A method for counting and classifying aphids using computer vision

•An automatic method for counting, classification and measurement of Rhopalosiphum padi, an economically important aphid species.•A new software to apply our method is presented: AphidCV.•A validation study show very good results in counting, classification and measurement of aphids, specially nymph...

Full description

Saved in:
Bibliographic Details
Published in:Computers and electronics in agriculture 2020-02, Vol.169, p.105200, Article 105200
Main Authors: Lins, Elison Alfeu, Rodriguez, João Pedro Mazuco, Scoloski, Sandy Ismael, Pivato, Juliana, Lima, Marília Balotin, Fernandes, José Maurício Cunha, da Silva Pereira, Paulo Roberto Valle, Lau, Douglas, Rieder, Rafael
Format: Article
Language:English
Subjects:
Aphids
Classification
Computer vision
Counting
Crops
Damage
Decision making
Evaluation
Image classification
Image processing
Insects
Machine learning
Measurement
Microorganisms
Plant resistance
Recording
Software
Species classification
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•An automatic method for counting, classification and measurement of Rhopalosiphum padi, an economically important aphid species.•A new software to apply our method is presented: AphidCV.•A validation study show very good results in counting, classification and measurement of aphids, specially nymph and wingless classes.•The biggest gain in the use of AphidCV is undoubtedly the time it takes to perform the laboratory analyzes.•AphidCV allow future integration with new and third party systems, and support to include new aphid species. Aphids are insects that attack crops and cause damage directly, by consuming the sap of plants, and indirectly, by vectoring microorganisms that can cause diseases. Cereal crops are hosts for many aphid species, including Rhopalosiphum padi (an economically important aphid species). Recording and classifying aphids are necessary for evaluating and predicting crop damage. Thus, serving as a basis for decision making on the utilization of control measures. It can also be useful to evaluate plant resistance to aphids. Traditionally, the recording process is manual and depends on magnification and well-trained staff. The manual counting is also a time-consuming process and susceptible to errors. With this in mind, this paper presents a method and software to automate the counting and classification of Rhopalosiphum padi using image processing, computer vision, and machine learning methods. The text also presents a comparison of manually counts from experts and values obtained with the software, considering 40 samples. The results showed strong positive correlation in counting and classification (rs = 0.92579) and measurement (r = 0.9799). Concluding, the software proved to be reliable and useful to aphid population monitoring studies.
ISSN:0168-1699
1872-7107
DOI:10.1016/j.compag.2019.105200