«Previous Article|Table of Contents|Next Article»

¡¶½¨Öþ¿ÆѧÓ빤³Ìѧ±¨¡·[ISSN:1673-2049/CN:61-1442/TU]

Issue:

2026Äê01ÆÚ

Page:

14-27

Research Field:

ÖÇÄܼì²âÓ뽨Ôì¼¼ÊõרÀ¸

Publishing date:

Info

Title:

Multiple articulated construction machinery efficiency analysis method ª¤based on local feature reª²identification

Author(s):

LU Yujie¹; 2;  ZHONG Lijian¹;  WEI Wei¹;  WANG Shuo¹

1. College of Civil Engineering, Tongji University, Shanghai 200092, China£» 2. Shanghai Research Institute for ª¤Intelligent Autonomous System, Tongji University, Shanghai 201210, China

Keywords:

multi-object re-identification;  local feature matching;  multi-object tracking;  machinery efficiency analysis;  construction machinery management

PACS:

TU713£»TP391.41

DOI:

10.19815/j.jace.2024.12012

Abstract:

In order to overcome the interruption issues caused by occlusion in existing vision-based machinery efficiency analysis methods applied to articulated construction machinery, and to achieve longª²term and intelligent efficient construction machinery efficiency analysis, a method for efficiency analysis of multiple articulated construction machinery based on local feature reª²identification was proposed. The proposed method utilized convolutional neural networks to extract local appearance features of the excavator for identity matching and target re-identification, effectively correcting the misjudgment of multiple target identities caused by occlusion. Based on multiª²object tracking, the activity recognition algorithms to achieve statistical analysis of multiple excavators activities and efficiency analysis were further applied. Taking a construction project in Shanghai as a case study, the excavator on the construction site was tracked and the efficiency was analyzed. The results show that the results of reª²identification and stable tracking (with a video duration of 25 minutes) using this method are more accurate, with the accuracy of machinery efficiency analysis reaching 96.74%. This study provides a research paradigm for multi-mechanical target re-identification in the construction engineering field and offers a practical example for intelligent efficiency analysis based on visual methods in complex scenarios.

References:

£Û 1 £ÝÑîîå , ÐíÇå·ç , Íõ׿ÁÕ . »ùÓÚ¾í»ýÉñ¾­ÍøÂçµÄ½á¹¹ËðÉËʶ±ðÑо¿½øÕ¹£Û J £Ý . ½¨Öþ¿ÆѧÓ빤³Ìѧ±¨ ,2022, ª© 39(4) ªª :38 - 57.

YANG Shuo, XU Qingfeng, WANG Zhuolin. Research progress on structural damage detection based on convolutional neural networks £Û J £Ý . Journal of Architecture and Civil Engineering, 2022, 39(4): 38 - 57.

£Û 2 £ÝÍõè±èª , Ф½¨×¯ , ¶ÎÕ仪 , µÈ . ½¨ÖþÎïÍâÁ¢ÃæËðÉ˼ì²âÖÇÄÜ»¯·¢Õ¹Ç÷ÊÆ£Û J £Ý . ½¨Öþ¿ÆѧÓ빤³Ìѧ±¨ ,2022, ª© 39(4) ªª :24 - 37.

WANG Pujin, XIAO Jianzhuang, DUAN Zhenhua, et al. Intelligent development trend of building enclosure damage detection £Û J £Ý . Journal of Architecture and Civil Engineering, 2022, 39(4): 24 - 37.

£Û 3 £ÝÂíºêΰ , ÁÖÒÝÖÞ , ÄôÕñ»ª . ÀûÓÃÉÙÁ¿´«¸ÐÆ÷ÐÅÏ¢ÓëÈ˹¤ÖÇÄܵÄÇÅÁº½á¹¹°²È«¼à²âз½·¨£Û J £Ý . ½¨Öþ¿ÆѧÓ빤³Ìѧ±¨ ,2018,35(5):9 - 23.

MA Hongwei, LIN Yizhou, NIE Zhenhua. New methods of structural health monitoring based on small amount of sensor information and artificial intelligence £Û J £Ý . Journal of Architecture and Civil Engineering, 2018, 35(5): 9 - 23.

£Û 4 £Ý AKHAVIAN R,BEHZADAN A H. Construction equipment activity recognition for simulation input modeling using mobile sensors and machine learning classifiers £Û J £Ý . Advanced Engineering Informatics, 2015, 29(4): 867 - 877.

£Û 5 £Ý KIM H, AHN C R, ENGELHAUPT D, et al. Application of dynamic time warping to the recognition of mixed equipment activities in cycle time measurement £Û J £Ý . Automation in Construction, 2018, 87: 225 - 234.

£Û 6 £Ý RASHID K M, LOUIS J. Times - series data augmentation and deep learning for construction equipment activity recognition £Û J £Ý . Advanced Engineering Informatics, 2019, 42: 100944.

£Û 7 £Ý KIM J, CHI S. Adaptive detector and tracker on construction sites using functional integration and online learning £Û J £Ý . Journal of Computing in Civil Engineering, 2017, 31(5): 04017026.

£Û 8 £Ý KIM J, CHI S. Action recognition of earthmoving excavators based on sequential pattern analysis of visual features and operation cycles £Û J £Ý . Automation in Construction, 2019, 104: 255 - 264.

£Û 9 £Ý KIM J, CHI S. Multi - camera vision - based productivity monitoring of earthmoving operations £Û J £Ý . Automation in Construction, 2020, 112: 103121.

£Û 10 £Ý YUAN C X, LI S, CAI H B. Vision - based excavator detection and tracking using hybrid kinematic shapes and key nodes £Û J £Ý . Journal of Computing in Civil Engineering, 2017, 31: 04016038.

£Û 11 £Ý SHRESTHA A,MAHMOOD A. Review of deep learning algorithms and architectures £Û J £Ý . IEEE Access, 2019, 7: 53040 - 53065.

£Û 12 £Ý MA J Y, JIANG X Y, FAN A X, et al. Image matching from handcrafted to deep features: a survey £Û J £Ý . International Journal of Computer Vision, 2021, ª© 129(1) ªª : 23 - 79.

£Û 13 £Ý REZAZADEH AZAR E, MCCABE B. Automated visual recognition of dump trucks in construction videos £Û J £Ý . Journal of Computing in Civil Engineering, 2012, 26(6): 769 - 781.

£Û 14 £Ý ROBERTS D, GOLPARVAR - FARD M. End - to - end vision - based detection, tracking and activity analysis of earthmoving equipment filmed at ground level £Û J £Ý . Automation in Construction, 2019, 105: 102811.

£Û 15 £Ý REN S Q, HE K M, GIRSHICK R, et al. Faster R - CNN: towards real - time object detection with region proposal networks £Û J £Ý . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137 - 1149.

£Û 16 £Ý WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric £Û C £Ý //IEEE. 2017 IEEE International Conference on Image Processing (ICIP). Beijing: IEEE, 2017: 3645 - 3649.

£Û 17 £Ý ZHU X Y, LUO Z B, FU P, et al. VOC - RelD: vehicle re - identification based on vehicle - orientation - camera £Û C £Ý //IEEE. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Seattle: IEEE, 2020: 2566 - 2573.

£Û 18 £Ý ZHANG X, NIE X S, SUN Z R, et al. Re - ranking vehicle re - identification with orientation - guide query expansion £Û J £Ý . International Journal of Distributed Sensor Networks, 2022, 18(3): 155014772110663.

£Û 19 £Ý YU Y, SI X S, HU C H, et al. A review of recurrent neural networks: LSTM cells and network architectures £Û J £Ý . Neural Computation, 2019, 31(7): 1235 - 1270.

£Û 20 £Ý VASWANI A, SHAZEER N M, PARMAR N, ª© et al ªª .Attention is all you need £Û C £Ý //VON LUXBURG U, GUYON I. Proceedings of the 31st International Conference on Neural Information Processing Syste. Long Beach: Curran Associates Inc, 2017: 1 - 11.

£Û 21 £ÝÁõΰáÍ , µË½£Ñó , Õž¸ÎÄ , µÈ . »ùÓÚÉî¶ÈѧϰµÄÍÚ¾ò»ú¹¤×÷½×¶ÎµÄ·ÖÀàÓëʶ±ð£Û J £Ý . ¶«±±´óѧѧ±¨ ( ×ÔÈ»¿Æѧ°æ ),2023,44(10):1464 - 1473.

LIU Weiwei, DENG Jianyang, ZHANG Jingwen, ª© et al ªª . Classification and identification of excavators ¬ð working stages based on deep learning £Û J £Ý . Journal of Northeastern University (Natural Science), 2023, ª© 44(10) ªª : 1464 - 1473.

£Û 22 £Ý³ÂÑ©½¡ , ÇØË®½é , °×ÖÒ³¼ , µÈ . Éî¶ÈѧϰÐÐΪʶ±ðµÄÍÚ¾ò»úÉú²úЧÂʼà¿Øϵͳ£Û J £Ý . ÖÇÄܼÆËã»úÓëÓ¦Óà ,2023,13(4):111 - 116,121.

CHEN Xuejian, QIN Shuijie, BAI Zhongchen, et al. Productivity analysis system of earthmoving excavator based on deep learning action recognition £Û J £Ý . Intelligent Computer and Applications, 2023, 13(4): 111 - 116, 121.

£Û 23 £Ý YI F, WEN H, JIANG T. ASFormer: transformer for action segmentation £Û C £Ý //BMVC. Proceedings of the 32nd British Machine Vision Conference. Beijing: BMVC, 2021: 236.

£Û 24 £Ý DU Y H, ZHAO Z C, SONG Y, et al. StrongSORT: make DeepSORT great again £Û J £Ý . IEEE Transactions on Multimedia, 2023, 25: 8725 - 8737.

£Û 25 £Ý TERVEN J, CORDOVA - ESPARZA D M, ROMERO - GONZALEZ J A. A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO - NAS £Û J £Ý . Machine Learning and Knowledge Extraction, 2023, 5(4): 1680 - 1716.

£Û 26 £Ý HE K M,ZHANG X Y,REN S Q, et al. Deep residual learning for image recognition £Û C £Ý //IEEE. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770 - 778.

£Û 27 £Ý LIANG Y, LI X, JAFARI N, et al. Video object segmentation with adaptive feature bank and uncertain - region refinement £Û EB/OL £Ý .(2020 - 10 - 15) £Û 2024 - 11 - 20 £Ý .https://arxiv.org/abs/2010.07958.

£Û 28 £Ý WU C Y, FEICHTENHOFER C, FAN H Q, et al. Long - term feature banks for detailed video understanding £Û EB/OL £Ý .(2018 - 12 - 12) £Û 2024 - 10 - 27 £Ý .https://arxiv.org/abs/1812.05038.

£Û 29 £Ý ZHOU C, LI X, LOY C C, et al. EdgeSAM: prompt - In - the - loop distillation for on - device deployment of SAM £Û EB/OL £Ý .(2023 - 12 - 11) £Û 2024 - 10 - 21 £Ý .https://arxiv.org/abs/2312.06660.

£Û 30 £Ý DENG J, DONG W, SOCHER R, et al. ImageNet: a large - scale hierarchical image database £Û C £Ý //IEEE. 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE, 2009: 248 - 255.

£Û 31 £Ý WANG P, JIAO B L, YANG L, et al. Vehicle re - identification in aerial imagery: dataset and approach £Û C £Ý //IEEE. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul: IEEE, 2019: 460 - 469.

£Û 32 £Ý XU S Y, WANG J, SHOU W C, et al. Computer vision techniques in construction: a critical review £Û J £Ý . Archives of Computational Methods in Engineering, 2021, 28(5): 3383 - 3397.

£Û 33 £Ý BERNARDIN K, STIEFELHAGEN R. Evaluating multiple object tracking performance: the CLEAR MOT metrics £Û J £Ý . EURASIP Journal on Image and Video Processing, 2008(1): 246309.

Memo

Memo:

-

Common functions

Last Update: 2026-01-20