施工现场的人机距离检测方法综述

doi:10.11896/jsjkx.240700098

摘要/Abstract

摘要： 随着建筑行业的发展,施工机械的使用日益频繁,由此带来的安全问题也愈发严峻。近年来,全国范围内发生的生产安全事故中,建筑起重机械类事故占比显著。因此,如何有效监测并预防施工现场工人与施工机械之间的潜在风险,成为当前研究的热点。首先,系统归纳了基于定位技术和深度学习方法的工人与施工机械距离检测技术,重点介绍深度学习的方法并阐述其关键技术;其次,根据距离检测方法总结国内外的研究现状,并对各方法的优势及局限性进行对比分析;然后,通过目前研究面临的挑战,提出相应的改进策略;最后,给出未来发展趋势,为相关领域的研究者提供有价值的参考。

关键词: 深度学习, 施工现场, 距离检测, 深度估计

Abstract: With the development of the construction industry,the use of construction machinery is becoming more and more frequent,and the resulting safety problems are becoming more and more serious.In recent years,among the production safety accidents that have occurred nationwide,construction lifting machinery accidents account for a significant proportion.Therefore,how to effectively monitor and prevent the potential risks between construction site workers and construction machinery become a hot topic of current research.Firstly,this paper systematically summarizes the distance detection technologies between workers and construction machinery based on positioning technology and deep learning method,focusing on the method of deep learning and expounding its key technologies.Secondly,according to the distance detection method,the research status at home and abroad is summarized,and the advantages and limitations of each method are compared and analyzed.Then,through the challenges faced by the current research,the corresponding improvement strategies are proposed.Finally,the future development trend is given for the follow-up research,which provides valuable reference for researchers in related fields.

Key words: Deep learning, Construction site, Distance detection, Depth estimation

中图分类号:

TP391

郝旭, 武文红, 牛恒茂, 石宝, 乌尼尔, 王嘉敏, 褚宏坤. 施工现场的人机距离检测方法综述[J]. 计算机科学, 2025, 52(6A): 240700098-10. https://doi.org/10.11896/jsjkx.240700098

HAO Xu, WU Wenhong, NIU Hengmao, SHI Bao, WU Nier, WANG Jiamin, CHU Hongkun. Survey of Man-Machine Distance Detection Method in Construction Site[J]. Computer Science, 2025, 52(6A): 240700098-10. https://doi.org/10.11896/jsjkx.240700098

参考文献

[1]Analysis of building safety situation in China[DB/OL].https://zhuanlan.zhihu.com/p/562479748.
[2]2022 National Special Equipment Safety Report[DB/OL].https://www.samr.gov.cn/tzsbj/qktb/tb/art/2023/art_67857a52cc3b41bd9cff0560e6b9b503.html.
[3]WU L F.Safety belt recognition and detection for aerial workbased on convolutional neural network [J].Modern Computer,2021,27(24):124-130.
[4]LI H,WU L Z,XUE X C,et al.Safety inspection of high-altitude operations based on computer vision [J].Chinese Journal of Safety Science,2023,33(9):69-75.
[5]YANGD W,ZHANG C C.Detection algorithm of helmet wearing based on improved YOLOv7 [J].Journal of Shenyang University of Technology,2024,43(1):16-21.
[6]FENG P Y,QIAN Y R,FAN Y Y,et al.Safety helmet detection algorithm based on improved Cascade R-CNN [J].Microelectronics and Computer,2024(1):63-73.
[7] FAN B Q,DONG B Y,WANG B,et al.Identification and application of unsafe behaviors of subway construction workers based on deep learning [J].Chinese Journal of Safety Science,2023,33(1):41-47.
[8]CHENG J,CHENG Z,SU Z,et al.Unsafe behavior management technology based on deep learning [J].Construction Technology( Chinese and English ),2023,52(20):118-121.
[9]LI W J,LIU X.Research on identification and early warningsystem of unsafe behavior of underground personnel based on deep learning [J].Metal Mine,2023(3):177-184.
[10]JIANG W,ZHANG L,ZHANG Y,et al.Infrastructure construction personnel management system supported by mobile positioning technology [J].VW Standardization,2022(23):70-72.
[11]SONG Z Y.Research on early warning of building construction object strike accident [J].Engineering Technology Research,2023,8(8):214-216.
[12]DER Y W,CHANG H K,HSIE Y C,et al.An Image Recognition-based Distance Measurement Technique for Real-time Locating of Construction Workers[C]//2021 IEEE 3rd Eurasia Conference on Biomedical Engineering,Healthcare and Sustainability(ECBIOS).IEEE,2021:148-151.
[13]LINDSAY G W.Convolutional neural networks as a model of the visual system:Past,present,and future[J].Journal of Cognitive Neuroscience,2021,33(10):2017-2031.
[14]JIANG J J,LI Z Y,LIU X M.Review of monocular depth estimation methods based on deep learning [J].Journal of ComputerScience,2022,45(6):1276-1307.
[15]CAI J C,DONG F M,SUN S F,et al.A review of unsupervised monocular depth estimation research [J].Computer Science,2024,51(2):117-134.
[16]DING J F,XIAO W T,LI M Y,et al.Substation cross-border violation detection combining visual perception and RTK positioning [J].Computer Technology and Development,2023,33(8):206-213.
[17]SUN Y H,XUE Z G,WANG C B,et al.Research on subway construction personnel positioning technology based on video image analysis and monocular vision technology [J].Electronic Design Engineering,2023,31(15):187-190,195.
[18] ZHANG X H,CHEN X,YANG W J,et al.Research on visual positioning method of anchoring equipment based on single laser beam information [J].Coal Science and Technology,2024,52(1):311-322.
[19]LI K W.Research and application of monocular depth estimation for transmission line scenarios [D].Jinan:Shandong University,2023.
[20]LI H,CHAN G,WONG J K W,et al.Real-time locating systems applications in construction[J].Automation in Construction,2016,63:37-47.
[21]PAUL A,PULANI S,MAHESWARI J U.Digital Twin Framework for Worker Safety using RFID Technology[C]//ISARC.Proceedings of the International Symposium on Automation and Robotics in Construction.IAARC Publications,2023:254-261.
[22]BRUSSELAERS N,HUANG H,MACHARIS C,et al.A GPS-based approach to measure the environmental impact of construction-related HGV traffic on city level[J].Environmental Impact Assessment Review,2023,98:106955.
[23]WU Y F,LIU S,LIU T Y.Research on indoor motion localization algorithm based on UWB [J].Computer Programming Skills and Maintenance,2024(4):151-153.
[24]EIGEN D,PUHRSCH C,FERGUS R.Depth map predictionfrom a single image using a multi-scale deep network[J].Advances in Neural Information Processing Systems,2014,27.
[25]ZHANG Y P.Vehicle detection and ranging based on convolutional neural network [D].Beijing:Beijing University of Posts and Telecommunications,2019.
[26]SHIBA Y,ONO S,FURUKAWA R,et al.Learning-based active 3D measurement technique using light field created by video projectors[J].IPSJ Transactions on Computer Vision and Applications,2019,11:1-14.
[27]BAO W,KOMATSU R,ASAMA H,et al.Applying Albedo Estimation and Implicit Neural Representations to Well-Posed Shape From Shading[J].IEEE Access,2023,11:40038-40048.
[28]LUO H,GAO B,XU J,et al.An approach for structured light system calibration[C]//2013 IEEE International Conference on Cyber Technology in Automation,Control and Intelligent Systems.IEEE,2013:428-433.
[29]LI Z,CHEN Z,LIU X,et al.Depthformer:Exploiting long-range correlation and local information for accurate monocular depth estimation[J].Machine Intelligence Research,2023,20(6):837-854.
[30]LAINA I,RUPPRECHT C,BELAGIANNIS V,et al.Deeperdepth prediction with fully convolutional residual networks[C]//2016 Fourth International Conference on 3D Vision(3DV).IEEE,2016:239-248.
[31]WANG D D,HOU J H,WANG F Q,et al.Research on target detection and ranging based on binocular vision [J].Electronic Production,2022,30(21):58-61.
[32]GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial networks[J].Communications of the ACM,2020,63(11):139-144.
[33]ZHAO C X,ZHANG X L,YANG Y.Three-dimensional reconstruction based on SGBM semi-global stereo matching algorithm [J].Laser Magazine,2021,42(4):139-143.
[34]GUO H L,LIU W P,ZHANG W S.Research on early warning system of workers’unsafe behavior integrating BIM and PT [J].Chinese Journal of Safety Science,2014,24(4):104-109.
[35] LI H,CHAN G,WONG J K W,et al.Real-time locating systems applications in construction[J].Automation in Construction,2016,63:37-47.
[36]DUAN L J,LI J K,ZHANG B.The application of engineering personnel and vehicle positioning in the construction of hydropower stations－Taking the Changlongshan Hydropower Station as an example [J].People’s Yangtze River,2019,50(S1):354-357.
[37] FAN L P.Research on safety situation assessment of construction workers’ trajectory based on real-time positioning [D].Xuzhou:China University of Mining and Technology,2023.
[38]ZHANG J J,HAN Y,MA G X,et al.Research on intelligent early warning system for falling accidents of construction wor-kers based on BIM and RFID [J].Journal of Engineering Ma-nagement,2015,29(6):17-21.
[39]DAI M Q.Study on hazard identification of construction site based on RFID technology [D].Shanghai:East China University of Technology,2014.
[40]TEIZER J,VENUGOPAL M,WALIA A.Ultrawideband forautomated real-time three-dimensional location sensing for workforce,equipment,and material positioning and tracking[J].Transportation Research Record,2008,2081(1):56-64.
[41]ZHANG Z T,WANNG Y Y,LUO Z B,et al.Automatic detection of dangerous scenes under the interaction of tower crane and worker space [J].Journal of Tsinghua University( Natural Science Edition ),2024,64(2):198-204.
[42] LIU H,LIAO K,LIN C,et al.Pseudo-lidar point cloud interpolation based on 3d motion representation and spatial supervision[J].IEEE Transactions on Intelligent Transportation Systems,2021,23(7):6379-6389.
[43] QIAN R,GARG D,WANG Y,et al.End-to-end pseudo-lidar for image-based 3d object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:5881-5890.
[44]SHEN J,YAN W,LI P,et al.Deep learning-based object identification with instance segmentation and pseudo-LiDAR point cloud for work zone safety[J].Computer-Aided Civil and Infrastructure Engineering,2021,36(12):1549-1567.
[45]LI M,LIU P,YU H L.Research on real-time safety early warning system for construction site construction personnel based on wearable technology [J].Industrial Safety and Environmental Protection,2018,44(11):32-35.
[46]KONG F S.Design and test analysis of beacon sensor earlywarning system in construction dangerous area [D].Xi’an:Xi’an University of Architecture and Technology,2021.
[47]SHI H T,LI G,FAN L T,et al.Crane dangerous area intrusion pedestrian machine vision positioning algorithm [J].Control Engineering,2021,28(4):759-765.
[48]KIM D,LIU M,LEE S H,et al.Remote proximity monitoring between mobile construction resources using camera-mounted UAVs[J].Automation in Construction,2019,99:168-182.
[49]SHAN F.Study on the method of front target detection and ranging of mining trucks based on deep learning [D].Shenyang:Northeastern University,2020.
[50]SHEN J,HUANG X H.Dangerous area intrusion alarm based on improved YOLOv5s algorithm [J].Computer System Application,2023,32(3):157-162.
[51]GAO Y F.Research on target detection and ranging based on binocular vision [D].Taiyuan:Taiyuan University of Science and Technology,2020.
[52]WANG K Q.Research on intrusion detection of constructiondangerous areas based on binocular stereo vision technology [D].Beijing:Beijing Jianzhu University,2023.
[53]ZHANG R.Research on dynamic distance estimation of substation foreign body intrusion based on binocular stereo vision and deep learning [D].Xi’an:Xi’an University of Technology,2023.
[54]ZHU Z,PARK M W,KOCH C,et al.Predicting movements of onsite workers and mobile equipment for enhancing construction site safety[J].Automation in Construction,2016,68:95-101.
[55]LEE Y J,PARK M W.3D tracking of multiple onsite workers based on stereo vision[J].Automation in Construction,2019,98:146-159.
[56]YAN X,ZHANG H,LI H.Computer vision-based recognition of 3D relationship between construction entities for monitoring struck-by accidents[J].Computer-Aided Civil and Infrastructure Engineering,2020,35(9):1023-1038.
[57]ZHOU Z,SI G,SUN H,et al.A robust clustering algorithmbased on the identification of core points and KNN kernel density estimation[J].Expert Systems with Applications,2022,195:116573.
[58]WANG K,LIU J L,HU Q Q,et al.Research on automatic detection of personal protective equipment in multi-operation scenarios [J].Journal of Safety and Environment,2023,23(11):3960-3967.
[59]TIEN P W,WEI S,CALAUTIT J.A computer vision-based occupancy and equipment usage detection approach for reducing building energy demand[J].Energies,2020,14(1):156.
[60]YU J Y.Research on moving target state detection in openscenes and construction areas [D].Qingdao:Qingdao University,2022.
[61] WANG M,WONG P,LUO H,et al.Predicting safety hazards among construction workers and equipment using computer vision and deep learning techniques[C]//Proceedings of the International Symposium on Automation and Robotics in Construction.IAARC Publications,2019:399-406.
[62]SHI H.Research on detection algorithm of safety helmet wea-ring on construction site based on deep learning [D].Wuhan:Wuhan University of Technology,2019.
[63]WU D.Research on safety condition monitoring technology of construction personnel based on computer vision [D].Harbin:Harbin University of Technology,2019.
[64] LEE J,LEE S.Construction site safety management:a computer vision and deep learning approach[J].Sensors,2023,23(2):944.
[65]GAO X R.Dynamic assessment of collision risk between con-struction site workers and mobile machinery [D].Chongqing:Chongqing University,2020.
[66]CAO Z Y.Research on collision safety assessment of construction workers based on CV & FI [D].Dalian:Dalian University of Technology,2020.
[67]ZHANG B,SONG Y B,WU B,et al.Two-stage Faster R-CNN for automatic analysis of pedestrian-vehicle collision risk at construction site [J].Manufacturing Automation,2022,44( 6 ):24-27,31.
[68]TAO C,CAO J,WANG C,et al.Pseudo-mono for monocular 3d object detection in autonomous driving[J].IEEE Transactions on Circuits and Systems for Video Technology,2023,33(8):3962-3975.
[69]LI P.Research and implementation of key technologies of construction site safety early warning based on target detection and depth estimation [D].Chengdu:University of Electronic Science and Technology of China,2021.
[70]HU X X.Research and application of ranging method based on monocular depth estimation [D].Beijing:North China Electric Power University,2022.
[71]YAN W J.Research on key technologies of 3D target recognition in construction site [D].Chengdu:University of Electronic Science and Technology of China,2022.
[72] QIN S X.Research and implementation of key technologies for monocular image depth estimation [D].Chengdu:University of Electronic Science and Technology of China,2022.
[73]SHEN J,YAN W,QIN S,et al.A self-supervised monoculardepth estimation model with scale recovery and transfer learning for construction scene analysis[J].Computer-Aided Civil and Infrastructure Engineering,2023,38(9):1142-1161.
[74]LEE J H,HAN M K,KO D W,et al.From Big to Small:Multi-Scale Local Planar Guidance for Monocular Depth Estimation[J].arXiv:1907.10326,2019.
[75]ANDRAGHETTI L,MYRIOKEFALITAKIS P,DOVESI P L,et al.Enhancing self-supervised monocular depth estimation with traditional visual odometry[C]//2019 International Conference on 3D Vision(3DV).IEEE,2019:424-433.
[76]GUIZILINI V,AMBRUS R,PILLAI S,et al.3d packing forself-supervised monocular depth estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:2485-2494.
[77]LI C,YUE C,LIU Y,et al.An Improved MonoDepth2 Algorithm for Vehicle Monocular Depth Estimation[J].Optik,2024,311:171936.
[78]YUAN W,GU X,DAI Z,et al.New crfs:Neural window fully-connected crfs for monocular depth estimation[J].arXiv:2203.01502,2022.
[79]GEIGER A,LENZ P,URTASUN R.Are we ready for autonomous driving? the kitti vision benchmark suite[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2012:3354-3361.
[80]ERICSSON L,GOUK H,HOSPEDALES T M.How well doself-supervised models transfer?[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:5414-5423.
[81]GUIZILINI V,HOU R,LI J,et al.Semantically-guided representation learning for self-supervised monocular depth[J].ar-Xiv:2002.12319,2020.
[82]BELLO J L G,KIM M.Self-supervised deep monocular depth estimation with ambiguity boosting[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(12):9131-9149.
[83]SAXENA A,SUN M,NG A Y.Make3d:Learning 3d scenestructure from a single still image[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,31(5):824-840.
[84]SILBERMAN N,FERGUS R.Indoor scene segmentation using a structured light sensor[C]//ICCV.2011:601-608.
[85]CHEN W,FU Z,YANG D,et al.Single-image depth perception in the wild[J].Advances in Neural Information Processing Systems,2016,29.
[86]HUANG X,WANG P,CHENG X,et al.The apolloscape open dataset for autonomous driving and its application[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,42(10):2702-2719.
[87]CORDTS M,OMRAN M,RAMOS S,et al.The cityscapes dataset for semantic urban scene understanding[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:3213-3223.
[88]GODARD C,MAC AODHA O,FIRMAN M,et al.Digging into self-supervised monocular depth estimation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:3828-3838.
[89]CASSER V,PIRK S,MAHJOURIAN R,et al.Unsupervisedmonocular depth and ego-motion learning with structure and semantics[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.2019.
[90]GUIZILINI V,AMBRUS R,PILLAI S,et al.3d packing forself-supervised monocular depth estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:2485-2494.
[91]PENG R,WANG R,LAI Y,et al.Excavating the potential capacity of self-supervised monocular depth estimation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:15560-15569.
[92]BIAN J,LI Z,WANG N,et al.Unsupervised scale-consistentdepth and ego-motion learning from monocular video[J].Advances in Neural Information Processing Systems,2019,32.
[93]JIANG Y,GONG X,LIU D,et al.Enlightengan:Deep light enhancement without paired supervision[J].IEEE Transactions on Image Processing,2021,30:2340-2349.
[94]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.
[95]WOO S,PARK J,LEE J Y,et al.Cbam:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:3-19.
[96]YANG Z,WANG P,XU W,et al.Unsupervised learning of geometry from videos with edge-aware depth-normal consistency[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018.
[97]WU J,ZHOU W,LUO T,et al.Multiscale multilevel context and multimodal fusion for RGB-D salient object detection[J].Signal Processing,2021,178:107766.
[98]JIAO J,CAO Y,SONG Y,et al.Look deeper into depth:Mono-cular depth estimation with semantic booster and attention-driven loss[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:53-69.
[99]RANJAN A,JAMPANI V,BALLES L,et al.Competitive collaboration:Joint unsupervised learning of depth,camera motion,optical flow and motion segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:12240-12249.
[100]RANFTL R,BOCHKOVSKIY A,KOLTUN V.Vision trans-formers for dense prediction[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:12179-12188.
[101]LAINA I,RUPPRECHT C,BELAGIANNIS V,et al.Deeper depth prediction with fully convolutional residual networks[C]//2016 Fourth International Conference on 3D Vision(3DV).IEEE,2016:239-248.
[102]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[103]BHAT S F,ALHASHIM I,WONKA P.Adabins:Depth estimation using adaptive bins[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:4009-4018.
[104]XIAN K,ZHANG J,WANG O,et al.Structure-guided ranking loss for single image depth prediction[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:611-620.
[105]WANG L,ZHANG J,WANG Y,et al.Cliffnet for monocular depth estimation with hierarchical embedding loss[C]//European Conference on Computer Vision.Cham:Springer InternationalPublishing,2020:316-331.
[106]SAHA S,OBUKHOV A,PAUDEL D P,et al.Learning to relate depth and semantics for unsupervised domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:8197-8207.
[107]HUYNH L,NGUYEN-HA P,MATAS J,et al.Guiding mono-cular depth estimation using depth-attention volume[C]//Computer Vision-ECCV 2020:16th European Conference,Glasgow,UK,August 23-28,2020,Proceedings,Part XXVI 16.Springer International Publishing,2020:581-597.
[108]LEE B U,LEE K,KWEON I S.Depth completion usingplane-residual representation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:13916-13925.
[109] GUIZILINI V,AMBRUS R,BURGARD W,et al.Sparse auxiliary networks for unified monocular depth prediction and completion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:11078-11088.
[110]IMRAN S,LIU X,MORRIS D.Depth completion with twin surface extrapolation at occlusionboundaries[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:2583-2592.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed