摘要
计算机图像分析技术被广泛应用于路面裂缝病害检测,并逐步成为热点之一,然而路面裂缝自动检测技术还未能良好地适应目前复杂的路面状况。针对非均匀背景中传统分割算法的高复杂性及低准确度,提出一种基于统计特征的路面裂缝自适应阈值分割算法。上述方法首先对图像灰度化处理,再利用灰度分布的统计特征结合D邻域滑动窗对像素点依次判别,最后对其结果形态学滤波完成精确的裂缝分割。实验结果表明,与传统边缘检测方法相比,上述方法环境适应能力强,边缘信息保留完整,对不同类型裂缝计算效率高且分割更准确。
Technology of image analysis is widely used in pavement crack detection,and become one of the hot spots gradually.However,the technology of pavement cracks automatic detection has not been adapted to the complex pavement conditions.In view of the high complexity and low accuracy of the traditional segmentation algorithm in non-uniform background,an adaptive threshold segmentation algorithm for pavement cracks based on statistical characteristics is proposed.This method first discriminates the image gray level,and then uses the statistical features of the gray distribution to distinguish the pixels in sequence with the D neighborhood sliding window,and finally the accurate segmentation of cracks is achieved by morphological filtering.The experimental results show that,compared with the traditional edge detection method,this method has the advantages of strong adaptability,complete edge information,high efficiency and more accurate segmentation for different types of cracks.
作者
李鹏
蒋威
顾彬彬
LI Peng;JIANG Wei;GU Bin-bin(Jiangsu Key Laboratory of Meteorological Observation and Information Processing,Nanjing University of Information Science and Technology,Nanjing Jiangsu 210044,China;Jiangsu Meteorological Sensor Network Technology Environment Center,Nanjing University of Information Science and Technology,Nanjing Jiangsu 210044,China;Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology,Nanjing University of Information Science and Technology,Nanjing Jiangsu 210044,China)
出处
《计算机仿真》
北大核心
2019年第12期117-121,共5页
Computer Simulation
基金
国家自然科学基金资助项目(41075115)
江苏省第11批六大高峰人才项目(2014-XXRJ-006)
江苏省重点研发计划社会发展项目(BE201569)
江苏省高校优势学科Ⅱ期建设工程项目
关键词
图像处理
裂缝分割
统计特征
滑动窗
Image processing
Crack segmentation
Statistical characteristics
Sliding window
