济南大学研究生招生信息

081200|计算机科学与技术专业硕士研究生指导教师

姓名 杨晓晖 性别
民族出生年月198511
学历|学位研究生|工学博士专业技术职务
行政职务
联系电话移动电话18560025816
邮箱ise_xhyang@ujn.edu.cn
通讯地址 | 邮编山东省济南市南辛庄西路336号济南大学信息科学与工程学院 | 250022
招生方向(领域) 01可视计算与自然交互,02智能计算与科学建模
研究领域、学习工作经历、学术兼职等情况

杨晓晖,工学博士,讲师,1985年11月出生。分别于2008年07月和2014年07月在山东大学信息科学与工程学院取得工学学士和工学博士学位。攻读博士期间,在国家建设高水平大学联合培养博士项目的资助下,于2011.09-2012.10赴美国University of California, San Diego访学,进行视频处理、人机交互领域的研究。博士毕业后,于2014.07进入山东省计算中心(国家超级计算济南中心)工作;2015.06进入济南大学信息科学与工程学院,从事教学与科研工作。在IEEE Signal Processing Letters、IEEE ICIP、IEEE ICASSP、IEEE VCIP等国际期刊和会议上发表论文20余篇,申请发明专利近10项。担任国际期刊《IEEE Transaction on Broadcasting》、《IEEE Signal Processing Letters》、《Electronics Letters》审稿人。主持国家自然科学基金1项,山东省重点研发计划1项,浙江大学CAD&CG国家重点实验室开放基金1项,济南大学博士基金1项,并参与国家重点研发计划“云端融合的自然交互设备和工具”。主要研究方向为模式识别、图像处理、视频处理。

 
代表性科研成果及奖励:
(包括项目、鉴定、论文、专著、专利等)

科研论文

2017

[23] Yang X. *, Feng Z., Xu T., Yan J., Tang H., Motion-compensated frame interpolation for multiview video using inter-view and intra-view correlations, in Proc. IEEE Int. Conf. Image Process. (ICIP'17), Beijing, P.R. China, 2017, pp. 4312-4316.

[22] Yang X. *, Feng Z., Xu T., Jiang Y. and Tang H., Superpixel-based depth map enhancement and hole filling for view interpolation, in Proc. Ninth Int. Conf. Digital Image Process. (ICDIP’17), Hongkong, 2017.

[21] Jiang Y., Yang X. *, Feng Z., Xia Y., An efficient 3d video frame interpolation method using color-depth-motion information, in Proc. IEEE ICCSS 2017.

[20] Xu T., Feng Z., Dong L., and Yang X., 2D Human Parsing with Deep Skin Model and Part-Based Model Inference, in Proc. Int. Conf. Intelligent Comput. (ICIC’17), 2017, pp. 776-787.

2016

[19] Yang X*, Liu J., Sun J., Feng Z., Tang H., and Wang L., Frame rate up-conversion based on depth guided extended block matching for 3d video, in Proc. IEEE Vis. Commun. Image Process. (VCIP'16). Chengdu, P.R. China, 2016, pp. 1-4.

[18] Yang X. *, Feng Z., 3D video frame interpolation via adaptive hybrid motion estimation and compensation, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP'16), Shanghai, P.R. China, 2016, pp. 1691-1695.

[17] Zhiquan Feng, Bo Yang, Hong Liu, Na Lv, Xiaohui Yang, Jianqin Yin, Yuan Zhang, Xiuyang Zhao, An HCI paradigm fusing flexible object selection and aom-based animation, Information Sciences, 2016, 369:368-387.

[16] Zhizhong Fu, Xue Wang, Yuan Li, Xiaohui Yang, Jin Xu, Adaptive luminance adjustment and neighborhood spreading strength information based view synthesis, Journal of Systems Engineering and Electronics, 2016, 37(3): 721-729.

2014

[15] Xiaohui Yang, Ju Liu, Jiande Sun, Yeejin Lee, Truong Q. Nguyen, Depth-assisted frame rate up-conversion for stereoscopic video, IEEE Signal Processing Letters, 2014, 21(4): 423-427.

[14] Zhao Y., Sun G., Liu J., Ge J., Wan W., Yang X., An improved FRUC scheme based on motion vector refinement, in Proc. 12th Int. Conf. Signal Process. (ICSP’14), Hangzhou, P.R. China, 2014, pp. 981-986.

[13] Fu Z., Li Y., Yang X., Xu J., Wang X., A view synthesis method based on local luminance and neighborhood spreading strength information, in Proc. 12th Int. Conf. Signal Process. (ICSP’14), Hangzhou, P.R. China, 2014, pp. 857-860.

2013

[12] Xiushan Nie, Ju Liu, Jiande Sun, Lianqi Wang, Xiaohui Yang, Robust video hashing based on representative-dispersive frames, Science China Information Sciences, 2013, 56 (6): 1-11.

[11] Yuxi Liu, Ju Liu, Weidong Guo, Hongji Xu, Guowei Zhang, Xiaohui Yang, Outage probability and bit-error rate analysis of distributed antenna systems in multicell environment, IET Communications, 2013, 7(9): 791-798.

[10] Wan W., Liu J., Sun J., Yang X., Improved logarithmic spread-transform dither modulation watermarking based on perceptual model, in Proc. IEEE Int. Conf. Image Process. (ICIP'13), Melbourne, Australian, 2013, pp. 4522-4526.

[9] Cheng C., Liu J., Yuan H., Yang X., Liu W., A DIBR method based on inverse mapping and depth-aided image inpainting, in Proc. 2013 IEEE China Summit & Int. Conf. Signal Information Process. (ChinaSIP’13), Beijing, P.R. China, 2013, pp. 518-522.

2012

[8] Xiaohui Yang, Jiande Sun, Ju Liu, Xinchao Li, Caixia Yang, Wei Liu, A remote gaze tracking system using gray-distribution-based video processing, Biomedical Engineering: Applications, Basis and Communications, 2012, 24(3): 217-227.

2011

[7] Yang X., Liu J., Sun J., Li X., Liu W., DIBR based view synthesis for free-viewpoint television, in Proc. IEEE 3DTV Conf. (3DTV-CON'11), Antalya, Turkey, 2011, pp. 1-4.

[6] Jiande Sun, Caixia Yang, Ju Liu, Xiaohui Yang, Gaze tracking based on similarity between spatial triangles and two-stage calibration, Electronics Letters, 2011, 47(4):254-255.

[5] Xinchao Li, Ju Li, Jiande Sun, Xiaohui Yang, Wei Liu, Step projection-based spread transform dither modulation, IET Information Security, 2011, 5(3):170-180.

2010

[4] Yang X., Sun J., Liu J., Chu J., Liu W., Gao Y., A gaze tracking scheme for eye-based intelligent control, in Proc. 8th IEEE World Congress on Intelligent Control and Automation (WCICA’10), Jinan, P.R. China, 2010, pp. 50-55.

[3] Jinyu Chu, Jiande Sun, Xiaohui Yang, Ju Liu, Wei Liu, A novel infrared gaze tracking system based on nonuniformed interpolation, Biomedical Engineering: Applications, Basis and Communications, 2010, 22(3):185-192.

[2] Sun J., Yang N., Liu J., Yang X., Li X., Video watermarking scheme based on spatial relationship of DCT coefficients, in Proc. 8th IEEE World Congress on Intelligent Control and Automation (WCICA’10), Jinan, P.R. China, 2010, pp. 56-59.

[1] Yang C., Sun J., Liu J., Yang X., Wang D., Liu W., A gray difference-based pre-processing for gaze tracking, in Proc. 12th Int. Conf. Signal Process. (ICSP’10), Beijing, P.R. China, 2010, pp. 1293-1296.

 

发明专利

1.杨晓晖,冯志全,唐好魁,蒋彦,徐涛,王灵垠.一种基于深度引导扩展块匹配的三维视频帧率提升方法.专利号:ZL201610247833.7,授权日期:2017.06.09.

2.杨晓晖,冯志全,唐好魁,徐涛,蒋彦,吕娜.基于超像素的深度图像预处理和深度空洞填充方法.专利号;ZL201610865067.0,授权日期:2017.06.16.

3.杨晓晖,冯志全.一种立体视频帧率提升中运动矢量检测与校正方法及系统.专利号:ZL201610976656.6,授权日期:2017.07.21.

4.刘琚,成聪,杨晓晖.多视点视频中基于空时结合的虚拟视点绘制方法.专利号:ZL201310188898.5,授权日期:2015.11.04.

5.杨晓晖,刘琚,孙建德,元辉,刘韶.立体视频帧率提升方法和装置.专利号:ZL201310073131.8,授权日期:2013.06.19.

6.刘琚,杨晓晖,孙建德,刘微.一种虚拟视点图像合成方法及装置.专利号:ZL201110267816.7,授权日期:2012.05.09.

7.孙建德,杨彩霞,刘琚,张杰,杨晓晖.一种基于双光源的视线跟踪方法.专利号:ZL201010618752.6,授权日期:2011.05.04.

8.孙建德,刘琚,杨彩霞,王地长生,杨晓晖.基于超分辨率的视线跟踪精度提升方法.专利号:ZL201010292929.8,授权日期:2011.02.02.

9.刘琚,孙建德,杨晓晖,褚金玉,杜煜.基于非均匀样本差值的眼动仪定标方法.专利号:ZL200910019741.3,授权日期:2009.11.11.

 

科研项目

1. 国家自然科学基金,61603151,驾驶情境下基于驾驶员眼动行为的注意机制与模型研究,2017.01-2019.12, 19万,在研,主持

2. 山东省重点研发计划,2017GGX10146,面向虚拟装配的自然交互系统关键技术研发,2018.01-2019.1220万,在研,主持

3. 浙江大学CAD&CG国家重点实验室开放基金,A1721, 基于深度学习的视线跟踪技术研究,2017.01-2017.12, 3万,在研,主持

4. 济南大学博士科研基金,XBS1621,人机交互中视线跟踪技术研究,2015.11-2017.10, 5万,在研,主持

 
教学及研究生培养情况

主讲课程(本科):

2015-2016学年秋季(第一)学期:《FPGA原理及应用》

2016-2017学年秋季(第一)学期:《FPGA原理及应用》、《FPGA课程设计》

2016-2017学年春季(第二)学期:《数字电子技术基础》

2017-2018学年秋季(第一)学期:《FPGA原理及应用》、《FPGA课程设计》

研究生指导:硕士在读1名

 
备注