Dear guest, welcome to this publication database. As an anonymous user, you will probably not have edit rights. Also, the collapse status of the topic tree will not be persistent. If you like to have these and other options enabled, you might ask Admin (Ivan Eggel) for a login account.
 [BibTeX] [RIS]
An Evaluation of the Generalization Capabilities of Machine Learning Models for Vine Line Detection
Type of publication: Inproceedings
Citation:
Year: 2022
Month: December
Pages: 1-6
Publisher: IEEE
Location: Gold Coast, Australia
Organization: 2022 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)
DOI: 10.1109/CSDE56538.2022.10089303
Abstract: Precision agriculture can optimize the production of agricultural crops by analyzing aerial images with varying resolutions and acquired from different sources. It is widely accepted that machine learning (ML) model, especially deep neural networks (DNN), are very efficient for image segmentation. DNNs have been used to segment complex texture and planting structures, such as vine lines, due to their variations in shape, color and orientation. However existing DNNs reach their limits to segment aerial images with varying resolution and multiple instance of vine lines crossing a entire image. In this paper, we present an improvement of the generalization capabilities of ML models to segment vine lines in satellite images. An approach from a previous works that combine neural networks and other classifiers allow us to improve the classification and generalize the models that increase the f-score by 17%.
Keywords: decision tree ensemble, Deep Neural Network, image analysis, image segmentation, machine learning, Neural Network, Precision agriculture, Transfer Learning, Vine Line Detection, Vineyards
Authors Treboux, Jerome
Pittet, Aurore
Genoud, Dominique
Added by: []
Total mark: 0
Attachments
  • CSDE2022_An_Evaluation_of_the_...
Notes
    Topics