改进组件树在隧道裂缝识别中的应用*

为提高衬砌裂缝病害事故隐患识别率，解决隧道表面普遍存在的对比度低、噪声污染严重、光照不均匀等问题，采用Retinex方法对图像进行噪声抑制和细节增强，结合组件树算法快速建立组件树并剪枝，建立1种新的隧道衬砌裂缝识别算法。研究结果表明:改进后的算法可有效平衡图像光照，保护图像中裂缝边缘信息，识别精度大于95%。研究结果可为识别隧道裂缝引起的安全隐患提供新的方法。

Application of improved component tree in tunnel crack identification

In order to improve the identification rate of potential safety hazard of lining crack disease,aiming at the ubiquitous problems of low contrast,serious noise pollution and uneven illumination on the surface of tunnel,the Retinex method was used to suppress noise and enhance details of the images.Combined with the component tree algorithm,the component tree was quickly established and pruned,and a new identification algorithm of tunnel lining crack was proposed.The results showed that the improved algorithm could effectively balance the image illumination,protect the edge information of cracks in the image,and the recognition accuracy was larger than 95%.The research results can provide a new method for identifying the potential safety hazard caused by tunnel cracks.