Next Article in Journal
Remote Sensing Calculation of the Influence of Wildfire on Erosion in High Mountain Areas
Next Article in Special Issue
Three-Dimensional Reconstruction of Soybean Canopy Based on Multivision Technology for Calculation of Phenotypic Traits
Previous Article in Journal
The Effect of a Preparation Containing Rhizobial Nod Factors on Pea Morphological Traits and Physiology
 
 
Article

Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images

by 1,*, 1,2,* and 1,3
1
Department of Computer Science, Prince Sultan University, Riyadh 12435, Saudi Arabia
2
CISTER Research Centre, ISEP, Polytechnic Institute of Porto, 4200-465 Porto, Portugal
3
Research Laboratory SEICT, LR18ES44, University of Carthage, Carthage 1054, Tunisia
*
Authors to whom correspondence should be addressed.
Academic Editors: Miguel Ángel Miranda Chueca and Bartomeu Alorda Ladaria
Agronomy 2021, 11(8), 1458; https://doi.org/10.3390/agronomy11081458
Received: 25 May 2021 / Revised: 10 July 2021 / Accepted: 16 July 2021 / Published: 22 July 2021
In this paper, we propose an original deep learning framework for the automated counting and geolocation of palm trees from aerial images using convolutional neural networks. For this purpose, we collected aerial images from two different regions in Saudi Arabia, using two DJI drones, and we built a dataset of around 11,000 instances of palm trees. Then, we applied several recent convolutional neural network models (Faster R-CNN, YOLOv3, YOLOv4, and EfficientDet) to detect palms and other trees, and we conducted a complete comparative evaluation in terms of average precision and inference speed. YOLOv4 and EfficientDet-D5 yielded the best trade-off between accuracy and speed (up to 99% mean average precision and 7.4 FPS). Furthermore, using the geotagged metadata of aerial images, we used photogrammetry concepts and distance corrections to automatically detect the geographical location of detected palm trees. This geolocation technique was tested on two different types of drones (DJI Mavic Pro and Phantom 4 pro) and was assessed to provide an average geolocation accuracy that attains 1.6 m. This GPS tagging allows us to uniquely identify palm trees and count their number from a series of drone images, while correctly dealing with the issue of image overlapping. Moreover, this innovative combination between deep learning object detection and geolocalization can be generalized to any other objects in UAV images. View Full-Text
Keywords: unmanned aerial vehicles; convolutional neural networks; Faster R-CNN; You Only Look Once (YOLO) unmanned aerial vehicles; convolutional neural networks; Faster R-CNN; You Only Look Once (YOLO)
Show Figures

Figure 1

MDPI and ACS Style

Ammar, A.; Koubaa, A.; Benjdira, B. Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images. Agronomy 2021, 11, 1458. https://doi.org/10.3390/agronomy11081458

AMA Style

Ammar A, Koubaa A, Benjdira B. Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images. Agronomy. 2021; 11(8):1458. https://doi.org/10.3390/agronomy11081458

Chicago/Turabian Style

Ammar, Adel, Anis Koubaa, and Bilel Benjdira. 2021. "Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images" Agronomy 11, no. 8: 1458. https://doi.org/10.3390/agronomy11081458

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop