Risk assessment and physical hazard detection in elderly living environments using multi-scale infrared and visible imagery fusion

With the rapid growth of the elderly population, smart elderly care has become a crucial solution to address this societal challenge, with safety concerns being paramount. Existing research often focuses on fall detection and localization, but overlooks the comprehensive identification of hazards in home environments. This work proposes a preventive hazard detection and safety assessment paradigm based on infrared visible dual-mode fusion, aiming to identify various potential hazards, including the risk of falling, and achieve a paradigm shift from “post response” to “pre prevention”. The model is designed with a channel space dual attention Transformer and a multi-scale adaptive fusion module, which improves the accuracy of hazard detection under different lighting conditions. Experimental results show a 15% improvement in detection accuracy over single-modality images on a custom-collected dataset. Compared to state-of-the-art methods such as DATFuse, IPLF, and Res2Fusion, our approach improves the mean Average Precision by 10%, with higher precision and recall in complex environments. Additionally, a Bayesian-optimized lightweight CNN achieves a 30% reduction in model size while maintaining high accuracy, making it suitable for deployment on resource-constrained devices. This study provides a robust tool for enhancing elderly safety in home environments and establishes a solid foundation for future research in smart elderly care. • Proposes a novel risk assessment framework for elderly living environments. • Combining Transformer and multi-scale fusion methods for two modality image fusion. • Demonstrates a 15% improvement in detection accuracy over single-modality images. • Improves mean Average Precision by 10% compared to state-of-the-art methods. • Propose a lightweight CNN with Bayesian optimization to reduce model size.