返回
Automated reliability-based multi-camera strategy for excavator tracking under dynamic occlusion using deep learning with instance segmentation
DOI:10.1016/j.autcon.2025.106589.png)
摘要
En 中文
• 提出了一种基于可靠性的自动化多相机挖掘机跟踪策略。
• 基于遮挡率(OR)和视角率(VPR)开发了可靠性曲面。
• 以加权F1-score为0.904实现了可靠的跟踪区域分类。
• 以多目标跟踪准确率84.41%验证了稳健的实际性能。
• 所提出的方法实现了生产力和碳分析的实时监控。
Keyword:
Excavator tracking
Occlusion
Vision-based monitoring
Deep learning instance segmentation
Tracking reliability
Multi-camera strategy
期刊
IF:
11.5
论文数:
6.3K
被引数:
4.2W
机构
暂无机构信息
引用论文
Shen, G., Zhang, Y., & Li, M. (2024). Construction vehicle tracking based on improved YOLOv7 and DeepSORT. In 2024 4th International Conference on Neural Networks, Information and Communication (NNICE), pp. 1653-1658. IEEE. https://doi.org/10.1109/NNICE61279.2024.10498941.沈, G., 张, Y., & 李, M. (2024). 基于改进YOLOv7和DeepSORT的工程车辆跟踪. 在2024年第4届神经网络、信息与通信国际会议(NNICE), pp. 1653-1658. IEEE. https://doi.org/10.1109/NNICE61279.2024.10498941.
Computer Vision-Based Tracking of Workers in Construction Sites Based on MDNet基于MDNet的计算机视觉工人在建筑工地的跟踪
Adaptive Detector and Tracker on Construction Sites Using Functional Integration and Online Learning
没有更多内容

