Effective segmentation of land-use and land-cover from hyperspectral remote sensing image

被引：0
作者：
Yele V.P. [1 ]
Alegavi S. [2 ]
Sedamkar R.R. [3 ]
机构：
[1] Department of Electronics and Telecommunication Engineering, Thakur College of Engineering and Technology, Maharashtra, Mumbai
[2] Department of Internet of Things, Thakur College of Engineering and Technology, Maharashtra, Mumbai
[3] Department of Computer Engineering, Thakur College of Engineering and Technology, Maharashtra, Mumbai
来源：
International Journal of Information Technology | 2024年 / 16卷 / 4期
关键词：
Hyperspectral imaging; Land cover; Land use; Segmentation; Spatial features;
D O I：
10.1007/s41870-023-01711-y
中图分类号：
学科分类号：
摘要：
Hyperspectral images (HSI) provide valuable data for Land-Use and Land-Cover (LU/LC) segmentation. Detecting buildings, roads, and LU/LC labels in satellite images is crucial for various applications. This research introduces a method combining Hybrid Dynamic Arithmetic Edge Detection with Bi-directional Long Short-Term Memory UNet (BiLSTMUNet) for segmentation. Initially, enhance the image quality with an Approximate Adaptive Noise Variance Wiener filtering technique (AANVW), and perform dynamic spatial-spectral feature extraction on pre-processed images. The proposed segmentation system is a hybrid of Arithmetic Optimization (AO) and BiLSTMUNet, reducing the entropy loss function. Then, processed a substantial amount of remote sensing images to achieve improved LU/LC segmentation. Results show the effectiveness of BiLSTMUNet with an accuracy of 98.5% on EuroSAT and 97.5% on DeepGlobe datasets. This approach holds promise for accurate and efficient high-resolution remote sensing image analysis. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.
引用
收藏
页码：2395 / 2412
页数：17
相关论文
共 41 条
  • [1] Nalepa J., Antoniak M., Myller M., Ribalta Lorenzo P., Marcinkiewicz M., Towards resource-frugal deep convolutional neural networks for hyperspectral image segmentation, Microprocess Microsyst, 73, (2020)
  • [2] Wang W., Li W., Zhang C., Zhang W., Improving object-based land use/cover classification from medium resolution imagery by markov chain geostatistical post-classification, Land, 7, (2018)
  • [3] Chen B., Xia M., Huang J., MFANet: a multi-level feature aggregation network for semantic segmentation of land cover, Remote Sens, 13, (2021)
  • [4] Liu L., Awwad E.M., Ali Y.A., Al-Razgan M., Maarouf A., Abualigah L., Hoshyar A.N., Multi-dataset hyper-CNN for hyperspectral image segmentation of remote sensing images, Process, 11, (2023)
  • [5] Cohrs J.-C., Bajaj C., Berkels B., A distribution-dependent mumford–shah model for unsupervised hyperspectral image segmentation, IEEE Trans Geosci Remote Sens, 60, pp. 1-21, (2022)
  • [6] Nalepa J., Myller M., Imai Y., Honda K.-I., Takeda T., Antoniak M., Unsupervised segmentation of hyperspectral images using 3-D convolutional autoencoders, IEEE Geosci Remote Sens Lett, 17, pp. 1948-1952, (2020)
  • [7] Qu L., Chen Z., Li M., Zhi J., Wang H., Accuracy improvements to pixel-based and object-based LULC classification with auxiliary datasets from Google Earth engine, Remote Sens, 13, (2021)
  • [8] Khan S.D., Alarabi L., Basalamah S., Deep hybrid network for land cover semantic segmentation in high-spatial resolution satellite images, Information, 12, (2021)
  • [9] Alsabhan W., Alotaiby T., Automatic building extraction on satellite images using unet and RESNET50, Comput Intell Neurosci, 2022, pp. 1-12, (2022)
  • [10] Lavanya K., Mahendran A., Selvanambi R., Mazzara M., Hemanth J.D., Tunicate Swarm algorithm with deep learning based land use and cover change detection in Nallamalla Forest India, Appl Sci, 13, (2023)
12345