当前位置: X-MOL 学术Vis. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Automatic darkest filament detection (ADFD): a new algorithm for crack extraction on two-dimensional pavement images
The Visual Computer ( IF 3.5 ) Pub Date : 2019-08-28 , DOI: 10.1007/s00371-019-01742-2
Wissam Kaddah , Marwa Elbouz , Yousri Ouerhani , Ayman Alfalou , Marc Desthieux

Pavement condition information is a significant component in pavement management systems. Precise extraction of road degradations particularly cracks is a critical task for surface safety. Manual surveys, which are labor intensive and costly, have induced several researchers to investigate the use of image processing to achieve automated pavement distress ratings. In the context of fine structures extraction, we present in this paper a novel approach for road crack detection under real conditions using several systems installed differently on a vehicle. It is such an automatic and effective approach that relies on both photometric and geometric characteristics of cracks. Based on an edge detection technique to avoid the bad conditions of image acquisition and an examination algorithm to verify the presence of high concentration of cracking pixels, this approach allows in a first step to select pixels that have great probability of belonging to a crack. Indeed, the originality of this approach stems from the proposed way to compute a set of thin filaments connecting the pixels selected at the first step between them. Finally, a post-processing step is applied to refine the obtained result and confirm either the presence or the absence of cracks in the image. Our proposed approach provides very robust and precise results on 2 D pavement images in a wide range of situations and in a fully unsupervised manner. Furthermore, its innovative aspect is reflected in its ability to analyze easily both 2 D and 3 D pavement images.

中文翻译:

自动最暗细丝检测(ADFD):一种用于二维路面图像裂缝提取的新算法

路面状况信息是路面管理系统的重要组成部分。精确提取道路退化,特别是裂缝是表面安全的一项关键任务。人工调查费时费力且成本高昂,这促使一些研究人员研究使用图像处理来实现自动路面损坏评级。在精细结构提取的背景下,我们在本文中提出了一种在实际条件下使用不同安装在车辆上的多个系统进行道路裂缝检测的新方法。这是一种自动且有效的方法,它依赖于裂缝的光度和几何特征。基于边缘检测技术避免图像采集的恶劣条件和检查算法来验证高浓度裂纹像素的存在,这种方法允许在第一步中选择很有可能属于裂缝的像素。事实上,这种方法的独创性源于所提出的计算一组细丝的方法,该细丝连接在它们之间的第一步中选择的像素。最后,应用后处理步骤来改进获得的结果并确认图像中是否存在裂缝。我们提出的方法在各种情况下以完全无监督的方式在二维路面图像上提供了非常稳健和精确的结果。此外,它的创新之处还体现在它能够轻松分析 2D 和 3D 路面图像。这种方法的独创性源于计算一组细丝的建议方法,这些细丝连接在它们之间的第一步中选择的像素。最后,应用后处理步骤来改进获得的结果并确认图像中是否存在裂缝。我们提出的方法在各种情况下以完全无监督的方式在二维路面图像上提供了非常稳健和精确的结果。此外,它的创新之处还体现在它能够轻松分析 2D 和 3D 路面图像。这种方法的独创性源于计算一组细丝的提议方法,这些细丝连接在它们之间的第一步中选择的像素。最后,应用后处理步骤来改进获得的结果并确认图像中是否存在裂缝。我们提出的方法在各种情况下以完全无监督的方式在二维路面图像上提供了非常稳健和精确的结果。此外,它的创新之处还体现在它能够轻松分析 2D 和 3D 路面图像。我们提出的方法在各种情况下以完全无监督的方式在二维路面图像上提供了非常稳健和精确的结果。此外,它的创新之处还体现在它能够轻松分析 2D 和 3D 路面图像。我们提出的方法在各种情况下以完全无监督的方式在二维路面图像上提供了非常稳健和精确的结果。此外,它的创新之处还体现在它能够轻松分析 2D 和 3D 路面图像。
更新日期:2019-08-28
down
wechat
bug