期刊文献+

基于改进SSD模型的道路病害检测研究

Research on Road Damage Detection Based on Improved SSD Model
下载PDF
导出
摘要 道路病害的准确检测可以及时定位并修复路面病害。对于保持良好的路况、交通运载、安全驾驶和出行等都具有重要的意义。为了提高现有人工智能道路裂缝检测精度和性能,提出一种基于不规则四边形标注框的改进SSD道路裂缝检测方法。该方法能够在裂缝检测过程中以较高的准确率检测出不同类型的道路裂缝。在建立的不规则四边形标注框数据集上,将改进算法与基于矩形预测框的SSD算法进行比较。实验结果表明,改进的SSD道路裂缝检测方法能够更好的根据裂缝形态进行检测,在检测精度方面有了较高的提升。 Accurate detection of road damage can locate and repair road damage in time.It is of great significance for maintaining good road conditions,traffic carrying,safe driving and travel.In order to improve the accuracy and performance of existing artificial intelligence road crack detection,an improved SSD road crack detection method based on irregular quadrilateral annotation frame is proposed.The method can detect different types of road cracks with high accuracy in the detection process.On the created dataset of irregular quadrilateral boxes,the improved algorithm is compared with the SSD algorithm which is based on rectangular prediction box.The experimental results show that the improved SSD road crack detection method can better detect cracks according to the shape of the cracks,and has a higher detection accuracy.
作者 周秋红 ZHOU Qiu-hong(Heilongjiang Provincial Highway Construction Center,Harbin,Heilongjiang 150090,China)
出处 《黑龙江交通科技》 2023年第4期30-32,共3页 Communications Science and Technology Heilongjiang
关键词 目标检测 SSD模型 道路病害检测 深度学习 target detection SSD model road damage detection deep learning
  • 相关文献

参考文献9

二级参考文献54

  • 1Wang K C P,Gong W,Li X,et al.Data analysis of real-time system for automated distress survey[J].Transportation Research Record:Journal of the Transportation Research Board,2002,1806(1):101-109.
  • 2Meignen D,Bernadet M,Briand H.One application of neural networks for detection of defects using video data bases:identification of road distresses[C]//Database and Expert Systems Applications,1997.Proceedings.,Eighth International Workshop on.IEEE,1997:459-464.
  • 3Klepka A,Staszewski W J,Jenal R B,et al.Nonlinear acoustics for fatigue crack detection-experimental investigations of vibro-acoustic wave modulations[J].Structural Health Monitoring,2012,11(2):197-211.
  • 4Ling L,Peikang H,Xiaohu W,et al.Image edge detection based on beamlet transform[J].Systems Engineering and Electronics,Journal of,2009,20(1):1-5.
  • 5Jiang X,Ma Z J,Ren W X.Crack detection from the slope of the mode shape using complex continuous wavelet transform[J].ComputerAided Civil and Infrastructure Engineering,2012,27(3):187-201.
  • 6Zou Q,Cao Y,Li Q,et al.Crack Tree:Automatic crack detection from pavement images[J].Pattern Recognition Letters,2012,33(3):227-238.
  • 7Yamaguchi T,Hashimoto S.Fast crack detection method for large-size concrete surface images using percolation-based image processing[J].Machine Vision and Applications,2010,21(5):797-809.
  • 8孙波成,邱延峻.路面裂缝图像处理算法研究[J].公路交通科技,2008,25(2):64-68. 被引量:33
  • 9张娟,沙爱民,孙朝云,高怀钢.基于相位编组法的路面裂缝自动识别[J].中国公路学报,2008,21(2):39-42. 被引量:41
  • 10刘凡凡,徐国爱,肖靖,杨义先.基于连通域相关及Hough变换的公路路面裂缝提取[J].北京邮电大学学报,2009,32(2):24-28. 被引量:12

共引文献85

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部