Multi-Worker Tracking Algorithm Based on Combined Feature Clustering
Publication: ICCREM 2022
ABSTRACT
The tracking of workers on construction sites is essential for safety management and resource management. However, existing vision-based worker tracking algorithms perform poorly in multi-target tracking and occlusion scenarios. A multi-worker tracking algorithm based on combined feature clustering is proposed in this study to fill the gap. Combined features are first extracted from construction scenarios to represent the targets—workers; then, feature screening and clustering are conducted to track worker targets. The algorithm is tested in a simulated scenario; the experiment result shows that the algorithm can detect and identify workers within 50 ms, with a tracking accuracy of 90.8%, thus being acceptable for construction management.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Brilakis, I., Park, M.-W., and Jog, G. (2011). “Automated Vision Tracking of Project Related Entities.” Advanced Engineering Informatics, 25, 713–724.
Cao, Z., Simon, T., Wei, S. E., and Sheikh, Y. (2017). “Realtime multi-person 2d pose estimation using part affinity fields.” The IEEE Conference on Computer Vision and Pattern Recognition, 7291–7299.
Fang, Q., Li, H., Luo, X., Ding, L., Rose, T. M., An, W., and Yu, Y. (2018). “A deep learning-based method for detecting non-certified work on construction sites.” Advanced Engineering Informatics, 35, 56–68.
Hachaj, T., and Ogiela, M. R. (2014). “Rule-based approach to recognizing human body poses and gestures in real time.” Multimedia Systems, 20(1), 81–99.
Kim, K., and Cho, Y. (2020). “Automatic recognition of workers’ motions in highway construction by using motion sensors and long short-term memory (LSTM) networks.” Journal of Construction Engineering and Management, 147(3), 04020184.
Lee, Y.-J., and Park, M.-W. (2019). “3D tracking of multiple onsite workers based on stereo vision.” Automation in Construction, 98, 146–159.
Park, M. W., and Brilakis, I. (2012a). “Enhancement of construction equipment detection in video frames by combining with tracking.” International Conference on Computing in Civil Engineering, Florida, US, 421–428.
Park, M.-W., and Brilakis, I. (2012b). “Construction worker detection in video frames for initializing vision trackers.” Automation in Construction, 28, 15–25.
Ren, S., He, K., Girshick, R., and Sun, J. (2016). “Faster R-CNN: Towards real-time object detection with region proposal networks.” Advances in Neural Information Processing Systems, 39(6), 1137–1149.
Xiao, B., and Kang, S.-C. (2021). “Vision-Based method integrating deep learning detection for tracking multiple construction machines.” Journal of Computing in Civil Engineering, 35(2), 04020071.
Zhu, Z., Ren, X., and Chen, Z. (2017). “Integrated detection and tracking of workforce and equipment from construction jobsite videos.” Automation in Construction, 81, 161–171.
Information & Authors
Information
Published In
ICCREM 2022
Pages: 276 - 283
History
Published online: Dec 15, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.