Ensuring public safety for women in transit environments, particularly within isolated train coaches, has emerged as a critical sociotechnical challenge. While contemporary AI-driven surveillance systems offer high accuracy, their deployment is frequently hindered by the prohibitive costs of specialized edge-computing hardware, such as NVIDIA Jetson modules, which limits large-scale implementation in developing infrastructure. This paper presents the design and development of a low-cost, multimodal safety response system optimized for the Raspberry Pi 5 platform. The technical architecture leverages OpenCV and TensorFlow Lite to perform concurrent blink detection (using Eye Aspect Ratio algorithms), human fall detection, and facial recognition to identify potential distress or medical emergencies. These responses include the immediate activation of high-intensity alarm lights and buzzers, the deployment of physical safety partitions through servo-driven mechanisms, and the release of a deterrent fog sprayer to obstruct an aggressor's vision .Furthermore, the system ensures reliable remote notification by employing a SIM800L GSM module to transmit instantaneous SMS alerts and GPS coordinates to railway authorities This study demonstrates that a highly functional, responsive, and realistic safety solution can be built using affordable edge-AI components, offering a scalable blueprint for enhancing public safety in mass transit systems
Duche et al. (Wed,) studied this question.