Comprehensive Benchmarking of Deep Learning Object Detection Models on Edge Computing Devices

This study comprehensively evaluates the performance of popular deep learning object detection models, including YOLOv8, EfficientDet Lite, and SSD, across various edge computing devices such as Raspberry Pi 3, 4, 5, Pi with TPU accelerators, and NVIDIA Jetson Orin Nano. The evaluation focuses on key metrics including inference time, energy consumption, and accuracy (mean Average Precision).