路面裂缝自动检测系统研究-信号与信息处理专业论文.docxVIP

摘要 摘 要 I I 路面裂缝作为一种常见的路面病害，受到公路管理和养护部门的高度重视。通过快 速、准确地获取路面破损信息，来制定相应的修理、养护计划。而传统的人工目测的方 法由于存在耗时、不精确、效率低、妨碍交通、危险、成本高等诸多劣势，已经不再适 合高速发展的公路交通事业，因此，深入研究路面裂缝自动检测技术对我国公路交通事 业的发展具有重要意义。 数字图像处理技术是本文的研究重点也是本软件的核心技术，主要有图像增强，分 割，特征提取等几部分。根据 CCD 摄像机拍摄的路面图像特点，本文使用一种运算简 单的匀光法对光照不均的图像进行了校正处理，使用加权平均滤波和大津阈值分割分别 对采集到的路面裂缝图像进行处理，得到含有少量孤立噪声的二值图像。为了更好地识 别和分析图像，使用网格黑色像素点阈值和网格最大连通区域两次去噪。为了便于后续 提取裂缝参数，使用细化方法对裂缝图像做进一步处理。在进行特征提取时，将原图像 划分为面积较小的正方形子块,结合裂缝特征来提取每个子块的参数，得到裂缝图像的 一组特征值 (xmax , ymax , sum, d) ，同时，对黑色像素点进行统计，根据其数目是否为零， 判断路面图像是否有裂缝，并可很好地计算出了各裂缝的参数，以便为后期公路养护提 供参数依据。 最后，采用 BP 神经网络对路面裂缝进行分类，以提取出来的特征向量作为分类器 的输入，输出结果包括横向裂缝、纵向裂缝、网状裂缝以及块状裂缝四种路面裂缝类型； 选取 84 幅各类型裂缝图像作为训练样本，对其进行训练，再利用训练好的神经网络， 对 96 幅测试样本实现分类并统计其识别率，结果为 87.5%，实验结果验证了本文所用 方法的有效性。 关键词：图像增强，图像分割，特征提取，裂缝检测，BP 神经网络 Abstract Abstract II II As a common pavement problem, pavement cracks always attract high level of attention from highway department of maintenance and preservation. By collecting details of pavement cracks rapidly and accurately, relevant plans of maintenance can be established. However, because of the weaknesses, such as inaccuracy, low-efficiency, high consumption of time and money, inconvenience and potential danger, the traditional manual road crack detection method is not suitable for measurement implemented in the field of pavement transportation which develops very fast currently. Therefore, further study on the aspect of automatic detection technology of pavement cracks becomes more and more important in our country. Digital image processing technology, which generally includes image enhancement, segmentation, feature extraction and so on, is the main study of this paper and the core part of this software. Based on the features of pavement images taken by CCD cameras, the uniform light method, which is simple, is adopted to correct mistakes existing in uneven images in this paper. Then the pavement crack image is processed by using the weighted average filter and dajin threshold segmentation method respectively. Aft