| 结合PSO的改进压缩跟踪方法 |
| |
| 引用本文： | 刘韶涛,姚灿荣. 结合PSO的改进压缩跟踪方法[J]. 华侨大学学报(自然科学版), 2017, 0(1): 121-126. DOI: 10.11830/ISSN.1000-5013.201701024 |
| |
| 作者姓名： | 刘韶涛 姚灿荣 |
| |
| 作者单位： | 华侨大学 计算机科学与技术学院, 福建 厦门 361021 |
| |
| 摘 要： | 针对基于在线检测的跟踪方法中目标在多尺度空间中的搜索和匹配问题,结合粒子群优化算法(PSO)和压缩感知思想,提出一种鲁棒的多尺度目标跟踪算法.首先,通过粒子群在多尺度空间中采集样本;然后,经过压缩感知提取特征;最后,通过粒子的迭代计算,搜索出当前目标的最佳匹配位置.实验结果表明:提出的算法能较好地适应目标的多尺度变化,在快速性和鲁棒性上具有更好的性能.
|
| 关 键 词： | 目标跟踪 压缩感知 粒子群优化 多尺度 |
Improved Compress Tracking Algorithm Based on PSO |
| |
| LIU Shaotao,YAO Canrong. Improved Compress Tracking Algorithm Based on PSO[J]. Journal of Huaqiao University(Natural Science), 2017, 0(1): 121-126. DOI: 10.11830/ISSN.1000-5013.201701024 |
| |
| Authors: | LIU Shaotao YAO Canrong |
| |
| Affiliation: | College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China |
| |
| Abstract: | For the searching and matching problem in multi-scale space of online detecting tracking method, a robust multi-scale tracking algorithm was proposed based on particle swarm optimization(PSO)and compress sensing. Firstly, feature was sampled with particles in multi-scale space. Then feature was extracted by compress sensing. Finally, targets would be searched quickly and robustly after calculate the best fitness and position of all the particle. The experimental results demonstrate that the proposed algorithm can adapt target in multi-scale change and has a better performance in robustness and rapidity. |
| |
| Keywords: | visual tracking compress sensing particle swarm optimization multi-scale |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《华侨大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《华侨大学学报(自然科学版)》下载全文 |
