Detecting functional field units from satellite images in smallholder farming systems using a deep learning based computer vision approach: a case study from Bangladesh
Improving agricultural productivity of smallholder farms (which are typically less than 2 ha) is key to food security for millions of people in developing nations. Knowledge of the size and location of crop fields forms the basis for crop statistics, yield forecasting, resource allocation, economic...
| Autores: | , , , , |
|---|---|
| Formato: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2020 |
| País: | México |
| Recursos: | Centro Internacional de Mejoramiento de Maíz y Trigo |
| Repositorio: | Repositorio Institucional de Publicaciones Multimedia del CIMMYT |
| OAI Identifier: | oai:repository.cimmyt.org:10883/20982 |
| Acesso em linha: | https://hdl.handle.net/10883/20982 |
| Access Level: | acceso abierto |
| Palavra-chave: | AGRICULTURAL SCIENCES AND BIOTECHNOLOGY Field Boundaries Smallholder Farming Deep Learning Convolutional Neural Networks FIELDS BOUNDARIES SMALLHOLDERS MACHINE LEARNING NEURAL NETWORKS |
| Resumo: | Improving agricultural productivity of smallholder farms (which are typically less than 2 ha) is key to food security for millions of people in developing nations. Knowledge of the size and location of crop fields forms the basis for crop statistics, yield forecasting, resource allocation, economic planning, and for monitoring the effectiveness of development interventions and investments. We evaluated three different full convolutional neural network (F–CNN) models (U-Net, SegNet, and DenseNet) with deep neural architecture to detect functional field boundaries from the very high resolution (VHR) WorldView-3 satellite imagery from Southern Bangladesh. The precision of the three F–CNN was up to 0.8, and among the three F–CNN models, the highest precision, recalls, and F-1 score was obtained using a DenseNet model. This architecture provided the highest area under the receiver operating characteristic (ROC) curve (AUC) when tested with independent images. We also found that 4-channel images (blue, green, red, and near-infrared) provided small gains in performance when compared to 3-channel images (blue, green, and red). Our results indicate the potential of using CNN based computer vision techniques to detect field boundaries of small, irregularly shaped agricultural fields. |
|---|