姓名:艾海舟

职称:教授

邮箱:ahz@tsinghua.edu.cn

URL:http://media.cs.tsinghua.edu.cn/cn/aihz

电话:010-62795495

传真:010-62795871

教育背景

工学学士 (计算机应用), 清华大学, 中国, 1985;

工学硕士 (计算机应用), 清华大学, 中国, 1988;

工学博士 (计算机应用), 清华大学, 中国, 1991.

研究领域

研究领域

计算机视觉与模式识别

讲授课程

数字图像处理 (40240062,本科);  计算机视觉 (70240083,研究生).

教学概况

从教20多年来,教过的课程有数理逻辑与集合论、专家系统、数字图象处理,计算机视觉专题,计算机视觉,涵盖了本科生的基础课、专业课及研究生的学位课。所写的数字图像处理电子课件获得清华大学优秀教学软件二等奖。负责翻译了两本国际著名教材:M. Sonka, V. Hlavac, and R. Boyle著, (艾海舟、苏延超 等译), 图像处理、分析与机器视觉(第3版),清华大学出版社, 2011.1;Richard Szeliski著, (艾海舟、兴军亮 等译), 计算机视觉:算法与应用,清华大学出版社,2012.1。

研究课题

国际合作课题:人脸及人体图像与视频的视觉处理技术研究 (2002-2014);

国家自然科学基金:图像与视频中基于人脸的内容标注与检索(2007-2009).

国家自然科学基金:行人视频的视觉内容抽取与分析 (2011-2013).

研究概况

近十年来主要从事人脸及人体视觉计算的研究,包括人脸及人体的检测、跟踪、配准、姿态估计、检索和识别等,特别地课题组所提出的人脸检测算法是目前世界上性能最好的算法之一,已经在国际上获得成功应用,有较大的影响。近期,重点开展了人体视觉计算研究,面向视觉监控和人机交互等需求,研究人体的检测、跟踪、分割、姿态估计和活动识别、再识别等问题。发表论文100余篇,其中在重要学术期刊和会议(TPAMI, TIP, ICCV, CVPR, ECCV)上发表论文10篇,其中PAMI 2篇,oral paper 3篇,已授权国际专利4项。

奖励与荣誉

清华大学优秀博士论文奖 (1992);

清华大学优秀教学软件二等奖(数字图象处理)(2002);

CVPR 2007:最佳学生论文奖 (2007),指导教师;

2008年度北京市优秀博士论文奖,指导教师;

2008年度首都教育先锋,教学创新先进个人。

 

学术成果

[1] Yuan LI, Haizhou AI, et.al, Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.30, No.10, pp. 1728-1740, 2008. (Extended version of CVPR2007 best student paper prize)

[2] Chang HUANG, Haizhou AI, et.al, High Performance Rotation Invariant Multiview Face Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.29, No.4, pp. 671-686, 2007.

[3] Junliang Xing, Haizhou Ai, Liwei Liu, Shihong Lao, Multiple Players Tracking in Sports Video: a Dual-Mode Two-Way Bayesian Inference Approach with Progressive Observation Modeling, IEEE Transaction on Image Processing, Vol. 20, No. 6, pp.1652-1667, JUNE 2011.

[4] Genquan Duan, Haizhou Ai, Junliang Xing, Song Cao, Shihong Lao, Scene Aware Detection and Block Assignment Tracking in Crowded Scenes, Image and Vision Computing ,Volume 30, Issues 4-5, May 2012, pp.292-305.

[5] Bo WU, Haizhou AI, Chang HUANG, Shihong LAO, Fast Rotation Invariant Multi-View Face Detection Based on Real Adaboost, In Proc. the 6th IEEE Conf. on Automatic Face and Gesture Recognition (AFG2004), Seoul, Korea, May 17-19, 2004.

[6] Nan Wang, Haizhou Ai and Feng Tang, What Are Good Parts for Hair Shape Modeling? IEEE Conference on Computer Vision and Pattern Recognition (CVPR2012), Providence, Rhode Island, USA. June 18-20, 2012.

[7] Wei GAO, Haizhou AI and Shihong LAO, Adaptive Contour Features in Oriented Granular Space for Human Detection and Segmentation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR2009), Miami Beach, Florida, USA, June 20-25, 2009.

[8] Junliang XING, Haizhou AI and Shihong LAO, Multi-Object Tracking through Occlusions by Local Tracklets Filtering and Global Tracklets Association with Detection Responses, IEEE Conference on Computer Vision and Pattern Recognition (CVPR2009), Miami Beach, Florida, USA, June 20-25, 2009.

[9] Li ZHANG, Haizhou AI, Shengjun XIN, et.al, Robust Face Alignment Based on Local Texture Classifiers, The IEEE International Conference on Image Processing (ICIP2005), Genoa, Italy, September 11-14, 2005.

[10] Nan Wang and Haizhou Ai, Who Blocks Who: Simultaneous Clothing Segmentation for Grouping Images, 13th International Conference on Computer Vision, November 6-13, 2011 (ICCV 2011), Barcelona, Spain.