Page 36 - 水利学报2025年第56卷第4期
P. 36

29 - 40.
                [13] 王晓玲,王栋,任 炳 昱,等.高 拱 坝 混 凝 土 振 捣 机 器 人 系 统 研 发 及 应 用 [J].水 利 学 报,2022,53(6):
                      631 - 643,654.
                [14] GUANS,WANGJ,WANGX,etal.ImprovedRefineDNetalgorithmforpreciseenvironmentalperceptionofau
                       tonomousearthmovingmachineryunderhazeandfugitivedustconditions [J].AdvancedEngineeringInformatics,
                      2024,59:102326.
                [15] MEIX,ZHOUX,XUF,etal.Humanintrusiondetectioninstatichazardousareasatconstructionsites:deep
                       learning - basedmethod [J].JournalofConstructionEngineeringandManagement,2023,149(1):04022142.
                [16] SUNS,ZHAOS,ZHENGJ.IntelligentsitedetectionbasedonimprovedYOLOalgorithm[C]??2021International
                       ConferenceonBigDataEngineeringandEducation(BDEE).2021.
                [17] HAMZENEJADIM H,MOHSENIH.Fine - tunedYOLOv5forreal - timevehicledetectioninUAVimagery:Ar
                       chitecturalimprovementsandperformanceboost[J].ExpertSystemswithApplications,2023,231:120845.
                [18] 曾拓程,王佳俊,王晓玲,等.大场景视频监控下大坝运输车改进多目标多视觉卸料识别模型研究 [J].
                       水利学报,2023,54(5):519 - 529,540.
                [19] ZHANGY,SUNP,JIANGY,etal.Bytetrack:Multi - objecttrackingbyassociatingeverydetectionbox[C]??
                       EuropeanConferenceonComputerVision.Cham :SpringerNatureSwitzerland,2022.
                [20] WANGJ,SUN K,CHENG T,etal.Deephigh - resolutionrepresentationlearningforvisualrecognition[J].
                       IEEETransactionsonPatternAnalysisandMachineIntelligence ,2020,43(10):3349 - 3364.
                [21] 段鸿杰,计洪图,李晓宇,等.基于监控视频的油田施工场景状态识别 [J].自动 化 技 术 与 应 用,2020,
                      39(8):80 - 85.
                [22] 刘相池.基于计算机视觉的建筑施工安全监控方法[D].天津:天津大学,2019.
                [23] 廖小烽,谢艳,田书函,等.基于 计 算 机 视 觉 的 施 工 进 度 自 动 监 控 方 法 [J].重 庆 大 学 学 报,2022,45
                       (S1):70 - 73.
                [24] 冯凯伦,唐一栋,梁森,等.塔吊 施 工 重 物 坠 落 情 景 智 能 感 知 方 法 研 究 [J].工 程 管 理 学 报,2022,36
                       (4):100 - 104.
                [25] 朱密.基于图像语义的建筑施工风险场景识别[D].大连:大连理工大学,2020.
                [26] 高星蓉.施工现场工人和移动机械的碰撞风险动态评估研究[D].重庆:重庆大学,2020.
                [27] ZHAOL,LIS.Objectdetectionalgorithm basedonimprovedYOLOv3[J].Electronics,2020,9(3):537.
                [28] ZENGT,WANGJ,CUIB,etal.Theequipmentdetectionandlocalizationoflarge - scaleconstructionjobsiteby
                       far - fieldconstructionsurveillancevideobasedonimprovingYOLOv3andgreywolfoptimizerimprovingextreme
                       learningmachine [J].ConstructionandBuildingMaterials,2021,291:123268.
                [29] ZHANGF,LIUH,CHENZ,etal.CollisionriskwarningmodelforconstructionvehiclesbasedonYOLO and
                       DeepSORTalgorithms [J].JournalofConstructionEngineeringandManagement,2024,150(6):04024053.
                [30] WANGZ,ZHANGY,MOSALAM KM,etal.Deepsemanticsegmentationforvisualunderstandingonconstruc
                       tionsites[J].Computer - AidedCivilandInfrastructureEngineering,2022,37(2):145 - 162.
                [31] JINKH,KANGKS,SHINBK,etal.Developmentofrobustdetectorusingtheweatherdeepgenerativemodel
                       foroutdoormonitoringsystem[J].ExpertSystemswithApplications,2023,234:120984.
                [32] HEK,ZHANGX,REN S,etal.Deepresiduallearningforimagerecognition[C]??ProceedingsoftheIEEE
                       ConferenceonComputerVisionandPatternRecognition.2016.
                [33] BOLYAD,ZHOUC,XIAOF,etal.Yolact:Real - timeinstancesegmentation[C]??ProceedingsoftheIEEE?
                       CVFInternationalConferenceonComputerVision.2019.
                [34] HEK,GKIOXARIG,DOLL?RP,etal.MaskR - CNN[C]??ProceedingsoftheIEEEInternationalConference
                       onComputerVision.2017.
                [35] CAIZ,VASCONCELOSN.CascadeR - CNN:Highqualityobjectdetectionandinstancesegmentation[J].IEEE
                       TransactionsonPatternAnalysisandMachineIntelligence,2019,43(5):1483 - 1498.
                [36] LINTY,MAIREM,BELONGIES,etal.Microsoftcoco:Commonobjectsincontext[C]??ComputerVision -
                       ECCV2014:13thEuropeanConference.Zurich:SpringerInternationalPublishing,2014.
                                                                                              (下转第 465页)

                —  4 5  —
                     4
   31   32   33   34   35   36   37   38   39   40   41