Performance Comparison Of Mobile GPUS For Object Detection In Edge Computing

Author

Stabak Das, Prairie View A&M University

Date of Award

8-2025

Document Type

Thesis

Degree Name

Master of Science

Degree Discipline

Electrical Engineering

Abstract

In recent years, deep learning models for computer vision applications like YOLO (You Only Look Once) have become widely used for real-time object detection tasks. Mobile GPUs such as the NVIDIA Jetson series are highly promising for deploying these models in resource-constrained edge computing environments. The objective of this thesis is to examine and compare the performance of object detection of different versions of YOLO models deployed on different NVIDIA Jetson mobile GPUs using different versions of the COCO datasets. This allows for evaluation of the four performance metrics, including detection accuracy, model size, execution time, and power consumption, which emphasizes different aspects across combinations of various YOLO versions, edge devices, and datasets. The experimental results offer important insights into the trade-off among the choices of different YOLO versions and mobile GPUs and their practical potential. Findings demonstrate that the YOLOv8 models maintain similar accuracy levels across all Jetson GPUs, where the accuracy of the models reaches 78% on the COCO8 dataset, underscoring their effectiveness for real-time applications in edge computing. Additionally, this analysis reveals significant variations in power consumption, with the Jetson AXG Orin showing an efficient balance between performance in inference time and energy usage, where the power consumption is only 11.05 W and the inference time is 78.1 ms even while running the most complex YOLOv8x model. This study will help researchers and practitioners to gain insight and select the best combination of mobile GPU and YOLO version for future object detection tasks in edge computing.

Index Terms: benchmarking, deep learning, edge computing, embedded systems, mobile GPUs, object detection, YOLOv8.

Committee Chair/Advisor

Xiangfang Li

Committee Member

Lijun Qian

Committee Member

Daniel Doe

Publisher

Prairie View A&M University

Rights

Date of Digitization

11/18/2025

Contributing Institution

J. B . Coleman Library

City of Publication

Prairie View

MIME Type

Application/PDF

Recommended Citation

Das, S. (2025). Performance Comparison Of Mobile GPUS For Object Detection In Edge Computing. Retrieved from https://digitalcommons.pvamu.edu/pvamu-theses/1655