Deep features and One-class classification with unsupervised data for weed detection in UAV images. Bah, M. D., Hafiane, A., Canals, R., & Emile, B. In 2019 NINTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA), of International Conference on Image Processing Theory Tools and Applications, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2019. IEEE. Backup Publisher: EURASIP; IEEE; Yeditepe Univ; IEEE Turkey Sect; Univ Paris Saclay; IEEE France Sect; IEEE Yeditepe, KEKAM ISSN: 2154-512X Type: Proceedings Paperabstract bibtex With the raise of the world population, increasing agricultural productivity has become a necessity for farmers. One way to reduce the cost of chemicals and environmental impact is to allocate the right doses of herbicide to the right place and at the right time (precision agriculture). Nowadays, automatic weeds detection is one of the most challenging problem for precision agriculture. However, weeds and crop are hard to discriminate because of their strong similarities. One of the approaches used for weed detection is machine learning. The main common point between machine learning algorithms is the need of training data. In this article we propose to use deep features and one-class classification on unsupervised data for weed detection in UAV images. The results show that one-class classification can be comparable to the literature and also to a deep learning model trained with supervised training data labeling. Results obtained on all test datasets can be up to 90% depending on the data used for the training.
@inproceedings{bah_deep_2019,
address = {345 E 47TH ST, NEW YORK, NY 10017 USA},
series = {International {Conference} on {Image} {Processing} {Theory} {Tools} and {Applications}},
title = {Deep features and {One}-class classification with unsupervised data for weed detection in {UAV} images},
isbn = {978-1-72813-975-3},
abstract = {With the raise of the world population, increasing agricultural productivity has become a necessity for farmers. One way to reduce the cost of chemicals and environmental impact is to allocate the right doses of herbicide to the right place and at the right time (precision agriculture). Nowadays, automatic weeds detection is one of the most challenging problem for precision agriculture. However, weeds and crop are hard to discriminate because of their strong similarities. One of the approaches used for weed detection is machine learning. The main common point between machine learning algorithms is the need of training data. In this article we propose to use deep features and one-class classification on unsupervised data for weed detection in UAV images. The results show that one-class classification can be comparable to the literature and also to a deep learning model trained with supervised training data labeling. Results obtained on all test datasets can be up to 90\% depending on the data used for the training.},
language = {English},
booktitle = {2019 {NINTH} {INTERNATIONAL} {CONFERENCE} {ON} {IMAGE} {PROCESSING} {THEORY}, {TOOLS} {AND} {APPLICATIONS} ({IPTA})},
publisher = {IEEE},
author = {Bah, M. Dian and Hafiane, Adel and Canals, Raphael and Emile, Bruno},
year = {2019},
note = {Backup Publisher: EURASIP; IEEE; Yeditepe Univ; IEEE Turkey Sect; Univ Paris Saclay; IEEE France Sect; IEEE Yeditepe, KEKAM
ISSN: 2154-512X
Type: Proceedings Paper},
keywords = {Deep features, Image processing, One-class SVM, Precision agriculture, Unmanned aerial vehicle, Weeds detection},
}
Downloads: 0
{"_id":"BvwTQv6dx2PnbgLtd","bibbaseid":"bah-hafiane-canals-emile-deepfeaturesandoneclassclassificationwithunsuperviseddataforweeddetectioninuavimages-2019","author_short":["Bah, M. D.","Hafiane, A.","Canals, R.","Emile, B."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"345 E 47TH ST, NEW YORK, NY 10017 USA","series":"International Conference on Image Processing Theory Tools and Applications","title":"Deep features and One-class classification with unsupervised data for weed detection in UAV images","isbn":"978-1-72813-975-3","abstract":"With the raise of the world population, increasing agricultural productivity has become a necessity for farmers. One way to reduce the cost of chemicals and environmental impact is to allocate the right doses of herbicide to the right place and at the right time (precision agriculture). Nowadays, automatic weeds detection is one of the most challenging problem for precision agriculture. However, weeds and crop are hard to discriminate because of their strong similarities. One of the approaches used for weed detection is machine learning. The main common point between machine learning algorithms is the need of training data. In this article we propose to use deep features and one-class classification on unsupervised data for weed detection in UAV images. The results show that one-class classification can be comparable to the literature and also to a deep learning model trained with supervised training data labeling. Results obtained on all test datasets can be up to 90% depending on the data used for the training.","language":"English","booktitle":"2019 NINTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA)","publisher":"IEEE","author":[{"propositions":[],"lastnames":["Bah"],"firstnames":["M.","Dian"],"suffixes":[]},{"propositions":[],"lastnames":["Hafiane"],"firstnames":["Adel"],"suffixes":[]},{"propositions":[],"lastnames":["Canals"],"firstnames":["Raphael"],"suffixes":[]},{"propositions":[],"lastnames":["Emile"],"firstnames":["Bruno"],"suffixes":[]}],"year":"2019","note":"Backup Publisher: EURASIP; IEEE; Yeditepe Univ; IEEE Turkey Sect; Univ Paris Saclay; IEEE France Sect; IEEE Yeditepe, KEKAM ISSN: 2154-512X Type: Proceedings Paper","keywords":"Deep features, Image processing, One-class SVM, Precision agriculture, Unmanned aerial vehicle, Weeds detection","bibtex":"@inproceedings{bah_deep_2019,\n\taddress = {345 E 47TH ST, NEW YORK, NY 10017 USA},\n\tseries = {International {Conference} on {Image} {Processing} {Theory} {Tools} and {Applications}},\n\ttitle = {Deep features and {One}-class classification with unsupervised data for weed detection in {UAV} images},\n\tisbn = {978-1-72813-975-3},\n\tabstract = {With the raise of the world population, increasing agricultural productivity has become a necessity for farmers. One way to reduce the cost of chemicals and environmental impact is to allocate the right doses of herbicide to the right place and at the right time (precision agriculture). Nowadays, automatic weeds detection is one of the most challenging problem for precision agriculture. However, weeds and crop are hard to discriminate because of their strong similarities. One of the approaches used for weed detection is machine learning. The main common point between machine learning algorithms is the need of training data. In this article we propose to use deep features and one-class classification on unsupervised data for weed detection in UAV images. The results show that one-class classification can be comparable to the literature and also to a deep learning model trained with supervised training data labeling. Results obtained on all test datasets can be up to 90\\% depending on the data used for the training.},\n\tlanguage = {English},\n\tbooktitle = {2019 {NINTH} {INTERNATIONAL} {CONFERENCE} {ON} {IMAGE} {PROCESSING} {THEORY}, {TOOLS} {AND} {APPLICATIONS} ({IPTA})},\n\tpublisher = {IEEE},\n\tauthor = {Bah, M. Dian and Hafiane, Adel and Canals, Raphael and Emile, Bruno},\n\tyear = {2019},\n\tnote = {Backup Publisher: EURASIP; IEEE; Yeditepe Univ; IEEE Turkey Sect; Univ Paris Saclay; IEEE France Sect; IEEE Yeditepe, KEKAM\nISSN: 2154-512X\nType: Proceedings Paper},\n\tkeywords = {Deep features, Image processing, One-class SVM, Precision agriculture, Unmanned aerial vehicle, Weeds detection},\n}\n\n","author_short":["Bah, M. D.","Hafiane, A.","Canals, R.","Emile, B."],"key":"bah_deep_2019","id":"bah_deep_2019","bibbaseid":"bah-hafiane-canals-emile-deepfeaturesandoneclassclassificationwithunsuperviseddataforweeddetectioninuavimages-2019","role":"author","urls":{},"keyword":["Deep features","Image processing","One-class SVM","Precision agriculture","Unmanned aerial vehicle","Weeds detection"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mcrimaldi","dataSources":["dq7oSdLvMkrCCarLK"],"keywords":["deep features","image processing","one-class svm","precision agriculture","unmanned aerial vehicle","weeds detection"],"search_terms":["deep","features","one","class","classification","unsupervised","data","weed","detection","uav","images","bah","hafiane","canals","emile"],"title":"Deep features and One-class classification with unsupervised data for weed detection in UAV images","year":2019}