Abstract
Abstract. Citrus producers need to monitor orchards frequently, and would benefit greatly from having automated tools to analyze aerial images acquired by drones over the plantations. However, analysing large aerial data sets to enable producers to take management decisions that would optimize productivity and sustainability over time and space remains challenging. Motivated by the success of deep learning in computer vision, this work proposes a novel approach based on Fully Convolutional Regression Networks and Multi-Task Learning to detect individual full-grown trees, tree seedlings, and tree gaps in citrus orchards for inventory tracking. We show that the proposal can identify eight-year-old orange trees with accuracy between 95–99% in high-density commercial plantations where adjacent crowns overlap. This quality of detection was achieved on RGB orthomosaics with a pixel size of about 9.5 cm and requires the nominal spacing between adjacent trees as a priori information. Our results also highlight that detecting tree seedlings and tree gaps remains a challenge. For these two categories, classification sensitivity (recall) was between 59–100% and 63–94%, respectively.
Highlights
Citrus growers need to monitor orchards to keep up-to-date records of the number of bearing trees, to inspect how seedlings develop, and to detect potential anomalies in the plantation that may influence productivity
We present a novel end-to-end architecture that tackles individual citrus inventory considering a single multi-task learning architecture based on fully convolutional regression networks to estimate a density map
Our method is composed of two main steps: (1) training a Fully Convolutional Regression Network (FCRN) in a multi-task learning setting to infer density maps centered at point locations of full-grown orange trees, tree seedlings, and tree gaps; and (2) post-processing and final classification
Summary
Citrus growers need to monitor orchards to keep up-to-date records of the number of bearing trees, to inspect how seedlings develop, and to detect potential anomalies in the plantation that may influence productivity. Traditional orchard monitoring relying on plot sampling and manual inspection of trees in situ is a laborious task and becomes challenging for large commercial plantations. Orchard monitoring using remote sensing is a promising alternative to complement traditional field inspections. In this context, advances in unmanned aerial vehicles (UAV or ”drones”) technology have opened the possibility of on-demand image acquisition, allowing farmers to monitor crops frequently. Drones are present in various applications such as field mapping, weed management, plant stress detection, inventory counting, biomass estimation, and chemical spraying (Hassler, Baysal-Gurel, 2019)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
