计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 220900155-5.doi: 10.11896/jsjkx.220900155
张恩华, 王卫杰, 段楠, 康楠
ZHANG Enhua, WANG Weijie, DUAN Nan, KANG Nan
摘要: 为探究湿润环境对沥青路面裂缝自动检测效果的影响,文章通过YOLOv5深度学习目标检测算法,建立了沥青路面裂缝检测模型;并在此基础上,设置了湿润与干燥环境下的裂缝检测对比实验,对比了在两种环境下沥青路面裂缝检测结果的准确度与置信度。研究结果表明,湿润环境扩大了沥青路面裂缝在深度学习网络中的识别特征,提高了裂缝检测的效果。干燥路面裂缝检测的准确度为80.70%,湿润路面裂缝检测的准确度为89.47%,湿润环境下的沥青路面裂缝检测模型准确率提升了8.77%。同时,统计同一裂缝两种环境下检测的置信度发现,置信度平均值在干燥环境下为0.72,在湿润环境下为0.78,且湿润与否与裂缝检测的置信度存在显著正相关关系。研究成果为沥青路面裂缝自动检测效果的提升提供了新的思路,为路面养护管理的决策提供了有效工具。
中图分类号:
[1]SONG M.Study on the causes and Treatment measures ofHighway Pavement Cracks[J].Science and Technology Innovation and Application,201,11(34):106-109. [2]XU Z G,CHE Y L,LI J L,et al.Research progress in automatic image processing of pavement damage[J].Journal of Traffic and Transportation Engineering,2019,19(1):172-190. [3]ZHANG J,SHA A M,GAO H G,et al.Automatic Pavement Crack Recognition and Evaluation System Based on Digital Image Processing[J].Journal of Chang’an University(Natural Science Edition),2004(2):18-22. [4]FUKUHARA T,TERADA K,NAGAO M,et al.Automaticpavement-distress-survey system[J].Journal of Transportation Engineering,1990,116(3):280-286. [5]DONG A G,ZHANG X Y,XUE H Z,et al.Multi-level clustering algorithm for crack detection of concrete surface[J].Journal of Traffic and Transportation Engineering,2013,13(6):7-13. [6]FUJITA Y,SHIMADA K,ICHIHARA M,et al.A MethodBased on Machine Learning Using Handcrafted Features for Crack Detection from Asphalt Pavement Surface Images[C]//Thirteenth International Conference on Quality Control by Artificial Vision 2017.Bellingham:SPIE,2017. [7]MEI Q M,GÜ L,AZIM M R.Densely connected deep neuralnetwork considering connectivity of pixels for automatic crack detection[J].Automation in Construction,2019,110:103018. [8]LI G,LIU Q W,REN W,et al.Automatic recognition and analysis system of asphalt pavement cracks using interleaved low-rank group convolution hybrid deep network and SegNet fusing dense condition random field-Science Direct[J].Measurement,2021,170:108693.1-108693.17. [9]CHEN T,CAI Z,ZHAO X,et al.Pavement Crack Detectionand Recognition Using the Architecture of SegNet[J].Journal of Industrial Information Integration,2020,18(2):100144. [10]WANG B,WANG X,CHEN F,et al.Road surface crack recognition in aerial image[J].Acta Optica Sinica,2017,37(8):126-132. [11]FAN M A,AL A.Pavement Crack Detection Using Sketch Token[J].Procedia Computer Science,2018,139:151-157. [12]SONG H X,MA J,WANG J F,et al.Identification of pavement crack based on dual camera stereo photogrammetry[J].China Journal of Highway and Transport,2015,28(10):18-25,40. [13]QIU Y J,WANG G L,YANG E H,et al.Crack Detection of 3D Asphalt Pavement Based on Multi-feature Test[J].Journal of Southwest Jiaotong University,2020,55(3):518-524. [14]ANGSTROM A.The Albedo of Various Surfaces of Ground[J].Geografiska Annaler,1925,7(4):323-342. [15]LEKNER J,DORF M.Why some things are darker when wet[J].Applied Optics,1988,27(7):1278-1280. [16]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition.2015:779-788. [17]REDMON J,FARHADI A.YOLOv3:an incremental improvement[C]//IEEE Conference on Computer Vision and Pattern Recognition.2018. [18]BOCHKOVSKIY A,WANG C Y,LIAO H.YOLOv4:Optimal speed and accuracy of objectdetection[C]//IEEE Conference on Computer Vision and Pattern Recognition.2020. [19]YU Z W,SHEN Y G,SHEN C K.A real-time detection ap-proach for bridge cracks based on YOLOv4-FPM[J].Automation in Construction,2021,122:103514. [20]LI S W,GU X Y,XU X R,et al.Detection of concealed cracks from ground penetrating radar images based on deep learning algorithm[J].Construction and Building Materials,2021,273:121949. |
|