摘要
路面裂缝常常混杂着随机的路面颗粒纹理和自然环境下的多种干扰,基于单一特征的检测方法无法较为准确地提取裂缝,为此提出一种多特征融合与格式塔理论相结合的路面裂缝检测算法.将多尺度局部区域中裂缝的灰度差异、出现概率以及边缘特性作为低层显著特征,根据裂缝纹理的不均匀性,结合裂缝不规则曲线结构的空间延续性,提出一种新的纹理各向异性度量方式(LFIA),以高效削弱噪声点与伪裂缝的干扰;然后引入格式塔理论中的相似性、接近性和完整性原则,采用迭代剪裁预分割LFIA图,基于区域内部以及区域间连接度的裂缝空间一致性增强策略,突出裂缝.在收集的各类裂缝图像数据库上的实验结果表明,该算法抗噪性能好、鲁棒性强;裂缝提取的准确性、完整性要优于已有的算法.
Pavement cracks are often mixed with random particle textures on road surface and a variety ofinterference under natural environment, results in the crack detection method based on single feature cannotrecognize real crack accurately. Therefore, this paper presents a novel pavement crack detection methodthrough integrating multi-features fusion and Gestalt principles. It extracts the intensity differences, theprobability of occurrence and edge property of cracks in multi-scale local regions as low-level salient featuresfirstly. Then, according to the texture inhomogeneity and the spatial continuity of the irregular curvilinearstructures of cracks, a novel texture anisotropy measure method （LFIA） is presented, which canweaken the disturbance of noisy points and pseudo-crack fragments efficiently. Based on the similarity,proximity and integrity principles of Gestalt theory, this paper adopts iterative clipping method topre-segment LFIA map and proposes a crack spatial consistency enhancement strategy based on intra-regional and inter-regional connectivity to extract cracks. The experimental results of various collectedpavement crack image database show the outstanding anti-noise performance and robustness. The precisionand recall of our method is significantly superior to several existing conventional algorithms.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2015年第1期147-156,共10页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金重点项目(90820306)
关键词
裂缝检测
多尺度低层特征
纹理不均匀性
纹理各向异性
格式塔理论
crack detection
multi-scale low-level features
texture inhomogeneity
texture anisotropy
Gestaltprinciples
