Remote Sensing Imagery Segmentation: A Hybrid Approach

In remote sensing imagery, segmentation techniques fail to encounter multiple regions of interest due to challenges such as dense features, low illumination, uncertainties, and noise. Consequently, exploiting vast and redundant information makes segmentation a difficult task. Existing multilevel thr...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Shreya Pare, Himanshu Mittal, Mohammad Sajid, Jagdish Chand Bansal, Amit Saxena, Tony Jan, Witold Pedrycz, Mukesh Prasad
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/d574c8ae68f6496f8f746ef672d2f527
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:d574c8ae68f6496f8f746ef672d2f527
record_format dspace
spelling oai:doaj.org-article:d574c8ae68f6496f8f746ef672d2f5272021-11-25T18:54:43ZRemote Sensing Imagery Segmentation: A Hybrid Approach10.3390/rs132246042072-4292https://doaj.org/article/d574c8ae68f6496f8f746ef672d2f5272021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4604https://doaj.org/toc/2072-4292In remote sensing imagery, segmentation techniques fail to encounter multiple regions of interest due to challenges such as dense features, low illumination, uncertainties, and noise. Consequently, exploiting vast and redundant information makes segmentation a difficult task. Existing multilevel thresholding techniques achieve low segmentation accuracy with high temporal difficulty due to the absence of spatial information. To mitigate this issue, this paper presents a new Rényi’s entropy and modified cuckoo search-based robust automatic multi-thresholding algorithm for remote sensing image analysis. In the proposed method, the modified cuckoo search algorithm is combined with Rényi’s entropy thresholding criteria to determine optimal thresholds. In the modified cuckoo search algorithm, the Lévy flight step size was modified to improve the convergence rate. An experimental analysis was conducted to validate the proposed method, both qualitatively and quantitatively against existing metaheuristic-based thresholding methods. To do this, the performance of the proposed method was intensively examined on high-dimensional remote sensing imageries. Moreover, numerical parameter analysis is presented to compare the segmented results against the gray-level co-occurrence matrix, Otsu energy curve, minimum cross entropy, and Rényi’s entropy-based thresholding. Experiments demonstrated that the proposed approach is effective and successful in attaining accurate segmentation with low time complexity.Shreya PareHimanshu MittalMohammad SajidJagdish Chand BansalAmit SaxenaTony JanWitold PedryczMukesh PrasadMDPI AGarticleimage segmentationremote sensing imagesmultilevel Rényi’s entropycuckoo searchoptimization algorithmsScienceQENRemote Sensing, Vol 13, Iss 4604, p 4604 (2021)
institution DOAJ
collection DOAJ
language EN
topic image segmentation
remote sensing images
multilevel Rényi’s entropy
cuckoo search
optimization algorithms
Science
Q
spellingShingle image segmentation
remote sensing images
multilevel Rényi’s entropy
cuckoo search
optimization algorithms
Science
Q
Shreya Pare
Himanshu Mittal
Mohammad Sajid
Jagdish Chand Bansal
Amit Saxena
Tony Jan
Witold Pedrycz
Mukesh Prasad
Remote Sensing Imagery Segmentation: A Hybrid Approach
description In remote sensing imagery, segmentation techniques fail to encounter multiple regions of interest due to challenges such as dense features, low illumination, uncertainties, and noise. Consequently, exploiting vast and redundant information makes segmentation a difficult task. Existing multilevel thresholding techniques achieve low segmentation accuracy with high temporal difficulty due to the absence of spatial information. To mitigate this issue, this paper presents a new Rényi’s entropy and modified cuckoo search-based robust automatic multi-thresholding algorithm for remote sensing image analysis. In the proposed method, the modified cuckoo search algorithm is combined with Rényi’s entropy thresholding criteria to determine optimal thresholds. In the modified cuckoo search algorithm, the Lévy flight step size was modified to improve the convergence rate. An experimental analysis was conducted to validate the proposed method, both qualitatively and quantitatively against existing metaheuristic-based thresholding methods. To do this, the performance of the proposed method was intensively examined on high-dimensional remote sensing imageries. Moreover, numerical parameter analysis is presented to compare the segmented results against the gray-level co-occurrence matrix, Otsu energy curve, minimum cross entropy, and Rényi’s entropy-based thresholding. Experiments demonstrated that the proposed approach is effective and successful in attaining accurate segmentation with low time complexity.
format article
author Shreya Pare
Himanshu Mittal
Mohammad Sajid
Jagdish Chand Bansal
Amit Saxena
Tony Jan
Witold Pedrycz
Mukesh Prasad
author_facet Shreya Pare
Himanshu Mittal
Mohammad Sajid
Jagdish Chand Bansal
Amit Saxena
Tony Jan
Witold Pedrycz
Mukesh Prasad
author_sort Shreya Pare
title Remote Sensing Imagery Segmentation: A Hybrid Approach
title_short Remote Sensing Imagery Segmentation: A Hybrid Approach
title_full Remote Sensing Imagery Segmentation: A Hybrid Approach
title_fullStr Remote Sensing Imagery Segmentation: A Hybrid Approach
title_full_unstemmed Remote Sensing Imagery Segmentation: A Hybrid Approach
title_sort remote sensing imagery segmentation: a hybrid approach
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/d574c8ae68f6496f8f746ef672d2f527
work_keys_str_mv AT shreyapare remotesensingimagerysegmentationahybridapproach
AT himanshumittal remotesensingimagerysegmentationahybridapproach
AT mohammadsajid remotesensingimagerysegmentationahybridapproach
AT jagdishchandbansal remotesensingimagerysegmentationahybridapproach
AT amitsaxena remotesensingimagerysegmentationahybridapproach
AT tonyjan remotesensingimagerysegmentationahybridapproach
AT witoldpedrycz remotesensingimagerysegmentationahybridapproach
AT mukeshprasad remotesensingimagerysegmentationahybridapproach
_version_ 1718410555799109632