期刊文献+

一种改进的多通道特征视觉跟踪算法 被引量:3

An improved multi-channel feature visual tracking algorithm
下载PDF
导出
摘要 为了解决核相关滤波视觉跟踪算法(KCF)因背景干扰和多峰响应导致出现跟踪失败的问题,提出一种多通道融合特征视觉跟踪算法。将目标的颜色通道(CN)特征和方向梯度直方图(HOG)特征融合为新特征,结合主成分分析(PCA)法,保证了与原始的KCF特征对齐。为了解决出现多峰响应干扰的问题,提出一种全新的多峰检测的方法,避免模型跟踪出现漂移。根据OTB50实验的结果,相比其他算法,本文算法具备更好的准确性和鲁棒性,能够提高目标跟踪算法的性能。 In order to solve the problem of tracking failure caused by background interference and multi-peak response of kernel correlation filtering(KCF)visual tracking algorithm,a multi-channel fusion feature visual tracking algorithm is proposed.The algorithm fuses the color channel feature(CN)and the direction gradient histogram(HOG)feature of the target into new features,and combines the principal component analysis(PCA)method to ensure alignment with the original KCF features.In order to solve the problem of multi-peak response interference,a new multi-peak detection method is proposed to avoid drift of model tracking.According to the results of the OTB50 experiment,the proposed algorithm has better accuracy and robustness than other algorithms,and can improve the performance of the target tracking algorithm.
作者 陈建伟 贺继林 CHEN Jianwei;HE Jilin(State Key Laboratory of High Performance Complex Manufacturing,Central South University,Changsha 410006,China;Sunward Intelligent Equipment Co Ltd,Changsha 410100,China)
出处 《传感器与微系统》 CSCD 2020年第3期120-123,共4页 Transducer and Microsystem Technologies
基金 湖南省科技计划项目(2016GK2032) 湖南省战略性新兴产业科技攻关项目(2016GK4007)。
关键词 核相关滤波 多特征融合 主成分分析法 多峰检测 视觉跟踪 kernel correlation filtering(KCF) multi-feature fusion principal component analysis(PCA) multi-peak detection visual tracking
  • 相关文献

参考文献2

二级参考文献20

  • 1王向军,王研,李智.基于特征角点的目标跟踪和快速识别算法研究[J].光学学报,2007,27(2):360-364. 被引量:48
  • 2Paragios N,Deriche R.Geodesic active contours and level sets for the detection and tracking of moving objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(3):266-280.
  • 3Hu W,Zhou X,Li W,et al.Active contour-based visual tracking by integrating colors,shapes,and motions[J].IEEE Transactions on Image Processing,2013,22(5):1778-1792.
  • 4Ababsa F,Mallem M.Robust camera pose estimation combining2D/3D points and lines tracking[C]∥2008 IEEE International Symposium on Industrial Electronics(ISIE),IEEE,2008:774-779.
  • 5Yussiff A L,Yong S P,Baharudin B B.Parallel Kalman filterbased multi-human tracking in surveillance video[C]∥2014 International Conference on Computer and Information Sciences(ICOCINS),IEEE,2014:1-6.
  • 6Yang T,Pan Q,Li J,et al.Real-time multiple objects tracking with occlusion handling in dynamic scenes[C]∥2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR),IEEE,2005:970-975.
  • 7Nummiaro K,Koller-Meier E,Van Gool L.An adaptive colorbased particle filter[J].Image and Vision Computing,2003,21(1):99-110.
  • 8Ross A A,Govindarajan R.Feature level fusion of hand and face biometrics[C]∥Int’l Conf on Defense and Security,International Society for Optics and Photonics,2005:196-204.
  • 9Teutsch M,Kruger W,Beyerer J.Fusion of region and point-feature detections for measurement reconstruction in multi-target Kalman tracking[C]∥2011 Proceedings of the 14th International Conference on Information Fusion,IEEE,2011:1-8.
  • 10孙凯,刘士荣.多目标跟踪的改进Camshift/卡尔曼滤波组合算法[J].信息与控制,2009,38(1):9-14. 被引量:38

共引文献15

同被引文献22

引证文献3

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部