首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于多特征融合的显著性跟踪算法
引用本文:杨阳,周海英.基于多特征融合的显著性跟踪算法[J].科学技术与工程,2017,17(26).
作者姓名:杨阳  周海英
作者单位:中北大学计算机与控制工程学院 山西太原 030051,中北大学计算机与控制工程学院 山西太原 030051
基金项目:山西省自然科学基金项目(2013011017-6)资助
摘    要:针对在线视觉跟踪中的高效特征提取以及模型漂移的问题,提出了一种基于显著性检测的核相关滤波器(KCF)跟踪算法。将颜色特征(CN)和方向梯度直方图(HOG)进行加权融合;并自适应地调节每种特征的权重。对于模型漂移问题,受生物视觉机制的启发,通过视觉显著性算法获得目标的显著区域;并在该区域内进行采样,实现了全局范围搜索,避免陷入局部极大值。此外,引入了一种基于关键点的模型来解决目标尺度固定的问题。为验证提出算法的有效性,在50个视频序列上与近年来的5种优秀算法进行了对比。实验结果表明,与以往算法相比,该算法在成功率和中心位置误差上都取得较好的效果;而且能有效地缓解目标模型漂移问题。

关 键 词:目标跟踪  核相关滤波器  多特征融合  变尺度  显著性检测
收稿时间:2017/2/22 0:00:00
修稿时间:2017/4/25 0:00:00

Saliency Tracking Algorithm Based on FusingMultiple Features
Yang Yang and Zhou Hai-ying.Saliency Tracking Algorithm Based on FusingMultiple Features[J].Science Technology and Engineering,2017,17(26).
Authors:Yang Yang and Zhou Hai-ying
Institution:North University of China,North University of China
Abstract:Aiming at the problems of high efficient feature extracting and dealing with the model drift, a kernel correlation filter tracking algorithm based on saliency detection is proposed. The color feature and the histogram of oriented gradient are weightedly merged,and features weights can be adjusted adaptively. For dealing with the model drift, and inspired by biological vision mechanism , target salient region is obtained by sampling in the region through the visual saliency algorithm. In that way, the sampling in the area is carried out to complete the global scope search which avoids local maximum. In addition, a model based on the key points is introduced to dealing with the problem that the target scale is changed. In order to verify the proposed algorithm effectiveness, it is compared with 5 kinds of excellent algorithms in recent years on 50 video sequences. Experimental results show that, the proposed algorithm can obtain better results in the success rate and the center position error, and what is more, the algorithm can effectively alleviate target model drift.
Keywords:target  tracking  kernel  correlation filter  multiple features  integration  scale  adaptive  saliency  detection
本文献已被 CNKI 等数据库收录!
点击此处可从《科学技术与工程》浏览原始摘要信息
点击此处可从《科学技术与工程》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号