paper-with-me

Papers

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

2025-02-06 · Lucas Rey, Ana M. Bernardos, Andrzej D. Dobrzycki, David Carramiñana, Luca Bergesio, Juan A. Besada, José Ramón Casar

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.

📄 PDF Abstract BibTeX arXiv:2502.15737

Code (0)

등록된 구현이 없습니다.

Tasks

NVIDIA Jetson Orin Nanoobject-detectionObject DetectionQuantizationRaspberry Pi 5

Similar Papers 제목 키워드 기반

LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss

2026-05-09 · Euntae Choi, Sumin Song, Sungjoo Yoo arxiv

Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primary deployment concern. Weight quantization is the standard tool for a…

An Efficient Cervical Whole Slide Image Analysis Framework Based on Multi-scale Semantic and Location Deep Features

2021-06-29 · Ziquan Wei, Shenghua Cheng, Junbo Hu, Li Chen 외

Digital gigapixel whole slide image (WSI) is widely used in clinical diagnosis, and automated WSI analysis is key for computer-aided diagnosis. Currently, analyzing the integrated descriptor of probabilities or feature m…

Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability

2022-07-20 · CVPR 2023 1 · Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky

Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. These methods evaluate a trained model on a new, "probe" dataset and correlate mode…

You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection

2025-03-21 · Daniel Kuhse, Harun Teper, Sebastian Buschjäger, Chien-Yao Wang 외

We introduce AnytimeYOLO, a family of variants of the YOLO architecture that enables anytime object detection. Our AnytimeYOLO networks allow for interruptible inference, i.e., they provide a prediction at any point in t…

object-detectionObject Detection

Lookism: The overlooked bias in computer vision

2024-08-21 · Aditya Gulati, Bruno Lepri, Nuria Oliver

In recent years, there have been significant advancements in computer vision which have led to the widespread deployment of image recognition and generation systems in socially relevant applications, from hiring to secur…

DiversityFairness