摘要
In visual tracking, how to select a suitable motion model is an important problem to deal with, since the movements in real world are always irregular in most cases. We propose a self-tuning motion model for target tracking in this paper, where the current motion model is computed according to the relative distance of the target positions in the last two frames. Our method has achieved excellent performance when experimenting on the sequences where the targets move unstably, abruptly or even when partial occlusion exists, and the method is particularly robust to the unsuitable initial motion model.
| 源语言 | 英语 |
|---|---|
| 主期刊名 | Cognitive Systems and Signal Processing - 3rd International Conference, ICCSIP 2016, Revised Selected Papers |
| 编辑 | Fuchun Sun, Huaping Liu, Dewen Hu |
| 出版商 | Springer Verlag |
| 页 | 74-81 |
| 页数 | 8 |
| ISBN（印刷版） | 9789811052293 |
| DOI | |
| 出版状态 | 已出版 - 2017 |
| 活动 | 3rd International Conference on Cognitive Systems and Information Processing, ICCSIP 2016 - Beijing, 中国 期限: 19 11月 2016 → 23 11月 2016 |
出版系列
| 姓名 | Communications in Computer and Information Science |
|---|---|
| 卷 | 710 |
| ISSN（印刷版） | 1865-0929 |
会议
| 会议 | 3rd International Conference on Cognitive Systems and Information Processing, ICCSIP 2016 |
|---|---|
| 国家/地区 | 中国 |
| 市 | Beijing |
| 时期 | 19/11/16 → 23/11/16 |
指纹
探究 'Self-tuning motion model for visual tracking' 的科研主题。它们共同构成独一无二的指纹。引用此
Tan, H., Zhao, Q., & Wang, X. (2017). Self-tuning motion model for visual tracking. 在 F. Sun, H. Liu, & D. Hu (编辑), Cognitive Systems and Signal Processing - 3rd International Conference, ICCSIP 2016, Revised Selected Papers (页码 74-81). (Communications in Computer and Information Science; 卷 710). Springer Verlag. https://doi.org/10.1007/978-981-10-5230-9_8