计算机科学 ›› 2024, Vol. 51 ›› Issue (11): 148-156.doi: 10.11896/jsjkx.231000148
赵卫东, 路明, 张睿
ZHAO Weidong, LU Ming, ZHANG Rui
摘要： 基于弱监督语义分割的道路裂缝检测方法大多基于先分块后检测的流程,分块增加了标注的工作量和误判的分块数量。针对上述问题,提出了基于深度强化学习的道路裂缝分块分类模型,根据道路裂缝图像特点,对智能体的状态、动作和获取的奖励进行了设计,训练智能体自主选择裂缝分块,并将选择结果作为分块标签用于多尺寸分块道路裂缝检测。在cqu-bpdd等数据集上进行的对比实验,证明了所提方法在道路裂缝分割性能、裂缝平均宽度的测量准确度方面优于现有方法。
中图分类号:
| [1] LI B,WANG K C P,ZHANG A,et al.Automatic classification of pavement crack using deep convolutional neural network[J].International Journal of Pavement Engineering,2020,21(4):457-463. [2] PING P,YANG X,GAO Z.A Deep Learning Approach forStreet Pothole Detection[C]//2020 IEEE Sixth International Conference on Big Data Computing Service and Applications,Oxford,United Kingdom.IEEE,2020:199-205. [3] HONG Y,LEE S,YOO S B.AugMoCrack:Augmented morphological attention network for weakly supervised crack detection[J].Electronics Letters,2022,58(17):651-653. [4] ZHANG Y,LI Q,ZHAO X,et al.TB-Net:A Three-StreamBoundary-Aware Network for Fine-Grained Pavement Disease Segmentation[C]//2021 IEEE Winter Conference on Applications of Computer Vision,Waikoloa.IEEE,2021:3654-3663. [5] YANG F,ZHANG L,YU S,et al.Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection[J].IEEE Transactions on Intelligent Transportation Systems,2020,21(4):1525-1535. [6] ZOU Q,ZHANG Z,LI Q,et al.DeepCrack:Learning Hierarchical Convolutional Features for Crack Detection[J].IEEE Transactions on Image Processing,2019,28:1498-1512. [7] LAU S L H,CHONG E K P,YANG X,et al.Automated Pavement Crack Segmentation Using U-Net-Based Convolutional Neural Network[J].IEEE Access,2020,8:114892-114899. [8] TANG W,HUANG S,ZHAO Q,et al.An Iteratively Optimized Patch Label Inference Network for Automatic Pavement Distress Detection[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(7):8652-8661. [9] YAN K,ZHANG Z.Automated Asphalt Highway PavementCrack Detection Based on Deformable Single Shot Multi-Box Detector Under a Complex Environment[J].IEEE Access,2021,9:150925-150938. [10] ZHU J S,SONG J B.Weakly supervised network based intelligent identification of cracks in asphalt concrete bridge deck-ScienceDirect[J].Alexandria Engineering Journal,2020,59(3):1307-1317. [11] HUANG G,HUANG S,HUANGFU L,et al.Weakly Super-vised Patch Label Inference Network with Image Pyramid for Pavement Diseases Recognition in the Wild[C]//ICASSP 2021-2021 IEEE International Conference on Acoustics,Speech and Signal Processing.Toronto,2021:7978-7982. [12] XU B,LIU C.Pavement crack detection algorithm based on ge-nerative adversarial network and convolutional neural network under small samples[J].Measurement,2022,196(9):111219. [13] LI Y,BAO T,XU B,et al.A deep residual neural networkframework with transfer learning for concretedams patch-level crack classification and weakly-supervised localization[J].Measurement,2022,188(1):110641. [14] WANG H,LI Y,DANG L M,et al.Pixel-level tunnel crack segmentation using a weakly supervised annotation approach[J].Computers in Industry,2021,133(12):103545. [15] DONG Z,WANG J,CUI B,et al.Patch-based weakly supervised semantic segmentation network for crack detection[J].Construction and Building Materials,2020,258(10):1-14. [16] RILL-GARCÍA R,DOKLADALOVA E,DOKLÁDAL P.Pixel-accurate road crack detection in presence of inaccurate annotations[J].Neurocomputing,2022,480(4):1-13. [17] INOUE Y,NAGAYOSHI H.Crack Detection as a Weakly-Supervised Problem:TowardsAchieving Less Annotation-Intensive Crack Detectors[C]//2020 25th International Conference on Pattern Recognition,Milan,Italy.2021:65-72. [18] CAICEDO J C,LAZEBNIK S.Active Object Localization with Deep Reinforcement Learning[C]//2015 IEEE International Conference on Computer Vision.Santiago,Chile,2015:2488-2496. [19] SILVER D,HUBERT T,SCHRITTWIESER J,et al.Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm[EB/OL].https://arxiv.org/abs/1712.01815. [20] YE D,LIU Z,SUN M,et al.Mastering Complex Control in MOBA Games with Deep Reinforcement Learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:6672-6679. [21] AHN J,KWAK S.Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,2018:4981-4990. [22] HUANG Z,WANG X,WANG J,et al.Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Gro-wing[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,2018:7014-7023. [23] WANG X,YOU S,LI X,et al.Weakly-Supervised SemanticSegmentation by Iteratively Mining Common Object Features[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,2018:1354-1362. [21] SUN G,WANG W,DAI J,et al.Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation[C]//Computer Vision－ECCV 2020.2020:347-365. [22] WANG Y,ZHANG J,KAN M,et al.Self-Supervised Equiva-riant Attention Mechanism for Weakly Supervised Semantic Segmentation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle,2020:12272-12281. [23] YANG X,LI H,YU Y,et al.Automatic Pixel-Level Crack Detection and Measurement Using Fully Convolutional Network[J].Computer-Aided Civil and Infrastructure Engineering,2018,33(12):1090-1109. [24] SELVARAJU R R,COGSWELL M,DAS A,et al.Grad-CAM:Visual Explanations from Deep Networks via Gradient-based Localization[C]//2017 IEEE International Conference on Computer Vision.Venice,2017:618-626. |
|
||
首页