The detection of insects present in large grain shipping sites are becoming crucial to reasoning out a possible treatment to protect them from a massive infestation, which could lead to significant financial losses. This study is oriented to show that hyperspectral imaging combined with a multivariate data processing pipeline can be used to detect insects in wheat. Our approach utilizes two hyperspectral cameras: one operating in the spectral range of 400 to 1000 nm (HySpex VNIR-1800), and the other covering the range of 1000 to 2500 nm (HySpex SWIR-384). This dual-camera setup allows for comprehensive spectral coverage, facilitating the extraction of detailed spectral information. In our multivariate data analysis strategy, we employ a combination of multivariate curve resolution-alternating least squares (MCR-ALS) [De Juan 2010] and factorial discriminant analysis (FDA) [Hand 1985]. MCR-ALS is utilized to extract chemically significant spectral signatures and generate distribution maps of wheat and insect images. The resulting MCR scores serve as input for FDA to distinguish pixels corresponding to wheat grains or insects. Additionally, insect identification is achieved using Multivariate Imaging Analysis-Toolbox functions. Our methodology is tested on images captured by the individual cameras separately. Subsequently, data from both cameras are merged using a fusion imaging strategy. By combining data from multiple hyperspectral cameras, we aim to improve the accuracy and reliability of insect detection and quantification. Comparison of results from individual MCR/FDA models and the fused model will be provided to assess the efficacy of each approach. Preliminary results are very encouraging that promote further investigation to propose the strategy studied as a good approach for the detection of insects that could help to reinforce insect control at the main shipping sites.