新闻

Ø2018年07月 张继超-舒叶芷关于图像转换的论文被多媒体会议ACM MM2018录用为Oral Paper

Ø2018年03月 王斌-王国锋关于组件装配的论文在虚拟现实会议IEEE VR2018上发表

Ø2017年10月 黄鸿关于三维模板跟踪的论文获China CAD&CG2017最佳论文奖

Ø2015年11月 王国锋关于目标跟踪的论文在图像处理的国际顶级期刊IEEE TIP上发表

Ø2014年12月 钟凡博士和杨松同学的论文在SIGGRAPH Asia2014发表

Ø2012年09月 钟凡博士的关于交互视频分割的论文被图形学顶级会议SIGGRAPH Asia2012录用

研究目标

实现动态环境中的智能式增强现实（Augmented Reality）技术是我们的研究目标。通过计算机视觉技术智能感知场景动态，驱使虚拟物体根据场景变化进行响应，并生成逼真的虚实融合效果。正在研究的智能感知技术包括：物体检测与识别、三维模板跟踪、目标跟踪、动作识别、光照估计、行为规划等，并且进行深度图矫正、修复、超分辨率、前背景分割、场景重绘等增强现实中的虚实融合技术的研究。正在开展的研究工作既有基于稀疏表达与深度学习的新方法，也有基于特征提取与跟踪的传统方法。技术相关领域以计算机视觉、机器学习、模式识别、图像分析与处理、计算机图形学为基础，对图像、深度图等进行分析解读，并以此为基础进一步展开数据的分析和理解。

增强现实技术正在迎来一个崭新的时代！诚挚期待有雄心的同学加入我们，围绕增强现实技术，开展高水平的前沿技术理论与应用研究。

研究方向

¨增强现实：虚拟物体与真实世界的无缝融合及其呈现技术、自然交互技术、多媒体计算

¨计算机视觉：三维模板检测识别、三维跟踪、目标跟踪、视频分割、深度学习、特征提取与跟踪

¨人工智能：行为分析与理解、光照估计、心音识别、数据分析与理解

教育与工作经历

l1988年毕业于北京大学数学系

l1991年研究生毕业于浙江大学CAD&CG国家重点实验室并获硕士学位

l1991年8月至1995年7月在中科院成都计算机应用技术研究所助理研究员

l2001年获广岛大学工学博士学位

l2003年1月至2008年6月在浙江大学CAD&CG国家重点实验室副研究员

l2016年3月至2017年3月在美国北卡大学教堂山分校访问学者

l2008年6月至今 bet356亚洲版在线体育教授、博士生导师

主持或参与科研项目

l主持国家自然科学基金项目：“基于深度视频的跨时空影像融合与沉浸式环境构建”，2017-2020

l主持合作开发项目：基于三维模板的物体跟踪技术，2017-2018。

l参加国家重点研发计划项目：“非配合虚实环境的实时注册融合技术与引擎”，2016-2019

l主持863国家高技术研究发展计划项目子课题：“动态场景的实时虚实融合技术”，2015-2017

l主持自然科学基金面上项目：“面向增强现实的虚拟化身行为建模关键技术研究”,2012-2015

l主持自然科学基金面上项目：“基于视频的混合现实关键技术技术”，2009.1 -2011.12

l主持山东省自然科学杰出青年基金项目：“虚拟产品在视频场景中的实时融合”,2010-2012,

l主持自然科学基金面上项目：“基于视频的混合现实关键技术技术”，2009.1 -2011.12

l主持863专题课题：“基于视觉的实时定位与虚实融合技术研究”,2007.7-2009.6

l主持自然科学基金面上项目：“视频图像序列与虚拟物体的融合技术”，2004.1 -2006.12

l主持留学归国人员基金一项,2004-2005

l参加973子课题“增强虚拟型混合环境的呈现”，2009.1 - 2013.12

l参加973子课题“增强型的虚拟技术研究”，2002.12 - 2007.12

主要论文

论文

1.Bin Wang, Guofeng Wang, Andrei Sharf, Yangyan Li, Fan Zhong,Xueying Qin, Daniel CohenOr, Baoquan Chen. Active Assembly Guidance with Online Video Parsing.IEEE Virtual Reality 2018.

2.李成龙，钟凡，马昕，秦学英：基于卡尔曼滤波和随机回归森林的实时头部姿态估计。计算机辅助设计与图形学学报，29(12): 2309-2316，2017。

3.Jichao Zhang, Fan Zhong, Gongze Cao,Xueying Qin. ST-GAN: Unsupervised Facial Image Semantic Transformation Using Generative Adversarial Networks. InThe 9th Asian Conference on Machine Learning ( ACML 2017), November 15 - 17, 2017, Yonsei University, Seoul, Korea.

4.Chenglong Li, Fan Zhong, Qian Zhang,Xueying Qin. Accurate and Fast 3D Head Pose Estimation with Noisy RGBD Images.Multimedia Tools Appl.77(12): 14605-14624 (2018).

5.Xibin Song, Jianmin Zheng, Fan Zhong,Xueying Qin. Modeling Deviations of RGB-D Cameras for Accurate Depth Map and Color Image.Multimedia Tools Appl. 77(12): 14951-14977 (2018).

6.Yuan Wang, Fan Zhong, Xiangyu Sun,Xueying Qin. Realistic Image Composite with Best-Buddy Prior of Natural Image Patches.International Conference on Image Processing 2017.

7.Bin Wang, Fan Zhong,Xueying Qin. Pose Estimation in Edge Distance Field for Textureless 3D Object Tracking.Computer Graphics International 2017.

8.Chenglong Li, Fan Zhong,Xueying Qin. Accurate 3D Head Pose Estimation with Noisy RGBD images.Computer Graphics International 2016.

9.Xibin Song, Yuchao Dai,Xueying Qin. Deep Depth Super-Resolution: Learning Depth Super-Resolution using Deep Convolutional Neural Network.AsianConference on Computer Vision2016.

10.Xibin Song, Haiyang Huang, Fan Zhong,Xueying Qin*:Edge-guided Depth Map Enhancement.InternationalConference onPatternRecognition2016.

11.Guofeng Wang,Xueying Qin, Fan Zhong, Yue Liu, Qunsheng Peng, Ming-Hsuan Yang: Visual Tracking via Sparse and Local Linear Coding.IEEE Transactions on Image Processing, 24(11): 3796-3804 ( 2015). (SCI)

12.Guofeng Wang, Bin Wang, Fan Zhong,Xueying Qin, Baoquan Chen: Global Optimal Searching for Textureless 3D object tracking.The Visual Computer, 31(6-8): 979-988 (2015). (SCI)

13.Xinbo Jiang, Fan Zhong, Qunsheng Peng,Xueying Qin:Action recognition based on global optimal similarity measuring.Multimedia Tools and Applications,Sept. 2016, 75 (18) :11019-11036. (2016)(SCI)

14.李成龙，钟凡，秦学英：基于3维模型的单视图不规则物体定位。计算机辅助设计与图形学学报，27(1):68-75,2015。

15.王斌，陈文拯，钟凡，屠长河，秦学英，彭群生：基于时空测地线传播的RGB-D视频分割。计算机辅助设计与图形学学报，27(10):1816-1822，2015。

16.Fan Zhong,Song Yang,Xueying Qin,Dani Lischinski,Daniel Cohen-Or,Baoquan Chen: Slippage-free background replacement for hand-held video.ACM Trans. Graph. 33(6): 199 (2014)

17.Xibin Song,Fan Zhong,Yanke Wang,Xueying Qin: Estimation of Kinect depth confidence through self-training.The Visual Computer 30(6-8): 855-865 (2014) (SCI)

18.Xinbo Jiang,Fan Zhong,Qunsheng Peng,Xueying Qin: Online robust action recognition based on a hierarchical model.The Visual Computer 30(9): 1021-1033 (2014)

19.Xinbo Jiang, Fan Zhong, Qunsheng Peng,Xueying Qin. Robust Action Recognition Based on a Hierarchical Model. InIEEE International Conference on Cyberworlds (CW 2013), pp. 191-198(2013).

20.Yanke Wang, Fan Zhong, Qunsheng Peng,Xueying Qin. Depth map enhancement based on color and depth consistency.The Visual Comput,30(10): 1157-1168 (2014).

21.Jun Wang, Fan Zhong, Guofeng Wang, Qunsheng Peng,Xueying Qin. Visual Tracking Via Subspace Motion Model.British Machine Vision Conference2013.

22.Rui Zhang, Fan Zhong, Lili Lin, Guanyu Xing, Qunsheng Peng,Xueying Qin. Basis image decomposition of outdoor time-lapse videos.The Visual Computer29(11):1197-1210 (2013). (SCI)

23.Chuan Niu, Fan Zhong, Songhua Xu, Chenglei Yang,Xueying Qin. Cylindrical panoramic mosaicing from a pipeline video through MRF based optimization Source.The Visual Computer 29(4): 253-263 (2013). (SCI)

24.GuanYu Xing, XueHong Zhou, YanLi Liu,Xueying Qin, QunSheng Peng.Online illumination estimation of outdoor scenes based on videos containing no shadow area.Science China Information Sciences,56(3):1-11(2013). (SCI)

25.Guanyu Xing,Xuehong Zhou,Qunsheng Peng,Yanli Liu,Xueying Qin: Lighting Simulation of Augmented Outdoor Scene Based on a Legacy Photograph.Comput. Graph. Forum 32(7): 101-110 (2013)

26.张锐，钟凡，彭群生，秦学英：室外场景光照估计的基图像分解算法。计算机辅助设计与图形学学报，25(4):442-449, 2013。

27.Fan Zhong, Xinbo Jiang,Xueying Qin, Qunsheng Peng. Motion-based Easy Initialization of Online Foreground Segmentation.International Conference on Computer Vision in Remote Sensing (CVRS )2012,pp.52-57.

28.Fan Zhong, Xueying Qin, Qunsheng Peng, Xiangxu Meng. Discontinuity-Aware Lazy Video Object Cutout,Accepted bySIGGRAPH Asia’2012(To appear onACM Transaction on Graphics). (SCI)

29.Guofeng Wang, Fan Zhong, Yue Liu, Hongbo Li, Qunsheng Peng, Xueying Qin. Visual Tracking in Continuous Appearance Space via Sparse Coding. Accepted by ACCV2012.

30.Guanyu Xing, Yanli Liu, Xueying Qin, Qunsheng Peng. A Practical Approach for Real Time Illumination Estimation of Outdoor Videos. To appearonComputers & Graphics.(SCI)

31.张锐，钟凡，彭群生，秦学英：室外场景光照估计的基图像分解算法。计算机辅助设计与图形学学报已录用。

32.Yanke Wang, Fan Zhong,ChaoLi, Hui Xiang, Qunsheng Peng, and Xueying Qin. Tele-AR System Based on Real-time Camera Tracking.International Conference on Virtual Reality and Visualization(ICVRV), 2012. (EI)

33.Yijiang Zhang, Julien Pettre, Jan Ondrej,Xueying Qin, Qunsheng Peng, and, Stephane Donikian. Mixed Crowds: Online Inserting Virtual Characters into Dynamic Video Scenes. To appear inComputer Animation and Virtual Worlds journal.(SCI)

34.Guanyu Xing, Yanli Liu,Xueying Qin, Qunsheng Peng.On-line Illumination Estimation of Outdoor Scenes Based on Area Selection for Augmented Reality.The 12^thInternational Conference on CAD/Graphics 2011.

35.Chuan Niu, Fan Zhong, Songhua Xu, Chenglei Yang, Xueying Qin. Creating Cylindrical Panoramic Mosaic from a Pipeline Video.The 12^thInternational Conference on CAD/Graphics 2011.

36.Na Li, Fan Zhong, Qunsheng Peng, Xueying Qin. Rhythm Motion based on Real-time Music Beat Tracking in Augmented Reality.2011 Asian Conference on Design and Digital Engineering.

37.Fan Zhong,Xueying Qin, Qunsheng Peng. Robust image segmentation against complex color distribution.The Visual Computer27(6-8): 707-716 (2011).(SCI)(The best student paper award)

38.李超，王延可，秦学英，向辉，彭群生：基于GPU的摄像机实时定标技术。第8届中国计算机图形学大会论文集，pp.42-50，2010。

39.刘艳丽，秦学英，刑冠宇，彭群生：面向增强现实的在线室外光照估计算法。计算机辅助设计与图形学学报，2011, 23(1):132~137。

40.张艺江，秦学英，Julien Pettré，彭群生：动态视频场景中虚拟群体的实时融合。计算机辅助设计与图形学学报，2011,23(1):185~191。

41.Fan Zhong, Xueying Qin, Qunsheng Peng. Transductive Segmentation of Live Video with Non-stationary Background.CVPR 2010.

42.Yanli Liu,Xueying Qin, Guanyu Xing, Qunsheng Peng. A New Approach to Illumination Estimation Based on Statistical Analysis for Augmented Reality.Computer Animation and Virtual Worlds journal ( CASA2010),Vol.21, No.3, pp.321-330, 2010.(SCI)

43.Fan Zhong,Xueying Qin, Jiazhou Chen, Wei Hua, Qunsheng Peng. Confidence-based color modeling for online video segmentation.ACCV2009, MP2-22.

44.Yuanlong Shao,Xinguo Liu,Xueying Qin,Yi Xu,Hujun Bao: Locally Developable Constraint for Document Surface Reconstruction.ICDAR 2009: 226-230

45.Guofeng Zhang, Wei Hua,Xueying Qin, Yuanlong Shao, and Hujun Bao. Video Stabilization Based on a 3D Perspective Camera Model.The visual Computer,Vol.25, No.11, pp. 997-1008,2009(SCI).

46.Yanli Liu,Xueying Qin, Songhua Xu, Eihachiro Nakamae, Qunsheng Peng. Light Source Estimation of Outdoor Scenes for Mixed Reality.CGI2009,The Visual Computer,Vol.25, No.5, pp.637-646,2009(SCI)

47.高俊鑫,华炜,章国锋,秦学英：带约束的摄像机定标方法。中国图形图象学报，2010,15(3):536~540。

48.钟凡，秦学英，陈佳舟，莫铭臻，彭群生：在线视频分割实时后处理。计算机学报,第32卷2期，2009年2月，pp. 261-267。(EI)

49.Songhua Xu,Suchao Chen,Kevin Y. Yip,Francis C. M. Lau,Xueying Qin: A Two-Stage Audio Retrieval Method for Searching Unannotated Audio Clips.ISM 2008: 334-339

50.钟凡，莫铭臻，秦学英，彭群生：基于WSSD的不规则图像块快速匹配，中国图像图形学报，2008，Chinagraph'2008

51.G. Zhang,X. Qin, W. Hua,T Wang, P. Heng, H. Bao. Robust Metric Reconstruction from Challenging Video Sequences.CVPR2007.[demo]

52.G. Zhang, W. Hua,X. Qin, T. Wong, H. Bao.Stereoscopic Video Synthesis with Commodity Video Camera.Accepted byIEEE Transactions on Visualization & Computer Graphics,13(4): 686-696 (2007).

53.G. Zhang,X. Qin, X. An, W. Chen, H. Bao. As-Consistent-As-Possible Compositing of Virtual Objects and Video Sequences.Computer Animation and Virtual Worlds journal ( CASA2006), 17:305-314. [img]

54.章国锋，秦学英，董子龙，华炜，鲍虎军，面向增强视频的基于结构和运动恢复的摄像机定标。计算机学报,第29卷12期，2006年12月，pp.2104-2111。[demo]

55.Y. Nagai, M. Fujiwara, K. Tadamura,X. Qin, E. Nakamae. Synthesizing Background Panned Video Sequence Images and CG Models for Design of Outdoor Vehicles.The journal of the society for art and science,Vol.5, No.2, pp.45-56, June, 2006. (In Japanese)

56.X. An,X. Qin, G. Zhang, W. Chen, H. Bao, Robust Camera Motion Estimation in Video Sequences. InInternational Conference on Computer Vision Theory and Applications 2006,Setúbal, Portugal, 25-28 February, pp.294-302.

57.X. An,X. Qin, H. Bao. Automatic and robust segmentation of motion layers in image sequences. InIS&T/SPIE 18th Annual Symposium Electronic Imaging: Science and Technology, 15–19 January 2006, San Jose, California,USA.

58.E. Nakamae,X. Qinand K. Tadamura. Compositing of Computer Graphics with Landscape Video Sequences.Visualization in Landscape and Environmental Planning – Technology and Applications, edited by I. Bishop and E. Lange, published by Taylor & Francis, London and New York, pp.226-233, 2005.

59.Yasuo Nagai, Katsumi Tadamura, Xueying Qin, Eihachiro Nakamae, Measurement of High Dynamic Range Luminance based on Video Signal,The Journal of The Institute of Image Information and Television Engineers, Volume 59, No. 10, 2005.

60.谢彦，王明福，秦学英。全景图的颜色校正算法。计算机研究与发展，42卷（增刊），313－317，2005。

61.马翔，王明福，秦学英，Eihachiro Nakamae。一种有物体相互反射效果的室外场景绘制方法。计算机研究与发展，42卷（增刊），173－177，2005。

62.陈琳，秦学英，王青。复杂三维模型的遮挡检测加速算法。工程图学学报，第26卷，第2期，pp.41-45,2005。

63.Guofeng Zhang, Xueying Qin, Xiaobo An, Wei Chen and Hujun Bao. Seamless Compositing of Virtual Objects And Video Sequences.In Pacific graphics2005, pp.78-81. (poster )

64.Xue-ying Qin, Eihachiro Nakamae, Wei Hua, Yasuo Nagai, and Qun-Sheng Peng. Anti-Aliased Rendering of Water Surface.Journal of Computer Science and Technology,Sept. 2004, Vol.19, No.5, pp.626-632(SCI)

65.王青，华炜，秦学英，鲍虎军。基于势函数的广义有理参数曲线。自然科学进展，第十四卷，第二期，pp.209-215,2004。

66.X. Qin, E. Nakamae,W.Hua, Y. Nagai, and Q. Peng. Anti-Aliasing of Reflection Effects of Water Surface.Proceedings of 8^thInternational Conference on CAD/Graphic, pp.61-66.(2003)

67.Katsumi Tadamura, Xueying Qin, Guofang Jiao, Yasuo Nagai, Eihachiro Nakamae.Landscapes Taking into Account Optical Effects of Clouds.画像电子学会志,第32卷,第四号,pp.346-354.(2003) (publishedin Japanese)

68.X. Qin, E. Nakamae,K. Tadamuraand Y. Nagai.Fast Photo-Realistic Rendering of Trees in Daylight.Computer Graphics Forum (Eurographics 2003),Vol.22, No.3, pp.243-252.[cgimg] [cgimg] [comp-img]

69.X. Qin, E. Nakamae and K. Tadamura.Automatically Compositing Still Images and Landscape Video Sequences.IEEE Computer Graphics and Applications, Vol.22, No.1, Jan./Feb., pp.68-78. (2002)(SCI) [avi][avi]

70.K. Tadamura,X. Qin, G. Jiao and E. Nakamae. Fast Rendering Water Surface for Outdoor Scenes.International Journal of Image and Graphics, Vol. 1, No. 2, pp.313-327. (2001)

71.E. Nakamae,X. Qinand K. Tadamura.Rendering of Landscapes for Environmental Assessment.Landscape and Urban Planning,Volume 54, Issues 1-4, 25 May, Pages 19-32. (2001)(SCI) [cgimg][cgimg]

72.K. Tadamura,X. Qin, G. Jiao and E. Nakamae. Rendering Optical Solar Shadows Using Plural Sunlight Depth Buffers.Journal of the Visual Computer,Vol.17, No.2, pp.76-90. (2001)(SCI)

73.X. Qin, K. Tadamura, T. Ishibashi and E. Nakamae. Composite Panned Landscape Video Sequences with Computer Generated Still Images.The Transactions of the Institute of Electronics, Information and Communication Engineers, Vol. J83-D-II, No.4, pp.1140-1152. (2000) (published in Japanese).

74.E. Nakamae,X. Qin, G. Jiao, P. Rokita and K. Tadamura. Computer Generated Still Images Composited with Panned/Zoomed Landscape Video Sequences.Journal of the Visual Computer, Vol.15, No.9, pp.429-442. (1999)(SCI)

75.X. Qin, K. Tadamura, Y. Nagai and E. Nakamae. Creating a Precise Panorama from Panned Video Sequence Images.Journal of Information Processing,Vol.40, No.10, pp.3685-3693, Oct. (1999) (published in Japanese).

76.K. Tadamura, G. Jiao,X. Qin, N. Kato and E. Nakamae. Rendering Optical Solar Shadows Using Plural Sunlight Depth Buffers.Journal of Information Processing,Vol.40, No.3, pp.1156-1168. (1999) (published in Japanese).

77.K. Tadamura,X. Qin,Y.Nagaiand E. Nakamae.Landscapes Taking into Account Optical Effects of Clouds. Proceedings – Industrial Systems and Engineering II, 6^thWorld MultiConference on Systemics, Cybernetics and Informatics, Vol.12, pp.85-90 (2002)(ISTP).

78.E. Nakamae ,X. Qin, K. Tadamura and Y. Nagai. Fast Rendering for Photo-Realistic Trees in Daylight.Animation Theaters of SIGGRAPH 2002.

79.X. Qin, E. Nakama and K. Tadamura. Creating a Precise Panorama from Panned Video Sequence Images.Proc. of Pacific Graphics, pp.6-11. (1999)

80.K. Tadamura,X. Qin, G. Jiao and E. Nakamae, Rendering Optical Solar Shadows Using Plural Sunlight Depth Buffers.Proc. of CG International, pp.166-173. (1999)(ISTP)

81.E. Nakamae,X. Qin, G. Jiao, P. Rokita, K. Tadamura and Y. Usagawa. Panned/Zoomed Landscape Video Sequences Composited with Computer Generated Still Images.SIGGRAPH'98 conference abstracts and applications, pp.279. (1998)(ISTP)

82.E. Nakamae,X. Qin, G. Jiao, P. Rokita, K. Tadamura and Y. Usagawa. Computer Generated Still Images Composited with Panned Landscape Video Sequence.Proceedings of the 1998 MultiMedia Modeling (MMM'98), pp.62-69. (1998)(ISTP)

83.S. Fu, Q. Peng andX. Qin, The Global Cube: A Light Energy Distributor For Light Propagation in General Environments.Proc. of Pacific Graphics, pp.129-147. (1994)