ESTIMATION OF SUNFLOWER SEEDLINGS COUNT AND WEED DETECTION USING DEEP LEARNING ON UAV-CAPTURED RGB IMAGES
I.A. Pestunov1,2, R.A. Kalashnikov1, N.V. Ovcharova3, V.I. Belyaev4, M.M. Silantieva3
1Federal Research Center for Information and Computational Technologies, Novosibirsk, Russia
2Institute of Automation and Electrometry, Siberian Branch, Russian Academy of Sciences, Novosibirsk, Russia
3Altai State University, Barnaul, Russia
4Altai State Agricultural University, Barnaul, Russia
Keywords: RGB images, UAV, sunflower seedlings, plant count, convolutional neural network, DeepLabV3+, ResNet-101, YOLOv8, semantic segmentation, weed detection
Abstract
Automated methods for counting the number of sunflower seedlings and constructing weed maps based on ultra-high spatial resolution RGB images obtained using an unmanned aerial vehicle are proposed. We propose automated methods for counting the number of sunflower seedlings and constructing weed vegetation maps from RGB images of ultra-high spatial resolution obtained by an unmanned aerial vehicle. The methods are based on the use of convolutional neural networks DeepLabv3+, ResNet-101, and YOLOv8. The results of experimental studies show that the accuracy of estimating the number of sunflower seedlings at early stages is 96% on the average.
|
