A Comprehensive Evaluation of Deep Learning Object Detection Models on Heterogeneous Edge Devices

TL;DR

This paper benchmarks various deep learning object detection models on diverse edge devices, analyzing their accuracy, latency, and energy efficiency under different scene complexities.

Contribution

It provides a comprehensive evaluation of multiple models across heterogeneous edge hardware, highlighting trade-offs and performance insights.

Findings

SSD MobileNet V1 has lowest latency and energy use but lowest accuracy.

YOLOv8 Medium achieves highest accuracy with higher computational cost.

TPU accelerators improve efficiency of SSD and EfficientDet Lite, but reduce YOLOv8 accuracy.

Abstract

Modern applications such as autonomous vehicles, intelligent surveillance, and smart city systems increasingly require object detection on resource-constrained edge devices. Yet, there is still limited understanding of how different object detection models behave across heterogeneous edge devices and under varying scene complexity. In this paper, we benchmark YOLOv8 (Nano, Small, Medium), EfficientDet Lite (Lite0, Lite1, Lite2), and SSD (SSD MobileNet V1, SSDLite MobileDet) on Raspberry Pi 3, 4, 5 with/without Coral TPU accelerators, Raspberry Pi 5 with AI HAT+, Jetson Nano, and Jetson Orin Nano. We evaluate energy consumption, inference time, and accuracy, and further examine how accuracy changes with the number of objects in the input image. The results reveal clear trade-offs among accuracy, latency, and energy efficiency across model-device combinations. SSD MobileNet V1 achieves the lowest latency and energy consumption but the lowest accuracy, whereas YOLOv8 Medium achieves the highest accuracy at higher computational cost. TPU-based Raspberry Pi devices improve the efficiency of SSD and EfficientDet Lite while reducing YOLOv8 accuracy. Orin Nano offers the most favorable overall balance across most model families. The object-count-based analysis further shows that models achieve more similar accuracy on simpler images, while the accuracy gap widens as scene complexity increases.