欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2020, Vol. 37 ›› Issue (3): 368-378.DOI: 10.7523/j.issn.2095-6134.2020.03.010

• 电子科学 • 上一篇    下一篇

一种在轨海上多运动舰船目标检测和跟踪方法

矫腾章1,2,3, 胡玉新1,2,3, 吕鹏1,2, 张凯1,2, 台宪青1   

  1. 1. 中国科学院电子学研究所, 北京 100190;
    2. 中国科学院空间信息处理与应用系统技术重点实验室, 北京 100190;
    3. 中国科学院大学, 北京 100049
  • 收稿日期:2019-01-16 修回日期:2019-03-22 发布日期:2020-05-15
  • 通讯作者: 吕鹏
  • 基金资助:
    国家重点研发计划(2017YFB0502900)和中国博士后科学基金(2019M650836)资助

A method of multi-ship target detection and tracking by on-orbit satellite

JIAO Tengzhang1,2,3, HU Yuxin1,2,3, Lü Peng1,2, ZHANG Kai1,2, TAI Xianqing1   

  1. 1. Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
    2. Key Laboratory of Spatial Information Processing and Application System Technology of Chinese Academy of Sciences, Beijing 100190, China;
    3. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2019-01-16 Revised:2019-03-22 Published:2020-05-15

摘要: 传统遥感卫星图像处理采用在地面进行目标检测和跟踪处理的模式,卫星将拍摄到的图像数据下传至地面数据处理中心,由地面数据处理系统对接收到的遥感图像数据进行目标检测和跟踪。然而,随着遥感图像分辨率的不断提高,需要下传的数据量增大,导致星地数据传输的时间大大增加,最终造成目标检测和跟踪的时效性降低。针对上述问题,提出一种基于多特征量判别的Canny边缘检测和联合概率数据关联的在轨海上多运动舰船目标检测和跟踪方法。将该方法利用中国科学院微小卫星创新研究院的高分微纳卫星实测数据在模拟星载的嵌入式开发平台上进行验证,结果表明该方法能够在轨对海上多运动舰船目标进行快速、准确的检测和跟踪。

关键词: 光学遥感图像, 星上数据处理, 舰船检测, 多目标跟踪

Abstract: The traditional method of remote sensing satellite image processing utilizes target detection and target tracking on the ground. The satellite transmits the image data to the data processing center on the ground, and the ground data processing system implements target detection and tracking based on the received remote sensing image data. However, with the spatial resolution increase of remote sensing images, the amount of data needed to be transmitted increases greatly. This results in a significant increase in ground-to-satellite data transmission time. Ultimately the efficiency of target detection and tracking reduces. In order to solve the problem, we propose a method based on the multi-feature Canny edge detection algorithm and the joint probability data association algorithm for moving multi-ship detection and tracking by on-orbit satellite. The proposed method is validated by using real data of an optical remote sensing satellite on satellite-based embedded development platform. The results show that the proposed method detects and tracks the multiple ships quickly and accurately.

Key words: optical remote sensing image, data processing on satellite, ship detection, multi-target tracking

中图分类号: