一种可靠的无人驾驶飞行器多舰追踪方法
Guoqing Zhang1, Jiandong Liu1, Yongxiang Zhao1
1North China Institute of Aerospace Engineering, Langfang, China.
PloS one
|January 10, 2025
概括
这项研究使用改进的AI算法增强了对无人机的船舶检测和跟踪. 该系统提高了监控海上交通的准确性,这对全球物流至关重要.
科学领域:
- 人工智能的人工智能
- 计算机视觉 计算机视觉
- 海上物流的海上物流
背景情况:
- 水路运输对全球物流至关重要,需要准确的船舶检测和跟踪.
- 无人驾驶飞行器 (UAV) 提供了增强监控的潜力,但面临着数据限制和检测准确性的挑战.
- 现有的多对象跟踪系统需要改进,以适用于现实世界的海上监控应用.
研究的目的:
- 开发一个先进的多对象跟踪系统,用于基于无人机的船舶检测和跟踪.
- 使用增强的YOLOv7.7来提高船舶检测的准确性和稳定性.
- 为了完善海上场景的深度SORT算法的跟踪性能.
主要方法:
- 使用YOLOv7进行对象检测,使用Deep SORT进行多对象跟踪.
- 员工转移学习以解决YOLOv7培训的有限船舶数据.
- 在YOLOv7中集成SimAM注意力机制和部分卷积 (PConv) 模块,以改善特征提取.
- 在深度SORT中用DIOU度量取代 IOU,以减少跟踪匹配期间的虚假负数.
主要成果:
- 增强的YOLOv7模型与SimAM和PConv展示了卓越的特征表示和检测能力.
- 经过修改的深度SORT算法与DIOU度量改善了轨道匹配,减少了错过的检测.
- 与基线YOLOv7+Deep SORT.相比,集成系统实现了多对象跟踪精度 (MOTA) 的6.9%提高至65.3%,多对象跟踪精度 (MOTP) 的3.0%提高至81.9%,比基线YOLOv7+Deep SORT.
- 该系统在船舶监控方面表现出强的性能,显著优于原始模型.
结论:
- 开发的AI系统为基于无人机的船舶检测和跟踪提供了重大进步.
- 整合SimAM,PConv和DIOU指标为海上监控提供了更准确,更有效的解决方案.
- 这项研究为提高自主系统在关键物流和安全应用中的能力提供了宝贵的参考.
更多相关视频
相关概念视频
01:30Types of Global Positioning System Surveys
49
GPS surveying methods vary in application, accuracy, and data collection techniques, catering to diverse surveying and mapping needs. Static GPS, kinematic GPS, and real-time kinematic (RTK) surveying are widely used. Each technique offers distinct advantages.Static GPS involves placing one receiver at a known reference point and another at the target point. It collects exact positional data by observing multiple satellite ranges over an extended period, achieving centimeter-level accuracy for...
49
01:26Errors in Global Positioning System
36
Global Positioning System (GPS) technology has revolutionized navigation and positioning, but its accuracy is often compromised by various errors. These errors, stemming from environmental, satellite, and receiver-related factors, require careful mitigation to ensure reliable performance across applications.Atmospheric ErrorsGPS signals travel through the Earth’s ionosphere and troposphere, introducing delays which affect accuracy. The ionosphere is strongly influenced by charged particles,...
36