Transformer Neural Network for Weed and Crop Classification of High Resolution UAV Images
Трансформерная нейронная сеть для классификации сорных и сельскохозяйственных растений на изображениях высокого разрешения, полученных с БПЛА
2022-01-26
SCID: 54.1/32vwgae7
Discuss with AI
UAV imageryVision Transformersremote sensingtransfer learningweed and crop classification
Figures from the paper
Abstract (AI)
Monitoring crops and weeds is a major challenge in agriculture and food production today. Weeds compete directly with crops for moisture, nutrients, and sunlight. They therefore have a significant negative impact on crop yield if not sufficiently controlled. Weed detection and mapping is an essential step in weed control. Many existing research studies recognize the importance of remote sensing systems and machine learning algorithms in weed management. Deep learning approaches have shown good performance in many agriculture-related remote sensing tasks, such as plant classification, disease detection, etc. However, despite the success of these approaches, they still face many challenges such as high computation cost, the need of large labelled datasets, intra-class discrimination (in growing phase weeds and crops share many attributes similarity as color, texture, and shape), etc. This paper aims to show that the attention-based deep network is a promising approach to address the forementioned problems, in the context of weeds and crops recognition with drone system. The specific objective of this study was to investigate visual transformers (ViT) and apply them to plant classification in Unmanned Aerial Vehicles (UAV) images. Data were collected using a high-resolution camera mounted on a UAV, which was deployed in beet, parsley and spinach fields. The acquired data were augmented to build larger dataset, since ViT requires large sample sets for better performance, we also adopted the transfer learning strategy. Experiments were set out to assess the effect of training and validation dataset size, as well as the effect of increasing the test set while reducing the training set. The results show that with a small labeled training dataset, the ViT models outperform state-of-the-art models such as EfficientNet and ResNet. The results of this study are promising and show the potential of ViT to be applied to a wide range of remote sensing image analysis tasks.
Key Findings
1
Data augmentation and transfer learning were used to support Vision Transformer training when labeled agricultural image datasets were limited.
2
Experiments examined how training, validation, and test-set sizes affect plant-classification performance, including reduced-training scenarios.
3
The results indicate that attention-based Vision Transformers are promising for crop–weed recognition and broader remote-sensing image analysis tasks.
4
The study applies Vision Transformers to classify crops and weeds in high-resolution UAV imagery collected from beet, parsley, and spinach fields.
5
With a small labeled training dataset, Vision Transformer models outperformed state-of-the-art EfficientNet and ResNet models.
Research Object
Weeds and crops in high-resolution UAV images from beet, parsley, and spinach fields
Research Subject
Visual Transformer-based classification performance for distinguishing weeds from crops, including the effects of labeled dataset size and train–test allocation
Publication Details
Publication Date
2022-01-26
Journal
Publisher
ISSN
Cited by
230
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai7
ImageNet classification with deep convolutional neural networks2017
Very Deep Convolutional Networks for Large-Scale Image Recognition2014
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Rethinking the Inception Architecture for Computer Vision2016
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale2020
Randaugment: Practical automated data augmentation with a reduced search space2020
Self-Attention Generative Adversarial Networks2018