A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications

TL;DR

This study evaluates YOLOv8 object detection models on various edge devices and cloud environments for UAV applications, analyzing their speed, accuracy, and energy use to optimize deployment strategies.

Contribution

It provides a comparative performance analysis of YOLOv8 models on resource-constrained UAV edge devices and cloud, including effects of quantization and communication latency.

Findings

YOLOv8n achieves 52 FPS on Jetson Orin NX and 65 FPS with INT8 quantization.

Raspberry Pi 5 cannot meet real-time processing requirements.

Communication latency impacts real-time UAV image processing.

Abstract

Advancements in embedded systems and Artificial Intelligence (AI) have enhanced the capabilities of Unmanned Aircraft Vehicles (UAVs) in computer vision. However, the integration of AI techniques o-nboard drones is constrained by their processing capabilities. In this sense, this study evaluates the deployment of object detection models (YOLOv8n and YOLOv8s) on both resource-constrained edge devices and cloud environments. The objective is to carry out a comparative performance analysis using a representative real-time UAV image processing pipeline. Specifically, the NVIDIA Jetson Orin Nano, Orin NX, and Raspberry Pi 5 (RPI5) devices have been tested to measure their detection accuracy, inference speed, and energy consumption, and the effects of post-training quantization (PTQ). The results show that YOLOv8n surpasses YOLOv8s in its inference speed, achieving 52 FPS on the Jetson Orin NX and 65 fps with INT8 quantization. Conversely, the RPI5 failed to satisfy the real-time processing needs in spite of its suitability for low-energy consumption applications. An analysis of both the cloud-based and edge-based end-to-end processing times showed that increased communication latencies hindered real-time applications, revealing trade-offs between edge (low latency) and cloud processing (quick processing). Overall, these findings contribute to providing recommendations and optimization strategies for the deployment of AI models on UAVs.