胡海峰

副教授

联系方式huhaif@mail.sysu.edu.cn

      胡海峰,博士生导师。2004年6月获中山大学博士学位,卡内基梅隆大学访问学者。近年来一直从事计算机视觉、模式识别、人工智能、机器学习等方面研究,对人脸识别、步态识别、动作识别、海量视频分析、图像描述、行人再标识等进行深入的研究。研究成果发表在IEEE汇刊, Pattern Recognition, Computer Vision and Image Understanding, Pattern Recognition Letters, 以及IET Computer Vision 等国际知名学术刊物上,SCI论文引用超过200多次。主持三项国家级和两项省级重点课题,参与多个国家级重大科技项目。

学术兼职和社会服务: 

【社会服务】

  • 国家自然科学基金评审人
  • 2012年-2015年中国生物识别大会程序委员会委员
  • IEEE会员
  • 首届全国研究生智慧城市技术与创意设计大赛“优秀指导教师”
  • 人工智能学会模式识别专委会委员
  • 计算机视觉专委会委员
  • TPAMI, TIP, TNNLS, TCSVT,TIFS以及PR等国际权威刊物审稿人
教育经历: 

【学习经历】

  • 1995年9月—1999 年7月,中山大学,自动控制专业,学士
  • 1999年9月—2004 年6月,中山大学,硕博连读,通信与信息系统专业,博士

研究工作经历

  • 2015年12月—现在,中山大学电子与信息工程学院,副教授
  • 2009年10月—2010年10月,美国卡内基梅隆大学机器人研究所进行学术交流

 

    授课课程: 

     数字图像处理、计算机视觉、模式识别、现代数字信号处理、概率论与数理统计

    研究方向: 

    计算机视觉、模式识别、人工智能、机器学习、大数据分析

    科研项目: 
    • 基于图像集人脸识别关键技术研究,国家自然科学基金面上项目(61673402),2017.1–2020.12,62万,主持
    • 非限制环境下人脸识别关键技术研究,国家自然科学基金面上项目(61273270),2013.1–2016.12,80万,主持
    • 人脸图像特征抽取及分类器设计若干问题研究,国家自然科学基金(60802069),2009.1–2011.12,18万,主持
    • 跨年龄人脸识别关键技术研究,广东省自然科学基金重点项目(2017A030311029),2017-2020, 50万,主持
    • 面向真实环境的四维人脸识别若干关键技术研究,广东省自然科学基金面上项目(2014A030313173),2015.1–2017.12,10万,主持
    • 基于身份识别的智能移动警务执法仪关键技术研究及示范应用,广州市产学研协同创新重大专项,2017.4-2019.4,100万,主持
    • 基于移动互联网的法定证件照片社会化采集检测处理与检索管理平台,广东省前沿与关键技术创新专项,2016.1-2017.12,500万,校方主持人
    • 面向智慧安防的网格化人脸轨迹分析关键技术及系统实现,广州市产学研协同创新重大专项,2016.4-2017.12,100万,校方主持人
    • 低分辨率视频监控环境下可变光照人脸识别关键技术及其系统实现,广州市科技计划(20143500042050476),2014.9-2015.12,30万,主持
    • 面向监控环境的海量视频搜索若干关键技术研究,广东顺德中山大学卡内基梅隆大学国际联合研究院自由申请项目(20150203),2015.1–2016.12,50万,主持
    代表性科研成果: 

    【部分发表论文】

    • Jianquan Gu, Haifeng Hu (通讯作者), Haoxi Li, Local Robust Sparse Representation for Face Recognition with Single Sample per Person, IEEE/CAA Journal of Automatica Sinica (JAS), Vol. 5, No.2, pp. 547- 554, 2018
    • Siyue Xie, Haifeng Hu (通讯作者), Ziyu Yin, Facial Expression Recognition Using Intra-class Variation Reduced Features and Manifold Regularization Dictionary Pair Learning, IET Computer Vision, doi: 10.1049/iet-cvi.2017.0422
    • Haoxi Li, Haifeng Hu (通讯作者), Chitung Yip, Comments on“Iterative Re-Constrained Group Sparse Face Recognition With Adaptive Weights Learning", IEEE Trans. on Image Processing, Vol. 26, No. 11 pp. 5475- 5476, 2017
    • Chen He, Haifeng Hu (通讯作者), Image Captioning with Text-Based Visual Attention, Neural Processing Letters, accepted
    • Jie Wu, Haifeng Hu (通讯作者), Cascade Recurrent Neural Network for Image Caption Generation, Electronics Letters, Vol.53, No.25, pp.1642-1643, 2017
    • Liang Yang, Haifeng Hu (通讯作者), TVPRNN for image caption generation, Electronics Letters, Vol.53, No.22, pp. 1471-1473, 2017
    • Weixuan Wang, Haifeng Hu (通讯作者), Multimodal Object Description Network for Dense Captioning, Electronics Letters, Vol. 53, No. 15, pp. 1041-1042, 2017
    • Lingshuang Du, Haifeng Hu (通讯作者), Modified Classification and Regression Tree for facial expression recognition with using difference expression images, Electronics Letters, Vol. 53, No. 9 pp. 590-592, 2017
    • Siyue Xie,Haifeng Hu (通讯作者), Facial expression recognition with feature redundancy-reduced Convolutional Neural Network, Electronics Letters, Vol. 53, No. 4, pp. 235-237, 2017
    • Haoxi Li, Haoshan Zou, Haifeng Hu (通讯作者), Modified Hidden Factor Analysis for Cross-Age Face Recognition, IEEE Signal Processing Letter, Vol. 24, No. 4, pp. 465-469, 2017
    • Haoshan Zhou, Haifeng Hu (通讯作者), Cross-age Face Recognition Using Reference Coding with Kernel Direct Discriminant Analysis, 2017 IEEE International Conference on Image Processing, Accepted
    • Xiang Xiao, Haifeng Hu (通讯作者), Weixuan Wang, Trajectories-based Motion Neighborhood Feature for Human Action Recognition, 2017 IEEE International Conference on Image Processing, Accepted.
    • Jianquan Gu, Haifeng Hu (通讯作者), Siyue Xie, Enhanced Dictionary Pair Learning Sparse Representation Model for Facial Expression Classification, 2017 IEEE International Conference on Image Processing, Accepted.
    • Weipeng Hu, Haifeng Hu (通讯作者), Heterogeneous Face Recognition based on Modality-independent Kernel Fisher Discriminant Analysis joint Sparse Auto-encoder, Electronics Letters, Vol. 52, No. 21, pp. 1753-1755, 2016
    • Xiaoying Wang, Haifeng Hu (通讯作者), Pose robust low-resolution face recognition via coupled kernel-based enhanced discriminant analysis, IEEE/CAA Journal of Automatica Sinica (JAS), Vol. 3, No. 2, pp. 203-212, 2016
    • Haifeng Hu, Jianquan Gu, Multi-Manifolds Discriminative Canonical Correlation Analysis for Face Recognition with Image Sets, Cognitive Computation, Vol. 8, pp. 900-909, 2016.
    • Jianquan Gu, Haifeng Hu (通讯作者), Weipeng Hu, Patch-based alignment-free generic sparse representation for pose-robust face recognition, 2016 IEEE International Conference on Image Processing, 2016: 3006-3010
    • Haifeng Hu, Sparse Discriminative Multi-Manifold Grassmannian Analysis for Face Recognition with Image Sets, IEEE Trans. on Circuit and System for Video Technology, 25(10), pp.1599-1611, 2015
    • Haifeng Hu, Illumination invariant face recognition based on dual-tree complex wavelet transform, IET Computer Vision, 9(2), pp. 163-173, 2015.
    • Haifeng Hu, Face Recognition with Image Sets Using Locally Grassmannian Discriminant Analysis, IEEE Trans. on Circuit and System for Video Technology, 24(9), pp.1461-1474, 2014
    • Haifeng Hu, Multi-View Gait Recognition based on Patch Distribution Feature and Uncorrelated Multilinear Sparse Local Discriminant Canonical Correlation Analysis, IEEE Trans. Circuits and System for Video Technology, 24(4), pp. 617-630, 2014.
    • Haifeng Hu, Enhanced Gabor Feature Based Classification Using a Regularized Locally Tensor Discriminant Model for Multiview Gait Recognition,IEEE Trans. Circuits and System for Video Technology, 23(7), pp 1274-1286, 2013.
    • Haifeng Hu, Augmented DT-CWT feature based classification using regularized neighborhood projection discriminant analysis for face recognition, Pattern Recognition, Vol. 44, pp. 519-531, 2011.
    • Haifeng Hu, Orthogonal neighborhood preserving discriminant analysis for face recognition, Pattern Recognition, Vol. 41, pp. 2045-2054, 2008.
    • Haifeng Hu, Multiscale Illumination Normalization for Face Recognition Using Dual Tree Complex Wavelet Transform in Logarithm Domain, Computer Vision and Image Understanding, Vol. 115, pp. 1384-1394, 2011.
    • Haifeng Hu, Variable Lighting Face Recognition Using Discrete Wavelet Transform, Pattern Recognition Letters, Vol. 32, pp. 1526-1534, 2011.
    • Haifeng Hu, Ping Zhang, F. De la Torre,Face recognition using enhanced linear discriminant analysis, IET Computer Vision, Vol. 4, No. 3, pp. 195-208, 2010.
    • Haifeng Hu, Ping Zhang and Zhengming Ma, Direct kernel neighborhood discriminant analysis for face recognition, Pattern Recognition Letters, Vol. 30, pp. 902-907, 2009.
    • Haifeng Hu, ICA-Based Neighborhood Preserving Analysis for Face Recognition, Computer Vision and Image Understanding, Vol. 112, pp. 286-295, 2008.

    【专利申请】

    • 胡海峰,曹向前,潘瑜,张伟,肖翔,基于视觉显著模型的图像分割方法,申请号:2016101238586,申请日:2016/3/4
    • 胡海峰,潘瑜,曹向前,肖翔,张伟,一种基于轨迹置信度的多目标跟踪方法,申请号:2016101285727,申请日:2016/3/7
    • 胡海峰,肖翔,张伟,顾建权,一种基于密集轨迹的动作识别方法,申请号:2016102499117,申请日:2016/4/20
    • 胡海峰,肖翔,张伟,顾建权,一种基于两层时空邻域特征的动作识别方法,申请号:2016102491505,申请日:2016/4/20
    • 胡海峰,潘瑜,曹向前,肖翔,顾建权,张伟,胡伟鹏,李昊曦,一种基于改进网络流图的多目标跟踪方法,申请号:2016102554487,申请日:2016/4/22
    • 胡海峰,顾建权,李昊曦,杨梁,一种基于区域稀疏的单张训练样本人脸识别方法,申请号:2016103696061,申请日:2016/5/27
    • 胡海峰,顾建权,李昊曦,肖翔,一种基于深度学习与字典表示的跨年龄人脸验证方法,申请号:2016103696061,2016/5/27
    • 胡海峰,潘瑜,曹向前,胡伟鹏,一种基于分层网络流图的多目标跟踪方法,申请号:2016103827814,2016/5/31
    • 胡海峰,李昊曦,顾建权,胡伟鹏,一种基于双线性联合CNN的人脸验证方法,申请号:201610399704X,2016/6/7

    通讯地址:广东省广州市大学城外环东路132号
    邮政编码:510006

    Copyright © 2007-2016, 中山大学电子与信息工程学院 , Sun Yat-sen University