| 基于机器视觉的路面破损检测系统研究 |
| |
| 引用本文： | 徐婷,祝站东,郭亚,朱彤.基于机器视觉的路面破损检测系统研究[J].武汉水运工程学院学报,2012(1):34-37. |
| |
| 作者姓名： | 徐婷 祝站东 郭亚 朱彤 |
| |
| 作者单位： | [1]长安大学汽车学院,西安710064 [2]福建工程学院交通运输系,福州350108 [3]江西理工大学电气与自动化学院,赣州341000 |
| |
| 基金项目： | 国家自然科学基金项目（批准号：51108036）; 中央高校基本科研业务费专项资金（批准号：CHD2011JC156）资助 |
| |
| 摘 要： | 分析了系统的基本组成和总体结构,介绍了软件设计流程以及网络设计与训练过程.同时考虑到传统图像分割算法的局限性,设计了一种检测图像内任意区域实时检测算法.可以适应路面龟裂、横裂、纵裂、块裂等多种缺陷以及缺陷并存的复杂道路样本图像.
|
| 关 键 词： | 路面检测 机器视觉 神经网络 检测系统 |
Development of Road Surface Inspection System Based on Computer Vision with Imporved Neural Network |
| |
| Authors: | Xu Ting Zhu Zhandong Guo Ya Zhu Tong |
| |
| Institution: | Xu Ting Zhu Zhandong Guo Ya Zhu Tong(School of Automobile, Chang＇an University, Xi＇an 7100642,China)1) (Transportation Department, Fujian University of Technology, Fujian 350108, China)2) (School of Electrical Engineering and Automation, J iangxi University of Science and Technology, Ganzhou 341000, China) |
| |
| Abstract: | This article analyzed the system basic composition and overall structure and introduced the system software flow as well as the network design and training process. The system has realized a kind of real-time online inspection method with the free region of image. The experimental result proved that.. It can adapt itself to the complex sample image analysis processing, so this inspection method has strong flexibility, simultaneously speed of examination was quick and completely satisfied the requirement of the real-time inspection and it can provide the onqine inspection the serious degree of defect analysis with rations. |
| |
| Keywords: | roadway surface inspection computer vision neural network defect detection system |
| 本文献已被 维普 等数据库收录！ |
|
