像素点特征加权的尺度自适应跟踪算法

doi:10.11959/j.issn.1000-436x.2015259

通信学报 ›› 2015, Vol. 36 ›› Issue (10): 200-210.doi: 10.11959/j.issn.1000-436x.2015259

像素点特征加权的尺度自适应跟踪算法

罗会兰¹,杜芳芳¹,孔繁胜²

¹ 江西理工大学信息工程学院，江西赣州 341000
² 浙江大学计算机科学技术学院，浙江杭州 310027

出版日期:2015-10-25 发布日期:2015-10-27
基金资助:
国家自然科学基金资助项目;国家自然科学基金资助项目;江西省教育厅科技基金资助项目

Pixel feature-weighted scale-adaptive object tracking algorithm

Hui-lan LUO¹,Fang-fang DU¹,Fan-sheng KONG²

¹ School of Information Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China
² School of Computer Science and Technology,Zhejiang University,Hangzhou 310027,China

Online:2015-10-25 Published:2015-10-27
Supported by:
The National Natural Science Foundation of China;The National Natural Science Foundation of China;The Science and Technology Foun-dation of Education Department of Jiangxi Province

摘要/Abstract

摘要：

针对目标运动过程中的姿态变化、旋转、干扰以及缩放等情况，提出了结合像素点特征加权的尺度自适应跟踪算法。首先利用目标区域中每个像素点的颜色特征和位置特征，建立目标模型；其次用目标的平均权值图估算尺度变化系数，以实现目标尺度的自适应；最后构建一个更新模型，对跟踪过程中的目标模型和背景模型进行更新。实验表明，提出的算法充分利用目标区域内各像素点间的差异，可以做到快速、有效的跟踪，且具有较强的顽健性。

关键词: 目标跟踪, 尺度自适应, 更新模型, 像素点特征加权

Abstract:

An effective object tracking method using weighted pixel features was proposed to deal with all kinds of complicated tracking situations,such as target movement,rotation,background interference and scaling and so on.First,the color feature and location information of the pixels in the target area were used to build the object model.Then the average weight image was used to estimate the scale variation coefficient.The aim was to adapt to the scale changes of the target.Finally,an update model was proposed,which was able to renew the object model and background model.The experimental results show that the proposed algorithm could make full use of the differences between pixels in the target area,so it can track more quickly and more effectively with strong robustness.

Key words: object tracking, scale-adaptive, model updating, pixel weighted-feature

罗会兰,杜芳芳,孔繁胜. 像素点特征加权的尺度自适应跟踪算法[J]. 通信学报, 2015, 36(10): 200-210.

Hui-lan LUO,Fang-fang DU,Fan-sheng KONG. Pixel feature-weighted scale-adaptive object tracking algorithm[J]. Journal on Communications, 2015, 36(10): 200-210.

图/表 6

图1

图2

表1

图3

表2

表3

参考文献 16

[1]	ZHANG K , SONG H . Real-time visual tracking via online weighted multiple instance learning[J]. Pattern Recognition, 2013,46(1): 397-411.
[2]	ZHANG K , ZHANG L , YANG M H . Real-time compressive tracking[A]. Computer Vision–ECCV 2012[C]. Springer Berlin Heidelberg, 2012. 864-877.
[3]	ZHANG K , ZHANG L , YANG M H . Real-time object tracking via online discriminative feature selection[J]. IEEE Transactions on Image Processing, 2013,22: 4664-4677.
[4]	COMANICIU D , RAMESH V , MEER P . Real-time tracking of non-rigid objects using mean shift[A]. Proc of IEEE Conference on Computer Vision and Pattern Recognition[C]. 2000. 142-149.
[5]	COMANICIU D , RAMESH V , MEER P . Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,25(5): 564-577.
[6]	NING J , ZHANG L , ZHANG D ,et al. Robust mean-shift tracking with corrected background-weighted histogram[J]. IET Computer Vision, 2012,6(1): 62-69.
[7]	NING J , ZHANG L , ZHANG D ,et al. Scale and orientation adaptive mean shift tracking[J]. Computer Vision,IET, 2012,6(1): 52-61.
[8]	ZHANG K , ZHANG L , YANG M H ,et al. Fast tracking via spatio-temporal context learning[J]. arXiv preprint arXiv:1311.1939, 2013.
[9]	赵凌, 冯镔, 邱锦波 . 基于自适应分块外观模型的视觉跟踪[J]. 通信学报, 2011,32(10): 166-173. ZHAO L , FENG B , QIU J B . Fragment-based visual tracking with adaptive appearance model[J]. Journal on Communications, 2011,32(10): 166-173.
[10]	罩光成, 尹浩, 陈强 ,等. 面向价值的战场信息处理与分发优化算法[J]. 通信学报, 2011,32(3): 60-68. QIN G C , YIN H , CHEN Q ,et al. Value-oriented optimal algorithm for battlefield information processing and disseminating[J]. Journal on Communications, 2011,32(3): 60-68.
[11]	CEHOVIN L , KRISTAN M , LEONARDIS A . An adaptive coupled-layer visual model for robust visual tracking[A]. Computer Vision(ICCV),2011 International Conference on[C]. 2011. 1363-1370.
[12]	SANTNEr J , LEISTNER C , SAFFARI A ,et al. Prost:parallel robust online simple tracking[A]. 2010 IEEE Conference on Computer Vision and Pattern Recognition(CVPR)[C]. 2010. 723-730.
[13]	KWON J , LEE K M . Visual tracking decomposition[A]. 2010 IEEE Conference on Computer Vision and Pattern Recognition(CVPR)[C]. 2010. 1269-1276.
[14]	KALAL Z , MIKOLAJCZYK K , MATAS J . Tracking learning detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(7): 1409-1422.
[15]	WANG S , LU H , YANG F ,et al. Superpixel tracking[A]. 2011 IEEE International Conference on Computer Vision(ICCV)[C]. 2011. 1323-1330.
[16]	GODEC M , ROTH P M , BISCHOF H . Hough-based tracking of non-rigid objects[J]. Computer Vision and Image Understanding, 2013,117(10): 1245-1256.

算法	torus	lemming	skating2
SOAMST	1 265.5	2 645.6	6 942.4
FTSTC	795.37	3 394.8	213 451
SAOTPFW	340.2	1 753.9	2 803.6

算法	torus	lemming	skating2	panda	bird2	skiing
Mean-shift	36.241 2	5.467 6	25.109 5	64.902 8	131.793 4	233.907 1
CBWH	3.402 9	3.332 6	14.138 0	4.504 0	6.223 4	8.724 2
CT	49.418 9	5.379 2	74.584 7	7.160 9	22.099 7	259.105 1
ODFS	36.658 4	28.030 5	55.446 3	5.057 5	15.208 6	223.992 7
SOAMST	14.112 1	5.406 8	25.689 9	63.401 6	24.766 9	265.284 3
FTSTC	59.638 0	27.978 6	197.911 3	16.521 3	20.376 3	282.115 7
SAOTPFW	3.676 3	3.027 5	13.995 7	2.925 2	5.747 6	8.367 2

算法	torus	lemming	skating2	panda	bird2	skiing
Mean-shift	8.172 5	30.128 8	39.034 7	10.535 4	4.573 3	2.660 1
CBWH	8.403 5	28.865 7	37.009 7	10.606 8	4.744 6	2.788 1
CT	13.989 0	40.770 5	44.603 2	25.645 8	7.146 9	5.429 2
ODFS	16.834 7	46.863 5	55.530 5	25.372 6	8.175 1	6.382 9
SOAMST	64.000 4	240.202 6	211.815 6	46.292 7	38.985 0	8.238 3
FTSTC	9.292 7	24.495 3	33.637 7	13.685 0	5.154 9	3.165 3
SAOTPFW	8.781 9	34.714 5	45.053 0	10.757 9	5.341 8	3.235 2

像素点特征加权的尺度自适应跟踪算法

Pixel feature-weighted scale-adaptive object tracking algorithm

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 16

相关文章 13

Metrics

推荐阅读 0

[1]	曾浩, 母王强, 杨顺平. 高机动目标跟踪ATPM-IMM算法[J]. 通信学报, 2022, 43(7): 93-101.
[2]	陈志旺, 张忠新, 宋娟, 雷海鹏, 彭勇. 在线目标分类及自适应模板更新的孪生网络跟踪算法[J]. 通信学报, 2021, 42(8): 151-163.
[3]	王洪雁, 张莉彬, 陈国强, 汪祖民, 管志远. 结合粒子滤波及度量学习的目标跟踪方法[J]. 通信学报, 2021, 42(5): 98-110.
[4]	程旭, 王莹莹, 张年杰, 付章杰, 陈北京, 赵国英. 基于空间感知的多级损失目标跟踪对抗攻击方法[J]. 通信学报, 2021, 42(11): 242-254.
[5]	柳超,张志国,孙进平. 基于幅度信息的海上多目标稳健跟踪方法[J]. 通信学报, 2019, 40(2): 60-69.
[6]	王亚文,陈鸿昶,李邵梅,高超. 融合遮挡感知的在线Boosting跟踪算法[J]. 通信学报, 2016, 37(9): 92-101.
[7]	卢旭,程良伦,罗世亮. 无线传感器网络自适应目标跟踪节点调度算法[J]. 通信学报, 2015, 36(4): 70-80.
[8]	蒋鹏1，宋华华1，林广2. 基于粒子群优化和M-H采样粒子滤波的传感器网络目标跟踪方法[J]. 通信学报, 2013, 34(11): 2-17.
[9]	蒋鹏,宋华华,林广. 基于粒子群优化和M-H抽样粒子滤波的传感器网络目标跟踪方法[J]. 通信学报, 2013, 34(11): 8-17.
[10]	王慧斌,陈哲,王鑫,马玉. 基于随机有限集的UPF-CPHD多目标跟踪[J]. 通信学报, 2012, 33(12): 147-153.
[11]	龙云利,盛卫东,徐晖,安玮. 锥扫型光学传感器像平面多目标轨迹跟踪[J]. 通信学报, 2011, 32(9): 123-128.
[12]	柳絮,李金宝,郭龙江,范斌,朱敬华. 传感器网络中一种能量有效的移动目标预测跟踪算法[J]. 通信学报, 2010, 31(9A): 135-143.
[13]	申兴发,陈积明,王智,戴国骏. 面向移动目标的传感器网络覆盖质量度量与优化[J]. 通信学报, 2008, 29(11): 246-252.