首页|期刊简介|投稿指南|分类索引|刊文选读|订阅指南|资料|样刊邮寄查询|常见问题解答|联系我们
申 远,杨文柱,周 杨. 一种尺度自适应的长时目标追踪算法[J]. 科学技术与工程, 2020, 20(23): 9478-9483.
SHEN Yuan,ZHOU Yang.A Scale Self-adaptive Long-term Target Tracking Algorithm[J].Science Technology and Engineering,2020,20(23):9478-9483.
一种尺度自适应的长时目标追踪算法
A Scale Self-adaptive Long-term Target Tracking Algorithm
投稿时间:2019-08-27  修订日期:2020-05-03
DOI:
中文关键词:  长时追踪  核相关滤波  尺度自适应  重新检测  模板更新
英文关键词:long-term tracking  kernelized correlation filter  scale self-adapted  re-detection  template update
基金项目:河北省自然科学基金
        
作者单位
申 远 河北大学
杨文柱 河北大学
周 杨 河北大学
摘要点击次数: 112
全文下载次数: 46
中文摘要:
      在长时追踪中,传统的核相关滤波算法受到目标尺度变化和环境因素的影响,追踪效果会有所下降。为解决这一问题提出了一种尺度自适应的长时目标追踪算法。首先,为了实现追踪过程中追踪器尺度的自适应,在核相关滤波算法中加入尺度因子池,通过不同尺度下候选目标的响应值判断目标的最佳尺度;其次,为了提高追踪的准确度,通过扩大候选目标的搜索范围,对追踪不准确的目标位置进行重新检测;最后为了提高跟踪效率,根据追踪的稳定性决定是否对追踪模板进行更新,提高追踪速度,减少过多错误信息的学入。实验结果表明,所提算法相较于其它追踪算法在精确度上提高了15.3%,在成功率上提高了17.1%。
英文摘要:
      In long-term tracking, the tracking accuracy of traditional kernelized correlation filter algorithm will be reduced because the scale changes of targets and environmental factors. To solve this problem, a scale self-adaptive KCF algorithm for long term object tracking was proposed. Firstly, in order to achieve the scale self-adaption in the tracking process, a scale factor pool was added to the kernel correlation filter algorithm, and the optimal scale of the target was judged by the response value of the candidate target at different scales. Secondly, in order to improve the accuracy of the tracking, we expanded the search area of the candidate targets and re-detected inaccurate target positions. Finally, in order to improve the tracking efficiency, the tracking template was updated according to the stability of the tracking. By this way, the tracking speed is improved, and the learning time of excessive error information is reduced. The results indicate that, compared with other classical tracking algorithms, the proposed algorithm improves the tracking accuracy by 15.3% and tracking success by 17.1%.
查看全文  查看/发表评论  下载PDF阅读器
关闭
你是第32690654位访问者
版权所有:科学技术与工程编辑部
主管:中国科学技术协会    主办:中国技术经济学会
Tel:(010)62118920 E-mail:stae@vip.163.com
京ICP备05035734号-4
技术支持:本系统由北京勤云科技发展有限公司设计

京公网安备 11010802029091号