SSResUnet 모델을 이용한 위성 영상 토지피복분류
Land Cover Classification of Satellite Image using SSResUnet Model
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문에서는 사용자의 개입없이 고해상도 위성 영상을 활용하여 정밀한 토지피복분류를 위해 U-Net 네트워크 모델에 SPADE구조를 결합한 SSResUNet 모델을 제안한다. 제안하는 네트워크는 위성 영상의 공간적 특성을 보존하여 복잡도가 높은 환경에서도강인한 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.
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.
참고문헌 (15)
- 백원경, "데이터 확장을 통한 토지피복분류 U-Net 모델의 성능 개선", 대한원격탐사학회지, 38(6), pp.1663~1676 (2022), 대한원격탐사학회
- W. Wang, "InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions", IEEE, 2023, 14408~14419
- B. Cheng, "Panoptic-DeepLab:A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation", IEEE, 2020, 12475~12485
- O. Ronneberger, "U-Net: Convolutional Networks for Biomedical Image Segmentation", Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015:18th International Conference, pp.234~241 (2015)
- J. Long, "Fully Convolutional Networks for Semantic Segmentation", IEEE conference on computer vision and pattern recognition, pp.3431~3440 (2015)
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
- Z. Zhou, "UNet++: A Nested U-Net Architecture for Medical Image Segmentation", 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)
- G. Huang, "Densely connected convolutional networks", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.4700~4708 (2017)
- T. Park, "Semantic Image Synthesis with Spatially-Adaptive Normalization", Proceedings of the IEEE, 2019, 2337~2346
- C. Dong, "Learning a deep convolutional network for image super-resolution", Computer Vision–ECCV 2014:13th European Conference, pp.184~199 (2014)
- Jaehun Kim, "Document Image Restore via SPADE-Based Super-Resolution Network", Electronics, 12(3), pp.748~ (2023), MDPI AG[DOI]
- S. Ioffe, "Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift", International conference on machine learning, pp.448~456 (2015)
- P. Liashchynskyi, "Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS", ~
- Rui Guo, "Pixel-Wise Classification Method for High Resolution Remote Sensing Imagery Using Deep Neural Networks", ISPRS International Journal of Geo-Information, 7(3), pp.110~ (2018), MDPI AG[DOI]
- H. Choi, "Pansharpening using guided filtering to improve the spatial clarity of VHR satellite imagery", Remote Sensing, 36(5), pp.961~973 (2019)[DOI]