首页 > 论文 > 激光与光电子学进展 > 56卷 > 2期(pp:21503--1)

基于特征融合与子空间学习的行人重识别算法

Person Re-Identification Algorithm Based on Feature Fusion and Subspace Learning

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对现存行人重识别算法不能较好地适应光照、姿态、遮挡等变化的问题, 提出一种基于特征融合与子空间学习的行人重识别算法。该算法对整幅行人图像提取方向梯度(HOG)直方图特征和HSV(Hue,Saturation,Value)直方图特征作为整体特征, 再在滑动窗口内提取色彩命名(CN)特征和两个尺度的尺度不变局部三元模式(SILTP)特征。为了使算法具有更好的尺度不变性, 对原图像进行两次下采样, 再对采样后的图像提取上述特征。提取特征后, 采用核函数分别将原始特征空间转换到非线性空间, 在非线性空间内学习一个子空间, 同时在子空间内学习一个相似性度量函数。在3个公开数据集上进行了实验, 结果表明, 所提算法可以较好地提高重识别率。

Abstract

Aiming at the problem that the existing person re-identification algorithm cannot be adapted well to the variances of illumination, attitude and occlusion, a novel person re-identification algorithm based on feature fusion and subspace learning is proposed, in which the Histogram of Oriented Gradient (HOG) feature and the Hue-Saturation-Value (HSV) histogram feature are first extracted from the entire pedestrian image as the overall feature and then the Color Naming (CN) feature and the two-scale Scale Invariant Local Ternary Pattern (SILTP) feature are extracted in a sliding window. In addition, in order to make this algorithm have better scale invariance, the original images are first down-sampled twice and then the above features are extracted from the sampled images. After the features are extracted, a kernel function is used to transform the original feature space into a nonlinear space, in which a subspace is learned. Simultaneously, in this subspace, a similarity function is learned. The experiments on three public datasets are conducted and the results show that the proposed algorithm can be used to improve the re-identification rate relatively well.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/lop56.021503

所属栏目:机器视觉

基金项目:国家自然科学基金(61861037)

收稿日期:2018-07-09

修改稿日期:2018-07-30

网络出版日期:2018-08-08

作者单位    点击查看

朱小波:宁夏大学物理与电子电气工程学院, 宁夏 银川 750021宁夏大学宁夏沙漠信息智能感知重点实验室, 宁夏 银川 750021
车进:宁夏大学物理与电子电气工程学院, 宁夏 银川 750021宁夏大学宁夏沙漠信息智能感知重点实验室, 宁夏 银川 750021

联系人作者:车进(koalache@126.com)

【1】Farenzena M, Bazzani L, Perina A, et al. Person re-identification by symmetry-driven accumulation of local features[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 13-18, 2010, San Francisco. New York: IEEE, 2010: 2360-2367.

【2】Huang X Y, Xu J L, Guo G, et al. Real-time pedestrian reidentification based on enhanced aggregated channel features[J]. Laser & Optoelecronics Progress, 2017, 54(9): 091001.
黄新宇, 许娇龙, 郭纲, 等. 基于增强聚合通道特征的实时行人重识别[J]. 激光与光电子学进展, 2017, 54(9): 091001.

【3】Zhao R, Ouyang W L, Wang X G. Learning mid-level filters for person re-identification[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus. New York: IEEE, 2014: 144-151.

【4】Liu C X, Gong S G, Loy C C, et al. Person reidentification: what features are important? [C]∥Proceedings of the 12th European Conference on Computer Vision, October 7-13, 2012, Florence. Berlin: Springer, 2012: 391-401.

【5】Fan C X, Zhu H, Li G F, et al. Person re-identification based on multi-features[J]. Journal of Image and Graphics, 2013, 18(6): 711-717.
范彩霞, 朱虹, 蔺广逢, 等. 多特征融合的人体目标再识别[J]. 中国图象图形学报, 2013, 18(6): 711-717.

【6】Yuan L, Tian Z R. Person re-identification based on multi-feature fusion[J]. Pattern Recognition and Artificial Intelligence, 2017, 30(3): 269-278.
袁立, 田子茹. 基于融合特征的行人再识别方法[J]. 模式识别与人工智能, 2017, 30(3): 269-278.

【7】Zheng W S, Gong S G, Xiang T. Reidentification by relative distance comparison[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(3): 653-668.

【8】Qi M B, Hong S S, Wang Y X, et al. Multi-feature Subspace and Kernel Learning for Person Re-identification[J]. Acta Automatica Sinica, 2016, 42(2): 299-308.
齐美彬, 檀胜顺, 王运侠, 等. 基于多特征子空间与核学习的行人再识别[J]. 自动化学报, 2016, 42(2): 299-308.

【9】Xu L, Zhao H T, Sun S Y. Monocular infrared image depth estimation based on deep convolutional neural networks[J]. Acta Optica Sinica, 2016, 36(7): 0715002.
许路, 赵海涛, 孙韶媛. 基于深层卷积神经网络的单目红外图像深度估计[J]. 光学学报, 2016, 36(7): 0715002.

【10】Zheng Z D, Zheng L, Yang Y. A discriminatively learned CNN embedding for person re-identification[J]. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2018, 14(1): 13.

【11】Cheng B, Zha Y F, Li Y Q, et al. Robust Convolutional Neural Networks Feature Learning for Person Re-identification[J]. Acta Optica Sinica, 2018, 38(7): 0720002.
陈兵, 查宇飞, 李运强, 等. 基于卷积神经网络全批量学习的行人重识别[J]. 光学学报, 2018, 38(7): 0720002.

【12】Jobson D J, Rahman Z, Woodell G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing, 1997, 6(7): 965-976.

【13】Zheng W S, Gong S, Xiang T. Person re-identification by probabilistic relative distance comparison[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2011. Colorado Springs, CO, USA. New York: IEEE, 2011: 649-656.

【14】Tan F G, Huang L, Zhai C, et al. A Cross-camera pedestrian re-identification algorithm for major transport hub[J]. Journal of The China Railway Society, 2017, 39(1): 76-82.
谭飞刚, 黄玲, 翟聪, 等. 一种用于大型交通枢纽的跨摄像机行人再识别算法研究[J]. 铁道学报, 2017, 39(1): 76-82.

【15】Liao S C, Hu Y, Zhu X Y, et al. Person re-identification by local maximal occurrence representation and metric learning[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 7-12, 2015, Boston. New York: IEEE, 2015: 2197-2206.

【16】Koestinger M, Hirzer M, Wohlhart P, et al. Large scale metric learning from equivalence constraints[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 16-21, 2012, Providence. New York: IEEE, 2012: 2288-2295.

【17】Gray D, Tao H. Viewpoint invariant pedestrian recognition with an ensemble of localized features[C]∥Proceedings of the 10th European Conference on Computer Vision, October 12-18, 2008, Marseille. Berlin: Springer, 2008, 5302: 262-275.

【18】Zheng W S, Gong S G, Xiang T. Associating groups of people[C]∥Proceedings of the 20th British Machine Vision Conference, September 7-10, 2009, London. New York: IEEE, 2009: 1-11.

【19】Baltieri D, Vezzani R, Cucchiara R. 3DPeS: 3D people dataset for surveillance and forensics[C]∥Proceedings of the 2011 Joint ACM Workshop on Human Gesture and Behavior Understanding, December 01, 2011, Scottsdale. New York: ACM, 2011: 59-64.

【20】Tian Z R, Wang H Y, Chen F H, et al. Person re-identification based on distance centralization and projection vectors learning[J]. Journal of Computer Research and Development, 2017, 54(8): 1785-1794.
丁宗元, 王洪元, 陈付华, 等. 基于距离中心化与投影向量学习的行人重识别[J]. 计算机研究与发展, 2017, 54(8): 1785-1794.

【21】Mignon A, Jurie F. Pcca: A new approach for distance learning from sparse pairwise constraints[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 16-21, 2012, Providence. New York: IEEE, 2012: 2666-2672.

【22】Pedagadi S, Orwell J, Velastin S, et al. Local fisher discriminant analysis for pedestrian reidentification[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 25-27, 2013, Portland. New York: IEEE, 2013: 3318-3325.

【23】Li Z, Chang S Y, Liang F, et al. Learning locally-adaptive decision functions for person verification[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2013, Portland. New York: IEEE, 2013: 3610-3617.

引用该论文

Zhu Xiaobo,Che Jin. Person Re-Identification Algorithm Based on Feature Fusion and Subspace Learning[J]. Laser & Optoelectronics Progress, 2019, 56(2): 021503

朱小波,车进. 基于特征融合与子空间学习的行人重识别算法[J]. 激光与光电子学进展, 2019, 56(2): 021503

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF