Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV Images
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....
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-02-01
|
Series: | Drones |
Subjects: | |
Online Access: | https://www.mdpi.com/2504-446X/4/1/7 |
id |
doaj-1a921fc11a884ce2a9ac03f3945c2c19 |
---|---|
record_format |
Article |
spelling |
doaj-1a921fc11a884ce2a9ac03f3945c2c192020-11-25T02:01:59ZengMDPI AGDrones2504-446X2020-02-0141710.3390/drones4010007drones4010007Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV ImagesRobert Chew0Jay Rineer1Robert Beach2Maggie O'Neil3Noel Ujeneza4Daniel Lapidus5Thomas Miano6Meghan Hegarty-Craver7Jason Polly8Dorota S. Temple9RTI International, Research Triangle Park, NC 27709, USARTI International, Research Triangle Park, NC 27709, USARTI International, Research Triangle Park, NC 27709, USARTI International, Research Triangle Park, NC 27709, USAIndependent Agri-Consultant, Kigali 20093, RwandaRTI International, Research Triangle Park, NC 27709, USARTI International, Research Triangle Park, NC 27709, USARTI International, Research Triangle Park, NC 27709, USARTI International, Fort Collins, CO 80528, USARTI International, Research Triangle Park, NC 27709, USAAccurate 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.https://www.mdpi.com/2504-446X/4/1/7remote sensingcrop analyticscrop mappinguavsmachine learningconvolutional neural networksdeep learningsmallholder systems |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Robert Chew Jay Rineer Robert Beach Maggie O'Neil Noel Ujeneza Daniel Lapidus Thomas Miano Meghan Hegarty-Craver Jason Polly Dorota S. Temple |
spellingShingle |
Robert Chew Jay Rineer Robert Beach Maggie O'Neil Noel Ujeneza Daniel Lapidus Thomas Miano Meghan Hegarty-Craver Jason Polly Dorota S. Temple Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV Images Drones remote sensing crop analytics crop mapping uavs machine learning convolutional neural networks deep learning smallholder systems |
author_facet |
Robert Chew Jay Rineer Robert Beach Maggie O'Neil Noel Ujeneza Daniel Lapidus Thomas Miano Meghan Hegarty-Craver Jason Polly Dorota S. Temple |
author_sort |
Robert Chew |
title |
Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV Images |
title_short |
Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV Images |
title_full |
Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV Images |
title_fullStr |
Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV Images |
title_full_unstemmed |
Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV Images |
title_sort |
deep neural networks and transfer learning for food crop identification in uav images |
publisher |
MDPI AG |
series |
Drones |
issn |
2504-446X |
publishDate |
2020-02-01 |
description |
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. |
topic |
remote sensing crop analytics crop mapping uavs machine learning convolutional neural networks deep learning smallholder systems |
url |
https://www.mdpi.com/2504-446X/4/1/7 |
work_keys_str_mv |
AT robertchew deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages AT jayrineer deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages AT robertbeach deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages AT maggieoneil deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages AT noelujeneza deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages AT daniellapidus deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages AT thomasmiano deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages AT meghanhegartycraver deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages AT jasonpolly deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages AT dorotastemple deepneuralnetworksandtransferlearningforfoodcropidentificationinuavimages |
_version_ |
1724954652306309120 |