Person Re-identification Based on Part Feature Importance

ZHANG Dengyi; WANG Qian; ZHU Bo; WU Xiaoping; CAO Yu; CAI Bo

doi:10.13203/j.whugis20150551

Volume 42 Issue 1

Jan. 2017

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2017 > 42(1): 84-90. > DOI: 10.13203/j.whugis20150551

ZHANG Dengyi, WANG Qian, ZHU Bo, WU Xiaoping, CAO Yu, CAI Bo. Person Re-identification Based on Part Feature Importance[J]. Geomatics and Information Science of Wuhan University, 2017, 42(1): 84-90. DOI: 10.13203/j.whugis20150551

Citation:

PDF (1459 KB)

Person Re-identification Based on Part Feature Importance

1.
School of Computer, Wuhan University, Wuhan 430072, China
2.
Wuhan Land Resources and Planning Information Center, Wuhan 430014, China

Funds:

Scientific and Technological Project in Hubei Province 2014BAA149

More Information

Corresponding author:
WANG Qian, PhD candidate. E-mail: wq1984a@qq.com
Received Date: April 29, 2016
Published Date: January 04, 2017

Graphical Abstract

Abstract

Abstract

In a video surveillance system, same person may looks different across different camera, while different people may look the same in one camera, thus making person re-identification a challenging problem. This paper carried out an algorithm based on part feature importance, firstly extract features such as color, texture and shape. Then cluster each part by classify different appearance of body parts, using an error accumulation method to figure out weight vector indicate the significant of the feature, which fit the type of appearance. Calculating the similarity at last, using this vector to weighting the features of each part, making the feature more suitable for the appearance. This algorithm indicate some features are more important than others for parts with different appearance. We had complete our experiments on the public datasets VIPeR, and evaluate the result by CMC curve, which indicated this algorithm achieved higher re-identification rate for re-identification, and more robust to viewing condition changes, illumination variations, background clutter and occlusion.
- video surveillance,
- person re-identification,
- part feature importance,
- cluster,
- CMC curve

FullText(HTML)

References (13)

References

[1]	Farenzena M, Bazzani L, Perina A, et al. Person re-Identification by Symmetry-Driven Accumulation of Local Features[C]. Computer Vision and Pattern Recognition, San Francisco, CA, USA, 2010 http://www.oalib.com/references/17181179
[2]	Zhao R, Ouyang W, Wang X. Unsupervised Salience Learning for Person Re-identification[C]. Computer Vision and Pattern Recognition, Columbus, Ohio, USA, 2014
[3]	Dong S C, Marco C, Michele S, et al. Custom Pictorial Structures for Re-identification[C]. British Machine Vision Conference, Dundee, UK, 2011 https://www.researchgate.net/publication/250003726_Custom_Pictorial_Structures_for_Re-identification
[4]	Ma B, Su Y, Jurie F. Local Descriptors Encoded by Fisher Vectors for Person Re-identification[C]. The 12th International Conference on Computer Vision, Florence, Italy, 2012
[5]	范彩霞, 朱虹, 蔺广逢, 等.多特征融合的人体目标再识别[J].中国图象图形学报, 2013, 18(6):711-717 http://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201306013.htm Fan Caixia, Zhu Hong, Lin Guangfeng, et al. Person Re-identification Based on Multi-features[J]. Journal of Image and Graphics, 2013, 18(6):711-717 http://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201306013.htm
[6]	曾明勇, 吴泽民, 田畅, 等.基于外观统计特征融合的人体目标再识别[J].电子与信息学报, 2014, 36(8):1844-1851 http://www.cnki.com.cn/Article/CJFDTOTAL-DZYX201408011.htm Zeng Mingyong, Wu Zemin, Tian Chang, et al. Fusing Appearance Statistical Features for Person Re-identification[J]. Journal of Electronics & Information Technology, 2014, 36(8):1844-1851 http://www.cnki.com.cn/Article/CJFDTOTAL-DZYX201408011.htm
[7]	Forssén P E. Maximally Stable Colour Regions for Recognition and Matching[C]. Computer Vision and Pattern Recognition, Minnesota, USA, 2007
[8]	Andriluka M, Roth S, Schiele B. Pictorial Structures Revisited:People Detection and Articulated Pose Estimation[C]. Computer Vision and Pattern Recognition, Miami, FL, USA, 2009 http://www.oalib.com/references/16891711
[9]	Douglas G, Hai T. Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features[C]. European Conference on Computer Vision, Marseille, France, 2008 https://www.researchgate.net/publication/221305183_Viewpoint_Invariant_Pedestrian_Recognition_with_an_Ensemble_of_Localized_Features
[10]	Liu C X, Gong S G, Chen C L, et al. Person Reidentification:What Features Are Important[C]. European Conference on Computer Vision, Florence, Italy, 2012
[11]	Mu Y D, Yan S C, Liu Y, et al. Discriminative Local Binary Patterns for Human Detection in Personal Album[C]. Computer Vision and Pattern Recognition, Anchorage, AK, USA, 2008
[12]	Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection[C]. Computer Vision and Pattern Recognition, San Diego, CA, USA, 2005 http://www.oalib.com/references/9287245
[13]	Davis J V, Kulis B, Jain P, et al. Information-Theoretic Metric Learning[C]. The 24th International Conference on Machine Learning, Corvalis, OR, USA, 2007

[1]	NIU Lei, SONG Yiquan, ZHANG Hongmin, HOU Shaoyang. A Hilbert-Curve-Based R^* Tree Index Optimized for Indoor Evacuation[J]. Geomatics and Information Science of Wuhan University, 2018, 43(9): 1416-1421. DOI: 10.13203/j.whugis20160352
[2]	daijing, wu　mingguang, zheng　peiｂei, wang　lei, cui　dengj i, chen　taisheng. an　improved　str－tree 　spatial 　index　al gorithm　based　on　hilbert－curve[J]. Geomatics and Information Science of Wuhan University, 2014, 39(7): 777-781.
[3]	GUO Qingsheng, HUANG Yuanlin, ZHANG Liping. The Method of Curve Bend Recognition[J]. Geomatics and Information Science of Wuhan University, 2008, 33(6): 596-599.
[4]	LEI Weigang, TONG Xiaohua, LIU Dajie. Data Process Methods of Line Feature Generalization Based on Curve Fit[J]. Geomatics and Information Science of Wuhan University, 2006, 31(10): 896-899.
[5]	ZHAO Xiuping, Phil Green. Evaluating Acceptability Threshold and Weighting for Color Difference on Gloss Paper Reproduction[J]. Geomatics and Information Science of Wuhan University, 2006, 31(9): 814-817.
[6]	WU Hehai. Multi-way Tree Structure Based on Curve Generalization Method[J]. Geomatics and Information Science of Wuhan University, 2004, 29(6): 479-483.
[7]	WANG Xinzhou, TANG Zhong'an, CHEN Zhihui. ε_m-Band Based on Spline Fitting Function of Anomalous Curves in GIS[J]. Geomatics and Information Science of Wuhan University, 2004, 29(1): 58-62.
[8]	TONG Xiaohua, LIU Dajie. Combined Adjustment Models of Road Curve Digitization in GIS[J]. Geomatics and Information Science of Wuhan University, 2001, 26(1): 64-69.
[9]	Wang Kongzheng, Wang Jiexian. An Algorithm for Error-band Determination of Curves in GIS[J]. Geomatics and Information Science of Wuhan University, 1999, 24(2): 142-144.
[10]	Liu Wenbao, Huang Youcai, Li Zonghua. On Measuring Complexity of Digital Curves and Separating Stochastic Part from Trend Movement of Digitizing Process[J]. Geomatics and Information Science of Wuhan University, 1995, 20(4): 289-295.

Cited By

Cited by

Periodical cited type(26)

1.	王盼龙，侯汶材，蒋光伟，王斌，程传录，李康. 顾及起算点误差的区域参考框架约束方法研究. 大地测量与地球动力学. 2024(01): 39-45 .
2.	杨承志，张晓明，张鸽. 基于WLS-KF的UWB室内定位滤波算法研究. 电子测量与仪器学报. 2024(01): 25-33 .
3.	姜颖颖，潘树国，孟骞，高旺. 基于鲁棒马氏距离统计量的多源融合抗差估计方法. 仪器仪表学报. 2024(02): 252-262 .
4.	李圣英，孟骞，姜颖颖，王立辉. 故障修复增强的抗差滤波PDR/GNSS行人导航方法. 仪器仪表学报. 2024(02): 233-242 .
5.	林雪原，刘丽丽，董云云，陈祥光，杨海利. 改进的GNSS/SINS组合导航系统自适应滤波算法. 武汉大学学报(信息科学版). 2023(01): 127-134 .
6.	沈子涵，赵修斌，张闯，张良，刘鑫贤. 基于长短期记忆神经网络的自适应容错方法. 系统工程与电子技术. 2023(03): 831-838 .
7.	刘原华，刘浩，牛新亮. 卫星导航自适应抗差滤波算法. 信息技术与信息化. 2022(06): 213-217 .
8.	朱璐瑛，孙炜玮，刘成铭，孙兆玮. 多传感器组合导航系统的联邦UKF算法研究. 电子测量与仪器学报. 2022(07): 91-98 .
9.	李霜，张敬霞，付贵，樊亚，张成龙. 小米8手机在城市环境下的单点定位精度研究. 导航定位学报. 2022(05): 160-169 .
10.	代晓霁，李敏，徐天河，江楠，许艳. 复杂环境下的UWB/PDR紧组合定位方法. 导航定位学报. 2022(06): 18-26 .
11.	蔡保杰，邵雷. 三段判别域与最小二乘拟合的抗差滤波算法. 系统工程与电子技术. 2021(05): 1346-1353 .
12.	葛宝爽，张海，唐志坤. 基于新息异常检测的改进抗差自适应卡尔曼滤波算法. 导航定位与授时. 2020(01): 48-54 .
13.	蔡保杰，邵雷，李正杰. 采用卡方检验和牛顿插值的抗差卡尔曼滤波新算法. 空军工程大学学报(自然科学版). 2020(01): 38-43 .
14.	赵修斌，高超，庞春雷，张闯，王勇. BP神经网络辅助的缓变故障双阈值检测法. 控制与决策. 2020(06): 1384-1390 .
15.	贺军义，杨丰，安葳鹏，尚家泽. 基于IGGⅢ方案的自适应渐消卡尔曼滤波器. 计算机工程与应用. 2020(14): 52-56 .
16.	蔡保杰，邵雷，李佳伟，李正杰. 基于牛顿插值的抗差卡尔曼滤波算法. 导航定位学报. 2020(05): 49-56 .
17.	刘韬，徐爱功，隋心，王长强. 新息向量的抗差Kalman滤波方法及其在UWB室内导航中的应用. 武汉大学学报(信息科学版). 2019(02): 233-239 .
18.	陈国通，范圆圆，刘琪. 一种改进的无迹Kalman滤波在SINS/GPS组合导航中的应用. 宇航总体技术. 2019(01): 23-28 .
19.	闫伟，牛小骥，旷俭. 光源编码+PDR组合的室内行人定位方法. 测绘通报. 2019(05): 7-11+54 .
20.	张闯，赵修斌，庞春雷，冯波，高超. LS-SVM辅助的小幅值及缓变故障检测与容错方法. 中国惯性技术学报. 2019(03): 415-420 .
21.	张建，喻国荣，潘树国，闫志跃，王彦恒. 基于卡方检验的GNSS观测值部分粗差抗差滤波算法. 仪器仪表学报. 2019(08): 102-109 .
22.	刘韬，徐爱功，隋心. 基于自适应抗差卡尔曼滤波的UWB室内定位. 传感技术学报. 2018(04): 567-572 .
23.	胡方强，吕涛，包亚萍. 改进的自适应Kalman滤波在SINS/GPS组合导航中的应用. 计算机工程与应用. 2018(05): 253-257+264 .
24.	陶贤露，张小红，朱锋，肖佳敏. 一种基于加表零偏稳定性的GNSS/SINS组合导航异常探测方法. 武汉大学学报(信息科学版). 2018(07): 1078-1084 .
25.	韩亚坤，文鸿雁，张艺航，陈冠宇，周吕. 基于卡方检验的抗差自适应Kalman滤波在变形监测中的应用. 大地测量与地球动力学. 2017(06): 604-608 .
26.	邹敏，王国栋，刘超. 抗差自适应Kalman滤波及其在GNSS导航中的应用. 河北工程大学学报(自然科学版). 2016(03): 89-93 .

Other cited types(24)

Get Citation

PDF

XML

Article views (1785) PDF downloads (410) Cited by(50)

Person Re-identification Based on Part Feature Importance

Abstract

References

Related Articles

Cited by

Periodical cited type(26)

Other cited types(24)

Catalog

Related

Person Re-identification Based on Part Feature Importance

Abstract

References

Related Articles

Cited by

Periodical cited type(26)

Other cited types(24)

Catalog

Related

Export File

Citation

Format

Content