RAMS: Resource-Adaptive and Detection-Conditioned Model Switching for Embedded Edge Perception
Researchers have developed RAMS, a novel runtime controller designed for embedded edge perception systems. RAMS dynamically switches between different tiers of YOLOv8 models based on real-time device resource monitoring and detection conditions. This adaptive approach aims to optimize the balance between inference latency and detection quality, particularly in resource-constrained environments like those found on Raspberry Pi 5 and NVIDIA Jetson Orin platforms. AI