Hybrid hesitant fuzzy linguistic bi-objective binary coyote clustering based segmentation and classification for land use land cover in hyperspectral image

Land use and land cover segmentation and classification from hyperspectral image is significant in many land use inventories. Though several techniques have been proposed for classification of land use and land cover, the classification accuracy is low in the prevailing approaches. This manuscript o...

Full description

Saved in:
Bibliographic Details
Published in:International journal of information technology (Singapore. Online) Vol. 16; no. 1; pp. 525 - 534
Main Authors: Yele, Vijaykumar P., Alegavi, Sujata, Sedamkar, R. R.
Format: Journal Article
Language:English
Published: Singapore Springer Nature Singapore 01.01.2024
Springer Nature B.V
Subjects:
Accuracy
Agriculture
Algorithms
Artificial Intelligence
Biodiversity
Classification
Climate change
Clustering
Computer Imaging
Computer Science
Computing time
Datasets
Decision making
Deep learning
Food security
Graph neural networks
Hyperspectral imaging
Image classification
Image Processing and Computer Vision
Image segmentation
Infrastructure
Land cover
Land use
Linguistics
Machine Learning
Natural resource management
Neural networks
Noise levels
Objectives
Optimization
Original Research
Pattern Recognition and Graphics
Preprocessing
Remote sensing
Segmentation
Semantics
Signal to noise ratio
Software Engineering
Urban planning
Vegetation
Vision
Land use and land cover segmentation
Anisotropic diffusion Kuwahara filtering
Land use and land cover classification
Hyperspectral image
Binary coyote optimization algorithm
ISSN:2511-2104, 2511-2112
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Land use and land cover segmentation and classification from hyperspectral image is significant in many land use inventories. Though several techniques have been proposed for classification of land use and land cover, the classification accuracy is low in the prevailing approaches. This manuscript offers Auto-Metric Graph Neural Network to improve the Land Use/Land Cover (AMGNN-LU/LC) classification. Land use and land cover classification is assessed with the help of EuroSAT dataset. The input image is enhanced with preprocessing method called Anisotropic Diffusion Kuwahara Filtering (ADKF). After preprocessing, Hesitant Fuzzy Linguistic Bi-objective Clustering (HFLBC) technique is utilized for segmentation. The Binary Coyote Optimization Algorithm (BCOA) is used for optimizing hesitant fuzzy linguistic bi-objective clustering. The segmented image is classified into land use/ land cover with the help of auto-metric graph neural network. The introduced method is implemented in PYTHON. The proposed approach attains 99% precision, 98.30% accuracy, 99% F1-score, 99.2% recall, 98.1% sensitivity, 99% specificity, 98% Structural Similarity Index Measure (SSIM), 44 dB Peak Signal-to-Noise Ratio (PSNR) and 2.7 s computational time and 0.12% loss. The AMGNN-LU/LC’s efficiency is compared to the prevailing approaches.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2511-2104
2511-2112
DOI:10.1007/s41870-023-01576-1