获取途径

作者

Hanqi Tang Dandan Zhou Haozhou Zhai Yalu Han

作者单位

¹School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China ²School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China ³Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, China

刊名

IEEE Access

年份

2024

卷号

Vol.12

页码

159738-159747

关键词

Cameras Real-time systems Computational modeling Defect detection YOLO Image edge detection Feature extraction Roads Neck Safety Real-time Detection Detection Model Real-time Detection Model Network Model High Precision Highway Detection Performance Real-time Performance Balance Performance Computational Overhead Edge Devices Neck Structure Model Performance Image Quality High-quality Images Light Weight Feature Fusion Residual Block Inference Time Precise Detection Camera Height Lightweight Model Performance Of Different Models Floating-point Operations Front Vehicle Camera Angle Important Metrics Subsequent Detection Kernel Principal Component Analysis Range Of Views

摘要

With a long-term usage, highways usually suffer from diverse pavement defects, which causes burdensome pavement defect detections on vast areas. To address this issue, the real-time and vehicle-mounted technique has been proposed and proved to be an efficient solution. However, as the detection systems are deployed on edge devices in complex environments, there exist several practical challenges in terms of real-time speed, detection performance and computational overhead. This study first provi...更多

With a long-term usage, highways usually suffer from diverse pavement defects, which causes burdensome pavement defect detections on vast areas. To address this issue, the real-time and vehicle-mounted technique has been proposed and proved to be an efficient solution. However, as the detection systems are deployed on edge devices in complex environments, there exist several practical challenges in terms of real-time speed, detection performance and computational overhead. This study first provides a dataset captured by real-time and vehicle-mounted camera system. The height and angle where the high frame rate camera locates has been carefully designed to achieve the acquisitions of real-time images on highways. Then, this study proposes a novel lightweight network model named Real-time Pavement Detection of You Only Look Once with a lightweight Light C3 Ghost block and an LCG Path Aggregation Network neck structure, which can fully reduce the computational overheads and maintain a high precision and high speed during detection. Through a series of comparison experiments with current models, RPD-YOLO excels in overall balanced performance and can be deployed in resource-constrained devices to achieve real-time pavement defect detection.收起

文献类型

期刊

浏览量

6