Mapping olive-tree geometric features from 3D models generated with an unmanned aerial vehicle
In: Precision agriculture '15Search for other papers by J. Torres-Sánchez in
Current site
Google Scholar
PubMed
Search for other papers by F. López-Granados in
Current site
Google Scholar
PubMed
Search for other papers by J.M. Peña in
Current site
Google Scholar
PubMed
Purchase instant access (PDF download and unlimited online access):
A detailed monitoring of the olive-tree dimensions can increase efficiency of precision oliviculture. This article presents an innovative and high-throughput methodology of obtaining this data based on two phases: (1) generation of 3D digital surface models of the olive field from unmanned aerial vehicle images; and (2) implementation of an object-based image analysis (OBIA) procedure for automatic mapping of the geometric features of each individual tree. The photogrammetric software was able to perform the 3D reconstruction of 100% of the olive trees, which were successfully detected by the OBIA methodology with minimum user interaction. Evaluation of the olive-tree (area-based) map reported 97.4% of overall accuracy, meanwhile the projected area, height and volume of each tree were automatically retrieved in tabular format for further analysis.