Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors
Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant inform...
| Main Authors: | , , , , , , |
|---|---|
| Format: | info:eu-repo/semantics/article |
| Language: | English |
| Published: |
MDPI
2021
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10835/9269 |
| _version_ | 1789406714545569792 |
|---|---|
| author | Guirado Hernández, Emilio Blanco Sacristám, Javier Rodríguez Caballero, Emilio Tabik, Siham Alcaraz Segura, Domingo Martínez Valderrama, Jaime Cabello García, Tomás |
| author_facet | Guirado Hernández, Emilio Blanco Sacristám, Javier Rodríguez Caballero, Emilio Tabik, Siham Alcaraz Segura, Domingo Martínez Valderrama, Jaime Cabello García, Tomás |
| author_sort | Guirado Hernández, Emilio |
| collection | DSpace |
| description | Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant information for dryland conservation ecology. For this reason, improving segmentation methods and understanding the effect of spatial resolution on segmentation results is key to improve dryland vegetation monitoring. We explored and analyzed the accuracy of Object-Based Image Analysis (OBIA) and Mask Region-based Convolutional Neural Networks (Mask R-CNN) and the fusion of both methods in the segmentation of scattered vegetation in a dryland ecosystem. As a case study, we mapped Ziziphus lotus, the dominant shrub of a habitat of conservation priority in one of the driest areas of Europe. Our results show for the first time that the fusion of the results from OBIA and Mask R-CNN increases the accuracy of the segmentation of scattered shrubs up to 25% compared to both methods separately. Hence, by fusing OBIA and Mask R-CNNs on very high-resolution images, the improved segmentation accuracy of vegetation mapping would lead to more precise and sensitive monitoring of changes in biodiversity and ecosystem services in drylands. |
| format | info:eu-repo/semantics/article |
| id | oai:repositorio.ual.es:10835-9269 |
| institution | Universidad de Cuenca |
| language | English |
| publishDate | 2021 |
| publisher | MDPI |
| record_format | dspace |
| spelling | oai:repositorio.ual.es:10835-92692023-04-12T19:00:41Z Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors Guirado Hernández, Emilio Blanco Sacristám, Javier Rodríguez Caballero, Emilio Tabik, Siham Alcaraz Segura, Domingo Martínez Valderrama, Jaime Cabello García, Tomás deep-learning fusion mask R-CNN object-based optical sensors cattered vegetation very high-resolution Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant information for dryland conservation ecology. For this reason, improving segmentation methods and understanding the effect of spatial resolution on segmentation results is key to improve dryland vegetation monitoring. We explored and analyzed the accuracy of Object-Based Image Analysis (OBIA) and Mask Region-based Convolutional Neural Networks (Mask R-CNN) and the fusion of both methods in the segmentation of scattered vegetation in a dryland ecosystem. As a case study, we mapped Ziziphus lotus, the dominant shrub of a habitat of conservation priority in one of the driest areas of Europe. Our results show for the first time that the fusion of the results from OBIA and Mask R-CNN increases the accuracy of the segmentation of scattered shrubs up to 25% compared to both methods separately. Hence, by fusing OBIA and Mask R-CNNs on very high-resolution images, the improved segmentation accuracy of vegetation mapping would lead to more precise and sensitive monitoring of changes in biodiversity and ecosystem services in drylands. 2021-01-11T10:48:49Z 2021-01-11T10:48:49Z 2021-01-05 info:eu-repo/semantics/article 1424-8220 http://hdl.handle.net/10835/9269 en https://www.mdpi.com/1424-8220/21/1/320 Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess MDPI |
| spellingShingle | deep-learning fusion mask R-CNN object-based optical sensors cattered vegetation very high-resolution Guirado Hernández, Emilio Blanco Sacristám, Javier Rodríguez Caballero, Emilio Tabik, Siham Alcaraz Segura, Domingo Martínez Valderrama, Jaime Cabello García, Tomás Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors |
| title | Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors |
| title_full | Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors |
| title_fullStr | Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors |
| title_full_unstemmed | Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors |
| title_short | Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors |
| title_sort | mask r-cnn and obia fusion improves the segmentation of scattered vegetation in very high-resolution optical sensors |
| topic | deep-learning fusion mask R-CNN object-based optical sensors cattered vegetation very high-resolution |
| url | http://hdl.handle.net/10835/9269 |
| work_keys_str_mv | AT guiradohernandezemilio maskrcnnandobiafusionimprovesthesegmentationofscatteredvegetationinveryhighresolutionopticalsensors AT blancosacristamjavier maskrcnnandobiafusionimprovesthesegmentationofscatteredvegetationinveryhighresolutionopticalsensors AT rodriguezcaballeroemilio maskrcnnandobiafusionimprovesthesegmentationofscatteredvegetationinveryhighresolutionopticalsensors AT tabiksiham maskrcnnandobiafusionimprovesthesegmentationofscatteredvegetationinveryhighresolutionopticalsensors AT alcarazseguradomingo maskrcnnandobiafusionimprovesthesegmentationofscatteredvegetationinveryhighresolutionopticalsensors AT martinezvalderramajaime maskrcnnandobiafusionimprovesthesegmentationofscatteredvegetationinveryhighresolutionopticalsensors AT cabellogarciatomas maskrcnnandobiafusionimprovesthesegmentationofscatteredvegetationinveryhighresolutionopticalsensors |