Method on Efficient Operation of Multiple Models for Vision-Based In-Flight Risky Behavior Recognition in UAM Safety and Security

The rapid development of urban air mobility (UAM) has emphasized the need for in-flight control and passenger safety management. Recently, with the significant spread of technology in the field of computer vision, research has been conducted to manage passenger safety and security with vision-based approaches. Previous research predominantly focuses on single-task vision models, which limits their ability to comprehensively recognize various situations. In addition, conventional vision-based deep learning models require substantial computational power, potentially reducing the operational sustainability of UAMs with limited electrical resources. In this study, we propose a novel cabin surveillance framework for passenger safety and security. The proposed method achieves high accuracy by using a single model optimized for a specific task and ensures maximum computational efficiency through a scheduler that executes the appropriate models based on the situation. It can effectively perform roles such as detecting prohibited items and recognition of dangerous/abnormal behavior. Moreover, it simplifies the management of the involved models by adding new models or updating the existing ones, and it provides a sustainable system by reducing energy consumption. Through comprehensive experiments on various benchmarks, we validated the effectiveness of each model and verified the practicality of the proposed framework in terms of time complexity and resource usage through practical tests.