Machine vision algorithm for whiteflies (Bemisia tabaci Genn.) scouting under greenhouse environment

Abstract

One of the main problems in greenhouse crop production is the presence of pests. Detection and classification of insects are priorities in integrated pest management (IPM). This document describes a machine vision system able to detect whiteflies (Bemisia tabaci Genn.) in a greenhouse by sensing their presence using hunting traps. The extracted features corresponding to the eccentricity and area of the whiteflies projections allow to establish differences among pests and other insects on both the trap surfaces and dust generated artefacts. Because of whiteflies geometrical characteristics, it was possible to design an efficient (related to manual counting) machine vision algorithm to scout and count units of this pest within a greenhouse environment. These algorithm results show high correlation indexes for both, sticky screens (R2 = 0.97) and plant leaf situations (R2 = 1.0). The machine vision algorithm reduces the scouting time and the associated human error for IPM‐related activities.

A Web Service for Assessing Insect Abundances for Meadow Birds by Image Analysis

“…To make such largescale monitoring possible a system would have to be developed that is capable of automatically determining the number of insects present on a trap, as well as grouping the insects in different size classes. Several earlier studies have created similar programs to count the number of pests caught on sticky traps placed in greenhouses (Barbedo, 2014;Solis-Sánchez et al, 2009), but our literature research did not indicate the existence of similar programs related to conservation efforts. This is important because the difference between the present research and these earlier studies is that there are no expectations to identify the species present on these sticky traps, but that the size of the insects is important to this study, whilst size was not a factor in the identification of various pests.…”

Automatic Segmentation and Counting of Aphid Nymphs on Leaves Using Convolutional Neural Networks

“…These strategies achieved low misclassification rate, but manual correction was involved in some cases. Similar approaches were taken by Solis-Sánchez et al in 2009 [10] and 2011 [11]. As Barbedo [8] suggested, designing more effective features to describe and detect the target could further improve segmentation performance.…”

Sampling of Bemisia tabaci adults using a pre-programmed autonomous pest control robot

“…Recognition, counting, and recording whiteflies collected on the sticky trap on the Cabbot were conducted by a software developed according to Xia et al (2012). Among numerous algorithms for detection of small sized insects (Cho et al, 2007;Solis Sánchez et al, 2009;Bechar et al, 2010;Kumar et al, 2010), multi-fractal analysis was employed to detect whitefly images from sticky trap images in our study since the method was outstanding in detection of small-sized pests against various noise produced on sticky traps under field conditions (Xia et al, 2012).…”