onr:"swepub:oai:slubar.slu.se:117825"
Search: onr:"swepub:oai:slubar.slu.se:117825" > Automatic late blig...
- 1 of 1
- Previous record
- Next record
- To hitlist
Automatic late blight lesion recognition and severity quantification based on field imagery of diverse potato genotypes by deep learning
-
- Liljeroth, Erland (author)
- Swedish University of Agricultural Sciences,Sveriges lantbruksuniversitet,Växtskyddsbiologi,Department of Plant Protection Biology
-
- Alexandersson, Erik (author)
- Swedish University of Agricultural Sciences,Sveriges lantbruksuniversitet,Växtskyddsbiologi,Department of Plant Protection Biology
- (creator_code:org_t)
- Elsevier BV, 2021
- 2021
- English.
- In: Knowledge-Based Systems. - : Elsevier BV. - 0950-7051. ; 214
- Journal article (peer-reviewed)
Abstract
Subject headings
Close
- The plant pathogen Phytophthora infestans causes the severe disease late blight in potato, which can result in huge yield loss for potato production. Automatic and accurate disease lesion segmentation enables fast evaluation of disease severity and assessment of disease progress. In tasks requiring computer vision, deep learning has recently gained tremendous success for image classification, object detection and semantic segmentation. To test whether we could extract late blight lesions from unstructured field environments based on high-resolution visual field images and deep learning algorithms, we collected similar to 500 field RGB images in a set of diverse potato genotypes with different disease severity (0%-70%), resulting in 2100 cropped images. 1600 of these cropped images were used as the dataset for training deep neural networks and 250 cropped images were randomly selected as the validation dataset. Finally, the developed model was tested on the remaining 250 cropped images. The results show that the values for intersection over union (IoU) of the classes background (leaf and soil) and disease lesion in the test dataset were 0.996 and 0.386, respectively. Furthermore, we established a linear relationship (R-2 = 0.655) between manual visual scores of late blight and the number of lesions detected by deep learning at the canopy level. We also showed that imbalance weights of lesion and background classes improved segmentation performance, and that fused masks based on the majority voting of the multiple masks enhanced the correlation with the visual disease scores. This study demonstrates the feasibility of using deep learning algorithms for disease lesion segmentation and severity evaluation based on proximal imagery, which could aid breeding for crop resistance in field environments, and also benefit precision farming. (C) 2021 Elsevier B.V. All rights reserved.
Subject headings
- LANTBRUKSVETENSKAPER -- Lantbruksvetenskap, skogsbruk och fiske -- Jordbruksvetenskap (hsv//swe)
- AGRICULTURAL SCIENCES -- Agriculture, Forestry and Fisheries -- Agricultural Science (hsv//eng)
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
- Knowledge-Based Systems (Search for host publication in LIBRIS)
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Liljeroth, Erlan ...
- Alexandersson, E ...
- About the subject
-
- AGRICULTURAL SCIENCES
- AGRICULTURAL SCI ...
- and Agriculture Fore ...
- and Agricultural Sci ...
- Articles in the publication
- Knowledge-Based ...
- By the university
- Swedish University of Agricultural Sciences
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
