Basic Information/基本信息

 

       Xuguang Lan, Ph.D.   

 Professor

  Institute of Artificial Intelligence and Robotics

   College of Artificial Intelligence 

    Xi'an Jiaotong University

兰旭光,博士

  教授,博士生、硕士生导师

  人工智能与机器人研究所

 人工智能学院

  西安交通大学

 

 

Contact Information

西安交通大学人工智能与机器人研究所西安市咸宁西路28 号,710049

邮箱:xglan@mail.xjtu.edu.cn

 

 

Biography/个人简介

兰旭光于2005年12月在西安交通大学模式识别与智能系统专业获得的工学博士学位。2005年5月到法国里昂中央理工大学作访问研究;同年12月进入西安交通大学计算机专业做博士后研究。2010年2月被选入西安交通大学“青年骨干教师培养计划”,2013.9-2014.10月在美国西北大学做访问学者。现为西安交通大学人工智能学院教授,副院长。

研究领域或方向:

1) 计算机视觉;

2)统计学习与模式识别;

3)深度强化学习与机器人学习;

4)人-机器人共融协作。

目前担任中国认知科学学会理事,副秘书长,人工智能学会“认知系统与信息处理”专职委员会副主任委员,“模式识别”专职委员会委员,自动化学会“混合智能”专职委员,IET Cognitive Computation and Systems期刊编委会,《机器人》期刊编委,《模式识别与人工智能》期刊编委,IEEE CYBER2019计划联合主席,曾多次担任IEEE ICME / ICASSP等国际会议的程序委员会委员。担任主席,已主持国家自然科学基金重点项目,重大专项,863,基金面上,国家973项目子课题等科研项目10余项。在IEEE反式等期刊和CVPR等国际会议上发表论文70余篇,获得国家发明专利授权10余项,获软件著作权4项。IEEE高级会员。

Research Interests/研究兴趣

主要研究方向:

1)计算机视觉;

2)统计学习与模式识别;

3)深度强化学习与机器人学习;

4)人-机器人共融协作;

主持国家自然科学基金重点项目1项,核高基1项,青年基金和面上4项,973子课题1项,863课题1项,陕西省重点项目1项,参加基金重点项目和其他863项目多项。

Research Interests:

1)Computer vision

2)Statistical Learning and Pattern Recognition

3)Deep Reinforcement Learning and Robot Learning

4)Human-Robot collaboration

We gratefully acknowledge the support of Nature Science Foundation of China no. 60805044 and 61175010, National Basic Research Program 973 no.2012CB316402, High-tech Program 863 no.2009AA011709, etc.

 人机协作

  

  

Publication

1)Journal papers

[30] Jin Li, Xuguang Lan, Yang Long, Yang Liu, Xingyu Chen, Ling Shao, and Nanning Zheng, A Joint Label

       Space for Generalized Zero-Shot Classification, IEEE Transactions on Image Processing,

       DOI:10.1109/TIP.2020.2986892

[29] Hanbo Zhang, Xinwen Zhou, Xuguang Lan, Jin Li, Zhiqiang Tian, Nanning Zheng. A Real-time Robotic

       Grasping Approach with Oriented Anchor Box. IEEE Trans. Syst. Man Cybern. Syst., Doi:10.1109/TIP.

       2019.2899782, 2019.

[28] 万里鹏, 兰旭光, 张翰博, 郑南宁,深度强化学习理论及其应用综述,模式识别与人工智能, Vol. 32,

  no.2, pp: 67-81, 2019.

[27] Guoqiang Liang, Xuguang Lan, Xingyu Chen, Kang Zheng, Song Wang, Nanning Zheng, Cross-View Person

       Identification based on Confidence-weighted Human Pose Matching. IEEE Trans. Image Processing, vol.28,

       no.8, pp.3821-3835, Aug. 2019.

[26] Hanbo Zhang, Xuguang Lan, Xinwen Zhou, Zhiqiang Tian, Yang Zhang, Nanning Zheng, Robotic Grasping

       in Multi-Object Stacking Scenes based on Visual Reasoning. SCIENTIA SINICA Technologica, Volume 48,

       Issue 12: 1341-1356, November 2018.

[25] Meng Yang, Ce Zhu, Xuguang Lan, Nanning Zheng, Efficient Estimation of View Synthesis Distortion

       for Depth Coding Optimization IEEE Trans. Multimedia, PP(99):1-1, September 2018. DOI:

      10.1109/TMM.2018.2870540.

[24] Guoqiang Liang, Xuguang Lan, Jiang Wang and Nanning Zheng, A limb-based Graphical Model for

       Human Pose EstimationIEEE Trans. Syst.  Man Cybern. Syst., vol.48, no.7, July 2018.

[23] Jin Li, Xuguang Lan, Xiangwei Li, Jiang Wang, Nanning Zheng, Ying Wu, Online Variable Coding Length

       Product Quantization for Fast Nearest  Neighbor Search in Mobile Retrieval, IEEE Trans. Multimedia,

       vol. 19, no. 3, pp:559-570, Mar. 2017.

[22] Xingyu Chen, Xuguang Lan, Guoqiang Liang, Jianyi Liu, Nanning Zheng, Pose-and-illumination-invariant

       Face Representation via a Triplet-loss  Trained Deep Reconstruction Model, Multimedia tools and application,

       2017, vol. 76, no. 21, pp.22043–22058, November 2017.

[21] Xiangwei Li, Xuguang Lan, Meng Yang, Jianru Xue, Nanning Zheng, A New Compressive Sensing Video

       Coding Framework Based on Gaussian Mixture Model, Signal Processing: Image Communication,2017,

       vol. 55, pp. 66-79, July 2017.

[20] Jin Li , Xuguang Lan, Jiang Wang , Meng Yang, Nanning Zheng, Fast Additive Quantization for Vector

       Compression in Nearest Neighbor SearchMultimedia tools and application, 2017, vol. 76, no. 22,

       pp 23273–23289, November 2017.

[19] Yi Lai, Xuguang Lan, Yuehu Liu, and Nanning Zheng, An efficient depth image-based rendering with depth

       reliability maps for view synthesisJournal of Visual Communication and Image Representation, 2016, vol. 41,

       pp. 176-184, Nov. 2016.

[18] Xiangwei Li, Xuguang Lan, Meng Yang, JianruXue and Nanning Zheng, Efficient Lossy Compression for

       Compressive Sensing  Acquisition of Images  in Compressive Sensing Imaging Systems, Sensors, vol.14,

       no.12, pp.23398-23418; doi:10.3390/s141223398,2014.

[17] M. Yang, Xuguang Lan, N. Zheng, and P. Cosman, Depth-assisted Temporal Error Concealment for Intra Frame

       Slices in 3D Video IEEE Trans. Broadcasting, Vol.60 , no. 2, pp. 385 – 393, Ju. 2014.

[16] Zhiqiang Tian, Nanning Zheng, Jianru Xue, Xuguang Lan, Ce Li, Gang Zhou, Video object segmentation with

       shape cue based on spatiotemporal superpixel neighborhood, IET Computer Vision, Vol.8, no.1,pp.16 – 25,

       2014.

[15] Shizhou Zhang, Jinjun Wang, Yihong Gong, Shun Zhang, Xinzi Zhang, Xuguang Lan, Image parsing by loopy

       dynamic programming. Neurocomputing 145: 240-249, 2014.

[14] Jianji Wang, Xuguang Lan, Nanning Zheng, Fractal image encoding with flexible classification sets, Chinese

       Science Bulletin, vol.59, no.14, pp.1597–1606, 2014.

[13] Zhiqiang Tian, Jianru Xue, Xuguang Lan, Ce Li, Nanning Zheng, Object Segmentation and Key-Pose based

       Summarization for Motion Video,Multimedia Tools and Applications, Vol. 72,no.2, pp 1773-1802, 2014.

[12] Meng Yang, Xuguang Lan, Nanning Zheng, Adaptive Multiple Description Coding for Hybrid Networks with

       Dynamic PLR and BER, Signal Processing: Image Communication, Vol. 28, no. 9, pp. 1132–1142, 2013.

[11] Ce Li, JianruXue, Nanning Zheng, Xuguang Lan, ZhiqiangTian, Spatio-temporal Saliency Perception Via

      Hypercomplex Frequency, Sensors, 2013.

[10] Xuguang Lan, Meng Yang, Yuan Yuan, Songlin Zhao, Nanning Zheng, Adaptively post-encoding multiple

       description videocodingNeurocomputing, 101: 149-160, 2013 .

[9] Xuguang Lan, Nanning Zheng, Wen Ma, Yuanyuan, Arbitrary ROI-based Wavelet VideoCoding, Neurocomputing,

     vol.74, issue 12-13, pp. 2114-2122, June 2011.

[8] Yi Lai, Xuguang Lan, Xiangwei Li, Yuehu Liu, and Nanning Zheng, An Efficient Region of Interest Support in

     Scalable Multi-view Video Coding, IEEE Trans.  Consumer Electronics, vol.57, no.3, pp. 1271-1279, Aug. 2011.

[7] Wei Hu,Jianru Xue,Xuguang Lan,Nanning Zheng,Local patch based regularized least squares model for

     compression artifacts removal, IEEE Trans. Consumer Electronics, vol.55, no. 4, pp. 2057 – 2065, 2009.

[6] Xuguang Lan, Nanning Zheng, Jianru Xue, Bin Gao and Xiaoguang Wu. Adaptive VoD Architecture based

     On Scalable Wavelet Video Coding. IEEE Trans.  Consumer Electronics, vol.53, no.4, pp.: 1401-1409,

     November 2007.

[5] Xuguang Lan, Nanning Zheng and Yuehu Liu. Low-Power and High-Speed VLSI Architecture of 2-D DWT for

     Forward and Backward Transform. IEEE Trans.Consumer  Electronics. vol.51, no. 2, pp.:379-385,

     May 2005.

[4] 兰旭光,郑南宁,梅魁志,刘跃虎. JPEG2000并行阵列式小波滤波器的VLSI结构设计.电子学报. Vol.32,

  No.11:1806-1809, 2004.

[3] 兰旭光,郑南宁,薛建儒,刘跃虎,梅魁志. 小波滤波器低功耗并行的VLSI结构设计. 计算机研究与发展.

  vol.42,No.11: 1889-1995, 2005.

[2] 刘在德,兰旭光,张明新,参数化的Deslauriers-Dubuc插值小波构造及图像编码性能分析,自动化学报,

  vol.40, no.10, pp.2234-2345, 2014.

[1] 兰旭光,李兴玉,温灏,宏块并行可复用的H.264帧内解码器的VLSI结构设计, 微电子学与计算机,

  vol.31,no.4,2014.

 

2)Conference Papers

[47] Xingyu Chen, Xuguang Lan, Fuchun Sun, Nanning Zheng. A Boundary Based Out-Of-Distribution

       Classifier for Generalized Zero-Shot Learning[C]//Proceedings of the European Conference on

       Computer Vision (ECCV).

[46] Hanbo Zhang, Site Bai, Xuguang Lan*, David Hsu, Nanning Zheng, Hindsight Trust Region Policy Optimization,

       https://arxiv.org/abs/1907.12439. submitted to ICML2020.

[45] Chenjie Yang, Xuguang Lan*, Hanbo Zhang, Nanning Zheng. Autonomous Tool Construction with

       Gated Graph Neural Network2020 IEEE International Conference on Robotics and Automation (ICRA).

       May. 31-June. 4, 2020. Paris, France.

[44] Jie Xu, Xuguang Lan, Jin Li, Xingyu, Chen, Nanning Zheng, EAN: Error Attenuation Network for

       Long-term Human Motion PredictionProceedings of 2nd China Symposium on Cognitive Computing

       and Hybrid Intelligence, CCHI 2019, pp.178-183, Sep. 2019, Xi'an China.

[43] Jieru Mei, Xingyu Chen, Chunyu,Wang, Alan,Yuille, Xuguang,Lan, Wenjun Zeng, Learning to Refine

       3D Human Pose SequencesProceedings of International Conference on 3D Vision(3DV) 2019,

        p.358-366, Canada, Sep. 2019.

[42] Yongchao Wang, Xuguang Lan, Chuzhen Feng, Lipeng Wan, Jin Li, Yuwang Liu and Decai Li,

       An experience-based policy gradient method for smooth manipulation,The 9th IEEE International

       Conference on CYBER Technology in Automation, Control, and Intelligent Systems(IEEE-CYBER

       2019),July, 2019,Suzhou, China

[41] Wensong Chan,Zhiqiang Tian, Shuai Liu, Jing Ren, Xuguang Lan, Action recognition with

       spatial-temporal attention,Proceedings of 12th International Conference of Intelligent

       Robotics and Applications(ICIRA) 2019, Lecture Notes in Computer Science, v.11742,  

       pp.461-471, Aug.2019, Shenyang China.

[40] Hanbo Zhang, Xuguang Lan*, Site Bai, Lipeng Wan, Chenjie Yang, Nanning Zheng. A Multi-task

       Convolutional Neural Network for Autonomous Robotic Grasping in Object Stacking Scenes.

       2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Nov. 4-8,

       2019. Macau, China.

[39] Chenjie Yang, Xuguang Lan*, Hanbo Zhang, Nanning Zheng. Task-oriented Grasping in Object

       Stacking Scenes with CRF-based Semantic Model. 2019 IEEE/RSJ International Conference on

       Intelligent Robots and Systems (IROS). Nov. 4-8, 2019. Macau, China.

[38] Hanbo Zhang, Xuguang Lan*, Site Bai, Xinwen Zhou, Zhiqiang Tian, Nanning Zheng. ROI-based

       Robotic Grasp Detection for Object Overlapping Scenes. 2019 IEEE/RSJ International Conference

       on Intelligent Robots and Systems (IROS). Nov. 4-8, 2019. Macau, China.

[37] Jin Li, Xuguang Lan, Yang Liu, Le Wang, Nanning Zheng, Compressing Unknown Classes with

       Product Quantizer for Efficient Zero-Shot Classification, IEEE CVPR 2019, June 16-20, USA, 2019.

[36] Kang Wang, Xuguang Lan, Chuzhen Feng, Distributed Depth Video Coding Based on Compressive

       Sensing and Gaussian Mixture ModelsChinese Automation Congress, November 30-December 2,

       Xi'an, China, 2018.

[35] Chenjie Yang, Xuguang Lan, Hanbo Zhang, Xinwen Zhou, Nanning Zheng. Visual Manipulation

       Relationship Detection with Fully Connected  CRFs for Autonomous Robotic Grasp. IEEE International

       Conference on Robotics and Biomimetics (ROBIO), Kuala Lumpur, Malaysia, December 12~15, 2018.

[34] Hanbo Zhang, Xuguang Lan*, Xinwen Zhou, Zhiqiang Tian, Yang Zhang, Nanning Zheng,

       Visual Manipulation Relationship Network for Autonomous Robotics, IEEE/RAS 18th International

       Conference on Humanoids Robots (Humanoids), November, 6-9, Beijing, China, 2018.

[33] Xinwen Zhou, Xuguang Lan, Hanbo Zhang, Zhiqiang Tian, Yang Zhang and Nanning Zheng,

       Fully Convolutional Grasp Detection Network with Oriented Anchor Box, IEEE International

       Conference on Intelligent Robots(IROS 2018), October, 1-5, Madrid, Spain, 2018.

[32] Guoqiang Liang, Xuguang Lan, Kang Zheng, Song Wang, Nanning Zheng, Cross-View Person

       Identification by Matching Human Poses Estimated with Confidence on Each Body Joint, In

       AAAI Conference on Artificial Intelligence 2018, New Orleans, USA, 2018.

[31] Kang Wang, Xuguang Lan, Xiangwei Li, Meng Yang, Nanning Zheng, Compressive Sensing Depth

       Video Coding via Gaussian Mixture  Models and Object Edges, PCM 2017, Harbin, China, 2017.

[30] Hanbo Zhang, Xuguang Lan, Xinwen Zhou, Vision-based robotic grasp success determination with

       convolutional neural network, The 7th  Annual IEEE Int. Conf. on CYBER Technology in Automation,

       Control, and Intelligent Systems (IEEE CYBER2017), Hawaii, USA, 2017.

[29] Guoqiang Liang, Xuguang Lan, Hanbo Zhang, Xingyu Chen, Nanning Zheng. Intention-based Human

       Robot Collaboration.19th International Conference on Intelligent Robotics and Applications (ICIRA 2017),

       Wuhan, China, 2017.

[28] Jin Li, Xuguang Lan, Nanning Zheng, Iteratively Multiple Projections Optimization for Product Quantization

       in Nearest Neighbor SearchInt’l. Conf. Big Knowledge (ICBK) 2017, Hefei, China, 2017.

[27] Xiangwei Li, Xuguang Lan, Meng Yang,Jianru Xue,Nanning Zheng, Efficient Compressive Sensing Video

       Compression Method Based on Gaussian Mixture Models, VCIP2016, pp. 1-4, 2016.

[26] Jiayi Chen, Xuguang Lan, Meng Yang, Efficient Detail-enhanced Exposure Correction Based on Auto-fusion for

       LDR Image, Proceedings of the IEEE 18th Workshop on Multimedia Signal Processing. Montreal, Canada, 2016.

[25] Guoqiang Liang, Xuguang Lan, Jiang Wang, Nanning Zheng, Human pose estimation based on human limbs,

       ICPR 2016, Cancun, Mexico, Dec. 2016.

[24] Qiong Xue, Xuguang Lan, and Meng Yang, Depth Map Coding by Modeling the Locality and Local

       Correlation of View Synthesis Distortion in 3-D Video, MMM2016, pp.1-12, Miami, Florida, USA, 2016.

[23] Xiangwei Li, Xuguang Lan, Meng Yang, Jianru Xue, and Nanning Zheng, Optimized Truncation Model

       for Adaptive Compressive Sensing  Acquisition of Images, IEEE VCIP 2015, pp.1-4, Singapore, 2015.

[22] Meng Yang, Ce Zhu, Xuguang Lan, and Nanning Zheng, Parameter-free View Synthesis Distortion

       Model with Application to Depth Video Coding, IEEE International Symposium on Circuits and

       Systems (ISCAS2015), pp.1-4, Portugal, 2015.

[21] Xiangwei Li, Xuguang Lan, Meng Yang, JianruXue, Nanning Zheng: Universal and low-complexity

       quantizer design for compressive sensing image coding. IEEE VCIP 2013: 1-5, 2013.

[20] Jin Li, Gang Hua, Xuguang Lan, Nanning Zheng: An Integrated Model for Bayesian Learning of Sparse

       Representation and Classifier Training. PCM 2013: 620-628, 2013.

[19] M. Yang, Y. Yang, P. Cosman, Depth-assisted Error Concealment for Intra Frame Slices in 3D Video,

       in Proc. ICIP 2012, Orlando, FL, USA, pp. 1281-1284, Oct.2012.

[18] Yi Lai, Xuguang Lan, Yuehu Liu, and Nanning Zheng, Improved view synthesis with depth reliability maps,

       The IEEE Data Compression Conference (DCC2012). April, 2012, Snowbird, Utah, USA.

[17] Yi Lai, Xuguang Lan, Yuehu Liu, and Nanning Zheng, Disocclusion using depth reliability map for

       view synthesisThe 37th IEEE International Conference on Acoustics, Speech, and Signal Processing

       (ICASSP2012). April, 2012, Japan.

[16] Yi Lai, Xuguang Lan, e.t., Region of Interest Support in Scalable Multi-View Video Coding, Proc.

       ICCE 2011, Las Vagas, USA, Jan. 2011.

[15] Meng Yang, Xuguang Lan, and Nanning Zheng, Explicit Network-Adaptive Robust Multiple Description

       CodingProc. IEEE DCC 2011, Las Vagas, USA, March 2011.

[14] Meng Yang, Xuguang Lan, and Nanning Zheng, Design of Error-Resilient M-description Codec over

       Wireless Broadcasting Networks Proc. 8th Annual IEEE Consumer Communications and Networking

       Conference (IEEE CCNC2011), Las Vagas, USA, Jan. 2011.

[13] Meng Yang, Xuguang Lan, and Nanning Zheng, Consecutive Redundancy Control for Robust

       Multiple Description Coding over Unreliable Networks, Proc. IEEE Wireless Communications and

       Networking Conference (IEEE WCNC2011), Mar. 2011.

[12] Zhiqiang Tian, Jianru Xue, Ce Li, Xuguang Lan, Nanning Zheng, Auto-generated Strokes for Motion

       Segmentation,IEEE International Symposium on Circuits and Systems 2011, May, 2011, Brazil

[11] Zhiqiang Tian, Jianru Xue, Nanning Zheng, Xuguang Lan, Ce Li, 3D Spatio-temporal Graph Cuts

       for Video Objects Segmentation,IEEE International Conference on Image Processing (ICIP 2011),

       Sep. 2011, Belguim

[10] Zhiqiang Tian, Jianru Xue, Xuguang Lan, Ce Li, Nanning Zheng, Key Object-based Static Video

       SummarizationACM Multimedia 2011, Nov. 2011

[9] Xuguang Lan, Nanning Zheng, e.t. Arbitrary ROI-based Wavelet Video Coding, Proc. IEEE Data

     Compression Conference (DCC 2010) 2010, March, 2010, Snowbird, Utah, USA.

[8] Xuguang Lan, Nanning Zheng, JianruXue, Ce Li, and Songlin Zhao. Joint Network-Source Video Coding

     based on Lagrangian Rate Allocation, Proc. IEEE Data Compression Conference (DCC 2009) 2009,

     March, 2009, Snowbird, Utah, USA.

[7] Xuguang Lan, Jianru Xue, A Peer-to-Peer Architecture with DRM, Proc. IEEE CCNC2009, Las Vagas,

     USA, pp.1-5, Jan. 2009.

[6] Xuguang Lan, Nanning Zheng, Jianru Xue, Songlin Zhao and Weike Chen, Scalable Multiple Description

     Coding Based On Bitplane And Lagrangian Rate Allocation, Proc. IEEE Consumer Communications &

     Networking Conference (CCNC 2008), pp. 811-812, Jan. 10 - 12,2008, Las Vegas, Nevada, USA.

[5] Xuguang Lan, Nanning Zheng, Jianru Xue, Weike Chen, Bin Wang and Wen Ma, Songlin Zhao. A

     Peer-to-Peer Architecture Based on Scalable Video Coding. Proc. IEEE Data Compression

     Conference (DCC 2008) 2008, pp.529, March 25 - 27, 2008, Snowbird, Utah, USA.

[4] Xuguang Lan, Nanning Zheng, Jianru Xue, Xiaoguang Wu and Bin Gao, Weike Chen, Manageable

     Peer-to-Peer Architecture for Video-on-DemandProc. 22nd IEEE International Parallel and Distributed

     Processing Symposium (IPDPS2008), pp.1-7, April 14-18, 2008, Miami, Florida USA.

[3] Xuguang Lan, Nanning Zheng, Jianru Xue, Xiaoguang Wu and Bin Gao. A Peer-to-Peer Architecture

     for Efficient Live Scalable Media Streaming on Internet, Proc. ACM Multimedia 2007, pp.783-786,

     Sep. 24-29, 2007, Augsburg, Germany

[2] Jianru Xue, Shugang Guo and Xugang Lan. Joint Content and Temporal Correlation Adaptive MCTF, Proc.

     The 26th Picture Coding Symposium (PCS2007).12-13 November 2007, Lisbon, Portugal.

[1] Xuguang Lan, Nanning Zheng and Yuehu Liu. Low-Power and High-Speed VLSI Architecture of 2-D DWT

     for JPEG 2000.Proc. IEEE International Symposium on Consumer Electronics Proceedings,

     pp.110-113.2004 UK.

 

3)Conference Proceedings

[2] Nanning Zheng, GerogeLoizou, Xiaoyi Jiang, XuguangLan and Xuelong Li (Guest Editors), Special Issue: Computer

     Vision and Pattern Recognition, International Journal of Computer Mathematics, Vol. 84, No. 9, September, 2007.

     ISSN 0020-7160

[1] Nanning Zheng, Xiaoyi Jiang, Xuguang. Lan (Eds.). Advances in Machine Vision, Image Processing, and Pattern

     Analysis, IWICPAS2006, Springer LNCS 4153, 2006, ISBN:3-540-37597-x; ISSN:0302-9743.

 

Patents/专利

 国家发明专利10余项授权

[17] 一种基于端对端网络的机器人视觉推理抓取方法。发明人:兰旭光;张翰博;周欣文;田智强;郑南宁。

   专利申请号:2019100939525, 中国,2019年1月

[16] 一种基于视觉推理的机器人作业方法。发明人:兰旭光;张翰博;周欣文;张扬;田智强;郑南宁。

   专利申请号:2018109249925, 中国,2018年8月

[15] 一种基于最优截断模型的自适应压缩感知图像获取方法。发明人:兰旭光,李翔伟,杨勐,薛建儒,郑南宁。

   专利号:ZL201510368776.3, 中国,2018年12月

[14] 一种基于高斯混合模型的压缩感知视频编解码方法。发明人:兰旭光,李翔伟,杨勐,薛建儒,郑南宁。

   专利申请号:201510944725.0 , 中国,2015年10月

[13] 并行阵列式帧内预测解码器VLSI结构设计方法,发明人:兰旭光,杨志远,韩骞逸,李兴玉,专利号:

   ZL201010223353.X,中国,2013年5月

[12] 并行流水运动补偿滤波器VLSI结构设计方法,发明人:兰旭光,惠苗,郜金金,李兴玉,专利号:

   ZL201010222854.6,中国,2013年2月

[11] P2P流媒体网络自适应分级传输结构设计方法,发明人:兰旭光,陈伟科,薛健儒,毕重远,王斌,郑南宁,

   专利号:ZL200810236553.1,中国,2012.1

[10] 可伸缩视频编码的P2P网络传输体系结构设计方法,发明人:兰旭光,薛建儒,郑南宁,吴晓光,高彬,

   ZL200710017759.0,中国,2009.11

[9] 易于管理的实时流媒体P2P网络传输系统设计方法,发明人:兰旭光,薛建儒,郑南宁,吴晓光,高彬,

  赵松霖,陈伟科,ZL200710017761.8,中国,2009.8

[8] 基于码率控制的可伸缩多描述视频编码结构设计方法,发明人:兰旭光,赵松霖,薛健儒,王斌,李策,

  惠苗,郑南宁,专利:ZL200810236445.4,中 国, 2011.6

[7] 基于感兴趣区域运动补偿时域滤波技术,发明人:兰旭光,马雯,薛健儒,王斌,郑南宁,专利号:

  ZL200810236531.5,中国,2011.6

[6] 基于感兴趣区域的自适应可伸缩视频编解码结构设计方法,发明人:兰旭光,薛健儒,郑南宁,惠苗,李策,

  陆硕,ZL200810232550.0,中国,2011.1

[5] 一种自适应运动补偿时域滤波的方法,发明人:薛建儒,郭树岗,郑南宁,兰旭光,ZL200710017715.8,中国

[4] 一种分布式多格式数字视频转码结构设计方法,发明人:薛健儒,杨国安,田智强,胡伟,付强,杨致远,

  兰旭光,ZL200810232701.2,中国, 2010.7

[3] 内在并行的二维离散小波变换的VLSI结构设计方法.专利号:ZL031146023,中国,授权公告日2005.2.2;

  发明人:兰旭光,郑南宁,周宁,梅魁志

[2] 可伸缩视频编解码体系结构设计方法, 专利号: ZL200510041909.2,中国, 发明人:薛建儒,兰旭光,郑南宁

[1] 高性能空域可伸缩的运动估计与运动矢量编码实现方法, 专利申请号:ZL200510041910.5,中国,

  发明人:兰旭光,薛建儒,郑南宁