Olive Tree Biovolume from UAV Multi-Resolution Image Segmentation with Mask R-CNN
| Autor: | Domingo Alcaraz-Segura, Siham Tabik, Emilio Guirado, Yuriy Maglinets, Anastasiia Safonova |
|---|---|
| Přispěvatelé: | Universidad de Alicante. Instituto Multidisciplinar para el Estudio del Medio 'Ramón Margalef' |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
010504 meteorology & atmospheric sciences
0211 other engineering and technologies 02 engineering and technology lcsh:Chemical technology 01 natural sciences Biochemistry Article Normalized Difference Vegetation Index Analytical Chemistry Olea Machine learning Deep neural networks lcsh:TP1-1185 Chile Electrical and Electronic Engineering Instrumentation 021101 geological & geomatics engineering 0105 earth and related environmental sciences Mathematics Remote sensing Ground truth Pixel Australia olive trees Agriculture Spectral bands Image segmentation Vegetation Ecología Atomic and Molecular Physics and Optics Olive trees Tree (data structure) Ultra-high resolution images machine learning ultra-high resolution images Italy deep neural networks Spain instance segmentation Instance segmentation Olive tree |
| Zdroj: | RUA. Repositorio Institucional de la Universidad de Alicante Universidad de Alicante (UA) Sensors (Basel, Switzerland) Sensors, Vol 21, Iss 1617, p 1617 (2021) Digibug: Repositorio Institucional de la Universidad de Granada Universidad de Granada (UGR) riUAL. Repositorio Institucional de la Universidad de Almería Universidad de Almería Digibug. Repositorio Institucional de la Universidad de Granada instname Sensors Volume 21 Issue 5 |
| Popis: | Olive tree growing is an important economic activity in many countries, mostly in the Mediterranean Basin, Argentina, Chile, Australia, and California. Although recent intensification techniques organize olive groves in hedgerows, most olive groves are rainfed and the trees are scattered (as in Spain and Italy, which account for 50% of the world’s olive oil production). Accurate measurement of trees biovolume is a first step to monitor their performance in olive production and health. In this work, we use one of the most accurate deep learning instance segmentation methods (Mask R-CNN) and unmanned aerial vehicles (UAV) images for olive tree crown and shadow segmentation (OTCS) to further estimate the biovolume of individual trees. We evaluated our approach on images with different spectral bands (red, green, blue, and near infrared) and vegetation indices (normalized difference vegetation index—NDVI—and green normalized difference vegetation index—GNDVI). The performance of red-green-blue (RGB) images were assessed at two spatial resolutions 3 cm/pixel and 13 cm/pixel, while NDVI and GNDV images were only at 13 cm/pixel. All trained Mask R-CNN-based models showed high performance in the tree crown segmentation, particularly when using the fusion of all dataset in GNDVI and NDVI (F1-measure from 95% to 98%). The comparison in a subset of trees of our estimated biovolume with ground truth measurements showed an average accuracy of 82%. Our results support the use of NDVI and GNDVI spectral indices for the accurate estimation of the biovolume of scattered trees, such as olive trees, in UAV images. Russian Foundation for Basic Research (RFBR) 19-01-00215 20-07-00370 European Research Council (ERC) European Commission 647038 Spanish Government RYC-2015-18136 Consejeria de Economia, Conocimiento y Universidad de la Junta de Andalucia P18-RT-1927 DETECTOR A-RNM-256-UGR18 European Research and Development Funds (ERDF) program |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|