A low-cost UAV framework towards ornamental plant detection and counting in the wild

Basit Öğe Kaydı
dc.authoridBayraktar, Ertugrul/0000-0002-7387-4783
dc.authoridBasarkan, Muhammed Enes/0000-0001-7477-5413
dc.authoridCELEBI, NUMAN/0000-0001-7489-9053
dc.authorwosidBayraktar, Ertugrul/A-4705-2015
dc.contributor.authorBayraktar, Ertugrul
dc.contributor.authorBasarkan, Muhammed Enes
dc.contributor.authorCelebi, Numan
dc.date.accessioned2021-12-01T18:49:47Z
dc.date.available2021-12-01T18:49:47Z
dc.date.issued2020
dc.department[Belirlenecek]en_US
dc.description.abstractObject detection still keeps its role as one of the fundamental challenges within the computer vision territory. In particular, achieving satisfying results concerning object detection from outdoor images occupies a considerable space. In this study, in addition to comparing handcrafted feature detector/descriptor performance with deep learning methods over ornamental plant images at the outdoor, we propose a framework to improve the detection of these plants. Firstly, we take query images in the RGB format from the onboard UAV camera. Secondly, our model classifies the scene as a planting or an urban area. Thirdly, if the images are from planting area, thirdly, we filter the field according to the color and acquire only the green parts. Lastly, we feed the object detector model with the filtered area and obtain the category and localization of the plants as a result. In parallel, we also estimate the number of interested plants using the geometrical relations and predefined average plant size, then we verify the outputs of the object detector with this results. The conducted experiments show that deep learning based object detection methods overtake conventional feature detector/descriptor techniques in terms of accuracy, recall, precision, and sensitivity rates. The field classifier model, VGGNet, achieves a 98.17% accuracy for this task, whilst YoloV3 achieves 91.6% accuracy with 0.12 IOU for object detection as the best method. The proposed framework also improves the overall performance of these algorithms by 1.27% for accuracy and 0.023 for IOU. By specifying the limits thoroughly and developing task-dependent approaches, we reveal the great potential of our framework plant detection and counting in the wild consisting of basic image preprocessing techniques, geometrical operations, and deep neural network.en_US
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TBTAK) [1139B411900149]en_US
dc.description.sponsorshipThe authors would like to thank Dr. Levent Calli and Arifiye Cicekcilik Fidancilik Ltd. Co. for their help in data collection using the UAV from the field for the outdoor experiments. This work is supported by The Scientific and Technological Research Council of Turkey (TBTAK) under Grant No. 1139B411900149.en_US
dc.identifier.doi10.1016/j.isprsjprs.2020.06.012
dc.identifier.endpage11en_US
dc.identifier.issn0924-2716
dc.identifier.issn1872-8235
dc.identifier.scopus2-s2.0-85087523754en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage1en_US
dc.identifier.urihttps://doi.org/10.1016/j.isprsjprs.2020.06.012
dc.identifier.urihttps://hdl.handle.net/20.500.12684/10777
dc.identifier.volume167en_US
dc.identifier.wosWOS:000561346200001en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.ispartofIsprs Journal Of Photogrammetry And Remote Sensingen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectObject countingen_US
dc.subjectPlant detectionen_US
dc.subjectRemote sensingen_US
dc.subjectAerial imageryen_US
dc.subjectGeometrical relationsen_US
dc.subjectSpatial-Resolutionen_US
dc.subjectClassificationen_US
dc.subjectImagesen_US
dc.titleA low-cost UAV framework towards ornamental plant detection and counting in the wilden_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
10777.pdf
Boyut:
1.29 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu