentation. Proceedings of the IEEE Transactions on Pattern Analysis Machine Intelligence, Boston, MA, USA.
29. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Scene Segmentation10.1109/TPAMI.2016.2644615 ↗
30. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
31. Yu, F., and Koltun, V. (2016, January 2–4). Multi-Scale Context Aggregation by Dilated Convolutions. Proceedings of the International Conference on Learning Representations (ICLR), San Juan, Puerto Rico.
32. Application of Convolutional Neural Networks in Classification of High Score Remote Sensing Images
33. Maggiori, E., Tarabalka, Y., Charpiat, G., and Alliez, P. (2016, January 10–15). Fully convolutional neural networks for remote sensing image classification. Proceedings of the 2016 IEEE Geoscience and Remote Sensing Symposium, Beijing, China.10.1109/IGARSS.2016.7730322 ↗
34. Agoub, A., Filippovska, Y., Schmidt, V., and Kada, M. (2019, January 15–20). Automatic Generation of Photorealistic Image Fillers for Privacy Enabled Urban Basemaps using Generative Adversarial Networks. Proceedings of the 29th International Cartographic Conference (ICC 2019), Tokyo, Japan.10.5194/ica-adv-1-1-2019 ↗
35. He, M., Li, X., Zhang, Y., Zhang, J., and Wang, W. (2016, January 10–15). Hyperspectral image classification based on deep stacking network. Proceedings of the 2016 IEEE Geoscience and Remote Sensing Symposium, Beijing, China.10.1109/IGARSS.2016.7729850 ↗