基于部位分割的人体再识别方法

doi:10.16182/j.issn1004731x.joss.17-0180

系统仿真学报 ›› 2019, Vol. 31 ›› Issue (6): 1085-1091.doi: 10.16182/j.issn1004731x.joss.17-0180

基于部位分割的人体再识别方法

姜华, 张良^*

中国民航大学智能信号与图像处理天津市重点实验室,天津 300300

收稿日期:2017-04-20 修回日期:2017-06-24 出版日期:2019-06-08 发布日期:2019-12-12
作者简介:姜华(1991-),男,安徽宣城,硕士生,研究方向为视频内容分析;张良(1970-),男,山东,博士,教授,研究方向为图像处理与模式识别、智能视频监控。
基金资助:
国家自然科学基金(61179045)

Human Re-identification Based on Part Segmentation

Jiang Hua, Zhang Liang^*

Tianjin Key Lab of Advanced Signal Processing, Civil Aviation University of China, Tianjin 300300, China

Received:2017-04-20 Revised:2017-06-24 Online:2019-06-08 Published:2019-12-12

摘要/Abstract

摘要： 人体再识别是非重叠视域多摄像机视频分析过程中需解决的难点问题。提出一种基于部位分割的人体再识别方法,首先基于深度骨骼点实现人体部位分割,对同一人体多帧图像分割后的所有部位使用评分的策略选择最优帧,将全局颜色特征和HOG特征分配不同的权重,融合特征建立人体目标模型,使用EMD(Earth Move’s Distance)距离度量目标间的相似性。在Kinect REID和BIWI RGBD-ID数据库上实验表明,该算法具有较高的鲁棒性和识别率。

关键词: 人体再识别, 部位分割, 深度信息, 颜色特征, HOG特征

Abstract: Human re-identification is a difficult problem to solve in process of video analysis of non-overlapping multi-camera surveillance system. A new algorithm of human re-identification is proposed on the basis of human part segmentation. Based on the depth of bone points to achieve the human body segmentation, the optimal key frame is selected by using the scoring strategy for all parts of the same human multi-frame image segmentation; the different weights for the global color feature and the HOG feature are assigned; all the characteristics to establish a human target model are combined; and the EMD (Earth Mover’s Distance) distance is used to determine the similarity between the targets. The effectiveness is validated on Kinect REID and BIWI RGBD-ID datasets which show that the proposed method has strong robustness and higher recognition rate.

Key words: person re-identification, human segmentation, depth information, color characteristics, HOG characteristics

中图分类号:

TP391

姜华, 张良. 基于部位分割的人体再识别方法[J]. 系统仿真学报, 2019, 31(6): 1085-1091.

Jiang Hua, Zhang Liang. Human Re-identification Based on Part Segmentation[J]. Journal of System Simulation, 2019, 31(6): 1085-1091.

参考文献

[1] Farenzena M, Bazzani L, Perina A, et al.Person re-identification by symmetry-driven accumulation of localfeatures[C]//Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010: 2360-2367.
[2] Liu Chunxiao, Gong Shaogang, Loy Change Chen, et al.Person re-identification: what features are important[C]// European Conference on Computer Vision. Heidelberg, Springer-Verlag Berlin, 2012: 391-401.
[3] 黄凯奇, 陈晓棠, 康运锋, 等. 智能视频监控技术综述[J]. 计算机学报, 2015, 38(6): 1093-1118.
Huang Kaiqi, Chen Xiaotang, Kang Yunfeng, et al.Survey of Intelligent Video Surveillance Technology[J] Journal of Computer Science, 2015, 38(6): 1093-1118.
[4] A Alahi, P Vandergheynst, M Bierlaire, et al.Cascade of descriptors to detect and track objects across any network of cameras[J]. Computer Vision and Image Understanding (S1077-3142), 2010, 114(6): 624-640.
[5] A Alahi, D Marimon, M Bierlaire, et al.A master-slave approach for object detection and matching with fixed and mobie cramera[C]// Image Processing, ICIP 2008. 15^th IEEE International Conference on. Piscataway: NJ, 2008: 1712-1715.
[6] S Bak, E Corvee, F Bremond, et al.Person re-identification using spatial covariance regions of human body parts[C]// 7^th IEEE International Conference on Advanced Video and Signal-Based Surveillance. Piscataway:NJ, 2010: 435-440.
[7] Jamie Shotton, Andrew Fitzgibbon, Mat Cook, et al.Real-Time Pose Recognition in Parts from Single Depth Images[C]//2011, IEEE, 10.1109/CVPR.2011.5995316.
[8] Arun R, Madhu S, Nair, et al. An Alpha Rooting Based Hybrid Technique for Image Enhancement[J]. Engineering Letters, 2011, 19(3): 159-168.
[9] Aibing Rao, Rhhini K, Srihari, et al. Spatial color histograms for content-based image retrieval[C]// Proceeding of IEEE International Conference on Tools with Artificial Intelligence. IEEE International Conference on Tools with Artificial Intelligence, 1999: 183-186.
[10] N Dalal, B Triggs.Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition, 2005 CVPR, IEEE Computer Society Conference on Rockcourt, 2005: 886-893.
[11] Anthony Y Fu, Liu Wenyin, Xiaotie Deng, et al.Detecting Phishing Web Pages with Visual Similarity Assessment Based on Earth Mover’s Distance (EMD)[J]. IEEE Transactions on Dependable & Secure Computing, 2006, 3(4): 301-311.
[12] Bolle R. M., Connell J. H., Pankanti S., Ratha N. K., & Senior A. W. (2005). The Relation between the ROC Curve and the CMC. IEEE Workshop on Automatic Identification Advanced Technologies.
[13] Federico Pala, Riccardo Satta, Giorgio Fumera, et al.Multimodal Person Reidentification Using RGB-D Cameras[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2016, 26(4):788-799.
[14] Zeynab Imani, Hadi Soltanizadeh, Person Reidentification Using Local Pattern Descriptors and Anthropometric Measures from Videos of Kinect Sensor[J]. IEEE Sensors Journal, 2016, 16(16): 6227-6238.
[15] Wu Ancong, Zheng Weishi, Lai Jianhuang.Depth-based Person Re-identification[C]. 2015 IAPP Asian Conference on Pattern Recognition, IEEE Transactions on Image Processing, 2015: 26-30.
[16] Matteo Munaro, Alberto Basso, Andrea Fossati, et al.3D Reconstruction of Freely Moving Persons for Re-Identification with a Depth Sensor[C]. 2014 IEEE International Conference on Robotics & Automation (ICRA), Piscataway: NJ, 2014: 4512-4519.
[17] Munaro M, Fossati A, Basso A, et al.One-Shot Person Re-identification with a Consumer Depth Camera[M]. Berlin: German, Person Re-Identification, 2014: 161-181.

基于部位分割的人体再识别方法

Human Re-identification Based on Part Segmentation

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	王远明, 张珺, 秦远辉, 柴秀娟. 基于多特征融合的指挥手势识别方法研究[J]. 系统仿真学报, 2019, 31(2): 346-352.
[2]	黎明, 彭秀姣, 王艳. 基于改进的字典学习与稀疏表示的人脸表情识别[J]. 系统仿真学报, 2018, 30(1): 28-36.
[3]	毛雁明, 章立亮. 基于Kinect深度信息的手势分割与识别[J]. 系统仿真学报, 2015, 27(4): 830-835.