Flight height, resolution and what a drone image can tell you.
Overview
A multirotor UAV with an RGB camera is a cheap, flexible remote sensing platform. The key trade-off is altitude: flying higher covers more area per image and means less data, but individual plants vanish.
Key concepts
Ground sampling distance
GSD is the ground size of one pixel: sensor width × altitude ÷ (focal length × image width). Halve the altitude and you halve the GSD.
Altitude trade-off
At 12 m and 25 m we could detect single thistle plants with YOLO; at 20–30 m in crops, single plants could no longer be distinguished, so we estimated weed pressure statistically from row structure instead.
Georeferencing
Markers placed in the field with known positions allow a geometric transformation from image pixels to map coordinates.
Orthophotos
Stitched, geometrically corrected mosaics that can be used like a map for row detection and zoning.
Code examples
Ground sampling distance (GSD) from camera and flight parameters
def gsd_cm(sensor_width_mm, focal_mm, altitude_m, image_width_px):
"""Ground sampling distance in cm per pixel."""
return sensor_width_mm * altitude_m * 100 / (focal_mm * image_width_px)
print(gsd_cm(13.2, 8.8, 25, 5472)) # 1-inch sensor camera at 25 m -> about 0.69 cm/px
Case study
Case studies from my work: weed pressure from 20–30 m images and thistle spot spraying from 12–25 m images.
References from my work
2025Q1
Aerial Image-Based Crop Row Detection and Weed Pressure Mapping Method
L. Moldvai, P. Á. Mesterházi, G. Teschner, A. Nyéki
Agronomy 2025, 15(8), 1762
Abstract
A six-phase, feature-based computer vision method that detects crop rows and generates weed pressure maps from UAV images taken at 20–30 m, without training data or deep learning. Tested on 208 images and 120 artificial datasets; the in-row concentration ratio (IRCR) tells whether a result is usable. With 678 crop plants and 600 weeds the method reached F1 = 86.32 %, and the weed-to-crop ratio correlated 98–99 % with ground truth.
UAV-Based Detection and Precision Management of Cirsium arvense: An End-to-End Workflow from Deep Learning to Variable-Rate Spraying
L. Moldvai, P. Á. Mesterházi, G. Teschner, A. Nyéki
Proceedings of the 17th International Conference on Precision Agriculture (ICPA) and 11th Brazilian Congress on Precision and Digital Agriculture, Porto Alegre, Brazil, 13–15 July 2026
Abstract
An end-to-end workflow for detecting creeping thistle (Cirsium arvense) in UAV imagery and turning the detections into sprayer-compatible management zones. A single-class YOLO model trained on 800 annotated tiles (augmented to 13,280 images) reached [email protected] = 78.97 % and F1 = 77.2 %. Herbicide was needed on only 32.43 % of the field, a 67.57 % reduction compared with full-area spraying.