Rapid and low-cost insect detection for analysing species trapped on yellow sticky traps

Abstract

While insect monitoring is a prerequisite for precise decision-making regarding integrated pest management (IPM), it is time- and cost-intensive. Low-cost, time-saving and easy-to-operate tools for automated monitoring will therefore play a key role in increased acceptance and application of IPM in practice. In this study, we tested the differentiation of two whitefly species and their natural enemies trapped on yellow sticky traps (YSTs) via image processing approaches under practical conditions. Using the bag of visual words (BoVW) algorithm, accurate differentiation between both natural enemies and the Trialeurodes vaporariorum and Bemisia tabaci species was possible, whereas the procedure for B. tabaci could not be used to differentiate this species from T. vaporariorum. The decay of species was considered using fresh and aged catches of all the species on the YSTs, and different pooling scenarios were applied to enhance model performance. The best performance was reached when fresh and aged individuals were used together and the whitefly species were pooled into one category for model training. With an independent dataset consisting of photos from the YSTs that were placed in greenhouses and consequently with a naturally occurring species mixture as the background, a differentiation rate of more than 85% was reached for natural enemies and whiteflies.

The Greenhouse Phyllosphere Microbiome and Associations with Introduced Bumblebees and Predatory Mites

“…The presence of these reads in the phyllosphere samples indicates that whiteflies (including eggs or instars) were present on the leaves. Indeed, the two departments in which Portiera reads were abundant suffered from a high number of whiteflies, according to sticky cards, a common method used to monitor pest pressure in greenhouses ( 22 ). This shows that the presence of Portiera in the phyllosphere microbiome could be further investigated as a marker for whitefly populations in greenhouses, possibly allowing for earlier detection and/or a reduction of labor compared to the current method of using sticky cards.…”

Deep Learning Object Detection for Image Analysis of Cherry Fruit Fly (Rhagoletis cerasi L.) on Yellow Sticky Traps

“…In the present study, five different deep learning models were applied to detect cherry fruit flies on yellow sticky traps images and, consequently, choose the better models for multi-class insect detection in the study area. This is a complementary of Böckmann et al (2021) study published in the literature. As indicated in Thenmozhi et al (2021) and Wenyong et al (2021), DL can be valuable modeling tools to help increase our understanding of the complex insect detection processes in pest management solution linked to the agricultural management practices.…”

“…Losses due to pests are not only economic (40% of the world's food supply is destroyed by pests) but also decreasing food security (IPPC Secretariat 2021). Responding appropriately to usually growing healthy food demands under these potentially threatening situations, necessitates the use of innovative pest detection techniques and technologies more than ever (Saleem et al 2021;Böckmann et al 2021). One of the main priorities of any pest management solution is to find suitable methods and models in order to detect insects better (Böckmann et al 2021).…”

“…Responding appropriately to usually growing healthy food demands under these potentially threatening situations, necessitates the use of innovative pest detection techniques and technologies more than ever (Saleem et al 2021;Böckmann et al 2021). One of the main priorities of any pest management solution is to find suitable methods and models in order to detect insects better (Böckmann et al 2021). Nowadays, scientific and technological advances, particularly in image processing techniques and computer vision technology have enabled the application of new tools for describing areas affected by insects and also facilitating pest management to increase yields in the context of precision horticulture (Zude-Sasse et al 2016;Cardim Ferreira Lima et al 2020).…”

Management of the Western Corn Rootworm (D. v. virgifera) in Corn Cultivation System

“…Given these values, it can say that all the traps tested are effective in monitoring activities, which after some authors is an action of detecting the population level of a culture at a time with low costs [34]. For this reason, it tried to combine both detection by capture and efficiency in control (as other researchers have seen in general insect studies) [35,36], because the fact that insects die after captivity in the sticky substance is clear that it is about reducing the population level.…”