Automatic objects detection & extraction by machine learning
Counting by machine learning, results obtained from a drone on a plot of olive trees of 13ha in Andalusia. Summary plan built in Pdf and Dwg formats, dedicated to the analysis of the spatial distribution of the 1948 plantations detected by machine learning.
Machine learning is a field of study of artificial intelligence that uses mathematical and statistical approaches to give computers the ability to “learn” from data. It improves their performance in solving tasks without being explicitly programmed for each one. More broadly, it concerns the design, analysis, optimization, development and implementation of such methods.
The arrival of artificial intelligence algorithms, coupled with the availability of satellite or aerial images, sounds like a revolution in the field of cartography. Indeed, it is now relatively quick and inexpensive to build geographic databases from raster data.
TECHNICAL INFORMATIONS
- Data processing service : Drones Imaging company.
- Sensor : A7R4 Quad Agrowing.
- Orthophoto : RVB GSD 5cm.
- Spatial accuracy : centimeter with GNSS EMLID Reach RS2.
- Surface totale inspectée : 13ha.
- Automatic counting : 1948 olive trees counted.
- Photogrammetry software : Agisoft Metashape.