王中元
9728太阳集团 计算机科学系 国家多媒体软件工程技术研究中心 教授 (博导)
姓名:王中元
主页:
性别:男
职称:教授 (博导)
学历学位:博士
电话:
办公地点:604
E-mail:wzy_hope ▇ 163.com 请手工替换符号
领域:多媒体技术与大数据分析,计算机视觉,空间信息处理,
招生信息:年度招收硕士0名,招收方向:。 招收博士0名,招收方向:。
|
研究方向
王中元,9728太阳集团、国家多媒体软件工程技术研究中心教授,博士生导师。长期从事多媒体信息处理、监控视频大数据分析、身份计算的研究,主持国家自然科学基金面上项目3项、重点项目1项,主持湖北省技术创新重大项目1项,担任新一代宽带无线移动通信网国家重大科技专项项目副组长。作为技术负责人研制的网络摄像机、视频服务器分别获得CES大奖、全国十大安防新锐产品,参加实施了东莞平安城市、深圳电子公交监控等重大工程项目,编制3项公安部标准,针对新冠肺炎人员防控研发的口罩人脸识别技术受到湖北日报、环球时报、中国科技新闻网等媒体广泛关注。在国际权威期刊和顶级国际会议发表论文80余篇(含5篇ESI热点/高被引论文),第一申请人授权发明专利30余项,其中3项专利技术被我国AVS国家标准采纳,指导研究生获得IEEE AIM 2019国际竞赛第二名。获得教育部、公安部、湖北省、广东省科技奖励6项。
教育背景
1991-1995, 9728太阳集团本科
1998-2001,9728太阳集团硕士
2001-2008,9728太阳集团博士
2012-2013, 美国Texas A&M大学博士后访问学者
工作经验
2001-2006,9728太阳集团助教
2006-2009,9728太阳集团讲师
2009-2014,9728太阳集团副教授
2014-,9728太阳集团教授
教授课程
数字图像处理、深度学习与计算机视觉、数字视频处理。
发表论文
[1] Zhongyuan Wang, Ruimin Hu, Shizheng Wang, Junjun Jiang, Face Hallucination via Weighted Adaptive Sparse Regularization, IEEE Transactions on Circuits and Systems for Video Technology, vol. 24, no. 5, pp. 802–813, 2014.
[2] ZhongYuan Wang, Zhen Han, RuiMin Hu, JunJun Jiang, Noise robust face hallucination employing Gaussian-Laplacian mixture model, Neurocomputing, 133:153-160, 2014.
[3] Zhongyuan Wang, Ruimin Hu, Zhenfeng Shao, Zhiqiang Hou, Parameter Estimation in Sparse Representation Based Face Hallucination, Digital Signal Processing, 31: 28-34, 2014.
[4] Rui Zhong, Ruimin Hu, Zhongyuan Wang, Shizheng Wang, Fast Synopsis for Moving Objects Using Compressed Video, Signal Processing Letters, 21 (7): 834-838, Jul. 2014.
[5] J. Jiang, R. Hu, Z. Wang, and Z. Han, Noise Robust Face Hallucination via Locality-constraint Representation, IEEE Transaction on Multimedia, 16(5):1268-1281 , Aug. 2014.
[6] Junjun Jiang, Ruimin Hu, Zhongyuan Wang, Zhen Han, Face Super-Resolution via Multi-layer Locality-constrained Iterative Neighbor Embedding and Intermediate Dictionaries Learning, IEEE Trans. on Image Process., 23(10): 4220 - 4231 ,Oct. 2014.
[7] Zhiqiang Hou, Ruimin Hu, Zhongyuan Wang, Cloud Model-based Dynamic Texture Synthesis for Video coding, ICPR 2014, pp. 838 -842.
[8] Jinhui Hu, Ruimin Hu, Zhongyuan Wang, Structure tensor based in-loop filter for depth video coding, Electronics Letters, 50 (4):274-276, 2014.
[9] Lin Jiang, Ruimin Hu, Xiaochen Wang, Maoshen Zhang, Zhongyuan Wang, AVS2 speech and audio coding scheme for high quality at low bitrates, ICME 2014, pp.1-6.
[10] Zhongyuan Wang, Jun Chang, Ruimin Hu, Rui Zhong, Generating algorithm for integer DST radixes in video coding, Journal of Visual Communication and Image Representation, 25 (8): 1918–1921, 2014.
[11] Shenming Qu, Ruimin Hu, Shihong Chen, Junjun Jiang, Zhongyuan Wang, Jun Chen, Face hallucination via re-identified K-nearest neighbors embedding,ICME 2014, pp.1-6.
[12] Rui Zhong, Ruimin Hu, Zhongyuan Wang, Shizheng Wang, 3D Hybrid Just Noticeable Distortion modeling for Depth Image-Based Rendering, Multimedia Tools and Applications, vol.74, no.23, pp. 10457-10478 , 2015.
[13] Shenming Qu, Ruimin Hu, Zhongyuan Wang, Shihong Chen, Face hallucination via Cauchy regularized sparse representation, ICASSP’2015, pp. 1216-1220.
[14] Jin Wang, Chao Liang, Xiaochen Wang, Zhongyuan Wang, Real-life Voice Activity Detection based on Audio-visual Alignment, PCM 2015, vol. 9315, pp.109-117.
[15] Zhongyuan Wang, Jing Xiao, Tao Lu, Zhenfeng Shao, Ruimin Hu, Tuning Sparsity for Face Hallucination Representation, PCM 2015, vol. 9314, pp.299-309.
[16] Mingshen Ma, Ruimin Hu, Shihong Chen, Jing Xiao, Zhongyuan Wang, Shenming Qu, Global Object Representation of Scene Surveillance Video Based on Model and Feature Parameters, PCM 2015, vol. 9314, pp. 223-232.
[17] 宋晓炜,刘清丽,杨蕾,刘洲峰,王中元.基于Kinect传感器的红外场景增强, 激光与红外, 45(3):325-330, 2015年3月.
[18] 王瑾,梁超,王晓晨,王中元,胡瑞敏.基于视觉显著度的说话检测, 9728太阳集团学报(理学版),2015,(04) .
[19] Zhongyuan Wang, Zhen Han, Qijun Wang, and Jinhui Hu, Face hallucination via trend-constrained regularization, Journal of Signal Processing Systems, 79 (1): 105-111,Apr. 2015.
[20] JingYa Zhu, ZhongYuan Wang, Rui Zhong, ShenMing Qu, Dictionary based surveillance image compression, J. Vis. Commun. Image R., 31: 225–230, Aug. 2015.
[21] Zhongyuan Wang, Jinhui Hu, ShiZheng Wang, Tao Lu, Trilateral constrained sparse representation for Kinect depth hole filling, Pattern Recognition Letters, 65(1): 95–102, 2015.
[22] Shenming Qu, Ruimin Hu, Shihong Chen, Junjun Jiang, Zhongyuan Wang, Maosheng Zhang, Super-resolution for face image with an improved K-NN search strategy, China Communications, vol. 13, no. 4, pp. 151-161, 2016.
[23] Junjun Jiang, Ruimin Hu, Zhongyuan Wang, Zhen Han, Jiayi Ma, Facial Image Hallucination through Coupled-Layer Neighbor Embedding, IEEE Trans. on Circuits and Systems for Video Technology, vol. 26, no.9, pp.1674-1684, Sept. 2016.
[24] Zhongyuan Wang, Xiaowei Song, ShiZheng Wang, Jing Xiao, Rui Zhong, Ruimin Hu, Filling Kinect depth holes via position-guided low rank matrix completion, Neurocomputing, vol.215, pp.48–52, Nov. 2016.
[25] Zhongyuan Wang, Ruimin Hu, Junjun Jiang, Zhen Han, Zhenfeng Shao, Heteroskedasticity tuned mixed-norm sparse regularization for face hallucination, Multimedia Tools and Applications, vol.75, no. 24, pp.17273–17301, Dec. 2016.
[26] Tang H., Liu X., Xiong C., Wang Z., Ez Eldin M., Proof of Nondeterministic Polynomial-Time Complete Problem for Soil Slope-Stability Evaluation, International Journal of Geomechanics, vol. 16, no. 5, Oct. 2016.
[27] Junjun Jiang, Zhongyuan Wang, Chen Chen, Tao Lu, L1-L1 norms for face super-resolution with mixed Gaussian-impulse noise, ICASSP 2016, pp. 2089-2093.
[28] Kefan Shen, Zhongyuan Wang, Zhen Han, Fast video enhancement transcoding, ICIP’2016, Phoenix, Arizona, USA, Sept. 25-28, 2016, pp. 2177-2181.
[29] Liguo Zhou, Zhongyuan Wang, Youming Fu, Jun Chen, Rui Xiang, Rui Zhong, Shizheng Wang, Depth image in-loop filter via graph cut, ICIP’2016, pp. 4027-4031.
[30] Jiayi Ma, Chang Li, Yong Ma, Zhongyuan Wang, Hyperspectral image denoising based on low-rank representation and superpixel segmentation, ICIP’2016, pp.3086 -3090.
[31] Liuyi Hu, Zhongyuan Wang, Mang Ye, Jing Xiao, Ruimin Hu, Spatiotemporal saliency based on location prior model, International Joint Conference on Neural Networks( IJCNN), 2016, pp.2526 -2533. (Oral)
[32] Liang Chen, Ruimin Hu, Zhen Han, Zhongyuan Wang, Qing Li, Zheng Lu. Face Super Resolution for VLQ facial images via parent patch matching. International Joint Conference on Neural Networks (IJCNN), 2016, pp. 2515-2521. (Oral)
[33] Qi wang,Zhongyuan Wang,Jing Xiao, Jun Xiao, Wenbin Li, Fine-grained Vehicle Recognition in Traffic Surveillance, PCM 2016, pp. 285-295. (Oral)
[34] Mengling Shao, Ruimin Hu, Xu Wang, Zhongyuan Wang, Jing Xiao, Ge Gao, Salient Object Detection in Video Based on Dynamic Attention Center, PCM 2016, pp.458-468.
[35] Mingfu Xiong, Jun Chen, Zheng Wang, Zhongyuan Wang, Ruimin Hu, Chao Liang, Daming Shi, Person re-identification via multiple coarse-to-fine deep metrics, European Conference on Artificial Intelligence (ECAI), 2016, pp. 355-362.
[36] Junjun Jiang, Jiayi Ma, Chen Chen, Zhongyuan Wang, Tao Lu, Smooth sparse representation for noise robust face super-resolution, VCIP 2016, pp.1-4.
[37] Chang Li,Yong Ma,Yuan Gao, Zhongyuan Wang, Jiayi Ma, Sparse unmixing of hyperspectral data based on robust linear mixing model, VCIP 2016, pp.1-4.
[38] Jinhui Hu, Zhongyuan Wang, Ruolin Ruan, Kinect Depth Holes Filling by Similarity and Position Constrained Sparse Representation, ICISP 2016: 378-387.
[39] Jing Xiao, Ruimin Hu, Liang Liao, Zhongyuan Wang, Zxixiang Xiong, Knowledge-based Coding of Objects for Multisource Surveillance Video Data, IEEE Transactions on Multimedia, 18(9): 1691-1706, 2016.
[40] Jing Xiao, Zhongyuan Wang, Yu Chen, Liang Liao, Jun Xiao, Gen Zhan, Ruimin Hu, A Sensitive object-oriented Approach to Big Surveillance Data Compression for Social Security Applications in Smart Cities, Software Experience and Practice, vol. 47, no. 8, pp.1061-1080, 2017.
[41] J. Jiang, J. Ma, C. Chen, X. Jiang, and Z. Wang, Noise robust face image super-resolution through smooth sparse representation, IEEE Transactions on Cybernetics, vol. 47, no. 11, pp. 3991–4002, 2017.
[42] Junjun Jiang, Xiang Ma, Chen Chen, Tao Lu, Zhongyuan Wang, Jiayi Ma, Single Image Super-Resolution via Locally Regularized Anchored Neighborhood Regression and Nonlocal Means, IEEE Transactions on Multimedia, 19(1):15-26, 2017.
[43] Junjun Jiang, Chen Chen, Jiayi Ma, Zheng Wang, Zhongyuan Wang, Ruimin Hu, SRLSP:A Face Image Super-Resolution Algorithm Using Smooth Regression with Local Structure Prior, IEEE Transactions on Multimedia, 19(1):27-40, 2017.
[44] Anna Zhang, Zhen Han, Zhongyuan Wang, Efficient mode decision for noisy video transcoding, ICASSP 2017, pp.1527-1531.
[45] Liang Chen, Ruimin Hu, Zhen Han, Zhongyuan Wang, Qing Li, A joint learning based face super resolution approach via contextual topological structure, ICASSP 2017, pp.1088-1092.
[46] Xu Wang, Ruimin Hu, Jing Xiao, Zhongyuan Wang, Cruise UAV Video Compression Based on Long-Term Wide-Range Background, DCC'2017, pp.466-466.
[47] Yong Ma, Huabing Zhou, Jun Chen, Jingshu Shi, Zhongyuan Wang, Non-Rigid Feature Matching for Image Retrieval Using Global and Local Regularizations, ICME 2017, pp. 1416 – 1421.
[48] Xiao Aoran, Shao Zhenfeng, Zhongyuan Wang, Sparse Coding for Super-Resolution via K-Means Classification, 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 10-14 July 2017, pp. 363-368.
[49] Zhongyuan Wang, Zhiqiang Hou, Jing Xiao, Ruoxi Wang, Rong Zhu, A Hybrid Intra Refresh and Reference Selection Scheme for Mobile Video Coding, 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 10-14 July 2017, pp. 357-362.
[50] Zhongyuan Wang, Liguo Zhou, Rong Zhu, Zheng He, Dan Chen, Sharpness preservation video upscaling, the 2017 10th International Congress on Image and Signal Processing (CISP’2017), 2017, pp. 1-5.
[51] Anna Zhang, Zhongyuan Wang, Zhen Han, Youming Fu, Zhen He, H.264 Based Screen Content Coding With HSV Quantization, CISP 2017, pp. 1-5.
[52] Huafeng Chen, Jun Chen, Ruimin Hu, Chen Chen, Zhongyuan Wang, Action recognition with temporal scale-invariant deep learning framework, China Communications, 14(2): 163-172, 2017.
[53] Tao Lu, Hao Wang, Zixiang Xiong, Junjun Jiang, Yanduo Zhang, Huabing Zhou, Zhongyuan Wang, Face hallucination using region-based deep convolutional networks, ICIP 2017.
[54] T. Lu, L. Pan, J. Wang, Y. Zhang, Z. Wang, and Z. Xiong, AWCR: Adaptive and weighted collaborative representations for face super-resolution with context residual-learning, Proc. PCM'2017, Harbin, China, Sept. 2017.
[55] Shu Wang, Zhongyuan Wang, Yimin Luo, Structured Convolutional Compressed Sensing Based on Deterministic Subsamplers, PCM 2017, pp. 400-410.
[58] 肖骏, 肖晶, 王中元, 陈宇, 面向刑事侦查的监控视频显著性检测仿真,计算机仿真
[59] Yimin Luo, Liguo Zhou, Shu Wang and Zhongyuan Wang, Video Satellite Imagery Super-Resolution via Convolutional Neural Networks, IEEE Geoscience and Remote Sensing Letters (GRSL), vol.14, no.12, pp. 2398-2402, 2017.
[60] Liguo Zhou, Zhongyuan Wang, Yimin Luo, and Zixiang Xiong, Separability and Compactness Network for Image Recognition and Superresolution, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 30, no. 11, pp. 3275-3286, Nov. 2019.
[61] Mingfu Xiong, Jun Chen, Zhongyuan Wang, Liang Chao and Ruimin Hu, A Multi-scale Triplet Deep Convolutional Neural Network for Person Re-identification, The Pacific-Rim Symposium on Image and Video Technology ( PSIVT 2017), v 10799 LNCS, p 30-41, 2018.
[62] Zhenfeng Shao, Jiajun Cai, Zhongyuan Wang, Smart Monitoring Cameras Driven Intelligent Processing to Big Surveillance Video Data, IEEE Transactions on Big Data, vol. 4, no. 1, pp. 105-116, 2018.
[63] Liguo Zhou, Zhongyuan Wang, Shu Wang and Yimin Luo, Coarse-to-Fine Image Super-Resolution Using Convolutional Neural Networks, 24th International Conference on Multimedia Modeling (MMM 2018) in Bangkok, Thailand, Feb. 5-7, 2018.
[64] Yujing Chen, Jing Xiao, Gen Zhan, Xu Wang, ZhongYuan Wang, Two-level Segment-based Bitrate Control for Live ABR Streaming, MMM 2018. (Oral)
[65] Xin Ding, Ruimin Hu, Zhen Han and Zhongyuan Wang, A Novel Frontal Facial Synthesis Algorithm Based on Individual Residual Face, MMM 2018.
[66] Junjun Jiang, Jiayi Ma, Chen Chen, Zhongyuan Wang, Lizhe Wang, SuperPCA: A Superpixelwise Principal Component Analysis Approach for Unsupervised Feature Extraction of Hyperspectral Imagery, Transactions on Geoscience and Remote Sensing (TGRS), vol.56, no.8, pp. 4581-4593, 2018.
[67] Junjun Jiang, Qing Ma, Tao Lu, Zhongyuan Wang, Jiayi Ma, Feature Matching based on Top K Rank Similarity, ICASSP 2018, Calgary, Canada, 15-20 April 2018, pp. 2316-2320.
[68] Liang Liao, Ruimin Hu, Jing Xiao, Zhongyuan Wang, Edge-Aware Context Encoder for Image Inpainting, ICASSP 2018, pp. 3156 -3160.
[69] Liguo Zhou, Rong Zhu, Yimin Luo, Siwen Liu and Zhongyuan Wang, Improving convolutional neural networks via compacting features, ICASSP 2018, pp. 2946 -2950.
[70] Aoran Xiao, Zhongyuan Wang, Lei Wang and Yexian Ren, Super-Resolution for “Jilin-1”Satellite Video Imagery via a Convolutional Network,Sensors, 18(4): 1194, 2018.
[71] Jing Xiao, Liuyi Hu, Zhongyuan Wang, et. al., Video Saliency Detection Using Spatiotemporal Cues, IEICE Transactions on Information and Systems, vol. E101D, no. 9, pp. 2201-2208, September 2018.
[72] Ma Minsheng, Hu Ruimin, Chen Shihong, Xiao Jing, Wang Zhongyuan, Robust Background Subtraction Method via Low-Rank and Structured Sparse Decomposition, China Communications, 15(7): 156 -167, 2018.
[73] Xuehua Tang, Zhongyuan Wang, Xiaojun Li, Zhen Han, Zheng He, Youming Fu, Performance Analysis for Multimedia Communication Systems with a Multilayer Queuing Network Model,China Communications, vol. 15, no.8, pp. 67-77, 2018.
[74] Zhangyang Xiong, Zhongyuan Wang, Changqing Du, Rong Zhu, Jing Xiao, Tao Lu, An Asian Face Dataset and How Race Influences Face Recognition, PCM 2018.
[75] Siwen Liu, Rong Zhu, Yimin Luo, Zhongyuan Wang, Liguo Zhou, Dataset Refinement for Convolutional Neural Networks via Active Learning, PCM 2018.
[76] Jin Guo, Jun Chen, Zhen Han, Han Liu, Zhongyuan Wang, Ruimin Hu, Adaptive Aggregation Network for Face Hallucination. PCM 2018: 190-199.
[77] Xi Yang, Tao Lu, Jiaming Wang, Yanduo Zhang, Yuntao Wu, Zhongyuan Wang, Zixiang Xiong, Enhanced Discriminative Generative Adversarial Network for Face Super-Resolution. PCM 2018: 441-452.
[78] Xu Wang, Ruimin Hu, Zhongyuan Wang, Jing Xiao, Virtual Background Reference Frame Based Satellite Video Coding, IEEE Signal Processing Letters (SPL), vol. 25, no.10, pp. 1445-1449, 2018.
[79] Kui Jiang, Zhongyuan Wang, Peng Yi, Junjun Jiang, A Progressively Enhanced Network for Video Satellite Imagery Superresolution, IEEE Signal Processing Letters (SPL), vol. 25, no. 11, pp. 1630-1634, 2018.
[80] Zhenfeng Shao, Wenjing Wu, Zhongyuan Wang, Wan Du, and Chengyuan Li,SeaShips: A Large-Scale Precisely-Annotated Dataset for Ship Detection, IEEE Transactions on Multimedia, vol. 20, no. 10, pp. 2593-2604, 2018.
[81] Kangli Zeng, Tao Lu, Junjun Jiang, Zhongyuan Wang, Nonlinear Contextual Face Hallucination, the 15th International Forum of Digital TV and Multimedia Communication (IFTC 2018), Sept. 20-21 2018, Shanghai China, pp. 249-258 .
[82] Tao Lu, Kangli Zeng, Junjun Jiang, Yanduo Zhang, Wei He, Zhongyuan Wang, Huabing Zhou, Face hallucination using manifold-regularized group locality-constrained representation, ICIP 2018.
[83] Tao Lu, Jiaming Wang, Huabing Zhou, Junjun Jiang, Jiayi Ma, and Zhongyuan Wang. "Rectangular-Normalized Superpixel Entropy Index for Image Quality Assessment", Entropy, 20(12), pp. 947, Dec. 2018.
[84] Kui Jiang, Zhongyuan Wang, Peng Yi, Junjun Jiang, Jing Xiao and Yuan Yao, Deep Distillation Recursive Network for Remote Sensing Imagery Super-Resolution, Remote Sensing, 10(11):1700, 2018.
[85] Zhongyuan Wang, Peng Yi, Kui Jiang, Junjun Jiang, Zhen Han, Tao Lu, and Jiayi Ma, Multi-Memory Convolutional Neural Network for Video Super-Resolution, IEEE Transactions on Image Processing, vol. 28, no.5, pp. 2530 -2544, 2019.
[86] Zhenfeng Shao, Linggang Wang, Zhongyuan Wang*, Wan Du, and Wenjing Wu, Saliency-Aware Convolution Neural Network for Ship Detection in Surveillance Video, IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no.3, pp.781-794, 2020.
[87] Zhongyuan Wang, Zhiqiang Hou, Ruimin Hu, Jing Xiao, A Lossless Recompression Approach for Video Streaming Transmission, IEEE Access, vol. 7, no. 1, pp. 35162-35172, 2019.
[88] Liang Liao, Ruimin Hu, Jing Xiao ,Zhongyuan Wang, Artist-Net: Decorating the Inferred Content with Unified Style for Image Inpainting, IEEE Access, vol. 7, no. 1, pp. 36921-36933, 2019.
[89] Guangcheng Wang, Zhongyuan Wang, Ke Gu, Zhifang Xia, Blind Quality Assessment for 3D-synthesized Images by Measuring Geometric Distortions and Image Complexity, ICASSP 2019, pp. 4040-4044.
[90] Yu Chen, Ruimin Hu, Jing Xiao, Zhongyuan Wang, Multisource Surveillance Video Coding by Exploiting 3D and 2D Knowledge, ICASSP 2019, pp. 1787-1791.
[91] Xu Wang, Ruimin Hu, Zhongyuan Wang, Jing Xiao, Yuhui Zhang, Long Term Background Reference Based Satellite Video Coding, ICASSP 2019, pp. 1822-1826.
[92] Xiaofen Wang, Jun Chen, Zhen Han, Mingfu Xiong, Chao Liang, Qi Zheng, Zhongyuan Wang, Rain Streak Removal via Multi-scale Mixture Exponential Power Model, ICASSP 2019, pp. 1767-1771.
[93] Xingyu Jiang, Junjun Jiang, Aoxiang Fan, Zhongyuan Wang, Jiayi Ma, Multiscale Locality and Rank Preservation for Robust Feature Matching of Remote Sensing Images, IEEE Transactions on Geoscience and Remote Sensing, 57(9): 6462-6472 , 2019.
[94] Kui Jiang, Zhongyuan Wang, Peng Yi, Guangcheng Wang, Tao Lu, Junjun Jiang, Edge-Enhanced GAN for Remote Sensing Image Superresolution, IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 8, pp. 5799-5812, 2019.
[95] K. Jiang, Z. Wang, P. Yi, J. Jiang, G. Wang, Z. Han, T. Lu, GAN-based Multi-Level Mapping Network for Satellite Imagery Super-Resolution, International Conference on Multimedia and Expo (ICME 2019), Shanghai, China, Jul 2019, pp. 526-531. (Oral)
[96] Shanfa Ke, Ruimin Hu, Gang Li, Tingzhao Wu, Xiaochen Wang, Zhongyuan Wang,Multi-Speakers Speech Separation Based on Modified Attractor Points Estimation and GMM Clustering, ICME 2019, pp. 1414-1419.
[97] Mengjun Qi, Zhongyuan Wang, Zheng He, Zhenfeng Shao, User Identification across Asynchronous Mobility Trajectories, Sensors 2019, 19(9), 2102.
[98] Mengjun Qi, Zhongyuan Wang, Zheng He, Tao Lu, Identifying Users by Asynchronous Mobility Trajectories, 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2019 ), Yokohama, Japan, 28 July-2 Aug. 2019, pp. 6811-6814.
[99] Qi Zheng, Jun Chen, Zhongyuan Wang, Junjun Jiang, Deep Segmentation Domain Adaptation Network with Weighted Boundary Constraint, IEEE Access, vol. 7, pp. 93909-93918, 2019.
[100] Tao Lu, Jiaming Wang, Yanduo Zhang, Zhongyuan Wang, Junjun Jiang, Satellite Image Super-resolution via Multi-scale Residual Deep Neural, Remote Sensing, vol. 11, no. 13, pp. 1588, 2019.
[101] Zhenfeng Shao, Lei Wang, Zhongyuan Wang, Juan Deng,Remote Sensing Image Super-resolution using Sparse Representation and Coupled Sparse AutoEncoder, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 12 (8): 2663-2674, 2019.
[102] Yu Chen, Ruimin Hu, Jing Xiao, Zhongyuan Wang, Multisource surveillance video coding with synthetic reference frame, Journal of Visual Communication and Image Representation (JVCI), J. Vis. Commun. Image R. 65 (2019) 102685.
[103] Yu Chen, Ruimin Hu, Jing Xiao, Liang Xu, Zhongyuan Wang, Multisource surveillance video data coding with hierarchical knowledge library, Multim. Tools Appl., 78(11): 14705-14731, 2019.
[104] Peng Yi, Zhongyuan Wang, Kui Jiang, Junjun Jiang and Jiayi Ma, Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations, IEEE International Conference on Computer Vision (ICCV), Seoul, 27 Oct.-2 Nov. 2019, pp. 3106-3115 (Oral).
[105] Wenqian Zhu, Ruimin Hu, Zhongyuan Wang, Dengshi Li, Xiyue Gao, Deep Structural Feature Learning: Vehicle Re-Identification In Structure-Aware Map Space, ACM Multimedia Asia 2019, 38:1-6, 2019.
[106] Guangcheng Wang, Zhongyuan Wang, Ke Gu, Leida Li, Zhifang Xia, Lifang Wu, Blind Quality Metric of DIBR-Synthesized Images in the Discrete Wavelet Transform Domain, IEEE Transactions on Image Processing, 29 (1): 1802-1814, 2020.
[107] Xu Wang, Ruimin Hu, Zhongyuan Wang, Jing Xiao, Shin’ichi Satoh, Long-Term Background Redundancy Reduction for Earth Observatory Video Coding, IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), DOI: 10.1109/TCSVT.2019.2950113, 2019.
[108] Zhongyuan Wang, Kui Jiang, Peng Yi, Zhen Han, Zheng He, Ultra-Dense GAN for Satellite Imagery Super-Resolution, Neurocomputing, vol. 398, pp. 328-337, 2020.
[109] Peng Yi, Zhongyuan Wang, Kui Jiang, Zhenfeng Shao, and Jiayi Ma, Multi-Temporal Ultra Dense Memory Network For Video Super-Resolution, IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 8, pp. 2503-2516, Aug. 2020.
[110] Jiayi Ma, Hao Zhang, Peng Yi, and Zhongyuan Wang*, SCSCN: A Separated Channel-Spatial Convolution Net with Attention for Single-view Reconstruction, IEEE Transactions on Industrial Electronics, 67 (10): 8649-8658, 2020.
[111] Qingnan Li, Ruimin Hu, Jing Xiao, Zhongyuan Wang, Yu Chen, Learning Latent Geometric Consistency for 6D Object Pose Estimation in Heavily Cluttered Scenes, Journal of Visual Communication and Image Representation (JVCI), vol. 70, 2020.
[112] Kui Jiang, Zhongyuan Wang, Peng Yi, Guangcheng Wang, Ke Gu, Junjun Jiang, ATMFN: Adaptive-threshold-based Multi-model Fusion Network for Compressed Face Hallucination, IEEE Transactions on Multimedia (TMM), vol. 22, no. 10, pp. 2734-2747, 2020.
[113] Kui Jiang, Zhongyuan Wang, Peng Yi, Chen Chen, Yuhong Yang, Xin Tian, Junjun Jiang, Attention-guided Deraining Network via Stage-wise Learning, ICASSP 2020, pp. 2618-2622.
[114] Yuerong Chen, Mengliang Zhang, Song Li, Zhongyuan Wang, Xin Tian, Cartoon-texture Decomposition-based Variational Pansharpening , ICASSP 2020, pp. 2688-2692.
[115] Mengliang Zhang, Ziping Zhao, Yuerong Chen, Zhongyuan Wang, Xin Tian, FusionNDVI: A Novel Fusion Method for NDVI in Remote Sensing, ICASSP 2020, pp. 4816-4820.
[116] Kuangye Liu, Zhen Han, Junkui Chen, Chunlei Liu, Jun Chen, Zhongyuan Wang, Image Super-resolution Using Residual Global Context Network, ICASSP 2020, pp. 2633-2637.
[117] Kui Jiang, Zhongyuan Wang, Peng Yi, Chen Chen, Baojin Huang, Yimin Luo, Jiayi Ma, Junjun Jiang, Multi-Scale Progressive Fusion Network for Single Image Deraining, CVPR 2020, pp. 8343-8352.
[118] Wenqian Zhu, Ruimin Hu, Zhongyuan Wang, Tell the truth from the front: anti-disguise vehicle re-identification, ICME 2020, pp. 1-6. (Oral)
[119] Zhenfeng Shao, Penghao Tang, Zhongyuan Wang, Nayyer Saleem, Sarath, BRRNet: A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images, Remote Sensing, 12(6): 1050 (2020).
[120] Zhongyuan Wang, Studying the Origin of COVID-19 from a Systematic Perspective, preprints:202004.0125.v1, April 2020.
[121] Xin Tian, Wei Chen, Fang Zhao, Bo Li, Zhongyuan Wang, Robust CBCT Reconstruction Based on Low-rank Tensor Decomposition and Total Variation Regularization, ICIP 2020.
[122] Kui Jiang, Zhongyuan Wang, Peng Yi, Junjun Jiang, Hierarchical Dense Recursive Network for Image Super-Resolution, Pattern Recognition (PR), vol. 107, 2020.
[123] Xuehua Tang, Qi Hong, Zhongyuan Wang, An Automatic Semantic Map Generation Method Using Trajectory Data, ISPRS Congresses 2020.
[124] Qi Hong, Zhongyuan Wang, Zheng He, Nanxi Wang, Xin Tian, Tao Lu, Masked Face Recognition with Identification Association, 32nd International Conference on Tools with Artificial Intelligence (ICTAI 2020), 2020.
[125] Baojin Huang, Zheng He, Zhongyuan Wang, Kui Jiang, Guangcheng Wang, Lightweight Progressive Residual Clique Network for Image Super-Resolution, 32nd International Conference on Tools with Artificial Intelligence (ICTAI 2020), 2020.
科研课题
国家自然科学基金面上项目“基于反向纹理合成的视频编码技术研究”
国家自然科学基金面上项目“基于时域选择特性和分级掩蔽的视频感知编码研究”
国家自然科学基金面上项目“面向视频卫星的多分辨率字典学习压缩视频超分辨率重建”
国家自然科学基金重点项目“面向监控摄像机网络的全局可信身份识别的理论与方法”
国家自然科学基金重点项目“三元空间身份计算理论及人物画像与定位技术”
国家自然科学基金面上项目,多通道多尺度时空融合的监控视频超分辨率重建
湖北省技术创新重大项目“面向多源大数据的身份追溯关键技术研究”
湖北省自然科学基金面上项目“面向立体视频监控的深度图像修复与编码”
武汉市应用基础研究计划项目“屏幕视频编码关键技术研究及应用”
深圳市基础研究项目“基于判别模版的监控视频事件检测关键技术研究”
中央高校基本科研业务费专项基金“多源异构空间大数据融合和信息挖掘”
深圳市基础研究项目“基于空间运动行为规律分析的异常社会安全行为发现 ”
华为创新研究项目“基于深度的视频增强”
华为空间信息技术创新实验室项目“面向社会安全的空间运动行为模式关键技术及应用研究”
9728太阳集团中南医院转化医学及交叉学科研究联合基金,“基于多模态医疗数据研究机械取栓出血转化预测模型”
湖北省高价值知识产权培育工程项目“8K超高清视频智能处理关键技术”
教育部-中国移动科研基金“基于WebRTC的实时视频通信能力关键技术研究”
湖北省自然科学基金创新群体项目“多媒体安防与刑事视频分析关键技术及应用研究”
湖北省技术创新重大项目, “新媒体智能播控关键技术及应用研究”
湖北省重点研发计划"深度伪造音视频鉴别关键技术研究与应用"
新一代宽带无线移动通信网国家重大科技专项课题“新型移动多媒体音视频编解码关键技术研发”
新一代宽带无线移动通信网国家重大科技专项课题“宽带移动业务关键技术开放式研究”子任务
新一代宽带无线移动通信网国家重大科技专项课题“新型移动业务控制网络的架构及关键技术”子任务
973计划子课题“面向智能监控的视频编码方法”
广东省现代信息服务发展专项资金“面向重点行业应用宽带无线多媒体接入系统开发和示范工程”
广东省教育部产学研项目“面向新一代移动通信设备的教育数字资源中心及应用”
广东省产学研项目“无线智能车载服务系统与产品的研发与产业化”
国家重点研发计划子课题“环境目标检测、识别与复杂交通场景构建”
“xxxxxxxxxx海上目标处理技术”
“xxxxxxxx卫星视频处理技术”
教育部中央高校基本科研业务费专项资金“基于视觉词袋模型的复杂海面环境下的舰船目标检测”
研究团队
研究生3~5名/年
知识产权
基于相似场景的低照度监控图像增强方法,王中元,朱婧雅,侯志强. 专利号: ZL 201210544491.7
一种基于最小二乘的多视点视频编码视点合成预测方法, 胡瑞敏,胡金晖,段漭,龚燕, 王中元, 专利号:ZL 2012102669459
基于纹理检测和颜色分割的视频图像运动目标提取方法, 胡瑞敏,侯志强, 王中元, 刘文杰,胡金晖,钟睿, 专利号:ZL 2012103514949
一种基于局部特征转换的人脸超分辨率重建方法,胡瑞敏,卢涛,王中元,韩镇,江俊君,夏洋,陈亮,黄克斌,高尚,王冰.专利号:ZL 201210575820.4
一种基于主成份稀疏表达的人脸图像超分辨率重建方法. 胡瑞敏,卢涛,江俊君,韩镇,王中元,黄克斌,专利号:ZL 201210574750.0
一种基于CFA的数码相机型号识别方法, 胡瑞敏,高尚,王中元,张茂胜,卢涛, 专利号:ZL 2012105621856
基于KINECT深度图的低光照图像增强方法及系统,胡瑞敏,胡金晖,王中元,郭春辉,侯志强,谭晓琼,杨阿慧,石艺.专利号:ZL 201310325623.1
基于白平衡的数码相机图像与计算机生成图像区分方法, 胡瑞敏,高尚,王中元,张茂胜,卢涛, 专利号:ZL 2012105638931
基于纹理与几何相似性的彩色图像空洞修复方法及系统, 胡瑞敏,钟睿,刘璐,石艺, 王中元, 专利号:ZL 2013102442740
一种H.264码率控制方法. 王中元,傅佑铭,侯志强,专利号: ZL 201310480150.2
基于K近邻重识别的人脸超分辨率重建方法,胡瑞敏,瞿慎明,江俊君,王中元,陈亮,黄振坤,胡金辉,ZL 201410074705.8
一种实时视频通信中的感兴趣区域提取方法. 王中元,朱婧雅,周治龙.专利号: ZL 201410333331.7
一种质量自适应的无线视频编码方法, 王中元,朱婧雅,胡孟凌. 专利号:ZL 201410536019.8
一种HEVC编码四叉树的递推译码方法,王中元,边学工,专利号: ZL 201510256658.3
一种视频卫星大数据的周期性编码方法,王中元,朱荣,牟海军,胡瑞敏, 专利号: ZL 201510344665.9
一种与H264标准兼容的屏幕内容编码解码方法, 王中元,傅佑铭,何政, 专利号: ZL 201510400827.6
一种基于过完备字典的视频监控图像压缩方法,王中元,朱婧雅,专利号: ZL 201510313822.X
一种抗模糊的图像放大方法,王中元,邵振峰,韩镇,肖晶,专利号:ZL 201510669656.7
一种基于计算机视觉的无人驾驶农机耕道测量装置及方法,王中元,马佳义,江俊君,朱荣,专利号:ZL 201610741333.9
一种多源数据融合的监控行人身份识别方法,王中元,胡瑞敏,怀念,朱荣,陈丹,专利号:ZL 201510903582.9
一种时空约束的监控视频行人重识别结果的二次优化方法,王中元,胡瑞敏,朱荣,陈丹,肖晶,梁超, 专利号:ZL 201510779639.9
基于自适应背景分割的监控视频移动目标跟踪方法及系统,邵振峰,蔡家骏,王中元,杨珂. 专利号:ZL 2015109928354
交通大数据采集中交通流分布估计及摄像头布点优化方法,邵振峰,王中元,蔡家骏, 专利号:ZL 201610806585.5
一种基于H.264和HSV颜色量化的屏幕图像编码方法,王中元,张安娜,朱荣,肖晶,专利号:ZL 201610143356.X
一种基于ImageNet检索的监控视频行人重识别方法,王中元,邵振峰,胡瑞敏,梁超,专利号:ZL 201510729442.4
一种面向可穿戴设备的视频直播方法,王中元,朱荣,傅佑铭,何政,专利号:ZL 201610303886.6
一种基于柯西正则化的人脸超分辨率方法,胡瑞敏,渠慎明,王中元,杨乘,江俊君, 丁新,董小慧,阮威健,专利号:ZL 201510151907.2
一种联合稀疏表示与深度学习的图像超分辨率方法及系统,邵振峰,王磊,王中元,蔡家骏,专利号:ZL201610216592X
异常行为预警信息约束的视频大数据快速检索方法及系统,邵振峰,蔡家骏,王中元, 杨珂,专利号:ZL201511022366X
徘徊事件时空大数据分析的异常行为预警方法及系统,邵振峰,蔡家骏,王中元,杨珂,专利号:ZL2015110279491
一种基于图像位置块近邻嵌入的人脸幻构方法,胡瑞敏,渠慎明,王中元,江俊君,张茂胜,廖良,关健,刘波,专利号:ZL 201510151884.5
基于全局显著边缘区域的人体动作特征提取方法,胡瑞敏,徐增敏,陈军,陈华锋,李红阳,王中元,郑淇,吴华,王晓,周立国,专利号:ZL 201610075788.1
一种内容复杂性自适应的视频卫星压缩图像超分辨率方法,王中元,韩镇,杜博,邵振峰,专利号:ZL 201710166661.5
一种面向屏幕视频编码的屏幕滚动检测方法,王中元,何政,傅佑铭,朱荣,专利号:ZL 201710318616.7
一种基于屏幕变化检测的屏幕视频编码方法,王中元,何政,常军,傅佑铭,专利号:ZL 201710852444.1
空间信息辅助的无人机视频大数据多时相关联分析方法,王中元,肖晶,陈丹,傅佑铭,专利号:ZL 201710166290.0
基于内容感知深度学习网络的遥感图像超分辨率重建,王中元,韩镇,杜博,邵振峰,专利号:ZL 201710301990.6
一种超分辨率图像重建方法及系统,邵振峰,肖傲然,王中元,专利号: ZL2017104884908
一种基于位置先验信息的时空域显著度检测方法,胡瑞敏,胡柳依,王中元,肖晶,王琦,邵孟灵,专利号:ZL201611078480.9
一种基于移动轨迹信息的用户行为模式画像的方法,王中元,祁梦军,何政,邵振峰,专利号:ZL201811031973.6
多社交网络用户关联系统软件,著作权人:9728太阳集团,证书号:4326497,登记号:2019SR0905740
监控场景下行人检索系统,著作权人:9728太阳集团,证书号:4326467,登记号:2019SR0905710
监控视频轨迹和手机轨迹时空关联系统,著作权人:9728太阳集团,证书号:4328634,登记号:2019SR0907877
自动口罩佩戴系统,著作权人:9728太阳集团,证书号:5597386,登记号:2020SR0718690
学术服务
跨域多维电子围网关键技术及应用,2019年广东省科技进步一等奖
高能效无线多媒体网络设计与优化研究,2016年湖北省自然科学二等奖
城市安防视频监控报警多级联网系统平台及关键技术研究,2011年广东省科技进步二等奖
车载多媒体通信系统,2009年教育部科技进步奖二等奖
Green2000数码彩扩机及数字图像光引擎,2010年度中国电子学会电子信息科学技术二等奖
基于转码的视频分发服务平台关键技术研究及示范,2010年公安部科技进步三等奖
IEEE AIM 2019 Challenge on Video Extreme Super-Resolution, 亚军.
英特尔杯”第一届中国研究生人工智能创新大赛全国总决赛三等奖,2019年
中国人工智能产业发展联盟“旷视人工智能开源大赛”,第三名, 2020年
城市监控报警联网系统 技术标准 第4部分:视音频编、解码技术要求
城市监控报警联网系统 技术标准 第5部分: 信息传输、交换、控制技术要求
城市监控报警联网系统 技术标准 第8部分:传输网络技术要求
Real-World Masked Face Dataset,口罩人脸数据集:
https://github.com/X-zhangyang/Real-World-Masked-Face-Dataset
成果展示
Real-World Masked Face Dataset,口罩人脸数据集
https://github.com/X-zhangyang/Real-World-Masked-Face-Dataset
A Progressive Fusion Generative Adversarial Network for Realistic and Consistent Video Super-Resolution (TPAMI 2020)
https://github.com/psychopa4/MSHPFNL
Multi-Memory Convolutional Neural Network for Video Super-Resolution(TIP 2019)
https://github.com/psychopa4/MMCNN
ATMFN: Adaptive-Threshold-Based Multi-Model Fusion Network for Compressed Face Hallucination (TMM 2020)
https://github.com/kuihua/ATMFN
Edge-enhanced GAN for remote sensing image superresolution,TGRS, 2019
https://github.com/kuihua/EEGAN
Blind Quality Metric of DIBR-Synthesized Images in the Discrete Wavelet Transform Domain(TIP 2020)
https://github.com/wgc-vsfm/DIBR-Image-Quality-Assessment
其他