[1]曹伟,韩华,王裕明,等.目标再确认中的优化扩散距离相似性度量[J].智能系统学报,2018,13(02):269-280.[doi:10.11992/tis.201607010]
 CAO Wei,HAN Hua,WANG Yuming,et al.Target re-identification based on optimized diffusion distance[J].CAAI Transactions on Intelligent Systems,2018,13(02):269-280.[doi:10.11992/tis.201607010]
点击复制

目标再确认中的优化扩散距离相似性度量(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第13卷
期数:
2018年02期
页码:
269-280
栏目:
出版日期:
2018-04-15

文章信息/Info

Title:
Target re-identification based on optimized diffusion distance
作者:
曹伟 韩华 王裕明 孙宪坤
上海工程技术大学 电子电气工程学院, 上海 201620
Author(s):
CAO Wei HAN Hua WANG Yuming SUN Xiankun
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
关键词:
优化扩散距离相似性度量多特征融合目标再确认
Keywords:
optimized diffusion distancesimilarity measuremulti-feature fusiontarget re-identification
分类号:
TP391.9
DOI:
10.11992/tis.201607010
摘要:
跨摄像头目标再确认是多摄像头监控领域中一个亟需解决的难点问题,如何获得准确率更高的距离度量算法成为解决该难点的关键。为此本文在提取优秀的多特征基础上,建立了一种无需训练,适应更多场景的度量算法:优化扩散距离相似性度量,用于跨摄像头目标再确认。在高维扩散距离的基础上,加入高斯金字塔图像采样和加权性优化处理,用于提高相似空间向量的辨别力,并提高计算效率。通过对高维扩散距离的二次优化建立起最终的相似性度量函数。最后对VIPeR和ETHZ数据库中的图片进行多次目标再确认实验,排名第一的图片的正确匹配率达到了50.5%。实验结果表明本文算法取得了较好的匹配结果。
Abstract:
Target re-identification via cross-camera is a challenging problem in the field of multi-camera surveillance. How to get a more accurate distance measurement algorithm is the key to solve this difficult problem. So, in this paper, we established a new measurement algorithm without training based on extracting more excellent features to do target re-identification, which is optimized diffusion distance. On the basis of high-dimensional diffusion distance, Gaussian pyramid image sampling and weight optimization are added to improve the discrimination of similar space vectors and increase computational efficiency. The final similarity measure function is established by the second optimization of the high-dimensional diffusion distance. At last, we do numerous target re-identification experiments based on databases VIPeR and ETHZ. The matching rate of rank first image can reach 50.5%. The experimental results show that the algorithm proposed in this paper has good performance.

参考文献/References:

[1] ZHAO R, OYANG W, WANG X. Person re-identification by saliency learning[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(2): 356-370.
[2] JIA J, RUAN Q, JIN Y. Geometric preserving local fisher discriminant analysis for person re-identification[J]. Neurocomputing, 2016, 205: 92-105.
[3] UKITA N, MORIGUCHI Y, HAGITA N. People re-identification across non-overlapping cameras using group features[J]. Computer vision and image understanding, 2016, 144(C): 228-236.
[4] MARTINEL N, MICHELONI C. Re-identify people in wide area camera network[C]//2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. RI, USA, 2012: 31-36.
[5] HUA J I, PAN M L. Person re-identification based on global color context[C]//ACCV’10 Proceedings of the 2010 international conference on Computer vision. Queenstown, New Zealand, 2010, 6468(I): 205-215.
[6] ZHAO T, NEVATIA R. Tracking multiple humans in complex situations[J]. IEEE transactions on pattern analysis and machine intelligence, 2004, 26(9): 1208-1221.
[7] LI P, WU H, CHEN Q. Person re-identification using color enhancing feature[C]//2015 3rd IAPR Asian Conference on Pattern Recognition. Kuala Lumpur, Malaysia, 2015: 86-90.
[8] 李金, 胡文广. 基于颜色的快速人体跟踪及遮挡处理[J]. 智能系统学报, 2010, 5(4): 353-359.
LI Jin, HU Wenguang. Tracking fast movement using colors while accommodating occlusion[J]. CAAI transactions on intelligent systems, 2010, 5(4): 353-359.
[9] 刘宇, 向高林, 王伊冰. 一种改进的行人导航算法研究[J]. 重庆邮电大学学报:自然科学版, 2016, 28(2): 233-238.
LIU Yu, XIANG Gaolin, WANG Yibing. An improved pedestrian navigation algorithm[J]. Journal of Chongqing university of posts and telecommunication: natural science edition, 2016, 28(2): 233-238.
[10] HU Y, LIAO S, LEI Z. Exploring structural information and fusing multiple features for person re-identification[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Portland, USA, 2013: 794-799.
[11] LIU P, GUO J M, CHAMNONGTHAI K, et al. Fusion of color histogram and lbp-based features for texture image retrieval and classification[J]. Information sciences, 2017, 1(390): 95-111.
[12] CHANG C, LIN C. LIBSVM: a library for support vector machines[J]. Journal ACM transactions on intelligent systems and technology, 2011, 2(3): 389-396.
[13] CAI Y, CHEN W, HUANG K, TAN T. Continuously tracking objects across multiple widely separated cameras[C]//ACCV’07 Proceedings of the 8th Asian conference on Computer vision. Tokyo, Japan, 2012(I): 843-852.
[14] PATHYA B, NAINAN S. Performance evaluation of face recognition using LBP, PCA and SVM[J]. International journal of advanced trends in computer science and engineering, 2016, 3(4): 85-88.
[15] 王彩玲, 詹松, 荆晓远. 基于图像显著特征的非重叠视域行人再识别[J]. 南京邮电大学学报: 自然科学版, 2016, 36(3): 106-111.
WANG Cailing, ZHAN Song, JING Xiaoyuan. Pedestrian re-identification based on salient features in non-overlapping areas[J]. Journal of Nanjing university of posts and telecommunications: natural science edition, 2016, 36(3): 106-111.
[16] FARENZENA M, BAZZANI L. Person re-identification by symmetry-driven accumulation of local features[C]//2010 IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA, 2010: 2360-2367.
[17] 彭程, 刘帅师, 万川, 等. 基于局部纹理ASM模型的人脸表情识别[J]. 智能系统学报, 2011,03: 231-238.
PENG Cheng, LIU Shuaishi, WAN Chuan, et al. An active shape model for facial expression recognition based on a local texture model[J]. CAAI transactions on intelligent systems,2011, 6(3): 231-238.
[18] FENG X, PIETIKAINEN M, HADID A. Facial expression recognition with local binary patterns and linear programming[J]. Pattern recognition and image analysis, 2005, 15(2): 550-552.
[19] PROSSER B, ZHENG W S, GONG S. Person re-identification by support vector ranking[C]//BMVC2010 British Machine Vision Conference. Aberystwyth, UK, 2010(42): 1-11.
[20] FANG C. People re-identification based on online multiple kernel learning in video surveillance[J]. Opto-electronic engineering, 2012, 39(9): 65-71.
[21] PANG Y, XIN-CHU S: Multiway histogram intersection for multi-target tracking[C]//2015 18th International Conference on Information Fusion. Washington, DC, USA, 2015: 1938-1945.
[22] YIN J, ZHOU J, JIN Z. Principal component analysis and kernel principal component analysis based on cosine angle distance[J]. Computer engineering and applications, 2011, 47(3): 9-12.
[23] HAIBIN L, OKADA K. Diffusion distance for histogram comparison[C]//Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC, USA, 2006, 1(1): 246-253.
[24] ROTHER C, KOLMOGOROV V, BLAKE A. “GrabCut”: interactive foreground extraction using iterated graph cuts[J]. ACM transactions on graphics, 2004, 23(3): 307-312.
[25] QING-JUN W, RU-BO Z. LPP-HOG: a new local image descriptor for fast human detection[C]//2008 IEEE International Symposium on Knowledge Acquisition and Modeling Workshop. Wuhan, China, 2008: 640-643.
[26] JUN Y. HOCK-SOON S: fuzzy diffusion distance learning for cartoon similarity estimation[J]. Journal of computer science and technology: English edition, 2011, 26(2): 203-216.
[27] MAZZON R, TAHIR S F, CAVALLARO A. Person re-identification in crowd[J]. Pattern recognition letters, 2012, 33(14): 1828-1837.
[28] CHENG D S, CRISTANI M, STOPPA M. Custom pictorial structures for re-identification[C]//BMVC2010 British Machine Vision Conference. Dundee, UK, 2011, (68): 1-11.
[29] MA B, SU Y, JURIE F. Local descriptors encoded by fisher vectors for person re-identification[C]//12th European Conference on Computer Vision Workshops. Florence, Italy, 2012, 7583: 413-422.
[30] ZHAO R, OUYANG W, WANG X. Unsupervised salience learning for person re-identification[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013, 9(4): 3586-3593.
[31] ZENG M Y, WU Z M, CHANG T. Fusing appearance statistical features for person re-identification[J]. Journal of electronics and information technology, 2014, 36(8): 1844-1851.
[32] GRAY D, TAO H. Viewpoint invariant pedestrian recognition with an ensemble of localized features[C]// ECCV’08 Proceedings of the 10th European Conference on Computer Vision. Marseille, France, 2008, (I): 262-275.
[33] ZHENG W S, GONG S, XIANG T. Reidentification by relative distance comparison[J]. IEEE transactions on pattern analysis and machine intelligence, 2013, 35(3): 653-668.
[34] DIKMEN M, AKBAS E, HUANG T S. Pedestrian recognition with a learned metric[C]//ACCV’10 Proceedings of the 10th Asian conference on Computer vision. Queenstown, New Zealand, 2010, 6495(IV): 501-512.

相似文献/References:

[1]韩华,丁永生,郝矿荣.综合颜色和小波纹理特征的免疫粒子滤波视觉跟踪[J].智能系统学报,2011,6(04):289.
 HAN Hua,DING Yongsheng,HAO Kuangrong.An immune particle filter video tracking method based on color and wavelet texture[J].CAAI Transactions on Intelligent Systems,2011,6(02):289.
[2]李海林,郭韧,万校基.基于特征矩阵的多元时间序列最小距离度量方法[J].智能系统学报,2015,10(03):442.[doi:10.3969/j.issn.1673-4785.201405047]
 LI Hailin,GUO Ren,WAN Xiaoji.A minimum distance measurement method for amultivariate time series based on the feature matrix[J].CAAI Transactions on Intelligent Systems,2015,10(02):442.[doi:10.3969/j.issn.1673-4785.201405047]
[3]李海林,梁叶.分段聚合近似和数值导数的动态时间弯曲方法[J].智能系统学报,2016,11(2):249.[doi:10.11992/tis.201507064]
 LI Hailin,LIANG Ye.Dynamic time warping based on piecewise aggregate approximation and data derivatives[J].CAAI Transactions on Intelligent Systems,2016,11(02):249.[doi:10.11992/tis.201507064]
[4]李海林,邹金串.基于分类词典的文本相似性度量方法[J].智能系统学报,2017,12(04):556.[doi:10.11992/tis.201608010]
 LI Hailin,ZOU Jinchuan.Text similarity measure method based on classified dictionary[J].CAAI Transactions on Intelligent Systems,2017,12(02):556.[doi:10.11992/tis.201608010]
[5]张倩倩,马媛媛,徐久成.基于关联熵系数的粗糙Vague集相似性度量方法[J].智能系统学报,2018,13(04):650.[doi:10.11992/tis.201706081]
 ZHANG Qianqian,MA Yuanyuan,XU Jiucheng.Measurement method of the similarity of rough vague sets based on relative entropy coefficient[J].CAAI Transactions on Intelligent Systems,2018,13(02):650.[doi:10.11992/tis.201706081]

备注/Memo

备注/Memo:
收稿日期:2016-07-13。
基金项目:国家自然科学基金项目(61305014);国家留学基金管理委员会项目(201508310033);上海市教育委员会和上海市教育发展基金会“晨光计划”(13CG60);上海高校青年教师培养资助计划(ZZGJD13006);上海工程技术大学人才行动计划(2017RC112015,nhrc-2015-11).
作者简介:曹伟,男,1989年生,硕士研究生,主要研究方向为多目标跟踪、目标传递;韩华,女,1983年生,副教授,主要研究方向为多目标跟踪、目标再确认、目标传递、智能计算;王裕明,男,1962年生,教授,主要研究方向为计算机信息技术研究。
通讯作者:韩华.E-mail:2070967@mail.dhu.edu.cn.
更新日期/Last Update: 1900-01-01