| 333 | 4 | 1521 |
| 下载次数 | 被引频次 | 阅读次数 |
为了更加精确高效地对道路裂缝进行分割提取，提出一种基于多尺度特征与上下文信息融合的ASPPUnet道路裂缝检测模型。ASPPUnet通过U形编码解码器进行多尺度特征的提取，通过引入ASPP模块进行不同范围上下文信息的融合；同时模型还引入了深度可分离卷积模块，用以实现模型的轻量化；采用融合Dice和交叉熵的损失函数，均衡模型的查全率和查准率；采用动态数据集增广方法，使得模型在小数据集上也能实现良好的检测效果。通过与Unet等模型的实验对比可以看出，ASPPUnet拥有更好的检测效果和可塑性，具有较好的应用价值。
Abstract：In order to segment and extract pavement cracks more accurately and efficiently, an ASPPUnet pavement crack detection model is proposed based on multi-scale features and context information fusion in this paper. In ASPPUnet, multi-scale features are extracted through U-shaped Encoder-Decoder, and context information of different ranges is fused by introducing ASPP module. And depthwise separable convolution is introduced into the model to realize lightweight of the model. The loss function of fusion Dice and cross entropy is adopted to balance the recall and precision of the model. Meanwhile, dynamic dataset augmentation method is adopted to achieve good detection effect on small data sets. Compared with Unet and other models, ASPPUnet has better detection effect and plasticity, which leads to better application value.
[1] OTSU N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66.
[2] KITTLER J,ILLINGWORTH J.Minimum error thresholding[J].Pattern Recognition,1986,19(1):41-47.
[3] KAPUR J N,SAHOO P K,WONG A K.A new method for gray-level picture thresholding using the entropy of the histogram[J].Computer Vision,Graphics,and Image Processing,1985,29(3):273-285.
[4] 沈照庆，彭余华，舒宁.一种基于SVM的路面影像损伤跨尺度识别方法[J].武汉大学学报(信息科学版),2013,38(8):993-997.SHEN Z Q,PENG Y H,SHU N.A road damage identification method based on scale-span image and SVM[J].Geomatics and Information Science of Wuhan University,2013,38(8):993-997.
[5] SHI Y,CUI L M,QI Z Q,et al.Automatic road crack detection using random structured forests[J].IEEE Transactions on Intelligent Transportation Systems,2016,17(12):3434-3445.
[6] 肖创柏，柏鳗晏，禹晶.基于Faster R-CNN的缝隙检测与提取算法[J].北京工业大学学报，2021,47(2):135-146.XIAO C B,BAI M Y,YU J.Crack detection and extraction based on Faster R-CNN[J].Journal of Beijing University of Technology,2021,47(2):135-146.
[7] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[8] 赵一航，宋淑彩，张博.采用YOLOv5模型的路面裂缝检测研究[J].福建电脑，2022,38(7):23-26.ZHAO Y H,SONG S C,ZHANG B.Research on asphalt pavement crack detection using YOLOv5 model[J].Journal of Fujian Computer,2022,38(7):23-26.
[9] 李鹏程，孙立双，谢志伟，等.基于改进MobileNet-SSD的路面裂缝图像检测算法[J].激光杂志，2022,43(7):123-127.LI P C,SUN L S,XIE Z W,et al.Improved pavement crack image detection algorithm based on MobileNet-SSD[J].Laser Journal,2022,43(7):123-127.
[10] 张晋赫，秦育罗，张在岩，等.复杂场景下农村道路裂缝分割方法[J].测绘通报，2022(5):74-78;88.ZHANG J H,QIN Y L,ZHANG Z Y,et al.Rural road crack segmentation method in complex scene[J].Bulletin of Surveying and Mapping,2022(5):74-78;88.
[11] BADRINARAYANAN V,KENDALL A,CIPOLLA R.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[12] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,USA,2016:770-778.
[13] 张伯树，张志华，张洋.改进的HRNet应用于路面裂缝分割与检测[J].测绘通报，2022(3):83-89.ZHANG B S,ZHANG Z H,ZHANG Y.Improved HRNet applied to segmentation and detection of pavement cracks[J].Bulletin of Surveying and Mapping,2022(3):83-89.
[14] SUN K,XIAO B,LIU D,et al.Deep high-resolution representation learning for human pose estimation[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach,USA,2019:5686-5696.
[15] RONNEBERGER O,FISCHER P,BROX T.U-Net:convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention.Munich,Germany,2015:234-241.
[16] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
[17] HOWARD A G,ZHU M,CHEN B,et al.MobileNets:efficient convolutional neural networks for mobile vision applications[DB/OL].(2017-04-17)[2024-02-15].https://doi.org/10.48550/arXiv.1704.04861.
[18] CHEN L C,PAPANDREOU G,SCHROFF F,et al.Rethinking atrous convolution for semantic image segmentation[DB/OL].(2017-06-17)[2024-02-15].https://doi.org/10.48550/arXiv.1706.05587.
[19] 郭海涛，卢俊，袁洲，等.Siam-DeepLabv3+网络遥感影像语义变化检测方法[J].测绘科学技术学报，2021,38(6):597-603.GUO H T,LU J,YUAN Z,et al.A semantic change detection method for remote sensing images based on Siam-DeepLabv3+[J].Journal of Geomatics Science and Technology,2021,38(6):597-603.
[20] 钟梅嘉，李宁，石林，等.基于注意力机制和多尺度特征融合的道路裂缝检测[J].计算机工程与设计，2023,44(12):3714-3721.ZHONG M J,LI N,SHI L,et al.Road crack detection based on attention mechanism and multi-scale feature fusion[J].Computer Engineering and Design,2023,44(12):3714-3721.
[21] HE K M,ZHANG X Y,REN S Q,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[22] DING X H,ZHANG X Y,HAN J G,et al.Scaling up your kernels to 31×31:revisiting large kernel design in CNNs[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans,USA,2022:11953-11965.
[23] IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning.San Diego,USA,2015:448-456.
[24] XU B,WANG N Y,CHEN T Q,et al.Empirical evaluation of rectified activations in convolutional network[DB/OL].(2015-05-05)[2024-02-15].https://doi.org/10.48550/arXiv.1505.00853.
[25] 许正森，雷相达，管海燕.多尺度局部特征增强Transformer道路裂缝检测模型[J].中国图象图形学报，2023,28(4):1019-1028.XU Z S,LEI X D,GUAN H Y.Multi-scale local feature enhanced Transformer network for pavement crack detection[J].Journal of Image and Graphics,2023,28(4):1019-1028.
[26] 谢安东.基于深度学习的道路裂缝检测方法研究与应用[D].杭州：浙江大学，2023:16-32.XIE A D.Research and application of pavement crack detection based on deep learning[D].Hangzhou:Zhejiang University,2023:16-32.
[27] SELVARAJU R R,COGSWELL M,DAS A,et al.Grad-CAM:visual explanations from deep networks via gradient-based localization[J].International Journal of Computer Vision,2020,128(2):336-359.
基本信息:
中图分类号:U418.6;TP391.41
引用信息:
[1]曹一冰,张江水,张政,等.一种基于ASPPUnet的道路裂缝检测模型[J].测绘科学技术学报,2025,41(01):49-56.
基金信息:
国家重点研发计划项目(2021YFB3900900)
2025-02-05
2025-02-05
2025-02-05