Improved Machine Learning Methodology for High Precision Agriculture
| Tipo de publicação: | Inproceedings |
| Citação: | |
| Ano: | 2018 |
| Mês: | May |
| Publisher: | Inproceedings of the 2018 Global Internet of Things Summit (GIoTS) |
| Location: | Bilbao, Spain |
| Resumo: | This paper presents the impact of machine learning in precision agriculture. State-of-the art image recognition is applied on a dataset composed of high precision aerial pictures of vineyards. The study presents a comparison of an innovative machine learning methodology compared to a baseline used classically on vineyard and agricultural objects. The baseline uses color analysis and is able discriminates interesting objects with an accuracy of 89.6 %. The machine learning innovative approach demonstrates that the results can be improved to obtain 94.27 % of accuracy. Machine Learning used to enrich and improve the detection of precise agricultural objects is also discussed in this study and opens new perspectives for the future of high precision agriculture. |
| Palavras-chave: | Agricultural health, Hyper-spectral images, Image recognition, machine learning, Precision agriculture, Prediction |
| Autores | |
| Adicionado por: | [] |
| Total mark: | 0 |
|
Anexos
|
|
|
|
|
Notas
|
|
|
|
|
|
Tópicos
|
|
|
|
