Title
Fusion of pixel and object-based features for weed mapping using unmanned aerial vehicle imagery.
Abstract
•Pixel and object-based features were fused for weed detection.•Random Forests was used as classifier for OBIA analysis.•Hough algorithm was used to detect maize row in orthomosaicked UAV imagery.•Cross validation was used to evaluate the performance of the Random Forests.•The accuracy of the weed map was evaluated by the random sampling windows.
Year
DOI
Venue
2018
10.1016/j.jag.2017.12.012
International Journal of Applied Earth Observation and Geoinformation
Keywords
Field
DocType
UAVs,Inter- and intra-row weed detection,Feature fusion,OBIA,Random forests,Hyperparameter tuning,Feature evaluation
Weed,Ground sample distance,Remote sensing,Hough transform,Precision agriculture,Ground truth,Pixel,Random forest,Geography,Cross-validation
Journal
Volume
ISSN
Citations 
67
0303-2434
10
PageRank 
References 
Authors
0.75
16
8
Name
Order
Citations
PageRank
Junfeng Gao111712.83
Wenzhi Liao240331.63
David Nuyttens3112.53
Peter Lootens4102.10
Jürgen Vangeyte5153.99
Aleksandra Pizurica61238102.29
Yong He74415.57
Jan G. Pieters8151.46