基于无监督方法的视频中的人物识别

doi:10.3969/j.issn.1006-2475.2014.12.011

计算机与现代化

基于无监督方法的视频中的人物识别

(南京理工大学计算机科学与工程学院，江苏南京 210094)

收稿日期:2014-09-28 出版日期:2014-12-22 发布日期:2014-12-22
作者简介:宁波（1988-），男，安徽合肥人，南京理工大学计算机科学与工程学院硕士研究生，研究方向：计算机视频图像处理; 宋砚（1983-），女，讲师，硕士生导师，博士，中国计算机学会(CCF)会员，研究方向：图像和视频内容的分析及理解。

Person Recognition in Video Based on Unsupervised Method

(School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China)

Received:2014-09-28 Online:2014-12-22 Published:2014-12-22

摘要/Abstract

摘要： 基于无监督的显著性学习方法提出一种新颖的人物识别方法。它在训练程序部分不需要身份标签就能提取出突出的特征。首先利用相邻约束斑块匹配在图片对之间构建稠密对应。该方法在处理由于较大的视觉角度变化和人物姿势变化而引起的图片对之间不对应的情况非常有效。其次，它应用一种无监督的方法来学习人物的显著性。为了提高实验的性能，在斑块匹配过程中融合了这种人物的显著性特征。在VIPeR数据集上进行的实验证实了该方法的正确性，且性能略优于文献中提出的eBiCov方法及eLDFV方法。

关键词: 图像处理, 无监督学习, 人物识别, 显著性

Abstract: In this paper, we propose a novel method for person recognition based on a salient learning with unsupervised. The salient features can be extracted without the person labels in the training procedure. First, we utilize patch matching with adjacency constrained to create dense correspondence between image pairs and it shows validity in processing misalignment problem caused by larger viewpoint and pose changes. Second, we learn person salience by applying an unsupervised approach. In order to improve the performance of experiment, the person salience is combined with patch matching. This approach on the VIPeR dataset is proved the effect is validated. And the performance is better than the eBiCov method and the eLDFV method.

Key words: image processing, unsupervised learning, person recognition, signification

中图分类号:

TP391

宁波，宋砚. 基于无监督方法的视频中的人物识别[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2014.12.011.

NING Bo, SONG Yan. Person Recognition in Video Based on Unsupervised Method[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2014.12.011.

参考文献

[1] Dikmen M, Akbas E, Huang T, et al. Pedestrian recognition with a learned metric[C]// Proceedings of the 2010 Asian Conference on Computer Vision. 2011:501-512.

[2] Prosser B, Zheng Weishi, Gong Shaogang, et al. Person re-identification by support vector ranking[C]// Proceedings of the 2010 British Machine Vision Conference. 2010: Article Number 21.

[3] Hirzer M, Roth P, Kostinger M, et al. Relaxed pairwise learned metric for person re-identification[C]// Proceedings of the 2012 European Conference on Computer Vision. 2012:780-793.

[4] Gray D, Tao Hai. Viewpoint invariant pedestrian recognition with an ensemble of localized features[C]// Proceedings of the 2008 European Conference on Computer Vision. 2008:262-275.

[5] Schwartz W, Davis L. Learning discriminative appearance-based models using partial least squares[C]// Proceedings of the 12th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI). 2009:322-329.

[6] Farenzena M, Bazzani L, Perina A, et al. Person re-identification by symmetry-driven accumulation of local features[C]// Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition. 2010:2360-2367.

[7] Ma Bingpeng, Su Yu, Jurie F. BiCov: A novel image representation for person re-identification and face verification[C]// Proceedings of the 2012 British Machine Vision Conference. 2012:231-239.

[8] Cheng D, Cristani M, Stoppa M, et al. Custom pictorial structures for re-identification[C]// Proceedings of the 2011 British Machine Vision Conference. 2011: Article Number 68.

[9] Liu Ce, Yuen J, Torralba A. Sift flow: Dense correspondence across scenes and its applications[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33(5):978-994.

[10] Ma Kai, Ben-Arie J. Vector array based multi-view face detection with compound exemplars[C]// Proceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition. 2012:3186-3193.

[11] Barnes C, Shechtman E, Finkelstein A, et al. PatchMatch: A randomized correspondence algorithm for structural image editing[J]. ACM Transactions on Graphics, 2009,28(3):534-542.

[12] Barnes C, Shechtman E, Goldman D, et al. The generalized patchMatch correspondence algorithm[C]// Proceedings of the 2010 European Conference on Computer Vision. 2010:29-43.

[13] Byers S, Raftery A. Nearest-neighbor clutter removal for estimating features in spatial point processes[J]. Journal of the American Statistical Association, 1998,93(442):577-584.

[14] Ma Bingpeng, Su Yu, Jurie F. Local descriptors encoded by Fisher vectors for person re-identification[C]// Proceedings of the 1st International Workshop on Re-identification. 2012:413-422.

[1]	叶力鸣, 陈蔚文. 一种结合语义分割和目标检测的级联式绝缘子缺陷检测方法[J]. 计算机与现代化, 2023, 0(06): 82-88.
[2]	刘志飞, 朱尚超, 魏战红, 臧一鸣, 孙文韬, 胡冠时. 基于IBM Qiskit的量子图像伪彩色增强方法[J]. 计算机与现代化, 2023, 0(04): 47-55.
[3]	朱卓樾, 黄欢, 宋清玲, 侯居攀. 基于心血管核磁共振图像的房室平面位移检测与重建[J]. 计算机与现代化, 2023, 0(04): 78-82.
[4]	李四杰, 唐清善, 高英华. 基于GMS和改进最佳缝合线的视差图像拼接算法[J]. 计算机与现代化, 2022, 0(12): 95-101.
[5]	丁婉莹, 陈伟, 李昭慧. 基于编解码结构的多特征融合眼底图像分割[J]. 计算机与现代化, 2022, 0(07): 1-7.
[6]	周璇, 朱苏磊, 何为. 基于显著性目标检测的弹着点定位算法[J]. 计算机与现代化, 2022, 0(01): 54-60.
[7]	文雅宏, 巨琛. 基于背景评估的贝叶斯模型显著性检测[J]. 计算机与现代化, 2021, 0(10): 63-68.
[8]	魏计鹏, 秦国峰. 基于深度图像增益的RGB-D显著性物体检测[J]. 计算机与现代化, 2021, 0(05): 26-30.
[9]	金安安, 丁双双, 熊卿智, 许婷婷, 习淑萍, 马继忠. 基于SWOMP算法的EPMA影像优化重构[J]. 计算机与现代化, 2020, 0(12): 104-111.
[10]	冯洋. 基于小波包变换的红外弱小目标检测[J]. 计算机与现代化, 2020, 0(12): 112-115.
[11]	张辉, 余厚云, 李克斌. 基于机械臂的涡轮壳零件表面质量视觉检测[J]. 计算机与现代化, 2020, 0(07): 121-126.
[12]	付磊,任德均,胡云起,郜明,邱吕. 基于ResNet网络的医用塑瓶制造缺陷检测方法[J]. 计算机与现代化, 2020, 0(04): 104-.
[13]	卢爱平，李盼池. 基于混沌序列的量子图像加密方案[J]. 计算机与现代化, 2020, 0(03): 86-.
[14]	买尔孜燕古丽·阿不都拉，冯向萍. 基于机器视觉的非接触式马体尺测量方法[J]. 计算机与现代化, 2019, 0(10): 108-.
[15]	纪超，黄新波，曹雯，朱永灿，张烨 . 改进的Fast-CNN模型在绝缘子特征检测中的研究[J]. 计算机与现代化, 2019, 0(04): 59-.

基于无监督方法的视频中的人物识别

Person Recognition in Video Based on Unsupervised Method

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价