Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV Images
Combining deep learning and UAV images to map wetland vegetation distribution has received increasing attention from researchers. However, it is difficult for one multi-classification convolutional neural network (CNN) model to meet the accuracy requirements for the overall classification of multi-o...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/22/5869 |
_version_ | 1797464027383726080 |
---|---|
author | Yuyang Li Tengfang Deng Bolin Fu Zhinan Lao Wenlan Yang Hongchang He Donglin Fan Wen He Yuefeng Yao |
author_facet | Yuyang Li Tengfang Deng Bolin Fu Zhinan Lao Wenlan Yang Hongchang He Donglin Fan Wen He Yuefeng Yao |
author_sort | Yuyang Li |
collection | DOAJ |
description | Combining deep learning and UAV images to map wetland vegetation distribution has received increasing attention from researchers. However, it is difficult for one multi-classification convolutional neural network (CNN) model to meet the accuracy requirements for the overall classification of multi-object types. To resolve these issues, this paper combined three decision fusion methods (Majority Voting Fusion, Average Probability Fusion, and Optimal Selection Fusion) with four CNNs, including SegNet, PSPNet, DeepLabV3+, and RAUNet, to construct different fusion classification models (FCMs) for mapping wetland vegetations in Huixian Karst National Wetland Park, Guilin, south China. We further evaluated the effect of one-class and multi-class FCMs on wetland vegetation classification using ultra-high-resolution UAV images and compared the performance of one-class classification (OCC) and multi-class classification (MCC) models for karst wetland vegetation. The results highlight that (1) the use of additional multi-dimensional UAV datasets achieved better classification performance for karst wetland vegetation using CNN models. The OCC models produced better classification results than MCC models, and the accuracy (average of IoU) difference between the two model types was 3.24–10.97%. (2) The integration of DSM and texture features improved the performance of FCMs with an increase in accuracy (MIoU) from 0.67% to 8.23% when compared to RGB-based karst wetland vegetation classifications. (3) The PSPNet algorithm achieved the optimal pixel-based classification in the CNN-based FCMs, while the DeepLabV3+ algorithm produced the best attribute-based classification performance. (4) Three decision fusions all improved the identification ability for karst wetland vegetation compared to single CNN models, which achieved the highest IoUs of 81.93% and 98.42% for Eichhornia crassipes and Nelumbo nucifera, respectively. (5) One-class FCMs achieved higher classification accuracy for karst wetland vegetation than multi-class FCMs, and the highest improvement in the IoU for karst herbaceous plants reached 22.09%. |
first_indexed | 2024-03-09T18:02:08Z |
format | Article |
id | doaj.art-89c8414acb4b47d89f152e428498b315 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T18:02:08Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-89c8414acb4b47d89f152e428498b3152023-11-24T09:51:47ZengMDPI AGRemote Sensing2072-42922022-11-011422586910.3390/rs14225869Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV ImagesYuyang Li0Tengfang Deng1Bolin Fu2Zhinan Lao3Wenlan Yang4Hongchang He5Donglin Fan6Wen He7Yuefeng Yao8College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Plant Conservation and Restoration Ecology in Karst Terrain, Guangxi Institute of Botany, Guangxi Zhuang Autonomous Region and Chinese Academy of Sciences, Guilin 541006, ChinaGuangxi Key Laboratory of Plant Conservation and Restoration Ecology in Karst Terrain, Guangxi Institute of Botany, Guangxi Zhuang Autonomous Region and Chinese Academy of Sciences, Guilin 541006, ChinaCombining deep learning and UAV images to map wetland vegetation distribution has received increasing attention from researchers. However, it is difficult for one multi-classification convolutional neural network (CNN) model to meet the accuracy requirements for the overall classification of multi-object types. To resolve these issues, this paper combined three decision fusion methods (Majority Voting Fusion, Average Probability Fusion, and Optimal Selection Fusion) with four CNNs, including SegNet, PSPNet, DeepLabV3+, and RAUNet, to construct different fusion classification models (FCMs) for mapping wetland vegetations in Huixian Karst National Wetland Park, Guilin, south China. We further evaluated the effect of one-class and multi-class FCMs on wetland vegetation classification using ultra-high-resolution UAV images and compared the performance of one-class classification (OCC) and multi-class classification (MCC) models for karst wetland vegetation. The results highlight that (1) the use of additional multi-dimensional UAV datasets achieved better classification performance for karst wetland vegetation using CNN models. The OCC models produced better classification results than MCC models, and the accuracy (average of IoU) difference between the two model types was 3.24–10.97%. (2) The integration of DSM and texture features improved the performance of FCMs with an increase in accuracy (MIoU) from 0.67% to 8.23% when compared to RGB-based karst wetland vegetation classifications. (3) The PSPNet algorithm achieved the optimal pixel-based classification in the CNN-based FCMs, while the DeepLabV3+ algorithm produced the best attribute-based classification performance. (4) Three decision fusions all improved the identification ability for karst wetland vegetation compared to single CNN models, which achieved the highest IoUs of 81.93% and 98.42% for Eichhornia crassipes and Nelumbo nucifera, respectively. (5) One-class FCMs achieved higher classification accuracy for karst wetland vegetation than multi-class FCMs, and the highest improvement in the IoU for karst herbaceous plants reached 22.09%.https://www.mdpi.com/2072-4292/14/22/5869karst wetlandsvegetation classificationone- and multi-class deep learningmodel fusiondecision fusionUAV images |
spellingShingle | Yuyang Li Tengfang Deng Bolin Fu Zhinan Lao Wenlan Yang Hongchang He Donglin Fan Wen He Yuefeng Yao Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV Images Remote Sensing karst wetlands vegetation classification one- and multi-class deep learning model fusion decision fusion UAV images |
title | Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV Images |
title_full | Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV Images |
title_fullStr | Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV Images |
title_full_unstemmed | Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV Images |
title_short | Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV Images |
title_sort | evaluation of decision fusions for classifying karst wetland vegetation using one class and multi class cnn models with high resolution uav images |
topic | karst wetlands vegetation classification one- and multi-class deep learning model fusion decision fusion UAV images |
url | https://www.mdpi.com/2072-4292/14/22/5869 |
work_keys_str_mv | AT yuyangli evaluationofdecisionfusionsforclassifyingkarstwetlandvegetationusingoneclassandmulticlasscnnmodelswithhighresolutionuavimages AT tengfangdeng evaluationofdecisionfusionsforclassifyingkarstwetlandvegetationusingoneclassandmulticlasscnnmodelswithhighresolutionuavimages AT bolinfu evaluationofdecisionfusionsforclassifyingkarstwetlandvegetationusingoneclassandmulticlasscnnmodelswithhighresolutionuavimages AT zhinanlao evaluationofdecisionfusionsforclassifyingkarstwetlandvegetationusingoneclassandmulticlasscnnmodelswithhighresolutionuavimages AT wenlanyang evaluationofdecisionfusionsforclassifyingkarstwetlandvegetationusingoneclassandmulticlasscnnmodelswithhighresolutionuavimages AT hongchanghe evaluationofdecisionfusionsforclassifyingkarstwetlandvegetationusingoneclassandmulticlasscnnmodelswithhighresolutionuavimages AT donglinfan evaluationofdecisionfusionsforclassifyingkarstwetlandvegetationusingoneclassandmulticlasscnnmodelswithhighresolutionuavimages AT wenhe evaluationofdecisionfusionsforclassifyingkarstwetlandvegetationusingoneclassandmulticlasscnnmodelswithhighresolutionuavimages AT yuefengyao evaluationofdecisionfusionsforclassifyingkarstwetlandvegetationusingoneclassandmulticlasscnnmodelswithhighresolutionuavimages |