个人简介(简历) 安平,教授(2007-),博士生导师(2008-)。1990年和1993年分别获得合肥工业大学工学学士和工学硕士学位,2002年获得上海大学工学博士学位。1993年进入上海大学(1994年5月前为上海工业大学)工作至今。德国柏林工业大学访问学者(2011-2012),澳大利亚悉尼科技大学短期访问学者(2015、2017)。入选2006年度上海市曙光学者计划、2018年度上海市优秀技术带头人计划。学术兼职包括上海市图像图形学学会副理事长、中国图像图形学学会理事、中国电子学会信号处理分会和消费电子分会委员、中国仪器仪表学会图像科学与工程分会常务理事。主持完成国家自然科学基金、国家科技部支撑计划、上海市科委/教委/经信委等省部级以上项目十多项,并与上海文广、华为、航空电子所等开展产学研合作。发表学术论文200余篇,出版学术著作2部,授权发明专利20余项,获上海市科技进步二等奖、教育部自然科学二等奖、中国电子学会自然科学二等奖、科技部世博科技先进个人等奖项。 科研方向 ⟡ 光场数据压缩与重建 ⟡ 智能视频编码 ⟡ 沉浸式视频(光场/3D/VR/AR)内容生成与质量评价 ⟡ 计算摄像与智能视觉技术 荣誉称号及科研获奖 ⟡ 上海市优秀技术带头人,2018 ⟡ 上海市曙光学者,2006 ⟡ 宝钢优秀教师奖,2009 ⟡ 世博科技先进个人,科技部,2011 ⟡ 三维自由视点电视关键技术研发及在世博会中国馆中的应用,上海市科技进步二等奖,排名第一,2011 ⟡ 自由视点视频编码理论和应用研究,教育部自然科学二等奖,排名第三,2015 ⟡ 新型视觉信号压缩与保护,中国电子学会自然科学二等奖,排名第四,2018 本科生教学 ⟡ 专业基础课《数据结构与算法基础》 ⟡ 专业课《数字图像处理》 ⟡ 高年级研讨课《超高清与智能3D技术》 ⟡ 新生研讨课《图与像的世界》 研究生培养 ⟡ 已毕业博士生:张秋闻(2009),张艳(2009),李贺建(2010),程浩(2010),李春华(2011),尤志翔(2011),左一帆(2012),马健(2013),刘德阳(2014),杨超(2014),金智鹏(2016),黄新彭(2016) ⟡ 已毕业硕士生:韩杰(2002),刘佳(2003),高欣(2003),刘鹏飞(2004),郭秋艳(2005),刘占伟(2005),鞠芹(2005),薛俊毅(2005工程),宓桃(2006),李振刚(2007),程明明(2008),吴妍非(2008),刘利亮(2009),王平(2009),刘晓敏(2009专),王奎(2010),郑专(2010),王立(2010专),邬芙琼(2011),赵冰(2011),闫吉辰(2011),张鑫(2011专),蒋杰(2012工程),郭晓煊(2012工程), 刘超(2012),蒋晟(2012专),王健鑫(2013),何宛文(2013),王浩(2013专),余芳(2014),严徐乐(2014),郑嘉杰(2014专),周杰(2015),杨玲(2015),高哲(2015),都腾跃(2015专),杨佳露(2016),余佳东(2016),单良(2016),王国平(2017),赵金波(2017),吴佩(2017),杨梦雅(2017专),倪超(2017专),孙源航(2018专),朱润杰(2018专) ⟡ 在读博士生:曹峰银,李响,孟春丽,黄琨强,粱如海,陈亦雷 ⟡ 在读硕士生:王维茜,丁文欣,陈欣,薛潮,刘欣,刘晓晓 承担或参与的科研项目 (1) 上海市优秀技术带头人计划项目,先进影像制作与质量评测研究,2018.5-2021.4,主持 (2) 国家自然科学基金海外及港澳台学者合作研究基金项目,光场图像深度信息提取研究,2019.1-2020.12,参加(国内合作方) (3) 上海市科委研发平台建设专项,上海市3D内容制作专业技术服务平台,2017.4-2020.3,主持 (4) 国家自然科学基金项目,3D Holoscopic密集视点视频编码方法研究,2016.1-2019.12,主持 (5) 国家自然科学基金广东省联合基金重点项目,高清3D裸眼视频内容生成与编码,2014.1-2017.12,参加(上海大学负责人) (6) 国家自然科学基金项目,面向绘制质量的深度提取及其编码方法研究,2012.1-2015.12,主持 (7) 上海市科委高校能力建设专项,基于深度的双目视频编码与真实场景重现,2010.11-2013.6,参加(排名第二,负责实施) (8) 科技部支撑计划-上海市科委世博专项,上海世博会中国馆3D自由视点电视应用系统,2010.3-2010.12,主持 (9) 国家自然科学基金重点项目,自由视点多视视频编码及3D立体基础理论与关键技术,2008.1-2012.12,参加(本校排名第2) (10) 上海市教委科研创新重点项目,面向用户端的立体电视编码与重构,2009.1-2012.3,主持 (11) 上海市科委科技攻关项目,3D立体视频节目制作与显示系统,2009.8-2010.3,主持 (12) 国家自然科学基金项目, 3DAV中的多视点视频编码及解码端视点绘制研究,2007.1-2009.12,主持 (13) 上海市曙光计划人才项目,基于光线空间的自由视点的表示与重现,2007.1-2009.12,主持 (14) 国家自然科学基金项目,多视点/三维视觉的分析与合成研究,2003.1-2003.12,主持 学术著作 [1] 安平、沈礼权、马然、王永芳,深度增强的3D视频处理技术,人民邮电出版社,2015 [2] 张兆杨、安平、张之江、沈礼权,二维和三维视频处理及立体显示技术,科学出版社,2010 学术论文 [1] Y. Chen, P. An, X. Huang, C. Yang, D. Liu, Q. Wu, “Light Field Compression Using Global Multiplane, Representation and Two-step Prediction,” IEEE Signal Processing Letters, 2020, accepted [2] C. Meng, P. An, X. Huang, C. Yang, D. Liu, “Full Reference Light Field Image Quality Evaluation Based on Angular-Spatial Characteristic,” IEEE Signal Processing Letters, Vol. 27: 525-529, 2020 [3] Y. Zuo, Q. Wu, Y. Fang, P. An, L. Huang, Z. Chen, “Multi-Scale Frequency Reconstruction for Guided Depth Map Super-Resolution via Deep Residual Network,” IEEE Transactions on Circuits and Systems for Video Technology, 30(2): 297-306, 2020 [4] Z. Jin, P. An, C. Yang, L. Shen, “Post-processing for Intra Coding Through Perceptual Adversarial Learning and Progressive Refinement”, Neurocomputing, Vol. 394, 158-167, 2020.6 [5] Z. Jin, P. An, C. Yang, L. Shen, “Video Intra Prediction Using Convolutional Encoder Decoder Network,” Neurocomputing, Vol. 394: 168-177, 2020.6 [6] D. Liu, P. An, R. Ma, W. Zhang, X. Huang, “Content-Based Light Field Image Compression Method with Gaussian Process Regression,” IEEE Transactions on Multimedia, 22(4): 846-859, 2020 [7] X. Huang, P. An, F. Cao, D. Liu, Q. Wu, “Light-field Compression Using A Pair of Steps and Depth Estimation,” Optical Express, 27(3): 3557-3573, 2019 [8] C. Li , P. An, L. Shen, and K. Li, “A Modified Just Noticeable Depth Difference Model Built in Perceived Depth Space”, IEEE Transactions on Multimedia, 21(6): 1464-1475, June 2019 [9] H. Cheng, J. Zhang, Q. Wu, and P. An, “A Computational Model for Stereoscopic Visual Saliency Prediction,” IEEE Transactions on Multimedia, 21(3): 678-689, Mar 2019 [10]J. Zhao, P. An, X. Huang, C. Yang, and L. Shen, “Light Field Image Compression via CNN-Based EPI Super-Resolution and Decoder-Side Quality Enhancement,” IEEE Access, vol. 7, 135982–135998, 2019 [11]L. Shan, P. An, C. Meng, X. Huang, C. Yang, and L. Shen, “A No-Reference Image Quality Assessment Metric by Multiple Characteristics of Light Field Images,” IEEE Access, Vol. 7, 127217-127229, 2019.9 [12]J. Yang, P. An, L. Shen, Y. Wang, “No-Reference Stereo Image Quality Assessment by Learning Dictionaries and Color Visual Characteristics,” IEEE Access, 2019 [13]Z. Gao, J. Huang, X. Yang, P. An, “Calibration of Rotating 2D LIDAR Based on Simple Plane Measurement,” Sensor Review, 39(2), 190-198, 2019 [14]Y. Zuo, Q. Wu, J. Zhang, and P. An, “Minimum Spanning Forest with Embedded Edge Inconsistency Measurement Model for Guided Depth Map Enhancement,” IEEE Transactions on Image Processing, 27(8): 4145-4159, 2018 [15]Y. Zuo, Q. Wu, J. Zhang, P. An, “Explicit Edge Inconsistency Evaluation Model for Color-Guided Depth Map Enhancement,” IEEE Transactions on Circuits and Systems for Video Technology, 28(2): 439-453, 2018 [16]X. Huang, P. An, L. Shen and R. Ma, “Efficient Light Field Images Compression Method Based on Depth Estimation and Optimization,” IEEE Access, 6:48984-48993, 2018 [17]D. Liu, P. An, R. Ma, C. Yang, L. Shen, K. Li, “Scalable Coding of 3D Holoscopic Image by Using a Sparse Interlaced View Image Set and Disparity,” Multimedia Tools and Applications, 77(1): 1261-1283, 2018 [18]L. Yang, P. An, D. Liu, et al, “3D Holoscopic Images Coding Scheme by Using A Sparse Viewpoint Image Array and Disparities,” Journal of Electronic Imaging, 27(3): 033030, 2018 [19]Z. You, P. An, D. Liu, “Scalable Kernel-Based Minimum Mean Square Error Estimate for Light-Field Image Compression,” EURASIP Journal on Image and Video Processing, online, 2018 [20]Y. Zuo, Q. Wu, P. An, X. Shang, “Integrated Cosparse Analysis Model with Explicit Edge Inconsistency Measurement for Guided Depth Map Upsampling,” Journal of Electronic Imaging, 27(4): 043004, 2018 [21]J. Ma, P. An, L. Shen, K. Li, “Joint Binocular Energy-Contrast Perception for Quality Assessment of Stereoscopic Images,” Signal Processing: Image Communication, 65:33-45, 2018 [22]J. Ma, P. An, L. Shen, K. Li, “Reduced-Reference Stereoscopic Images Quality Assessment Using Natural Scene Statistics and Structural Degradation,” IEEE Access, Vol. 6: 2768-2780, 2018 [23]J. Ma, P. An, L. Shen, K. Li, “Blind Quality Assessment of 3D Images Using Joint Statistics of Binocular Rivalry and Orientation Tuned Responses,” Journal of Electric Imaging, 27(4), 2018 [24]Z. Jin, P. An, C. Yang, L. Shen, “Fast QTBT Partition Algorithm for Intra Frame Coding Through Convolutional Neural Network,” IEEE Access, Vol. 6: 54660-54673, 2018 [25]X. Huang, P. An, Q. Zhang, “Efficient AMP Decision and Search Range, Adjustment Algorithm for HEVC,” EURASIP Journal on Image and Video Processing, Vol. 2017(1): 1-15, 2017 [26]J. Ma, P. An, L. Shen, K. Li, “Full-Reference Quality Assessment of Stereoscopic Images by Learning Binocular Visual Properties,” Applied Optics, 56(29): 8291-8302, 2017 [27]C. Yang, P. An, D. Liu, L. Shen, K. Li, “Bit Allocation for 3D Video Coding Based on Lagrangian Multiplier Adjustment,” Signal Processing-Image Communication, Vol. 52: 1-5, 2017 [28]C. Yang, P. An, L. Shen, and D. Liu, “Adaptive Bit Allocation for 3D Video Coding,” Circuits Systems and Signal Processing, Vol. 36: 2102-2124, 2017 [29]C. Yang, P. An, L. Shen, R. Ma, N. Feng, “Fast Depth Map Coding Based on Virtual View Quality,” Signal Processing: Image Communication, Vol. 47: 183-192, 2016 [30]Y. Zuo, P. An, L. Shen, D. Liu, C. Li, R. Ma, “Integration of Colour and Affine Invariant Feature for Multi-View Depth Video Estimation,” Imaging Science Journal, 64(6): 313-320, 2016 [31]D. Liu, P. An, R. Ma, C. Yang, L. Shen, K. Li, “Three-Dimensional Holoscopic Image Coding Scheme using High-Efficiency Video Coding with Kernel-Based Minimum Mean-Square-Error Estimation,” Journal of Electronic Imaging, 25(4): 043015, 2016 [32]D. Liu, P. An, R. Ma, C. Yang, L. Shen, “3D Holoscopic Image Coding Scheme Using HEVC with Gaussian Process Regression”, Signal Processing: Image Communication,Vol.47: 438-451, 2016 [33]H. Li, P. An, Z. Zhang, “Full High-Definition Real-Time Depth Estimation for 3D Video System,” Optical Engineering, 53(9): 093108-1~ 093108-11, 2014 [34]Q. Zhang, P. An, Y. Zhang, L. Shen, Z. Zhang, “Efficient Depth Map Compression for View Rendering in 3D Video,” Image Science Journal, 61(4): 385-395, 2013 [35]Q. Zhang, P. An, Y. Zhang, L. Shen, Z. Zhang, “Low Complexity Multiview Video Plus Depth Coding,” IEEE Transactions on Consumer Electronics, 57(4): 1857-1865, 2011 [36]T. Yan, P. An, L. Shen, Z. Zhang, “Bit Allocation and Rate Control Algorithm for MVC,” Imaging Science Journal, 59(4): 202-210, 2011 [37]Q. Zhang, P. An, Z. Zhang, H. Wang, Y. Wu, G. Jiang, “New Reconstruction Method for Intermediate Views from Multiple Views,” The Image Science Journal, 58(2): 89-95, 2010 [38]Liu Suxing, An Ping*, Zhang Zhaoyang, Zhang Qian, Shen Liquan, “High Quality Virtual View Synthesis Based on Corrected Surface Mapping and Image Fusion,” Electronics Letters, 45(1): 30-32, 2009 [39]S. Liu, P. An, Z. Zhang, Q. Zhang, T. Yan, “Multi-view Video Coding Based on Vector Estimation and Weighted Disparity Interpolation,” Circuits System Signal Process, 28(6): 913-923, 2009 [40]S. Liu, P. An, Z. Zhang, Q. Zhang, L. Shen, “On the Relationship Between Multi-View Data Capturing and Quality of Rendered Virtual View,” Imaging Science Journal, 57(5): 250-259, 2009 授权发明专利 [1] 安平、余芳、严徐乐,一种基于3D显著性和视点合成预测的3D-HEVC编码方法,专利号 ZL 201610889330.X,授权日期: 2019.8.6 [2] 马然,李攀攀,侯宇,安平,一种可分级多视点视频加深度宏块编码模式快速选择方法,专利号:ZL 201511015791.6,授权日期: 2019.7.23 [3] 郑嘉杰,滕国伟,安平,一种基于运动检测的人体异常行为检测方法,专利号:ZL 201610104559.8,授权日期: 2019.4.2 [4] 王健鑫、安平、周杰、郑帅、严徐乐,一种基于匹配区域的点云配准方法,专利号:ZL 201610023654.5,授权日期: 2018.10.30 [5] 马然、李攀攀、康朦朦、安平,一种MVD视点可分级编码中的快速模式选择方法,专利号 ZL 201610190391.7,授权日期: 2018.10.23 [6] 都腾跃、尤志翔、安平、周杰,一种联合空间时间轴的双视点立体视频稳定方法,授权号 ZL 201611115334.9,授权日期: 2018.8.7 [7] 安平、王健鑫、尤志翔、张兆杨、尚峰、范金慧、施剑平,一种对Kinect深度图像中的空洞进行实时填充的方法,专利号 ZL 201410327220.5,授权日期:2017.5.31 [8] 安平、赵冰、王健鑫、张兆杨,一种对Kinect深度图像进行空洞修复的方法,专利号: ZL201410196630.0,授权日期: 2017.5.10 [9] 胡锦雯、滕国伟、尚峰、安平、晏轲、杨骁,一种基于纹理复杂度的HEVC编码尺寸快速判定方法,专利号:ZL 201410147363.8, 授权日期: 2017.5.10 [10]郑专、安平、邬芙琼、王奎、张兆杨,双目系统中一种基于GPU的实时绘制方法,专利号:ZL 201210366761.X, 授权日期:2016.1.13 [11]邬芙琼、安平、郑专、张秋闻、张兆杨,基于JNDD模型的快速深度图编码模式选择方法,专利号:ZL 201210237892.8,授权日期:2015.7.1 [12]安平、李春华、尤志翔、闫吉辰、张兆杨,一种平行摄像机阵列下的已标定多视图像校正方法,专利号:ZL 201210516827.9,授权日期:2015.5.6 [13]安平、李贺建、张兆杨, 一种立体视频实时深度估计系统硬件实现方法,专利号: ZL 201310154526.0,授权日期:2015.5.6 [14]张艳、安平、张兆杨、张秋闻、郑专,一种基于双目最小可辨失真模型的立体视频质量评价方法,专利号:ZL201110391478.8,授权日期:2014.2.12 [15]安平、张倩、张兆杨,感兴趣区域增强的视点绘制方法,专利号:ZL201010215416.7,授权日期:2012.12.19 [16]张洋、张兆杨、安平、王贺、刘利亮,平行式相机阵列的未标定多视点图像校正方法,专利号:ZL201010545107.6,授权日期:2012.10.31 [17]傅瀛、王永芳、刘静、武翠芳,多视点视频解码端去块滤波方法,专利号:ZL201110053291.7,授权日期:2012.10.31 [18]安平、鞠芹、张兆杨、张倩、吴妍菲,基于颜色分割的多目摄像立体匹配获取深度图像的方法,专利号:ZL200910198231.7,授权日期:2011.12.21 [19]周利、安平、张兆杨、刘苏醒,基于光线空间的自由视点图像质量评价方法,专利号:ZL200810203999.4,授权日期:2011.1.19 [20]张兆杨、刘苏醒、安平、沈礼权、宓桃、张倩、严涛,汇聚式相机的多视采集/显示系统中的新视点重建方法,专利号:ZL200810040630.6,授权日期:2010.9.15 [21]张兆杨、安平、骆艳,一种立体视频流编码/解码器及其立体视频编解码系统,专利号:ZL03116541.9,授权日期, 2005.6.1 |