结合NSCT和图像形态学的路面裂缝检测

路面图像的复杂性及裂缝信息的弱信号性导致对路面裂缝进行检测非常困难,为此提出一种基于非下采样contourlet变换(NSCT)和图像形态学的路面裂缝检测算法.首先对图像进行NSCT得到不同尺度、不同方向上的变换系数,在NSCT域中根据变换系数自适应地确定阈值,并应用广义非线性增益函数来增强较弱细节的局部对比度;然后对增强处理后的变换系数进行反变换;最后用图像形态学方法和中值滤波实现裂缝检测及孤立噪声点去除.通过对实际的高速路面图像测试表明,与直方图增强、小波变换及contourlet变换相比,该算法能更有效地增强弱对比度的细小裂缝,克服了常规算法易受离散噪声点以及光照条件等干扰的问题,具有较强的鲁棒性且高效实用.

Pavement Cracks Detection Based on NSCT and Morphology

The complex nature of road images and weak signal make the detection pavement cracks particularly difficult. An algorithm for pavement cracks detection based on nonsubsampled contourlet transform (NSCT) and morphology is proposed. Firstly, the coefficients at different scales and in different directions are obtained by image decomposition using the NSCT, then coefficients thresholds are adaptively set and the generalized nonlinear gain function is used to enhance the features with low contrast while preventing the strong contrast features from over enhancing in the NSCT domain. After the enhancement, the inverse transform is performed, and morphological and median filters are employed to detect cracks and remove noise. The proposed algorithm is tested by real highway pavement images. The experimental results show that our algorithm is more robust and effective to detect road cracks especially for weak contrast cracks and thin cracks than other algorithms, such as histogram enhancement, wavelet transform, or contourlet transform.