基于图像补偿的隧道衬砌裂缝检测方法

针对检测平台振动导致隧道衬砌裂缝图像识别准确率低、检测数据可靠性差的问题，提出基于图像补偿的隧道衬砌裂缝检测方法.开发车载式隧道衬砌裂缝检测系统，提出图像帧间自适应运动估计的方法. 对采用环境光增强处理得到的图像进行基于特征点匹配的自适应运动估计，建立图像帧间的运动关系，用卡尔曼滤波算法对运动参数进行滤波，去除采集平台的无规则振动，经过双三次插值实现图像补偿. 提出基于自适应分块综合滤波和形态学方法的衬砌图像裂缝分割方法，有效地完成裂缝提取和裂缝参数计算. 实验结果表明，利用提出的方法能够较好地补偿采集平台的振动误差，准确地提取裂缝信息，实现隧道衬砌裂缝的高精度检测.

Tunnel lining crack detection method based on image compensation

A tunnel lining crack detection method based on image compensation was proposed aiming at the problems of low accuracy for tunnel lining crack image recognition and poor reliability of detection data caused by the vibration of detection platform. A vehicle mounted tunnel lining crack detection system was developed, and a method for adaptive motion estimation between image frames was proposed. Adaptive motion estimation based on feature point matching was conducted on the image obtained by ambient light enhancement processing in order to establish the motion relationship between image frames. The Kalman filter algorithm was utilized to filter the motion parameters in order to remove the random vibration of the acquisition platform. Then the image compensation was realized through bicubic interpolation. A method for lining image crack segmentation based on adaptive block comprehensive filtering and morphological methods was proposed to effectively complete crack extraction and crack parameter measurement. The experimental results show that the proposed method can better compensate the vibration error of the acquisition platform, accurately extract the crack information, and realize the high-precision detection of the tunnel lining crack.