journal article·2024-03-28Open access

Time of Flight Distance Sensor–Based Construction Equipment Activity Detection Method

Young-Jun Park, Chang-Yong Yi

Applied Sciences· Volume 14· Issue 7

Abstract

In this study, we delve into a novel approach by employing a sensor-based pattern recognition model to address the automation of construction equipment activity analysis. The model integrates time of flight (ToF) sensors with deep convolutional neural networks (DCNNs) to accurately classify the operational activities of construction equipment, focusing on piston movements. The research utilized a one-twelfth-scale excavator model, processing the displacement ratios of its pistons into a unified dataset for analysis. Methodologically, the study outlines the setup of the sensor modules and their integration with a controller, emphasizing the precision in capturing equipment dynamics. The DCNN model, characterized by its four-layered convolutional blocks, was meticulously tuned within the MATLAB environment, demonstrating the model’s learning capabilities through hyperparameter optimization. An analysis of 2070 samples representing six distinct excavator activities yielded an impressive average precision of 95.51% and a recall of 95.31%, with an overall model accuracy of 95.19%. When compared against other vision-based and accelerometer-based methods, the proposed model showcases enhanced performance and reliability under controlled experimental conditions. This substantiates its potential for practical application in real-world construction scenarios, marking a significant advancement in the field of construction equipment monitoring.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Occupational Health and Safety Research

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Intelligent Construction Automation Center, Kyungpook National University, Daegu 41566, Republic of Korea

Funding

Kyungpook National University Development Project Research Fund

References (35)

Show source-provided references
1. Activity Analysis of Construction Equipment Using Audio Signals and Support Vector Machines10.1016/j.autcon.2017.06.005 ↗
2. A Hierarchical Machine Learning Framework for the Identification of Automated Construction
3. Construction Performance Monitoring via Still Images, Time-Lapse Photos, and Video Streams: Now, Tomorrow, and the Future10.1016/j.aei.2015.01.011 ↗
4. Real-Time Decision Support for Planning Concrete Plant Operations Enabled by Integrating Vehicle Tracking Technology, Simulation, and Optimization Algorithms10.1139/l07-029 ↗
5. Construction Equipment Activity Recognition for Simulation Input Modeling Using Mobile Sensors and Machine Learning Classifiers10.1016/j.aei.2015.03.001 ↗
6. Peurifoy, R.L., Schexnayder, C., Schmitt, R., and Shapira, A. (2018). Construction Planning, Equipment, and Methods, McGraw-Hill Education. [9th ed.].
7. Automated Excavators Activity Recognition and Productivity Analysis from Construction Site Surveillance Videos10.1016/j.autcon.2019.103045 ↗
8. SODA: A Large-Scale Open Site Object Detection Dataset for Deep Learning in Construction10.1016/j.autcon.2022.104499 ↗
9. Development of an Image Data Set of Construction Machines for Deep Learning Object Detection10.1061/(ASCE)CP.1943-5487.0000945 ↗
10. Advanced Sound Classifiers and Performance Analyses for Accurate Audio-Based Construction Project Monitoring10.1061/(ASCE)CP.1943-5487.0000911 ↗
11. Visual–Auditory Learning Network for Construction Equipment Action Detection10.1111/mice.12983 ↗
12. Construction Activity Recognition with Convolutional Recurrent Networks10.1016/j.autcon.2020.103138 ↗
13. Automated Activity Identification for Construction Equipment Using Motion Data from Articulated Members10.3389/fbuil.2019.00144 ↗
14. Activity Recognition of Construction Equipment Using Fractional Random Forest10.1016/j.autcon.2020.103465 ↗
15. Montaser, A., and Moselhi, O. (2012, January 21–23). RFID+ for Tracking Earthmoving Operations. Proceedings of the Construction Research Congress 2012, West Lafayette, IN, USA.10.1061/9780784412329.102 ↗
16. Vision-Based Action Recognition of Earthmoving Equipment Using Spatio-Temporal Features and Support Vector Machine Classifiers10.1016/j.aei.2013.09.001 ↗
17. Automated 2D Detection of Construction Equipment and Workers from Site Video Streams Using Histograms of Oriented Gradients and Colors10.1016/j.autcon.2012.12.002 ↗
18. Vision-Based Method Integrating Deep Learning Detection for Tracking Multiple Construction Machines10.1061/(ASCE)CP.1943-5487.0000957 ↗
19. Action Recognition of Earthmoving Excavators Based on Sequential Pattern Analysis of Visual Features and Operation Cycles10.1016/j.autcon.2019.03.025 ↗
20. Dual Attention-Based Deep Learning for Construction Equipment Activity Recognition Considering Transition Activities and Imbalanced Dataset10.1016/j.autcon.2024.105300 ↗
21. Benefits and Barriers of Construction Project Monitoring Using High-Resolution Automated Cameras10.1061/(ASCE)CO.1943-7862.0000164 ↗
22. Zhang, S., and Zhang, L. (2021, January 2–4). Vision-Based Excavator Activity Analysis and Safety Monitoring System. Proceedings of the 38th International Symposium on Automation and Robotics in Construction, Dubai, United Arab Emirates.10.22260/ISARC2021/0009 ↗
23. A Deep Learning-Based Approach to Enable Action Recognition for Construction Equipment10.1155/2020/8812928 ↗
24. Performance Evaluation of Ultra Wideband Technology for Construction Resource Location Tracking in Harsh Environments10.1016/j.autcon.2011.05.001 ↗
25. Ultrawideband for Automated Real-Time Three-Dimensional Location Sensing for Workforce, Equipment, and Material Positioning and Tracking10.3141/2081-06 ↗
26. Deterioration of UWB Positioning during Construction10.1016/j.autcon.2012.02.009 ↗
27. Estimating Productivity of Earthmoving Operations Using Spatial Technologies 1 This Paper Is One of a Selection of Papers in This Special Issue on Construction Engineering and Management10.1139/l2012-059 ↗
28. Framework for near Real-Time Simulation of Earthmoving Projects Using Location Tracking Technologies10.1016/j.autcon.2014.02.018 ↗
29. Mathur, N., Aria, S.S., Adams, T., Ahn, C.R., and Lee, S. (2015, January 21–23). Automated Cycle Time Measurement and Analysis of Excavator’s Loading Operation Using Smart Phone-Embedded IMU Sensors. Proceedings of the Computing in Civil Engineering 2015, Austin, TX, USA.10.1061/9780784479247.027 ↗
30. An Integrated Data Collection and Analysis Framework for Remote Monitoring and Planning of Construction Operations10.1016/j.aei.2012.04.004 ↗
31. Application of Low-Cost Accelerometers for Measuring the Operational Efficiency of a Construction Equipment Fleet10.1061/(ASCE)CP.1943-5487.0000337 ↗
32. Automatic Identification of Excavator Activities Using Joystick Signals10.1007/s12541-019-00219-5 ↗
33. Times-Series Data Augmentation and Deep Learning for Construction Equipment Activity Recognition10.1016/j.aei.2019.100944 ↗
34. Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.
35. Hybrid Kinematic–Visual Sensing Approach for Activity Recognition of Construction Equipment10.1016/j.jobe.2021.102709 ↗