周治国^1,,,
荆朝¹,
王秋伶¹,
屈崇^{1, 2}
1.北京理工大学信息与电子学院 北京 100081
2.中国船舶重工集团公司第七一一研究所 上海 201108

详细信息

作者简介:周治国：男，1977年生，副教授，研究方向为海上目标探测、识别理论及方法
荆朝：男，1995年生，硕士生，研究方向为智能无人航行器信息感知与导航
王秋伶：女，1994年生，硕士生，研究方向为智能无人航行器信息感知与导航
屈崇：男，1980年生，高级工程师，研究方向为智能船舶

通讯作者:周治国　zhiguozhou@bit.edu.cn

中图分类号:TN911.73; TP391.4

计量

文章访问数:590
HTML全文浏览量:196
PDF下载量:136
被引次数:0

出版历程

收稿日期:2020-03-31
修回日期:2020-09-29
网络出版日期:2020-09-30
刊出日期:2021-06-18

Object Detection and Tracking of Unmanned Surface Vehicles Based on Spatial-temporal Information Fusion

Zhiguo ZHOU^1,,,
Zhao JING¹,
Qiuling WANG¹,
Chong QU^{1, 2}
1. School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China
2. Shanghai Marine Diesel Engine Research Institute, China State Shipbuilding Corporation Limited, Shanghai 201108, China


摘要
摘要:在无人艇(USV)的导航、避障等多种任务中，目标检测与跟踪都十分重要，但水面环境复杂，存在目标尺度变化、遮挡、光照变化以及摄像头抖动等诸多问题。该文提出基于时空信息融合的无人艇水面视觉目标检测跟踪，在空间上利用深度学习检测，提取单帧深度语义特征，在时间上利用相关滤波跟踪，计算帧间方向梯度特征相关性，通过特征对比将时空信息进行融合，实现了持续稳定地对水面目标进行检测与跟踪，兼顾了实时性和鲁棒性。实验结果表明，该算法平均检测速度和精度相对较高，在检测跟踪速度为15 fps情况下，检测跟踪精确度为0.83。
关键词:无人艇/
水面目标/
检测跟踪/
时空信息融合
Abstract:Object detection and tracking is essential in the navigation, obstacle avoidance and other tasks of Unmanned Surface Vehicles (USV). However, the environment on the water is complex, and there are many problems such as object scale variation, occlusion, illumination variation and camera shaking, etc. This paper proposes the visual object detection and tracking of USV based on spatial-temporal information fusion. Deep learning detection in space is used to extract single-frame depth semantic features and correlation filter tracking in time is used to calculate the correlation of oriented gradient feature between frames. Temporal and spatial information through feature comparison are combined to achieve continuous and stable object detection and tracking with strong robustness at real-time. The experiments results demonstrate that the average detection and tracking accuracy is 0.83 with the average running speed of 15 fps, which illustrates the accuracy is improved and the speed is high.
Key words:Unmanned Surface Vehicle (USV)/
Surface vehicle object/
Detection and tracking/
Spatial-temporal information Fusion



PDF全文下载地址:

https://jeit.ac.cn/article/exportPdf?id=c6fad202-1ef0-4a16-8692-755e40e1f696