基于支持樣本間接式的行人再識別

孫銳; 方蔚; 黃啟恒; 高雋

doi:10.11999/JEIT170215

基于支持樣本間接式的行人再識別

doi: 10.11999/JEIT170215

基金項(xiàng)目:

國家自然科學(xué)基金(61471154)，安徽省科技攻關(guān)科技強(qiáng)警項(xiàng)目(170d0802181)

計(jì)量
- 文章訪問數(shù): 987
- HTML全文瀏覽量: 145
- PDF下載量: 282
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-03-17
- 修回日期: 2017-09-15
- 刊出日期: 2017-12-19

Indirect Person Re-identification Based on Support Samples

Funds:

The National Natural Science Foundation of China (61471154), Anhui Province Science and Technology Research (170d0802181)

摘要

摘要: 行人再識別就是在無重疊視域多攝像機(jī)監(jiān)控系統(tǒng)中，識別出相同的行人。針對來自于不同攝像頭行人圖片存在著視角、光照和尺度變化的問題。該文提出了基于支持樣本間接式匹配的行人再識別方法。該算法首先通過聚類的方法分別提取不同攝像頭下的支持樣本，當(dāng)要對來自不同攝像頭的行人進(jìn)行匹配時，在距離測度的基礎(chǔ)上利用支持樣本分別判別出其所在攝像頭下的行人類別，通過類別的對比判斷是否為同一行人。該方法避免了不同攝像頭下行人圖片直接匹配，有效解決不同攝像頭帶來的視角、光照和尺度問題。實(shí)驗(yàn)結(jié)果表明該文的算法相比一些經(jīng)典算法識別率有一定的提高，并且在數(shù)據(jù)集VIPeR, CAVIAR4ReID和CUHK01上，Rank1分別達(dá)到了43.60%, 41.36%, 43.82%。
- 行人再識別 /
- 支持樣本 /
- 間接匹配
Abstract: Person re-identification is the identification of the same pedestrian in a multi camera surveillance without overlapping views. Aiming at the problem of the existence of visual angle, illumination and scale change in pedestrian images which from different camera. An indirect person re-identification method is proposed based on the support samples. At first, the algorithm extracts the support samples from different cameras by the clustering method. When it comes to matching pedestrians from different cameras, the support samples are used to distinguish the pedestrians categories under the camera on the basis of the distance metric, by comparing the categories to determine whether the same pedestrian. The method avoids the direct matching of pedestrian images under different cameras, which effectively solve the problem of the existence of visual angle, illumination and scale change in different camera. The experimental results show that the algorithm has a high recognition rate, and on the data set VIPeR, CAVIAR4ReID and CUHK01the, Rank1 reaches 43.60%, 41.36% and 43.82% respectively.
- Person re-identification /
- Support samples /
- Indirect matching

HTML全文

參考文獻(xiàn)(31)

ZHAO R, OUYANG W L, WANG X G, et al. Person Re-identification by Salience Matching[C]. IEEE International Conference on Computer Vision, Sydney, Australia, 2013: 2528-2535. doi: 10.1109/ICCV.2013.314.

DORETTO G, SEBATIAN T, TU P, et al. Appearance- based person re-identification in camera networks: Problem overview and current approaches[J]. Journal of Ambient Intelligence and Humanized Computing, 2011, 2(2): 127-151. doi: 10.1007/s12652-010-0034-y.

齊美彬, 顫勝順, 王運(yùn)俠, 等. 基于多特征子空間與核學(xué)習(xí)的行人再識別[J]. 自動化學(xué)報, 2016, 42(2): 299-308. doi: 10.16383/i.aas.2016.c150344.

QI Meibin, TAN Shengshun, WANG Yunxia, et al. Multi- feature subspace and kernel learning for person re- identification[J]. Acta Automatica Sinica, 2016, 42(2): 299-308. doi: 10.16383/i.aas.2016.c150344.

ZHAO Rui, OUYANG Wanli, and WANG Xiaogang. Person re-identification by saliency learning[J]. IEEE Transations on Pattern Analysis and Machine Intelligence, 2017, 39(2): 356-370. doi: 10.1109/TPAMI.2016.2544310.

XIAO Tong, LI Hongsheng, OUYANG Wanli, et al. Recurrent convolutional network for vidieo-baesd person re-identification[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, US, 2016: 1325-1334. doi: 10.1109/CVPR.2016.148.

SUN Chong, WANG Dong, and LU Huchaun. Person re-identification via distance metric learning with latent variables[J]. IEEE Transactions on Image Processing, 2017, 26(1): 23-34. doi: 10.1109/TIP.2016.2619261.

SATHISH P K and BALAJI S. Person re-identification using part based hybrid descriptor[C]. 2016 Second International Conference on Cognitive Computing and Information Processing, Mysuru, India, 2016: 1-4. doi: 10.1109/CCIP. 2016.7802849.

GAO Bin, ZENG Mingyong, and XU Shiming. Person re- identtification with discriminatively trained viewpoint invariant orthogonal dictionaries[J]. Electronics Letters, 2016, 52(23): 1914-1916. doi: 10.1049/el.2016.2639.

ZHENG Liang, WANG Shengjin, TIAN Lu, et al. Scalar person re-identification: A benchmark[C]. IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1116-1124. doi: 10.1109/ICCV.2015.133.

WANG Taiqing, GONG Shaogang, ZHU Xiatian, et al. Person re-identification by discriminative selection in video ranking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(12): 2501-2514. doi: 10.1109/ TPAMI.2016.2522418.

GRAY D and TAO H. Viewpoint invariant pedestrian recognition with an ensemble of localized features[C]. European Conference on Computer Vision, Marseille France, 2008: 262-275. doi: 10.1007/978-3-540-88682-2_21.

YANG Y, YANG J, YAN J, et al. Salientcolor names for person re-identification[C]. European Conference on Computer Vision, Zurich, 2014: 536-550. doi: 10.1007/978- 3-319-10590-1_35.

FARENZENA M, BAZZANI L, PERINA A, et al. Person re-identification by symmetry-driven accumulation of local features[C]. 2010 IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, USA, 2010: 2360-2367. doi: 10.1109/CVPR.2010.5539936.

MA B, SU Y, and JURIE F. Local descriptors encoded by fisher vectors for person re-identification[C]. European Conference on Computer Vision, Firence, Italy, 2012: 413-422. doi: 10.1007/978-3-642-33863-2_41.

LIAO S C, HU Y, ZHU X Y, et al. Person re-identification by local maximal occurrence representation and metric learning [C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 2015: 2197-2206. doi: 10.1109/CVPR.2015. 7298832.

KOSTINGER M, HIRZER M, WOHLHART P, et al. Large scale metric learning from equivalence constraints[C]. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Rhode, Island, 2012: 2288-2295. doi: 10.1109/ CVPR.2012.6247939.

PROSSER B, ZHNEG W S, GONG S, et al. Person reidentification by support vector ranking[C]. British Machine Vision Conference, Aberystwyth, UK, 2010: 21.1-21.11. doi: 10.5244/C.24.21.

TAO D, JIN L, WANG Y, et al. Person reidentification by regularized smoothing kiss metric learning[J]. IEEE Transaction on Circuit and Systems for Video Technology, 2013, 23(10): 1675-1685. doi: 10.1109/ TCSVT.2013.225413.

AHMED E, JONES M, and MARKS T K. An improved deep learning architecture for person re-identification[C]. 2015 IEEE Conference on Computer Visionand Pattern Recognition, Boston, USA, 2015: 3908-3916. doi: 10.1109/ CVPR.2015.7299016.

LI W, ZHAO R, XIAO T, et al. DeepReID: Deep filter pairing neural network for person re-identification[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 152-159. doi: 10.1109/ CVPR.2014.27.

ZHENG Liang, WANG Shenjin, WANG Jingdong, et al. Accurate image search with multi-scalar contextual evidences [J]. International Journal of Computer Vision, 2016, 120(1): 1-13. doi: 10.1007/s11263-016-0889-2.

CHENG D S, CRISTANI M, STOPPA M, et al. Custom pictorial structures for re-identification[C]. British Machine Vision Conference, Scotland, UK, 2011: 68.1-68.11. doi: 10.5244/C.25.68.

LI Z, CHANG S Y, LIANG F, 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. doi: 10.1109/CVPR.2013. 463.

ZHAO R, OUYANG W L, and WANG X G. Unsupervised salience learning for person re-identification[C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013: 3586-3593. doi: 10.1109/CVPR.2013. 460.

ZHENG W S, GONG S G, and XIANG T. Person re-identification by probabilistic relative distance comparison [C]. 2011 IEEE Conference on Computer Vision and Pattern Recognition. Conneticut, USA, 2011: 649-656. doi: 10.1109/ CVPR.2011.5995598.

XIAO Tong, LI Hongsheng, OUYANG wanly, et al. Learning deep feature representations with domain guided dropout for person re-identification[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 2016: 1249-1258. doi: 10.1109/CVPR.2016. 140.

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, Rhode, Island, 2012: 2666-2672. doi: 10.1109/ CVPR.2012.6247987.

PEDAGADI S, ORWELL J, VELASTIN S, et al. Local fisher discriminant analysis for pedestrian Re-identification[C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013: 3318-3325. doi: 10.1109/ CVPR.2013.426.

ZHAO R, OUYANG W L, and WANG X G. Learning mid-level filters for person re-identification[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 144-151. doi: 10.1109/CVPR.2014.26.

XIONG F, GOU M R, CAMPS O, et al. Person re-identification using kernel-based metric learning methods [C]. European Conference on Computer Vision, Zurich, Switzerland, 2014: 1-16. doi: 10.1007/978-3-319- 10584-0_1.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)