计算机应用 ›› 2016, Vol. 36 ›› Issue (9): 2550-2554.DOI: 10.11772/j.issn.1001-9081.2016.09.2550
收稿日期:
2016-03-03
修回日期:
2016-04-28
出版日期:
2016-09-10
发布日期:
2016-09-08
通讯作者:
杨超
作者简介:
蔡晓东(1971-),男,广西桂林人,教授,博士,主要研究方向:并行化图像和视频处理、模式识别与智能系统、基于云架构的智能传感器网络;杨超(1990-),男,四川南充人,硕士研究生,主要研究方向:并行化视频及图像处理、模式识别;王丽娟(1991-),女,安徽芜湖人,硕士研究生,主要研究方向:数据挖掘、模式识别;甘凯今(1992-),男,广西贵港人,硕士研究生,主要研究方向:并行化视频及图像处理、模式识别。
基金资助:
CAI Xiaodong, YANG Chao, WANG Lijuan, GAN Kaijin
Received:
2016-03-03
Revised:
2016-04-28
Online:
2016-09-10
Published:
2016-09-08
Supported by:
摘要: 找到能减小类内距离、增大类间距离的特征表示方法是行人识别的一个挑战。提出一种基于行人验证和识别相融合的深度网络模型来解决这一问题。首先,识别监督学习网络模型增加不同个人的类间间距,验证监督学习网络模型减少同一个行人的类内间距;然后,将行人验证和识别的深度网络融合,提取到更有分辨能力的行人特征向量;最后,采用了联合贝叶斯的行人比对方法,通过监督学习排名的方式,提高行人比对的准确率。实验结果表明,所提方法在VIPeR库上同其他深度网络相比有较高的识别准确率,融合网络与单独的识别和验证网络相比有更高的收敛速度和识别准确率。
中图分类号:
蔡晓东, 杨超, 王丽娟, 甘凯今. 验证和识别相融合的深度行人识别网络[J]. 计算机应用, 2016, 36(9): 2550-2554.
CAI Xiaodong, YANG Chao, WANG Lijuan, GAN Kaijin. Deep network for person identification based on joint identification-verification[J]. Journal of Computer Applications, 2016, 36(9): 2550-2554.
[1] ZHENG W S, GONG S, XIANG T. Person re-identification by probabilistic relative distance comparison [C]// CVPR '11: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2011: 649-656. [2] SATTA R, FUMERA G, ROLI F, et al. A multiple component matching framework for person re-identification [C]// MAINO G, FORESTI G L. Image Analysis and Processing—ICIAP 2011, LNCS 6979. Berlin: Springer, 2011: 140-149. [3] LIU C, GONG S, CHEN C L, et al. Person re-identification: what features are important? [C]// ECCV '12: Proceedings of the 12th International Conference on Computer Vision. Berlin: Springer, 2012: 391-401. [4] SCHVGERL P, SORSCHAG R, BAILER W, et al. Object re-detection using SIFT and MPEG-7 color descriptors [C]// MCAM 2007: Proceedings of the 2007 International Workshop Multimedia Content Analysis and Mining, LNCS 4577. Berlin: Springer, 2007: 305-314. [5] WANG X, DORETTO G, SEBASTIAN T, et al. Shape and appearance context modeling [C]// ICCV 2007: Proceedings of the 2007 IEEE 11th International Conference on Computer Vision. Washington, DC: IEEE Computer Society, 2007: 1-8. [6] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [EB/OL]. [2015-10-27]. https://datajobs.com/data-science-repo/ImageNet-Neural-Net-%5bHinton-et-al%5d.pdf. [7] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [C]// CVPR 2014: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2014: 580-587. [8] SUN Y, WANG X, TANG X. Deep learning face representation by joint identification-verification [EB/OL]. [2016-01-03]. http://www.ee.cuhk.edu.hk/~xgwang/papers/sunWTarxiv14.pdf. [9] CHEN D, CAO X, WANG L, et al. Bayesian face revisited: a joint formulation [M]// FITZGIBBON A, LAZEBNIK S, PERONA P, et al. Computer Vision—ECCV 2012, LNCS 7574. Berlin: Springer, 2012: 566-579. [10] TOSHEV A, SZEGEDY C. DeepPose: human pose estimation via deep neural networks [C]// CVPR 2014: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2013: 1653-1660. [11] AHMED E, JONES M, MARKS T K. An improved deep learning architecture for person re-identification [C]// CVPR 2015: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2015: 3908-3916. [12] BROMLEY J, BENTZ J W, BOTTOU L, et al. Signature verification using a "siamese" time delay neural network [EB/OL]. [2015-11-16]. http://papers.nips.cc/paper/769-signature-verification-using-a.pdf. [13] YI D, LEI Z, LIAO S, et al. Deep metric learning for person re-identification [C]// ICPR '14: Proceedings of the 2014 22nd International Conference on Pattern Recognition. Washington, DC: IEEE Computer Society, 2014: 34-39. [14] YI D, LEI Z, LI S Z, et al. Deep metric learning for practical person re-identification [EB/OL]. [2015-11-23]. http://xueshu.baidu.com/s?wd=paperuri%3A%2869b67efb26b657d43e6d3bbf4e2a05d4%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Fde.arxiv.org%2Fpdf%2F1407.4979&ie=utf-8&sc_us=8632976325773889661. [15] HU W, HU M, ZHOU X, et al. Principal axis-based correspondence between multiple cameras for people tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006, 28(4): 663-671. [16] GRAY D, TAO H. Viewpoint invariant pedestrian recognition with an ensemble of localized features [C]// ECCV '08: Proceedings of the 2008 10th European Conference on Computer Vision. Berlin: Springer, 2008: 262-275. [17] KE Y, SUKTHANKAR R. PCA-SIFT: a more distinctive representation for local image descriptors [EB/OL]. [2015-11-16]. http://www-cgi.cs.cmu.edu/afs/cs.cmu.edu/user/rahuls/www/pub/irp-tr-03-15-rahuls.pdf. |
[1] | 章悦, 张亮, 谢非, 杨嘉乐, 张瑞, 刘益剑. 基于实例分割模型优化的道路抛洒物检测算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3228-3233. |
[2] | 孙琳, 袁玉波. 基于人眼状态的瞌睡识别算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3213-3218. |
[3] | 葛晨宇, 董良, 许伊昆, 常毅, 张宏鸣. 基于总变分低秩组稀疏的全球雷达数据修复算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3353-3361. |
[4] | 闫钧华, 侯平, 张寅, 吕向阳, 马越, 王高飞. 基于多尺度多分类器卷积神经网络的混合失真类型判定方法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3178-3184. |
[5] | 李福海, 蒋慕蓉, 杨磊, 谌俊毅. 基于生成对抗网络的梯度引导太阳斑点图像去模糊方法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3345-3352. |
[6] | 曹建芳, 闫敏敏, 贾一鸣, 田晓东. 融合迁移学习的Inception-v3模型在古壁画朝代识别中的应用[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3219-3227. |
[7] | 谌贵辉, 刘会康, 李忠兵, 彭娇, 汪少天, 林瑾瑜. 基于仲裁机制的生成对抗网络改进算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3185-3191. |
[8] | 杨鼎康 黄帅 王顺利 翟鹏 李一丹 张立华. 基于对抗生成网络和网络集成的面部表情识别方法EE-GAN[J]. 计算机应用, 0, (): 0-0. |
[9] | 秦庭威 赵鹏程 秦品乐 曾建朝 柴锐 黄永琦. 基于残差注意力机制的点云配准算法[J]. 计算机应用, 0, (): 0-0. |
[10] | 裴仪瑶, 郭会明, 张丹普, 陈文博. 基于定位不确定性的鲁棒3D目标检测方法[J]. 计算机应用, 2021, 41(10): 2979-2984. |
[11] | 许学斌, 张佳达, 刘伟, 路龙宾, 赵雨晴. 融合空间和通道特征的高精度乳腺癌分类方法[J]. 计算机应用, 2021, 41(10): 3025-3032. |
[12] | 魏淳武, 赵涓涓, 唐笑先, 强彦. 基于多时期蒸馏网络的随访数据知识提取方法[J]. 计算机应用, 2021, 41(10): 2871-2878. |
[13] | 李自强, 王正勇, 陈洪刚, 李林怡, 何小海. 基于外观和动作特征双预测模型的视频异常行为检测[J]. 计算机应用, 2021, 41(10): 2997-3003. |
[14] | 汪虹余, 张彧, 杨恒, 穆楠. 基于蚁群优化算法的弱光图像显著性目标检测[J]. 计算机应用, 2021, 41(10): 2970-2978. |
[15] | 张怡 孙永荣 赵科东 李华 曾庆化. 空中加油场景下的目标联合检测跟踪算法[J]. 计算机应用, 0, (): 0-0. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||