Pavement Crack Detection in Infrared Images Using a DCNN and CCL Algorithm
Pavement Crack Detection in Infrared Images Using a DCNN and CCL Algorithm
复制标题
使用 DCNN 和 CCL 算法进行红外图像中的路面裂缝检测
DOI：
10.1109/jsen.2022.3161104
复制
发表时间：
2023-03
影响因子：
4.3
通讯作者：
Zhengkun Zhu
中科院分区：
文献类型：
--
作者：
Dongwei Qiu;Mingjian Xiao;Shanshan Wan;Chuan Qin;Zhengkun Zhu
在路面裂缝检测中，图像分割技术可以在复杂背景的路面图像中准确识别和提取裂缝，但由于噪声和非裂缝损伤的干扰，产生的无关非裂缝区域降低了提取精度。针对上述问题，本文提出了一种道路裂缝分割模型，该模型由U-Net的跳跃连接和解码器、编码部分的残差块和端点的连通分量标记算法（CCL）组成。提出的方法，深度可分离卷积取代标准卷积，以减少参数的数量和操作成本。后处理采用连通域标记算法，解决了不相关非裂纹区域的干扰问题。4710幅红外图像被用于模型的训练和测试。实验结果表明，该方法对不同阴影图像下的路面裂缝检测效果良好，检测准确率可达92.23%，算法对比表明，该算法明显优于目前广泛使用的传统算法。在相似性方面，Dice相似系数（DSC）分别比FCN、U-Net和DeeplabV 3+网络提高了5.97%、5.22%和1.49%。因此，该方法对不同路面红外图像中的裂缝检测是有效的，能够显著提高分割结果的准确性，降低错误率，提高分割的准确性和鲁棒性，能够很好地提取路面红外图像中的裂缝。
In-pavement crack detection, image segmentation techniques can accurately identify and extract cracks in pavement images with complex backgrounds, however, due to the interference of noise and non-crack damage, the resulting irrelevant non-crack regions reduce the extraction accuracy. To address the above problems, this research presents a road crack segmentation model consisting of a skip connection and decoder of U-Net, residual blocks in the encoding part, and the connected components labeling algorithm (CCL) in the extremity. The proposed method, depth-wise separable convolution replaces the standard convolution to reduce the number of parameters and operation cost. Post-processing using the connected components labeling algorithm solves the interference of irrelevant non-cracked regions. 4710 infrared images are used for the training and testing of the model. The testing results show that the new method for the pavement crack detection in different shadowed images is satisfactory, the detection accuracy can be up to 92.23%, and the algorithm comparison proves that the proposed algorithm is much better than that by the widely used traditional algorithms. In terms of similarity, the Dice Similarity Coefficient (DSC) is improved by 5.97%, 5.22%, and 1.49% compared to FCN, U-Net, and DeeplabV3+ networks, respectively. Therefore, the method is effective in detecting cracks in different pavement IR images, and can significantly improve the accuracy of segmentation results, reduce the error rate, improve the segmentation accuracy and robustness, and can extract cracks in pavement IR images well.
登录
查看更多内容
DOI：
10.1061/(asce)cp.1943-5487.0000775
发表时间：
2018-09
期刊：
J. Comput. Civ. Eng.
影响因子：
--
作者：
Allen A. Zhang;Kelvin C. P. Wang;Yue Fei;Yang Liu;Siyu Tao;Cheng Chen;J. Li;Baoxian Li
通讯作者：
Allen A. Zhang;Kelvin C. P. Wang;Yue Fei;Yang Liu;Siyu Tao;Cheng Chen;J. Li;Baoxian Li
影响因子：
2.7
作者：
Rajadurai, Rajagopalan-Sam;Kang, Su-Tae
通讯作者：
Kang, Su-Tae
DOI：
10.1177/1475921720940068
发表时间：
2020-07
期刊：
Structural Health Monitoring
影响因子：
--
作者：
Lingxin Zhang;Junkai Shen;Baijie Zhu
通讯作者：
Lingxin Zhang;Junkai Shen;Baijie Zhu
DOI：
10.1109/tpami.2018.2858826
发表时间：
2020-02-01
影响因子：
23.6
作者：
Lin, Tsung-Yi;Goyal, Priya;Dollar, Piotr
通讯作者：
Dollar, Piotr
DOI：
--
发表时间：
2015-03
期刊：
ArXiv
影响因子：
--
作者：
D. Powers
通讯作者：
D. Powers