Portable, in-field, multispectral imaging sensor for real-time detection of insect viral-vectors

Grieve, Bruce; Veys, Charles; Dingle, Jose; Colvin, John; Nwezeobi, Joachim

doi:10.1109/icsens.2017.8234206

Cited by 2 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Red scales were the smallest insects on the traps as the spatial evaluation performed through the camera attached to the microscope later confirmed. From the literature, it was found that the red scale is the smallest insect along with the whiteflies (1mm -2 mm length) studied by Grieve et al [11], which had a green appearance, very different from red scales. The other insects were bigger, even with a size of some centimeters.…”

Section: Morphological Featuresmentioning

confidence: 96%

“…However, the high cost of NIR image sensors promoted the use of other spectral ranges such as the VIS and the ultraviolet (UV) when deploying multispectral imaging (MSI) systems [11,12]. To reduce the cost, smaller sensors in size are selected in the NIR, providing lower spatial resolution.…”

Section: Introductionmentioning

confidence: 99%

“…Despite this fact, MSI allows useful spatial information to be obtained rather than only spectral data, which can help during insect detection and classification. Grieve et al [11] developed a MSI device for identifying and discriminating species of the Bemisia tabaci whitefly. It consisted of 63 narrow-band light-emitting diodes (LEDs) covering from 380 nm to 940 nm, a modified color CMOS sensor with the spectral range extended to the NIR (<1125 nm) and a macro lens to image the small whiteflies.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Use of spectral information for red scale pest control

García-Guerra¹,

Burgos-Fernández²,

Canals³

et al. 2021

cic

View full text Add to dashboard Cite

Decreasing the use of pesticides is one of the main goals of current agriculture, which requires fast, precise and continuous assessments of crop pests. Citrus pests cause a lot of damage worldwide and the techniques to evaluate them are mainly based on manual, time-consuming readings of insects stuck on traps spread over the crops. This is the case of red scale insects, whose control is notably challenging due to their small size and high reproduction rate. Hence, in this work, we carry out a spectral characterization of this insect in the visible range through spectrometric devices, microscopy and hyperspectral imaging technology to analyze the feasibility of using this information as a means of automatically identifying specimens belonging to this species in this era of precision agriculture. The results obtained show that spectral reflectance differences between red scales and other insects can be recorded at long (red) wavelengths and that red scales are morphologically different, i.e., smaller and more rounded. A reflectance ratio computed from spectral images taken at 774 nm and 410 nm is proposed as a new approach for automated discrimination of red scales from other insects.

show abstract

Section: Morphological Featuresmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Use of spectral information for red scale pest control

García-Guerra¹,

Burgos-Fernández²,

Canals³

et al. 2021

cic

View full text Add to dashboard Cite

show abstract

A method for real-time classification of insect vectors of mosaic and brown streak disease in cassava plants for future implementation within a low-cost, handheld, in-field multispectral imaging sensor

et al. 2018

Self Cite

View full text Add to dashboard Cite

BackgroundThe paper introduces a multispectral imaging system and data-processing approach for the identification and discrimination of morphologically indistinguishable cryptic species of the destructive crop pest, the whitefly Bemisia tabaci. This investigation and the corresponding system design, was undertaken in two phases under controlled laboratory conditions. The first exploited a prototype benchtop variant of the proposed sensor system to analyse four cryptic species of whitefly reared under similar conditions. The second phase, of the methodology development, employed a commercial high-precision laboratory hyperspectral imager to recover reference data from five cryptic species of whitefly, immobilized through flash freezing, and taken from across four feeding environments.ResultsThe initial results, for the single feeding environment, showed that a correct species classification could be achieved in 85–95% of cases, utilising linear Partial Least Squares approaches. The robustness of the classification approach was then extended both in terms of the automated spatial extraction of the most pertinent insect body parts, to assist with the spectral classification model, as well as the incorporation of a non-linear Support Vector Classifier to maintain the overall classification accuracy at 88–98%, irrespective of the feeding and crop environment.ConclusionThis study demonstrates that through an integration of both the spatial data, associated with the multispectral images being used to separate different regions of the insect, and subsequent spectral analysis of those sub-regions, that B. tabaci viral vectors can be differentiated from other cryptic species, that appear morphologically indistinguishable to a human observer, with an accuracy of up to 98%. The implications for the engineering design for an in-field, handheld, sensor system is discussed with respect to the learning gained from this initial stage of the methodology development.

show abstract

Portable, in-field, multispectral imaging sensor for real-time detection of insect viral-vectors

Cited by 2 publications

References 8 publications

Use of spectral information for red scale pest control

Use of spectral information for red scale pest control

A method for real-time classification of insect vectors of mosaic and brown streak disease in cassava plants for future implementation within a low-cost, handheld, in-field multispectral imaging sensor

Contact Info

Product

Resources

About