Spectral Complexity of Hyperspectral Images: A New Approach for Mangrove Classification

Darko, Patrick Osei; Kalácska, Margaret; Arroyo‐Mora, J. Pablo; Fagan, Matthew E.

doi:10.3390/rs13132604

Cited by 15 publications

(4 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This distinction is typically influenced by the condition of the internal chlorophyII structure and leaf cellulose, as they play a role in reflecting near-infrared electromagnetic waves. Distinguishing mangroves from other types of vegetation can be achieved through the utilization of shortwave-infrared reflectance (Osei Darko et al, 2021;Yang et al, 2022).…”

Section: Comparison Of Spectral Curvesmentioning

confidence: 99%

Mangrove forest mapping from object-oriented multi-feature ensemble classification using Sentinel-2 images

Zhang,

Xia,

Dai

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

Accurate mapping of mangrove forests is crucial for understanding their ecosystem function and developing effective management policies. However, the absence of an operational multi-feature fusion approach and an ensemble classification system restricts the achievement of this goal. This study aims to develop an object-oriented multi-feature ensemble classification scheme (OMEC). First, an enhanced mangrove spectral index (EMSI) is established by analyzing the spectral reflectance differences between mangrove forests and other land cover types. Sentinel-2 images are segmented into objects using the multi-resolution segmentation method. Then, spectral, textural, and geometric features are extracted, and these features (including EMSI) are inputted into the nearest neighbor classifier to implement mangrove classification. The experiment was conducted in three typical mangrove areas in China using Sentinle-2 images. The results demonstrate that EMSI exhibits good spectral separability for mangroves and performs well in the ensemble classification scheme. The overall accuracy of mangrove classification exceeds 90%, with a Kappa coefficient greater than 0.88. The object-oriented multi-feature ensemble classification scheme significantly improves accuracy and exhibits excellent performance. The method enhances the accuracy of mangrove classification, enriches the approach to mangrove remote sensing interpretation, and offers data support and scientific references for the restoration, management, and protection of coastal wetlands.

show abstract

Section: Comparison Of Spectral Curvesmentioning

confidence: 99%

Mangrove forest mapping from object-oriented multi-feature ensemble classification using Sentinel-2 images

Zhang,

Xia,

Dai

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

show abstract

“…Mangroves include a group of woody vegetation that exist mostly in tropical and semi-tropical areas (Bihamta Toosi et al, 2020;Estoque et al, 2018;Syahid et al, 2020). This type of evergreen flora, a mixture of tree and shrub species, can survive in severe saline environments (Osei Darko et al, 2021;Vaghela et al, 2018). These ecosystems offer a variety of environmental services, including storm protection, water purification, and carbon sequestration (Devaney et al, 2021;Yancho et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Identifying Suitable Locations for Mangrove Plantation Using Geospatial Information System and Remote Sensing

Sahraei

Ghorbanian²,

Kanani-Sadat³

et al. 2023

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Mangroves provide numerous environmental benefits, such as carbon sequestration, water purification, climate change mitigation, and flood and Tsunami impact reduction. Despite these unique advantages, mangroves are threatened by the combined adverse impacts of human activities and climate change. Therefore, it is essential to implement reasonable practices to avoid further degradation of mangroves and provide efficient workflows to increase their extent. Accordingly, better plantation policies are principally required for their conservation and rehabilitation. In this study, we desired to detect suitable locations for mangrove plantation in coastal areas of Hormozgan Province, Iran. We considered a relatively new Multi Criteria Decision Making (MCDM) technique to combine ten criteria derived from remote sensing in a GIS environment. The Best Worst Method (BWM), as an MDCM technique, was implemented to determine the relative importance of each criterion. Afterward, all criteria were aggregated using the Weighted Linear Combination (WLC) method to produce a mangrove plantation suitability map. Statistical measures, including Overall Accuracy (OA = 95%), Kappa Coefficient (KC = 87.9%), and Area Under Curve (AUC = 98.79%), indicated the high applicability of the implemented method for mangrove plantation site allocation. The produced map could give managers a profound insight into finding optimal spots to plant mangroves.

show abstract

“…In recent years, scholars have further explored deep learning research, which provides a highly positive effect for the semantic segmentation of remote sensing images and meets the accuracy requirements of computer vision applications [13][14][15][16][17][18][19][20][21]. The fully convolutional neural network was proposed in 2015 [22].…”

Section: Introductionmentioning

confidence: 99%

Convolution Feature Inference-Based Semantic Understanding Method for Remote Sensing Images of Mangrove Forests

Zhao

Wang

et al. 2023

Electronics

View full text Add to dashboard Cite

The semantic segmentation and understanding of remote sensing images applying computer technology has become an important component of monitoring mangrove forests’ ecological changes due to the rapid advancement of remote sensing technology. To improve the semantic segmentation capability of various surface features, this paper proposes a semantic understanding method for mangrove remote sensing images based on convolution feature inference. Firstly, the sample data is randomly selected, and next a model of convolution feature extraction is used to obtain the features of the selected sample data and build an initial feature set. Then, the convolution feature space and rule base are generated by establishing the three-dimensional color space distribution map for each class and domain similarity is introduced to construct the feature set and rules for reasoning. Next, a confidence reasoning method based on the convolution feature region growth, which introduces an improved similarity calculation, is put forward to obtain the first-time reasoning results. Finally, this approach adds a correction module, which removes the boundary information and reduces the noise from the results of the first-time reasoning as a new sample to correct the original feature set and rules, and uses the corrected feature set and rules for reasoning and understanding to obtain the final image segmentation results. It uses the corrected feature set and rules for reasoning and understanding to obtain the final image segmentation results. Experiments show that this algorithm has the benefits of a simple process, a short training time, and easy feature acquisition. The effect has been obviously improved compared to a single threshold segmentation method, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and other image segmentation methods.

show abstract

Spectral Complexity of Hyperspectral Images: A New Approach for Mangrove Classification

Cited by 15 publications

References 71 publications

Mangrove forest mapping from object-oriented multi-feature ensemble classification using Sentinel-2 images

Mangrove forest mapping from object-oriented multi-feature ensemble classification using Sentinel-2 images

Identifying Suitable Locations for Mangrove Plantation Using Geospatial Information System and Remote Sensing

Convolution Feature Inference-Based Semantic Understanding Method for Remote Sensing Images of Mangrove Forests

Contact Info

Product

Resources

About