Space multi-target detection by second variance | |
Huang T(黄涛); Li ZL(李祝莲); Zhou Y(周钰); Li YQ(李语强); Xiong YH(熊耀恒); Huang T(黄涛); Li ZL(李祝莲); Li YQ(李语强); Xiong YH(熊耀恒); Zhou Y(周钰) | |
2013 | |
会议名称 | 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer, MEC 2013 |
会议日期 | 2013-12-20 |
会议地点 | Shenyang, China |
页码 | 1506-1511 |
英文摘要 | Detecting small multi-target in aerospace is both a significant and difficult issue for the satellite tracking system. It is fundamentally challenging due to the existence of strong noise in captured images, the few characteristic of spot-like target, the simultaneous multiple targets and the real-time requirement. To address these challenges, we formulate space multi-target as a two-step detection problem, which integrates the variance vector detection and 2th variance detection. The pixels of images are projected to the variance subspace of two-dimension. In the first step, the candidate targets are extracted with the optimal threshold achieved by K-means and proposed Weighted Maximum Right Probability, namely WMRP. In the second step, the true targets are checked out by adopting the proposed 2th variance feature and multiscale threshold. Experiments demonstrate the proposed two-step framework can efficiently and rapidly detect the small multiple targets, which can satisfy the common application of space multi-target tracking. |
收录类别 | EI |
产权排序 | 第一完成单位 |
会议录 | Proceedings - 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer, MEC 2013 |
会议录出版者 | Institute of Electrical and Electronics Engineers Inc. |
学科主题 | 天文学 |
语种 | 英语 |
ISBN号 | 9781479925650 |
内容类型 | 会议论文 |
源URL | [http://ir.ynao.ac.cn/handle/114a53/7335] |
专题 | 云南天文台_应用天文研究组 |
通讯作者 | Huang T(黄涛) |
推荐引用方式 GB/T 7714 | Huang T,Li ZL,Zhou Y,et al. Space multi-target detection by second variance[C]. 见:2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer, MEC 2013. Shenyang, China. 2013-12-20. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论