一级黄色片免费播放|中国黄色视频播放片|日本三级a|可以直接考播黄片影视免费一级毛片

高級(jí)搜索

留言板

尊敬的讀者、作者、審稿人, 關(guān)于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復(fù)。謝謝您的支持!

姓名
郵箱
手機(jī)號(hào)碼
標(biāo)題
留言內(nèi)容
驗(yàn)證碼

基于雙向參考集矩陣度量學(xué)習(xí)的行人再識(shí)別

陳瑩 許瀟月

陳瑩, 許瀟月. 基于雙向參考集矩陣度量學(xué)習(xí)的行人再識(shí)別[J]. 電子與信息學(xué)報(bào), 2020, 42(2): 394-402. doi: 10.11999/JEIT190159
引用本文: 陳瑩, 許瀟月. 基于雙向參考集矩陣度量學(xué)習(xí)的行人再識(shí)別[J]. 電子與信息學(xué)報(bào), 2020, 42(2): 394-402. doi: 10.11999/JEIT190159
Ying CHEN, Xiaoyue XU. Matrix Metric Learning for Person Re-identification Based on Bidirectional Reference Set[J]. Journal of Electronics & Information Technology, 2020, 42(2): 394-402. doi: 10.11999/JEIT190159
Citation: Ying CHEN, Xiaoyue XU. Matrix Metric Learning for Person Re-identification Based on Bidirectional Reference Set[J]. Journal of Electronics & Information Technology, 2020, 42(2): 394-402. doi: 10.11999/JEIT190159

基于雙向參考集矩陣度量學(xué)習(xí)的行人再識(shí)別

doi: 10.11999/JEIT190159
基金項(xiàng)目: 國家自然科學(xué)基金(61573168)
詳細(xì)信息
    作者簡(jiǎn)介:

    陳瑩:女,1976年生,教授,博士生導(dǎo)師,研究方向?yàn)槟J阶R(shí)別、信息融合

    許瀟月:女,1994年生,碩士生,研究方向?yàn)樾腥嗽僮R(shí)別

    通訊作者:

    陳瑩 chenying@jiangnan.edu.cn

  • 中圖分類號(hào): TN911.73; TP391

Matrix Metric Learning for Person Re-identification Based on Bidirectional Reference Set

Funds: The National Natural Science Foundation of China (61573168)
  • 摘要:

    針對(duì)行人再識(shí)別中由于外觀差異不顯著導(dǎo)致特征描述不準(zhǔn)確的問題,該文提出一種基于雙向參考集矩陣度量學(xué)習(xí)(BRM2L)的行人再識(shí)別算法。首先通過互近鄰算法獲得每個(gè)攝像頭下的互近鄰參考集,為保證參考集的魯棒性,聯(lián)合考慮各攝像頭下的互近鄰參考集獲得雙向參考集。通過雙向參考集挖掘出困難樣本進(jìn)行特征描述,從而得到準(zhǔn)確的外觀差異描述。最后利用該特征描述進(jìn)行更有效的矩陣度量學(xué)習(xí)。在多個(gè)公開數(shù)據(jù)集上的實(shí)驗(yàn)結(jié)果證明了該算法比現(xiàn)有算法具有更好的行人再識(shí)別性能。

  • 圖  1  差異矩陣描述子

    圖  2  算法框架圖

    圖  3  雙向參考集與隨機(jī)參考集結(jié)果對(duì)比圖

    表  1  兩個(gè)攝像頭下參考集里的樣本標(biāo)簽的重疊率$\sigma $(%)

    行人行人1行人2行人3行人4
    重疊率$\sigma $20501025
    下載: 導(dǎo)出CSV

    表  2  在3個(gè)數(shù)據(jù)集上采用不同特征的匹配精度(%)

    方法VIPeRCHUK01PRID450S
    Rank-1Rank-5Rank-1Rank-5Rank-1Rank-5
    ${{\rm{L}}_{\rm{2}}}$范數(shù)(GoG)19.0038.0024.1751.3332.4460.00
    F范數(shù)(GoG)20.1741.8334.5069.8352.2280.22
    ${\rm{BR}}{{\rm{M}}^{\rm{2}}}{\rm{L}}$(GoG)38.3369.1745.3370.5054.4480.67
    ${{\rm{L}}_{\rm{2}}}$范數(shù)(FCTNN)29.0046.0037.4458.0031.7357.96
    F范數(shù)(FCTNN)30.0049.8346.5672.1144.4072.84
    ${\rm{BR}}{{\rm{M}}^{\rm{2}}}{\rm{L}}$(FCTNN)41.3368.1747.4277.4445.5172.96
    下載: 導(dǎo)出CSV

    表  3  VIPeR數(shù)據(jù)集上的結(jié)果

    方法Rank-1Rank-5Rank-10Rank-20
    PCCA[16]19.348.964.980.3
    KISSME[18]19.648.062.277.0
    BiCov[17]20.643.256.168.0
    eSDC[19]26.346.458.672.8
    DeepMetric[24]28.259.373.486.4
    Midfilter[21]29.152.565.979.9
    LADF[20]30.064.080.092.0
    FTCNN[15]+XQDA31.259.874.083.5
    RD[6]33.365.178.388.5
    GoG[14]+XQDA37.367.477.289.6
    SCNCD[22]37.868.581.290.4
    ${\rm{D}}{{\rm{M}}^{\rm{3}}}$[4]38.367.277.089.3
    DeepRanking[25]38.469.281.390.4
    LOMO+XQDA[23]40.068.580.591.0
    DeepList[26]40.569.180.191.2
    ${\rm{BR}}{{\rm{M}}^2}{\rm{L}}$(GoG)38.3369.1781.5089.50
    ${\rm{BR}}{{\rm{M}}^2}{\rm{L}}$(FTCNN)41.3368.1782.0090.33
    下載: 導(dǎo)出CSV

    表  4  PRID 450S數(shù)據(jù)集上的結(jié)果

    方法Rank-1Rank-5Rank-10Rank-20
    KISSME[18]33.059.871.079.0
    CBRA[27]26.457.171.083.2
    CSL[28]44.471.682.289.8
    Mirror[29]55.479.387.893.9
    DRML[30]56.482.290.2
    DM3[4]56.783.188.494.7
    ${\rm{BR}}{{\rm{M}}^2}{\rm{L}}$(GoG)54.4480.6789.7895.56
    ${\rm{BR}}{{\rm{M}}^2}{\rm{L}}$(FTCNN)59.2084.5394.5399.78
    下載: 導(dǎo)出CSV

    表  5  CUHK01數(shù)據(jù)集上的結(jié)果

    方法Rank-1Rank-5Rank-10Rank-20
    SDALF[1]9.922.630.341.0
    TML[12]20.043.556.069.3
    MidFilter[21]34.355.165.074.9
    ImprovedDeep[31]47.571.080.0
    RD[6]31.168.579.1
    ${\rm{D}}{{\rm{M}}^{\rm{3}}}$[4]43.770.177.488.7
    ${\rm{BR}}{{\rm{M}}^2}{\rm{L}}$(GoG)45.3370.5086.5090.00
    ${\rm{BR}}{{\rm{M}}^2}{\rm{L}}$(FTCNN)47.4277.4488.3398.33
    下載: 導(dǎo)出CSV
  • FARENZENA M, BAZZANI L, PERINA A, et al. Person re-identification by symmetry-driven accumulation of local features[C]. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, USA, 2010: 2360–2367.
    李幼蛟, 卓力, 張菁, 等. 行人再識(shí)別技術(shù)綜述[J]. 自動(dòng)化學(xué)報(bào), 2018, 44(9): 1554–1568. doi: 10.16383/j.aas.2018.c170505

    LI Youjiao, ZHUO Li, ZHANG Jing, et al. A survey of person re-identification[J]. Acta Automatica Sinica, 2018, 44(9): 1554–1568. doi: 10.16383/j.aas.2018.c170505
    ZHENG Lilei, DUFFNER S, IDRISSI K, et al. Pairwise identity verification via linear concentrative metric learning[J]. IEEE Transactions on Cybernetics, 2018, 48(1): 324–335. doi: 10.1109/TCYB.2016.2634011
    WANG Zheng, HU Ruimin, CHEN Chen, et al. Person reidentification via discrepancy matrix and matrix metric[J]. IEEE Transactions on Cybernetics, 2018, 48(10): 3006–3020. doi: 10.1109/TCYB.2017.2755044
    CHEN Xiaojing, AN Le, and BHANU B. Reference set based appearance model for tracking across non-overlapping cameras[C]. 2013 International Conference on Distributed Smart Cameras, Palm Springs, USA, 2013: 1–6.
    AN Le, KAFAI M, YANG Songfan, et al. Person reidentification with reference descriptor[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2016, 26(4): 776–787. doi: 10.1109/TCSVT.2015.2416561
    LIAO Shengcai and LI S Z. Efficient PSD constrained asymmetric metric learning for person re-identification[C]. 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 3685–3693.
    ZHONG Zhun, ZHENG Liang, CAO Donglin, et al. Re-ranking person re-identification with k-reciprocal encoding[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 3652–3661.
    SUN Yipeng, TAO Xiaoming, LI Yang, et al. Robust two-dimensional principal component analysis via alternating optimization[C]. 2013 IEEE International Conference on Image Processing, Melbourne, Australia, 2013: 340–344.
    GRAY D, BRENNAN S, and TAO Hai. Evaluating appearance models for recognition, reacquisition, and tracking[C]. The 10th IEEE International Workshop on Performance Evaluation for Tracking and Surveillance, Rio de Janeiro, 2007: 1–7.
    ROTH P M, HIRZER M, K?STINGER M, et al. Mahalanobis Distance Learning For Person Re-identification[M]. London: Springer, 2014: 247–267.
    LI Wei, ZHAO Rui, and WANG Xiaogang. Human reidentification with transferred metric learning[C]. The 11th Asian Conference on Computer Vision, Daejeon, Korea, 2012: 31–44.
    WANG Xiaogang, DORETTO G, SEBASTIAN T, et al. Shape and appearance context modeling[C]. The 11th IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil, 2007: 1–8.
    MATSUKAWA T, OKABE T, SUZUKI E, et al. Hierarchical gaussian descriptor for person re-identification[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 1363–1372.
    MATSUKAWA T and SUZUKI E. Person re-identification using CNN features learned from combination of attributes[C]. The 23rd International Conference on Pattern Recognition, Cancun, Mexico, 2016: 2428–2433.
    MIGNON A and JURIE F. PCCA: A new approach for distance learning from sparse pairwise constraints[C]. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 2666–2672.
    MA Bingpeng, SU Yu, and JURIE F. Bicov: A novel image representation for person re-identification and face verification[C]. British Machive Vision Conference, Surrey, UK, 2012: 57. 1–57.
    K?STINGER M, HIRZER M, WOHLHART P, et al. Large scale metric learning from equivalence constraints[C]. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 2288–2295.
    ZHAO Rui, OUYANG Wanli, and WANG Xiaogang. Unsupervised salience learning for person re-identification[C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013: 3586–3593.
    LI Zhen, CHANG Shiyu, LIANG Feng, et al. Learning locally-adaptive decision functions for person verification[C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013: 3610–3617.
    ZHAO Rui, OUYANG Wanli, and WANG Xiaogang. Learning mid-level filters for person re-identification[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 144–151.
    YANG Yang, YANG Jimei, YAN Junjie, et al. Salient color names for person re-identification[C]. The 13th European Conference on Computer Vision, Zurich, Switzerland, 2014: 536–551.
    LIAO Shengcai, HU Yang, ZHU Xiangyu, et al. Person re-identification by local maximal occurrence representation and metric learning[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 2197–2206.
    YI Dong, LEI Zhen, LIAO Shengcai, et al. Deep metric learning for person re-identification[C]. 2014 International Conference on Pattern Recognition, Stockholm, Sweden, 2014: 34–39.
    CHEN Shizhe, GUO Chaochun, and LAI Jianhuang. Deep ranking for person re-identification via joint representation learning[J]. IEEE Transactions on Image Processing, 2016, 25(5): 2353–2367. doi: 10.1109/TIP.2016.2545929
    WANG Jin, WANG Zheng, GAO Changxin, et al. DeepList: Learning deep features with adaptive listwise constraint for person reidentification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(3): 513–524. doi: 10.1109/tcsvt.2016.2586851
    DE CARVALHO PRATES R F and SCHWARTZ W R. CBRA: Color-based ranking aggregation for person re-identification[C]. 2015 IEEE International Conference on Image Processing, Quebec City, Canada, 2015: 1975–1979.
    SHEN Yang, LIN Weiyao, YAN Junchi, et al. Person re-identification with correspondence structure learning[C]. 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 3200–3208.
    CHEN Yingcong, ZHENG Weishi, and LAI Jianhuang. Mirror representation for modeling view-specific transform in person re-identification[C]. The 24th International Conference on Artificial Intelligence, Buenos Aires, Argentina, 2015: 3402–3408.
    YAO Wenbin, WENG Zhenyu, and ZHU Yuesheng. Diversity regularized metric learning for person re-identification[C]. 2016 IEEE International Conference on Image Processing, Phoenix, USA, 2016: 4264–4268.
    AHMED E, JONES M, and MARKS T K. An improved deep learning architecture for person re-identification[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 3908–3916.
  • 加載中
圖(3) / 表(5)
計(jì)量
  • 文章訪問數(shù):  3695
  • HTML全文瀏覽量:  1167
  • PDF下載量:  70
  • 被引次數(shù): 0
出版歷程
  • 收稿日期:  2019-03-18
  • 修回日期:  2019-05-24
  • 網(wǎng)絡(luò)出版日期:  2019-07-03
  • 刊出日期:  2020-02-19

目錄

    /

    返回文章
    返回