<p>Food loss caused by postharvest insect infestations is a major challenge to global food security, resulting in significant economic losses and wastage of agricultural resources. Conventional methods for detecting stored grain insect pests, such as visual inspection and trap-based monitoring, are often labor- intensive, destructive, and insufficiently sensitive to detect early-stage infestations, and still, there is a lack in comparing the effectiveness of different imaging technologies and their integration with advanced artificial intelligence and real-time monitoring systems for practical grain storage applications. Therefore, the objective of this to review the applications of hyperspectral imaging, X-ray imaging, and thermal imaging for detecting damage in stored grain insect pests, and to examine the recent advances in deep learning techniques for pest segmentation and classification. This study was based on a comprehensive review related to imaging-based pest detection technologies, focusing on their operational principles, detection performance, advantages, limitations, and integration with Internet of Things (IoT)-based systems. The findings reveal that imaging technologies combined with deep learning approaches significantly enhance the speed, accuracy, and non-invasive detection of stored grain insect pests compared with conventional methods. In Hyperspectral imaging showed high sensitivity in detecting internal grain damage, X-ray imaging proved effective for identifying hidden infestations, and thermal imaging demonstrated strong potential for rapid monitoring applications. Further, IoT integration enables real-time, automated, and scalable pest monitoring in grain storage facilities. This review provides the advancement of intelligent pest detection systems and highlights the policy-related implications for improving food safety, minimizing postharvest losses, enhancing storage management practices, and supporting sustainable agricultural supply chain development.</p>