Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

Land Cover Classification of Satellite Image using SSResUnet Model

SSResUnet 모델을 이용한 위성 영상 토지피복분류

  • Joohyung Kang (Satellite Image Processing Team, CONTEC) ;
  • Minsung Kim (Dept. of Electronic Engineering, Hanbat National University) ;
  • Seongjin Kim (Dept. of Electronic Engineering, Hanbat National University) ;
  • Sooyeong Kwak (Dept. of Electronic Engineering, Hanbat National University)
  • Received : 2023.11.21
  • Accepted : 2023.12.20
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we introduce the SSResUNet network model, which integrates the SPADE structure with the U-Net network model for accurate land cover classification using high-resolution satellite imagery without requiring user intervention. The proposed network possesses the advantage of preserving the spatial characteristics inherent in satellite imagery, rendering it a robust classification model even in intricate environments. Experimental results, obtained through training on KOMPSAT-3A satellite images, exhibit superior performance compared to conventional U-Net and U-Net++ models, showcasing an average Intersection over Union (IoU) of 76.10 and a Dice coefficient of 86.22.

본 논문에서는 사용자의 개입없이 고해상도 위성 영상을 활용하여 정밀한 토지피복분류를 위해 U-Net 네트워크 모델에 SPADE 구조를 결합한 SSResUNet 모델을 제안한다. 제안하는 네트워크는 위성 영상의 공간적 특성을 보존하여 복잡도가 높은 환경에서도 강인한 분류모델이라는 장점이 있다. 다목적실용위성 3A 영상을 통해 학습한 결과 기존 U-Net, U-Net++ 대비 뛰어난 결과를 보였으며 평균 IoU 76.10, Dice 86.22의 성능을 도출하였다.

Keywords

Acknowledgement

This results was supported by "Regional Innovation Strategy (RIS)" through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(MOE)(2021RIS-004)

References

  1. W. Baek, M. Lee and H. Jung, "The Performance Improvement of U-Net Model for Landcover Semantic Segmentation through Data Augmentation." Korean Journal of Remote Sensing, vol.38, no.6, pp.1663-1676, 2022.
  2. W. Wang, Ji. Dai, Z. Chen, Z. Huang, Z. Li, X. Zhu, X. Hu, T. Lu, L. Lu, H. Li, X. Wang and Y. Qiao, "InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions," IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.14408-14419, 2023. DOI: 10.48550/arXiv.2211.05778
  3. B. Cheng, M. D. Collins, Y. Zhu, T. Liu, T. S. Huang, H. Adam and L.-C Chen, "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation," IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.12475-12485, 2020. DOI: 10.48550/arXiv.1911.10194
  4. O. Ronneberger, P. Fischer and T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, pp.234-241, 2015. DOI: 10.48550/arXiv.1505.04597
  5. J. Long, E. Shelhamer and T. Darrell, "Fully Convolutional Networks for Semantic Segmentation," IEEE conference on computer vision and pattern recognition, pp.3431-3440, 2015. DOI: 10.48550/arXiv.1411.4038
  6. K. He, X. Zhang, S. Ren and J. Sun, "Deep residual learning for image recognition," In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770-778, 2016. DOI: 10.48550/arXiv.1512.03385
  7. Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh and J. Liang, "UNet++: A Nested U-Net Architecture for Medical Image Segmentation," In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, pp.3-11, 2018. DOI: 10.48550/arXiv.1807.10165
  8. G. Huang, Z. Liu, L. V. D. Maaten and K. Q. Weinberger, "Densely connected convolutional networks," In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700-4708, 2017. DOI: 10.48550/arXiv.1608.06993
  9. T. Park, M.-Y Liu, T.-C Wang and J.-Y Zhu, "Semantic Image Synthesis with Spatially-Adaptive Normalization," In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.2337-2346, 2019. DOI: 10.48550/arXiv.1903.07291
  10. C. Dong, C. C. Loy, K. He and X. Tang, "Learning a deep convolutional network for image super-resolution," In Computer Vision-ECCV 2014: 13th European Conference, pp.184-199, 2014. DOI: 10.1007/978-3-319-10593-2_13
  11. J. Kim, and Y. Choe, "Document Image Restore via SPADE-Based Super-Resolution Network," Electronics, 12(3), 748, 2023. DOI: 10.3390/electronics12030748
  12. S. Ioffe and C. Szegedy, "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift," In International conference on machine learning, pp.448-456, 2015. DOI: 10.48550/arXiv.1502.03167
  13. P. Liashchynskyi and P. Liashchynskyi, "Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS," DOI: 10.48550/arXiv.1912.06059
  14. R. Guo, J. Liu, N. Li, S. Liu, F. Chen, B. Cheng, J. Duan, X. Li and C. Ma, "Pixel-Wise Classification Method for High Resolution Remote Sensing Imagery Using Deep Neural Networks," ISPRS International Journal of Geo-Information, 7(3), DOI: 10.3390/ijgi7030110
  15. H. Choi, D. Seo and J.-w Choi, "Pansharpening using guided filtering to improve the spatial clarity of VHR satellite imagery," Remote Sensing, 36(5), 961-973, 2019. DOI: 10.3390/rs11060633