融合遮挡感知的在线Boosting跟踪算法

doi:10.11959/j.issn.1000-436x.2016181

Abstract

Abstract:

Online Boosting tracking algorithm combined with occlusion sensing was presented.In this method,occlusion sensor was introduced to check the tracking results,and classifier updating strategy was adjusted depending on the occlusion checking results.By this way,the feature pool of the classifier can be kept pure,which will improve the tracking robustness under occlusion.Experimental results show that compared with traditional Boosting tracking algorithm,improved algorithm can solve the problem of occlusion very well.

Key words: online Boosting, occlusion sensing, ORB feature, object tracking

Ya-wen WANG,Hong-chang CHEN,Shao-mei LI,Chao GAO. Online Boosting tracking algorithm combined with occlusion sensing[J]. Journal on Communications, 2016, 37(9): 92-101.

Figures/Tables 10

References 16

[1]	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): 200-211. LUO H L , DU F F , KONG F S . Pixel feature-weighted scale-adaptive object tracking algorithm[J]. Journal on Communication, 2015,36(10): 200-211.
[2]	张焕龙, 胡士强, 杨国胜 . 基于外观模型学习的视频目标跟踪方法综述[J]. 计算机研究与发展, 2015,52(1): 177-190. ZHANG H L , HU S Q , YANG G S . Video object tracking based on appearance models learning[J]. Journal of Computer Research and Development, 2015,52(1): 177-190.
[3]	BAI Y , TANG M . Robust tracking via weakly supervised ranking SVM[C]// The IEEE Conference on Computer Vision and Pattern Recognition. 2012: 1854-1861.
[4]	GRABNER H , BISCHOF H . On-line boosting and vision[C]// The IEEE Conference on Computer Vision and Pattern Recognition. 2006: 260-267.
[5]	程有龙, 李斌, 张文聪 ,等. 融合先验知识的自适应行人跟踪算法[J]. 模式识别与人工智能, 2009,22(5): 704-708. CHENG Y L , LI B , ZHANG W C ,et al. An adaptive pedestrian tracking algorithm with prior knowledge[J]. PR & AI, 2009,22(5): 704-708.
[6]	颜佳, 吴敏渊 . 遮挡环境下采用在线Boosting的目标跟踪[J]. 光学精密工程, 2012,20(2): 439-446. YAN J , WU M Y . On-line boosting based target tracking under occlusion[J]. Optics and Precision Engineering, 2012,20(2): 439-446.
[7]	ADAM A , RIVLIN E , SHIMSHONI I . Robust fragments-based tracking using the integral histogram[C]// The IEEE Conference on Computer Vision and Pattern Recognition. 2006: 798-805.
[8]	HU H , MA B , WU Y ,et al. Kernel regression based online boosting tracking[J]. Journal of Information Science and Engineering, 2015,31(1): 267-282.
[9]	YANG F , LU H , YANG M H . Robust visual tracking via multiple kernel boosting with affinity constraints[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2014,24(2): 242-254.
[10]	GRABNER H , LEISTNER C , BISCHOF H . Semi-supervised on-line boosting for robust tracking[C]// The European Conference on Computer Vision. 2008: 234-247.
[11]	陈思, 苏松志, 李绍滋 ,等. 基于在线半监督 Boosting 的协同训练目标跟踪算法[J]. 电子与信息学报, 2014,36(4): 888-895. CHEN S , SU S Z , LI S Z ,et al. A novel co-training object tracking algorithm based on online semi-supervised Boosting[J]. Journal of Electronics & Information Technology, 2014,36(4): 888-895.
[12]	BABENKO B , YANG M H , BELONGIE S . Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33(8): 1619-1632.
[13]	RUBLEE E , RABAUD V , KONOLIGE K ,et al. ORB:an efficient alternative to SIFT or SURF[C]// The International Conference on Computer Vision. 2011: 2564-2571.
[14]	唐剑琪, 谢林江, 袁庆生 ,等. 基于 ORB 的镜头边界检测算法[J]. 通信学报, 2013,34(11): 184-190. TANG J Q , XIE L J , YUAN Q S ,et al. Shot boundary detection algorithm based on ORB[J]. Journal on Communication, 2013,34(11): 184-190.
[15]	PERNICI F , DEL B A . Object tracking by oversampling local features[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014,36(12): 2538-2551.
[16]	WU Y , LIM J , YANG M H . Online object tracking:a benchmark[C]// The IEEE Conference on Computer Vision and Pattern Recognition. 2013: 2411-2418.

Metrics

Recommended 0

No Suggested Reading articles found!

λ_o	利用faceOcc1测试的结果		利用faceOcc2测试的结果
λ_o	漏检率	误检率	漏检率	误检率
5	3.6%	55.2%	4.4%	55.4%
10	5.1%	48.8%	6.4%	51.7%
15	5.9%	40.1%	6.8%	29.1%
20	9.2%	30.0%	10.8%	21.6%
25	11.5%	22.4%	15.5%	16.1%
30	14.2%	17.7%	17.0%	10.1%
35	14.8%	15.4%	17.9%	7.2%
40	15.1%	10.7%	23.6%	6.4%
45	15.6%	7.0%	24.8%	6.1%
50	16.0%	6.4%	32.7%	5.9%
55	19.8%	4.9%	36.4%	5.9%
60	25.4%	3.3%	41.9%	5.7%
65	29.0%	2.9%	50.5%	5.4%
70	35.3%	1.2%	54.9%	5.1%
75	40.8%	0.8%	57.7%	4.7%
80	48.4%	0.6%	62.7%	4.6%

测试序列名称	遮挡感知器漏检率	遮挡感知器误检率
coke	23.1%	14.2%
tiger2	26.4%	18.5%
faceOcc1	22.9%	14.9%
faceOcc2	23.7%	10.6%
walking2	18.0%	12.3%
woman	12.0%	8.7%

序列	TLD	MIL	ASLA	Struck	VTD	IVT	CT	DFT	SCM	CSK	本文算法（排名）
fish	13.1	19.2	8.8	11.3	9.4	10.7	14.9	20.4	9.5	21.4	7.7(1)
motorRolling	173.0	163.9	201.6	149.3	161.1	181.4	160.6	177.8	157.6	424.4	127.5(1)
liquor	36.4	140.5	71.0	65.6	100.7	112.8	175.3	220.4	81.9	127.3	49.2(2)
deer	25.1	55.4	142.1	10.6	207.5	179.8	233.5	259.7	75.9	363.0	15.8(2)
girl	9.8	16.9	5.3	4.6	11.6	26.8	17.3	23.2	4.1	14.7	4.2(2)
mountainBike	193.0	7.5	23.5	11.7	9.7	13.3	188.8	8.4	17.4	8.2	8.0(2)
singer2	196.6	169.1	9.7	166.6	184.2	182.4	182.1	39.4	111.5	183.4	99.6(3)
doll	7.9	21.7	17.4	30.3	8.9	16.2	11.1	94.5	7.4	437.8	13.0(4)
shaking	36.6	14.1	19.5	106.4	13.2	85.5	161.9	102.4	13.8	169.2	18.6(4)
walking1	95.4	4.4	2.9	5.1	5.4	2.9	5.4	81.8	3.6	7.1	4.8(5)
soccer	72.6	36.8	121.2	110.2	22.6	146.5	80.0	112.0	157.7	30.8	104.0(6)
matrix	55.2	41.9	61.6	167.1	70.2	109.8	72.4	127.8	51.9	65.1	69.4(6)

跟踪算法	运算速度/(frame·s^?1)
OAB	15.23
SBT	7.47
MIL	34.40
Frag	4.47
本文算法	8.84

Online Boosting tracking algorithm combined with occlusion sensing

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 16

Related Articles 6

Metrics

Recommended 0

[1]	Zhiwang CHEN, Zhongxin ZHANG, Juan SONG, Haipeng LEI, Yong PENG. Tracking algorithm of Siamese network based on online target classification and adaptive template update [J]. Journal on Communications, 2021, 42(8): 151-163.
[2]	Xu CHENG, Yingying WANG, Nianjie ZHANG, Zhangjie FU, Beijing CHEN, Guoying ZHAO. Multi-level loss object tracking adversarial attack method based on spatial perception [J]. Journal on Communications, 2021, 42(11): 242-254.
[3]	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.
[4]	Hui-bin WANG,Zhe CHEN,Xin WANG,Yu MA. Random finite sets based UPF-CPHD multi-object tracking [J]. Journal on Communications, 2012, 33(12): 147-153.
[5]	Qian-qian REN,Jian-zhong LI,Jin-bao LI,Jing-hua ZHU. Energy-efficient object tracking algorithm in wireless sensor networks [J]. Journal on Communications, 2009, 30(4): 50-59.
[6]	Chen REN,Wei-ying LI,Hua YAN. Multiple egress routing solution on GLBP and IP SLAs protocol [J]. Journal on Communications, 2006, 27(11A): 121-125.