Evaluation of the potential of Near Infrared Hyperspectral Imaging for monitoring the invasive brown marmorated stink bug

TL;DR

This study evaluates Near Infrared Hyperspectral Imaging (NIR-HSI) for detecting invasive brown marmorated stink bugs on various backgrounds, combining chemometric and deep learning methods to enhance pest monitoring capabilities.

Contribution

It introduces a novel combined chemometric and CNN approach for BMSB detection using NIR-HSI, addressing mimicry and background variability issues.

Findings

Successful discrimination of BMSB from backgrounds using NIR-HSI

Enhanced detection accuracy by merging spectral selection with CNN

Potential for real-time pest monitoring with UAVs and IoT devices

Abstract

The brown marmorated stink bug (BMSB), Halyomorpha halys, is an invasive insect pest of global importance that damages several crops, compromising agri-food production. Field monitoring procedures are fundamental to perform risk assessment operations, in order to promptly face crop infestations and avoid economical losses. To improve pest management, spectral cameras mounted on Unmanned Aerial Vehicles (UAVs) and other Internet of Things (IoT) devices, such as smart traps or unmanned ground vehicles, could be used as an innovative technology allowing fast, efficient and real-time monitoring of insect infestations. The present study consists in a preliminary evaluation at the laboratory level of Near Infrared Hyperspectral Imaging (NIR-HSI) as a possible technology to detect BMSB specimens on different vegetal backgrounds, overcoming the problem of BMSB mimicry. Hyperspectral images of BMSB were acquired in the 980-1660 nm range, considering different vegetal backgrounds selected to mimic a real field application scene. Classification models were obtained following two different chemometric approaches. The first approach was focused on modelling spectral information and selecting relevant spectral regions for discrimination by means of sparse-based variable selection coupled with Soft Partial Least Squares Discriminant Analysis (s-Soft PLS-DA) classification algorithm. The second approach was based on modelling spatial and spectral features contained in the hyperspectral images using Convolutional Neural Networks (CNN). Finally, to further improve BMSB detection ability, the two strategies were merged, considering only the spectral regions selected by s-Soft PLS-DA for CNN modelling.