| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Agricultura Digital. Para informações adicionais entre em contato com cnptia.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Agricultura Digital. |
|
Data corrente: |
28/04/2025 |
|
Data da última atualização: |
29/04/2025 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
TETILA, E. C.; WIRTI JUNIOR, G.; HIGA, G. T. H.; COSTA, A. B. da; AMORIM, W. P.; PISTORI, H.; BARBEDO, J. G. A. |
|
Afiliação: |
EVERTON CASTELÃO TETILA, UNIVERSIDADE FEDERAL DA GRANDE DOURADOS; GELSON WIRTI JUNIOR, UNIVERSIDADE FEDERAL DA GRANDE DOURADOS; GABRIEL TOSHIO HIROKAWA HIGA, UNIVERSIDADE CATÓLICA DOM BOSCO; ANDERSON BESSA DA COSTA, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; WILLIAN PARAGUASSU AMORIM, UNIVERSIDADE FEDERAL DA GRANDE DOURADOS; HEMERSON PISTORI, UNIVERSIDADE CATÓLICA DOM BOSCO, UNIVERSIDADE FEDERAL DE MATO GROSSO DO SUL; JAYME GARCIA ARNAL BARBEDO, CNPTIA. |
|
Título: |
Deep learning models for detection and recognition of weed species in corn crop. |
|
Ano de publicação: |
2025 |
|
Fonte/Imprenta: |
Crop Protection, v. 195, 107237, Sept. 2025. |
|
Páginas: |
8 p. |
|
ISSN: |
0261-2194 |
|
DOI: |
https://doi.org/10.1016/j.cropro.2025.107237 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Weed detection and control are important challenges in modern agriculture. Weed infestation can significantly reduce crop yields. The identification of weeds by species, along with their location, is important to reduce production costs and the environmental impact resulting from the use of chemical control across the plantation. In this study, we assessed four deep learning models for detection and recognition of weed species in corn crop. UAV flights were carried out over six corn farming areas at an altitude of 10 meters. Using LabelImg, we labeled almost 10,000 samples of six weed species with high incidence in corn crops. The resulting WEED6C-Dataset was made available for academic purposes. Model assessment was carried out using a 5-fold cross-validation, three metrics for classification evaluation, and six metrics for detection evaluation. Experimental results showed evidence for statistically significant differences between the assessed models. In our experiments, the Faster RCNN architecture obtained the best results for recall, f-score, RMSE, MAE, R2, mAP50, mAP75 and mAP50-95. On the other hand, the SABL, FoveaBox and YOLOv3 architectures achieved higher precision rates for weed recognition in corn. |
|
Palavras-Chave: |
Aprendizado profundo; Deep learning; Detecção de objeto; Weed. |
|
Thesagro: |
Agricultura de Precisão; Milho; Zea Mays. |
|
Thesaurus Nal: |
Corn; Precision agriculture. |
|
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
|
Marc: |
LEADER 02173naa a2200337 a 4500
001 2175179
005 2025-04-29
008 2025 bl uuuu u00u1 u #d
022 $a0261-2194
024 7 $ahttps://doi.org/10.1016/j.cropro.2025.107237$2DOI
100 1 $aTETILA, E. C.
245 $aDeep learning models for detection and recognition of weed species in corn crop.$h[electronic resource]
260 $c2025
300 $a8 p.
520 $aWeed detection and control are important challenges in modern agriculture. Weed infestation can significantly reduce crop yields. The identification of weeds by species, along with their location, is important to reduce production costs and the environmental impact resulting from the use of chemical control across the plantation. In this study, we assessed four deep learning models for detection and recognition of weed species in corn crop. UAV flights were carried out over six corn farming areas at an altitude of 10 meters. Using LabelImg, we labeled almost 10,000 samples of six weed species with high incidence in corn crops. The resulting WEED6C-Dataset was made available for academic purposes. Model assessment was carried out using a 5-fold cross-validation, three metrics for classification evaluation, and six metrics for detection evaluation. Experimental results showed evidence for statistically significant differences between the assessed models. In our experiments, the Faster RCNN architecture obtained the best results for recall, f-score, RMSE, MAE, R2, mAP50, mAP75 and mAP50-95. On the other hand, the SABL, FoveaBox and YOLOv3 architectures achieved higher precision rates for weed recognition in corn.
650 $aCorn
650 $aPrecision agriculture
650 $aAgricultura de Precisão
650 $aMilho
650 $aZea Mays
653 $aAprendizado profundo
653 $aDeep learning
653 $aDetecção de objeto
653 $aWeed
700 1 $aWIRTI JUNIOR, G.
700 1 $aHIGA, G. T. H.
700 1 $aCOSTA, A. B. da
700 1 $aAMORIM, W. P.
700 1 $aPISTORI, H.
700 1 $aBARBEDO, J. G. A.
773 $tCrop Protection$gv. 195, 107237, Sept. 2025.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Agricultura Digital (CNPTIA) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 2 | |
| 1. |  | COLEBROOK, E.; COELHO FILHO, M. A.; LIOYD, Y. L. D.; THOMAS, S.; PHILLIPS, A.; WHALLEY, W. R.; HEDDEN, P. The role of gibberellin in the response to drying soil. WORKSHOP ON BIOTIC AND ABIOTIC STRESS TOLERANCE IN PLANTS, 2013, Ilhéus. The challenge for the 21st century: book of abstracts. [S.l.]: International Advanced Biology Consortium, 2013. Online. S0P04.| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Mandioca e Fruticultura. |
|    |
| Registros recuperados : 2 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
