Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Multi-Worker Tracking Algorithm Based on Combined Feature Clustering
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.
Multi-Worker Tracking Algorithm Based on Combined Feature Clustering
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.
Multi-Worker Tracking Algorithm Based on Combined Feature Clustering
Zhou, Ying (Autor:in) / Lin, Xiao (Autor:in) / Luo, Zhubang (Autor:in) / Guo, Hongling (Autor:in)
International Conference on Construction and Real Estate Management 2022 ; 2022 ; Virtual Conference
ICCREM 2022 ; 276-283
15.12.2022
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
GPS tracking comes to the aid of track worker
| IuD Bahn | 2012
| British Library Online Contents | 2018
| British Library Online Contents | 2018
WORKER DETECTION DEVICE, WORKER DETECTION METHOD, AND WORKER DETECTION PROGRAM
| Europäisches Patentamt | 2020