GLDCNet: A novel convolutional neural network for grapevine leafroll disease recognition using UAV-based imagery

GLDCNet: A novel convolutional neural network for grapevine leafroll disease recognition using UAV-based imagery. Liu, Y., Su, J., Zheng, Z., Liu, D., Song, Y., Fang, Y., Yang, P., & Su, B. Computers and Electronics in Agriculture, 218:108668, Elsevier, 3, 2024.

Paper doi abstract bibtex

High-throughput phenotyping of grapevine leafroll disease (GLD) at the canopy scale helps develop fast and effective management in viticulture. However, detecting GLD efficiently in a vineyard is challenging owing to the limited adaptation of prior art. Therefore, we propose a novel convolutional neural network called GLDCNet to improve GLD recognition using unmanned aerial vehicle–based imagery. The effectiveness of the GLDCNet is attributed to the four new network designs used and is validated through ablation experiments. The GLDCNet achieves a classification accuracy of 99.57% using the RGB dataset and obtains more efficient and accurate results than nine other state-of-the-art methods. Furthermore, we systematically evaluated the impacts of image spatial resolution and vegetation indexes on the classification performance of the model. Experimental results suggest that improving image spatial resolution is more cost-effective than enhancing multispectral information for improving GLD recognition. Our proposed method offers a rapid, scalable, and accurate diagnostic protocol for detecting GLD in vineyards.

@article{
 title = {GLDCNet: A novel convolutional neural network for grapevine leafroll disease recognition using UAV-based imagery},
 type = {article},
 year = {2024},
 keywords = {Deep learning,Grapevine leafroll disease,Multispectral,Spatial resolution,UAV,Vegetation index},
 pages = {108668},
 volume = {218},
 month = {3},
 publisher = {Elsevier},
 day = {1},
 id = {9e131e8a-39cf-3631-bbbf-bc63d1cbc53c},
 created = {2024-09-16T07:07:27.796Z},
 accessed = {2024-09-16},
 file_attached = {true},
 profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},
 group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
 last_modified = {2024-09-16T07:07:31.977Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 folder_uuids = {4dd63b9a-2e78-4e16-b45d-b692d8e0c5c3},
 private_publication = {false},
 abstract = {High-throughput phenotyping of grapevine leafroll disease (GLD) at the canopy scale helps develop fast and effective management in viticulture. However, detecting GLD efficiently in a vineyard is challenging owing to the limited adaptation of prior art. Therefore, we propose a novel convolutional neural network called GLDCNet to improve GLD recognition using unmanned aerial vehicle–based imagery. The effectiveness of the GLDCNet is attributed to the four new network designs used and is validated through ablation experiments. The GLDCNet achieves a classification accuracy of 99.57% using the RGB dataset and obtains more efficient and accurate results than nine other state-of-the-art methods. Furthermore, we systematically evaluated the impacts of image spatial resolution and vegetation indexes on the classification performance of the model. Experimental results suggest that improving image spatial resolution is more cost-effective than enhancing multispectral information for improving GLD recognition. Our proposed method offers a rapid, scalable, and accurate diagnostic protocol for detecting GLD in vineyards.},
 bibtype = {article},
 author = {Liu, Yixue and Su, Jinya and Zheng, Zhouzhou and Liu, Dizhu and Song, Yuyang and Fang, Yulin and Yang, Peng and Su, Baofeng},
 doi = {10.1016/J.COMPAG.2024.108668},
 journal = {Computers and Electronics in Agriculture}
}

Downloads: 0

{"_id":"nfpSFp9fkGNW3YhbL","bibbaseid":"liu-su-zheng-liu-song-fang-yang-su-gldcnetanovelconvolutionalneuralnetworkforgrapevineleafrolldiseaserecognitionusinguavbasedimagery-2024","author_short":["Liu, Y.","Su, J.","Zheng, Z.","Liu, D.","Song, Y.","Fang, Y.","Yang, P.","Su, B."],"bibdata":{"title":"GLDCNet: A novel convolutional neural network for grapevine leafroll disease recognition using UAV-based imagery","type":"article","year":"2024","keywords":"Deep learning,Grapevine leafroll disease,Multispectral,Spatial resolution,UAV,Vegetation index","pages":"108668","volume":"218","month":"3","publisher":"Elsevier","day":"1","id":"9e131e8a-39cf-3631-bbbf-bc63d1cbc53c","created":"2024-09-16T07:07:27.796Z","accessed":"2024-09-16","file_attached":"true","profile_id":"f1f70cad-e32d-3de2-a3c0-be1736cb88be","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2024-09-16T07:07:31.977Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"folder_uuids":"4dd63b9a-2e78-4e16-b45d-b692d8e0c5c3","private_publication":false,"abstract":"High-throughput phenotyping of grapevine leafroll disease (GLD) at the canopy scale helps develop fast and effective management in viticulture. However, detecting GLD efficiently in a vineyard is challenging owing to the limited adaptation of prior art. Therefore, we propose a novel convolutional neural network called GLDCNet to improve GLD recognition using unmanned aerial vehicle–based imagery. The effectiveness of the GLDCNet is attributed to the four new network designs used and is validated through ablation experiments. The GLDCNet achieves a classification accuracy of 99.57% using the RGB dataset and obtains more efficient and accurate results than nine other state-of-the-art methods. Furthermore, we systematically evaluated the impacts of image spatial resolution and vegetation indexes on the classification performance of the model. Experimental results suggest that improving image spatial resolution is more cost-effective than enhancing multispectral information for improving GLD recognition. Our proposed method offers a rapid, scalable, and accurate diagnostic protocol for detecting GLD in vineyards.","bibtype":"article","author":"Liu, Yixue and Su, Jinya and Zheng, Zhouzhou and Liu, Dizhu and Song, Yuyang and Fang, Yulin and Yang, Peng and Su, Baofeng","doi":"10.1016/J.COMPAG.2024.108668","journal":"Computers and Electronics in Agriculture","bibtex":"@article{\n title = {GLDCNet: A novel convolutional neural network for grapevine leafroll disease recognition using UAV-based imagery},\n type = {article},\n year = {2024},\n keywords = {Deep learning,Grapevine leafroll disease,Multispectral,Spatial resolution,UAV,Vegetation index},\n pages = {108668},\n volume = {218},\n month = {3},\n publisher = {Elsevier},\n day = {1},\n id = {9e131e8a-39cf-3631-bbbf-bc63d1cbc53c},\n created = {2024-09-16T07:07:27.796Z},\n accessed = {2024-09-16},\n file_attached = {true},\n profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2024-09-16T07:07:31.977Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n folder_uuids = {4dd63b9a-2e78-4e16-b45d-b692d8e0c5c3},\n private_publication = {false},\n abstract = {High-throughput phenotyping of grapevine leafroll disease (GLD) at the canopy scale helps develop fast and effective management in viticulture. However, detecting GLD efficiently in a vineyard is challenging owing to the limited adaptation of prior art. Therefore, we propose a novel convolutional neural network called GLDCNet to improve GLD recognition using unmanned aerial vehicle–based imagery. The effectiveness of the GLDCNet is attributed to the four new network designs used and is validated through ablation experiments. The GLDCNet achieves a classification accuracy of 99.57% using the RGB dataset and obtains more efficient and accurate results than nine other state-of-the-art methods. Furthermore, we systematically evaluated the impacts of image spatial resolution and vegetation indexes on the classification performance of the model. Experimental results suggest that improving image spatial resolution is more cost-effective than enhancing multispectral information for improving GLD recognition. Our proposed method offers a rapid, scalable, and accurate diagnostic protocol for detecting GLD in vineyards.},\n bibtype = {article},\n author = {Liu, Yixue and Su, Jinya and Zheng, Zhouzhou and Liu, Dizhu and Song, Yuyang and Fang, Yulin and Yang, Peng and Su, Baofeng},\n doi = {10.1016/J.COMPAG.2024.108668},\n journal = {Computers and Electronics in Agriculture}\n}","author_short":["Liu, Y.","Su, J.","Zheng, Z.","Liu, D.","Song, Y.","Fang, Y.","Yang, P.","Su, B."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/18141dfa-26aa-a21f-5c8a-1d2a5723050a/full_text.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"liu-su-zheng-liu-song-fang-yang-su-gldcnetanovelconvolutionalneuralnetworkforgrapevineleafrolldiseaserecognitionusinguavbasedimagery-2024","role":"author","keyword":["Deep learning","Grapevine leafroll disease","Multispectral","Spatial resolution","UAV","Vegetation index"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":["deep learning","grapevine leafroll disease","multispectral","spatial resolution","uav","vegetation index"],"search_terms":["gldcnet","novel","convolutional","neural","network","grapevine","leafroll","disease","recognition","using","uav","based","imagery","liu","su","zheng","liu","song","fang","yang","su"],"title":"GLDCNet: A novel convolutional neural network for grapevine leafroll disease recognition using UAV-based imagery","year":2024}