Redirigiendo al acceso original de articulo en 22 segundos...
Inicio  /  Drones  /  Vol: 4 Par: 1 (2020)  /  Artículo
ARTÍCULO
TITULO

Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV Images

Robert Chew    
Jay Rineer    
Robert Beach    
Maggie O?Neil    
Noel Ujeneza    
Daniel Lapidus    
Thomas Miano    
Meghan Hegarty-Craver    
Jason Polly and Dorota S. Temple    

Resumen

Accurate projections of seasonal agricultural output are essential for improving food security. However, the collection of agricultural information through seasonal agricultural surveys is often not timely enough to inform public and private stakeholders about crop status during the growing season. Acquiring timely and accurate crop estimates can be particularly challenging in countries with predominately smallholder farms because of the large number of small plots, intense intercropping, and high diversity of crop types. In this study, we used RGB images collected from unmanned aerial vehicles (UAVs) flown in Rwanda to develop a deep learning algorithm for identifying crop types, specifically bananas, maize, and legumes, which are key strategic food crops in Rwandan agriculture. The model leverages advances in deep convolutional neural networks and transfer learning, employing the VGG16 architecture and the publicly accessible ImageNet dataset for pretraining. The developed model performs with an overall test set F1 of 0.86, with individual classes ranging from 0.49 (legumes) to 0.96 (bananas). Our findings suggest that although certain staple crops such as bananas and maize can be classified at this scale with high accuracy, crops involved in intercropping (legumes) can be difficult to identify consistently. We discuss the potential use cases for the developed model and recommend directions for future research in this area.

 Artículos similares

       
 
Chinyang Henry Tseng, Woei-Jiunn Tsaur and Yueh-Mao Shen    
In detecting large-scale attacks, deep neural networks (DNNs) are an effective approach based on high-quality training data samples. Feature selection and feature extraction are the primary approaches for data quality enhancement for high-accuracy intrus... ver más
Revista: Future Internet

 
Hua Huang, Zhenfeng Peng, Jinkun Hou, Xudong Zheng, Yuxi Ding and Han Wu    
Disc buckle steel pipe brackets are widely used in building construction due to the advantages of its simple structure, large-bearing capacity, rapid assembling and disassembling, and strong versatility. In complex construction projects, the uncertaintie... ver más
Revista: Buildings

 
Feifei He, Qinjuan Wan, Yongqiang Wang, Jiang Wu, Xiaoqi Zhang and Yu Feng    
Accurately predicting hydrological runoff is crucial for water resource allocation and power station scheduling. However, there is no perfect model that can accurately predict future runoff. In this paper, a daily runoff prediction method with a seasonal... ver más
Revista: Water

 
Benjamin Burrichter, Juliana Koltermann da Silva, Andre Niemann and Markus Quirmbach    
This study employs a temporal fusion transformer (TFT) for predicting overflow from sewer manholes during heavy rainfall events. The TFT utilised is capable of forecasting overflow hydrographs at the manhole level and was tested on a sewer network with 9... ver más
Revista: Hydrology

 
Jun Li, Chenyang Zhang, Jianyi Zhang and Yanhua Shao    
To address the challenge of balancing privacy protection with regulatory oversight in blockchain transactions, we propose a regulatable privacy protection scheme for blockchain transactions. Our scheme utilizes probabilistic public-key encryption to obsc... ver más
Revista: Future Internet