Road Crack Model Based on Multi-Level Feature Fusion and Attention Mechanism

doi:10.3778/j.issn.1002-8331.2203-0531

Abstract

Abstract: In order to solve the problem that existing crack detection methods are easily interfered by various noises, which leads to false detection and missed detection of small-scale cracks, this paper proposes a road crack detection model based on multi-level feature fusion and attention mechanism, and adopts the codec structure DeepCrack network as the basic framework. A single-scale multi-level feature fusion module is designed for feature extraction, and the detailed features of cracks are enhanced through multi-level network representation. At the same time, the improved triple attention module is introduced into the symmetric fusion part of the codec end, and cross-dimensional interaction is carried out from the channel, height and width dimensions to highlight crack features and suppress noise features, and cross-dimensional feature fusion is carried out to obtain more complementary crack features. Experiments show that the model achieves the current best in several edge evaluation indexes on the road crack data set CRKWH100, and the generalization of the model is also verified in the Stone331 stone crack data set.

Key words: deep learning, encoder-decoder network, crack detection, feature fusion, attention mechanism

摘要： 针对现有裂缝检测方法易受各类噪声干扰从而导致误检及小尺度裂缝漏检的问题，提出一种基于多层次特征融合和注意力机制的道路裂缝检测模型，采用编解码结构DeepCrack网络作为基本架构。设计单尺度多层次特征融合模块应用于特征提取，通过多级网络表征增强裂缝的细节特征。同时在编解码端对称融合部位，引入改进后的三重注意力模块，从通道、高和宽3个维度进行跨维度交互，凸显裂缝特征和抑制噪声特征，并进行跨维度的特征融合，以获得更具互补性的裂缝特征。实验表明，在道路裂缝数据集CRKWH100上，模型在多个边缘评估指标上实现了当前最优，同时在Stone331石材裂缝数据集中也验证了该模型的泛化性。

关键词: 深度学习, 编解码网络, 裂缝检测, 特征融合, 注意力机制

SONG Rongrong, WANG Caiyong, TIAN Qichuan, ZHANG Qi. Road Crack Model Based on Multi-Level Feature Fusion and Attention Mechanism[J]. Computer Engineering and Applications, 2023, 59(13): 281-288.

宋榕榕, 王财勇, 田启川, 张琪. 多层次特征融合和注意力机制的道路裂缝模型[J]. 计算机工程与应用, 2023, 59(13): 281-288.

References

[1] Ministry of Transport.Statistical bulletin on the dervelopment of the transportation industry in 2020[EB/OL].（2021-05?17）[2022-02-15].https：//xxgk.mot.gov.cn/2020/jigou/zhghs/202105/t20210517_3593412.html.
[2] ZHU Q B.Pavement crack detection algorithm based on image processing analysis[C]//Proceedings of the International Conference on Intelligent Human-Machine Systems and Cybernetics，2016：15-18.
[3] AKAGIC A，BUZA E，OMANOVIC S，et al.Pavement crack detection using Otsu thresholding for image segmentation[C]//Proceedings of the International Convention on Information and Communication Technology，Electronics and Microelectronics，2018：1092-1097.
[4] SONG Q，LIN G Y，MA J Q，et al.An edge-detection method based on adaptive canny algorithm and iterative segmentation threshold[C]//Proceedings of the International Conference on Control Science and Systems Engineering，2016：64-67.
[5] FERNANDEZ A，RODRIGUEZ-LOZANO F，VILLATORO R，et al.Efficient pavement crack detection and classification[J].EURASIP Journal on Image and Video Processing，2017（1）：1-11.
[6] WU G F，SUN X M，ZHOU L P，et al.Research on morphological wavelet operator for crack detection of asphalt pavement[C]//Proceedings of the 2016 IEEE International Conference on Information and Automation，2016：1573-1577.
[7] 瞿中，鞠芳蓉，陈思琪.结构森林边缘检测与渗流模型相结合的混凝土表面裂缝检测[J].计算机科学，2018，45（11）：288-291.
QU Z，JU F R，CHEN S Q.Concrete surface cracks detection combining structured forest edge detectionand percolation model[J].Computer Science，2018，45（11）：288-291.
[8] RONNEBERGER O，FISCHER P，BROX T.U-Net：convolutional networks for biomedical image segmentation[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention，2015：234-241.
[9] BADRINARAYANAN V，KENDALL A，CIPOLLA R，et al.SegNet：a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（12）：2481-2495.
[10] CHEN T Y，CAI Z H，ZHAO X，et al.Pavement crack detection and recognition using the architecture of SegNet[J].Journal of Industrial Information Integration，2020，18：100144.
[11] LAU S，CHONG E，YANG X，et al.Automated pavement crack segmentation using U-Net-based convolutional neural network[J].IEEE Access，2020，8：114892-114899.
[12] ZOU Q，ZHANG Z，LI Q Q，et al.DeepCrack：learning hierarchical convolutional features for crack detection[J].IEEE Transactions on Image Processing，2019，28（3）：1498-1512.
[13] MISRA DA，NALAMADA T，ARASANIPALAI A U，et al.Rotate to attend：convolutional triplet attention module[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision and Pattern Recognition，2021：3139-3148.
[14] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2980-2988.
[15] ZOU Q，CAO Y，LI Q Q，et al.CrackTree：automatic crack detection from pavement images[J].Pattern Recognition Letters，2012，33（3）：227-238.
[16] K?NIG J，JENKINS M D，MANNION M，et al.Optimized deep encoder-decoder methods for crack segmentation[J].Digital Signal Processing，2021，108（10）：29-37.
[17] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[18] WOO S，PARK J C，LEE J Y，et al.CBAM：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision，2018：3-19.
[19] PARK J C，WOO S，LEE J Y，et al.BAM：bottleneck attention module[C]//Proceedings of the British Machine Vision Conference，2018：147-159.
[20] WANG Q L，WU B G，ZHU P H，et al.ECA-Net：efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE Conference on Applications of Computer Vision and Pattern Recognition，2020：11531-11539.
[21] XIE S N，TU Z W.Holistically-nested edge detection[J].International Journal of Computer Vision，2017，125（1）：3-18.
[22] LIU Y，CHENG M M，HU X W，et al.Richer convolutional features for edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2019，41（8）：1939-1946.