Olive Tree Biovolume from UAV Multi-Resolution Image Segmentation with Mask R-CNN

Abstract

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.

In-Field Automatic Detection of Grape Bunches under a Totally Uncontrolled Environment

“…The trained network was then “fine-tuned” with pear tree images to also detect pears. To estimate the biovolume of olive trees, Safonova et al [ 31 ] used deep learning instance segmentation methods. They analyzed RGB images and two well-known normalized difference vegetation indexes.…”

Water tank and swimming pool detection based on remote sensing and deep learning: Relationship with socioeconomic level and applications in dengue control

“…From the input data (Step 1), we performed a data processing step (Step 2), because the original UAV images were larger than 15000 × 15000 pixels and over 1 GB in size, which required high processing power. To resolve this problem, we reduced the file size of the images using ArcGIS 10.5 by converting from TIFF to JPG, because the JPG is the most suitable format for training the DL model [ 50 ]. It is important to highlight that the spatial resolution remained at approximately 0.03 m/pixel, because, although the JPG files are a loss compression format, when the conversion is done properly, such as through professional software like ArcGIS, it still obtains good quality images.…”

Deep Convolutional Neural Network for Large-Scale Date Palm Tree Mapping from UAV-Based Images

“…The mapping and detection of individual tree crowns, tree/plant/vegetation species, crops, and wetlands from UAV-based images are achieved by diverse CNN architectures, which are used to perform different tasks, including path-based classification [78][79][80][81][82][83][84][85][86][87], object detection [88][89][90][91][92][93][94][95][96][97], and semantic segmentation [98][99][100][101][102][103][104][105][106][107]. Recently, semantic segmentation, a commonly used term in computer vision where each pixel within the input imagery is assigned to a particular class, has been a widely used technique in diverse earth-related applications [108].…”