DEEP CONVOLUTIONAL NEURAL NETWORKS FOR WEED DETECTION IN AGRICULTURAL CROPS USING OPTICAL AERIAL IMAGES

The presence of weeds in agricultural crops has been one of the problems of greatest interest in recent years as they consume natural resources and negatively affect the agricultural process. For this purpose, a model has been implemented to segment weed in aerial images. The proposed model relies o...

Full description

Saved in:
Bibliographic Details
Published in:International archives of the photogrammetry, remote sensing and spatial information sciences. remote sensing and spatial information sciences., 2020-11, Vol.XLII-3/W12-2020, p.551-555
Main Authors: Ramirez, W., Achanccaray, P., Mendoza, L. F., Pacheco, M. A. C.
Format: Article
Language:English
Subjects:
Agricultural land
Artificial neural networks
Crops
High resolution
Image resolution
Imagery
Natural resources
Resolution
Saccharides
Weeds
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The presence of weeds in agricultural crops has been one of the problems of greatest interest in recent years as they consume natural resources and negatively affect the agricultural process. For this purpose, a model has been implemented to segment weed in aerial images. The proposed model relies on DeepLabv3 architecture trained upon patches extracted from high-resolution aerial imagery. The dataset employed consisted in 5 high-resolution images that describes a sugar beet agricultural field in Germany. SegNet and U-Net architectures were selected for comparison purposes. Our results demonstrate that balancing of data, together with a greater spatial context leads better results with DeepLabv3 achieving up to 0.89 and 0.81 in terms of AUC and F1-score, respectively.
ISSN:2194-9034
1682-1750
2194-9034
DOI:10.5194/isprs-archives-XLII-3-W12-2020-551-2020