Automatic internal crack detection from a sequence of infrared images with a triple-threshold Canny edge detector
Automatic internal crack detection from a sequence of infrared images with a triple-threshold Canny edge detector
复制标题
DOI：
10.1088/1361-6501/aa9857
复制
发表时间：
2018-02-01
影响因子：
2.4
通讯作者：
Yuan, Maodan
中科院分区：
文献类型：
--
作者：
Wang, Gaochao;Tse, Peter W.;Yuan, Maodan
金属结构状况的目视检查和评估对于安全至关重要。脉冲热成像产生可见红外图像，已被广泛应用于结构和材料中的缺陷检测和表征。当应用主动热成像技术（一种无损检测工具）时，可以避免大量人工检查的必要性。然而，用主动热成像检测内部裂纹仍然很困难，因为它通常在所收集的红外图像序列中是不可见的，这使得内部裂纹的自动检测更加困难。此外，复杂的检查环境会妨碍内部裂纹的检测。为了提出一种鲁棒的自动视觉检测方法，提出了一种基于计算机视觉的阈值化方法。在本文中，图像信号是一个序列的红外图像采集的实验装置与热相机和两个闪光灯作为刺激。每帧图像的像素对比度先用Canny算子增强，然后用三阈值系统重建。从重建信号中提取两个特征，即时域均值和频域最大幅度，以帮助区分裂纹像素。最后，一个二值图像表示的内部裂纹的位置是由一个K-均值聚类方法生成。建议的程序已被应用到一个铁管，其中包含两个内部裂纹和表面磨损。对基于计算机视觉的裂纹自动检测方法进行了改进。该方法可应用于工业上实现多幅红外图像中内部裂纹的自动检测。
Visual inspection and assessment of the condition of metal structures are essential for safety. Pulse thermography produces visible infrared images, which have been widely applied to detect and characterize defects in structures and materials. When active thermography, a non-destructive testing tool, is applied, the necessity of considerable manual checking can be avoided. However, detecting an internal crack with active thermography remains difficult, since it is usually invisible in the collected sequence of infrared images, which makes the automatic detection of internal cracks even harder. In addition, the detection of an internal crack can be hindered by a complicated inspection environment. With the purpose of putting forward a robust and automatic visual inspection method, a computer vision-based thresholding method is proposed. In this paper, the image signals are a sequence of infrared images collected from the experimental setup with a thermal camera and two flash lamps as stimulus. The contrast of pixels in each frame is enhanced by the Canny operator and then reconstructed by a triple-threshold system. Two features, mean value in the time domain and maximal amplitude in the frequency domain, are extracted from the reconstructed signal to help distinguish the crack pixels from others. Finally, a binary image indicating the location of the internal crack is generated by a K-means clustering method. The proposed procedure has been applied to an iron pipe, which contains two internal cracks and surface abrasion. Some improvements have been made for the computer vision-based automatic crack detection methods. In the future, the proposed method can be applied to realize the automatic detection of internal cracks from many infrared images for the industry.