In-vehicle vision-based automatic identification of bulldozer operation cycles with temporal action detection DOI
Cheng Zhou, Yuxiang Wang,

Ke You

et al.

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102899 - 102899

Published: Oct. 1, 2024

Language: Английский

3D keypoint detection-based automated rebar spacing inspection: Application for robotic integration DOI

Lu Deng,

Songyue Wang, Jingjing Guo

et al.

Advanced Engineering Informatics, Journal Year: 2025, Volume and Issue: 66, P. 103418 - 103418

Published: May 7, 2025

Language: Английский

Citations

0
A novel data fusion based intelligent identification approach for working cycle stages of hydraulic excavators DOI
Haoju Song,

Guiqin Li,

Xin Xiong

et al.

ISA Transactions, Journal Year: 2024, Volume and Issue: 148, P. 78 - 91

Published: March 6, 2024

Language: Английский

Citations

3
Data-driven AI algorithms for construction machinery DOI
Ke Liang,

Jiahao Zhao,

Zhiqing Zhang

et al.

Automation in Construction, Journal Year: 2024, Volume and Issue: 167, P. 105648 - 105648

Published: Aug. 25, 2024

Language: Английский

Citations

3
Construction digital twin: a taxonomy and analysis of the application-technology-data triad DOI

Wahib Saif,

SeyedReza RazaviAlavi,

Mohamad Kassem

et al.

Automation in Construction, Journal Year: 2024, Volume and Issue: 167, P. 105715 - 105715

Published: Aug. 30, 2024

Language: Английский

Citations

3
Classification and Application of Deep Learning in Construction Engineering and Management – A Systematic Literature Review and Future Innovations DOI Creative Commons

Qingze Li,

Yang Yang, Gang Yao

et al.

Case Studies in Construction Materials, Journal Year: 2024, Volume and Issue: unknown, P. e04051 - e04051

Published: Nov. 1, 2024

Language: Английский

Citations

3
A vision-based approach for detecting occluded objects in construction sites DOI
Qian Wang, Hongbin Liu, Wei Peng

et al.

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: 36(18), P. 10825 - 10837

Published: March 28, 2024

Language: Английский

Citations

2
Computer vision-based excavator bucket fill estimation using depth map and faster R-CNN DOI Creative Commons
Bobo Helian, Xiaoqian Huang, Meng Yang

et al.

Automation in Construction, Journal Year: 2024, Volume and Issue: 166, P. 105592 - 105592

Published: July 4, 2024

Excavators are crucial in the construction industry, and developing autonomous excavator systems is vital for enhancing productivity reducing reliance on manual labor. Accurate estimation of volume bucket fill key monitoring evaluating system automation performance. This paper presents use 2D depth maps as input to a Faster Region Convolutional Neural Network (Faster R-CNN) deep learning model estimation. structure enables high accuracy while maintaining fast processing speed. An operation test bench was established, datasets used study were self-generated training. A loss function proposed, combining Cross Entropy with Root Mean Squared Error improve generalization precision. Comparative results indicate that proposed approach achieves 96.91% factor predicts real-time at about 10 fps, highlighting its potential practical automated operations.

Language: Английский

Citations

2
A systematic review and evaluation of synthetic simulated data generation strategies for deep learning applications in construction DOI
Li-Qun Xu, Hexu Liu, Bo Xiao

et al.

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102699 - 102699

Published: July 11, 2024

Language: Английский

Citations

2
Semantic segmentation-based framework for concrete pouring progress monitoring by using multiple surveillance cameras DOI Creative Commons
Bin Yang, Biaoli Gao, Yilong Han

et al.

Developments in the Built Environment, Journal Year: 2023, Volume and Issue: 16, P. 100283 - 100283

Published: Nov. 23, 2023

Traditional construction progress monitoring methods face challenges in real-time of concrete pouring due to performance limitations and issues with registration occlusion. This study proposes a framework based on multi-camera semantic fusion for the pouring. The site images are first segmented into probabilities by deep neural network. Dempster-Shafer evidence theory is then applied fusion, providing comprehensive depiction progress. To reduce errors Building Information Model (BIM), perspective transformation algorithm proposed compensate slight camera movements. Finally, inference method fully-connected Conditional Random Fields (CRFs) employed address occlusion leveraging context BIM floor plan. Comparative analysis confirmed these modules' performance, remarkable reduction relative error from 9.60% 0.26%, enabling great potential continuous

Language: Английский

Citations

5
Generating realistic training images from synthetic data for excavator pose estimation DOI
Hieu T.T.L. Pham, SangUk Han

Automation in Construction, Journal Year: 2024, Volume and Issue: 167, P. 105718 - 105718

Published: Aug. 23, 2024

Language: Английский

Citations

1