视觉感知与机器学习团队

团队简介

拥有教授1人、副教授1人、博士讲师4人，省研究生教学名师/高水平导师1人；面向多模态智能感知、机器智能及智能生成等领域的共性技术需求为驱动，在基于深度学习计算机视觉自然/医学图像复原增强、基于数据特征的质量控制与预测、工业领域数据样本智能生成、医学图像智能诊断、行人重识别、多视角在线学习、3D点云处理与可视化、深度图网络学习等方面开展一列研究。研究成果可为消费电子、智能行业软件及智能制造等工程应用提供关键技术支撑。近年来主持或承担国家自然科学基金项目2项、省部级以上项目8项、产学研合作及协同创新项目2项, 发表SCI/EI论文60余篇, 获国家发明专利10余项。

团队成员

近年主要科研项目：

[1] 国家自科基金面上项目(61971004), 基于深度生成模型的图像及视频超分辨研究及应用， 2020/01-2023/12, 主持

[2] 国家自科基金青年项目(62206006), 基于多语义伪标签估计的无监督行人重识别方法与理论研究, 2023/01-2025/12, 主持

[3] 安徽省自然科学基金(2008085MF190), 深度卷积图像超分辨网络的多阶特征注意力机制研究, 2020/01-2022/12, 主持

[4] 军委装备发展部预先研究项目（共用技术）（80912020104），弱小移动目标数据扩充和自动标注的实时侦测与识别方法研究，2022/09-2023/12，第一主研

[5] 教育部计算智能与信号处理重点实验室开放课题（2020A002），基于自监督学习与注意力机制的视频超分辨方法研究，2020/01-2022/12，主持

[6] 安徽省自然科学基金(1808085QF210),  基于结构化表示的相关投影分析方法研究, 2018/06-2020/06, 主持

[7] 安徽省教育厅自科基金重点项目(KJ2021A0375), 基于伪标签估计的无监督行人重识别研究, 2022/01-2023/12, 主持

[8] 安徽省高校协同创新重大项目（GXXT-2019-018），全自动转盘挤奶机套杯机器人的研发与应用子课题，2020/01-2021.12，主持

[9] 安徽省自然科学基金项目面上项目(1608085MF129)，基于深度学习隔空动态手势身份识别机理及应用研究, 2016/01-2018.12, 主持。

[10] 安徽省高校自然科学研究重大项目，基于深度学习的多模态动态手势身份识别原理研究，2015/01-2017/12，主持

近年主要论文：

[1] Yongzhen Wang, Jiamei Xiong, Xuefeng Yan, et al. USCFormer: Unified Transformer with Semantically Contrastive Learning for Image Dehazing[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24: 1-13.

[2] 王永振, 童鸣, 燕雪峰等. 面向真实战场环境的Transformer-CNN多特征聚合图像去雾算法[J]. 兵工学报, 2023: 1-11.

[3] Zhiheng Hu, Yongzhen Wang, Peng Li, et al. iSmallNet: Densely Nested Network with Label Decoupling for Infrared Small Target Detection[C]. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023: 1-5.

[4] Yanbiao Niu, Xuefeng Yan, Yongzhen Wang, et al. Three-dimensional collaborative path planning for multiple UCAVs based on improved artificial ecosystem optimizer and reinforcement learning[J]. Knowledge-Based Systems, 2023, 276: 110782.

[5] Yanbiao Niu, Xuefeng Yan, Yongzhen Wang, et al. Three-dimensional UCAV path planning using a novel modified artificial ecosystem optimizer[J]. Expert Systems with Applications, 2023, 217: 119499.

[6] Yongzhen Wang, Xuefeng Yan, Donghai Guan, et al. Cycle-SNSPGAN: Towards Real-World Image Dehazing via Cycle Spectral Normalized Soft Likelihood Estimation Patch GAN[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11):20368-20382.

[7] Yongzhen Wang, Xuefeng Yan, Hexiang Bao, et al. Detecting Occluded and Dense Trees in Urban Terrestrial Views with a High-quality Tree Detection Dataset[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-12.

[8] Yongzhen Wang, Xuefeng Yan, Kaiwen Zhang, et al. TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning [J]. Computer Graphics Forum, 2022, 41(7): 465-476.

[9] Heng Liu, Jianyong Liu, Feng Chen. Progressive Residual Learning with Memory Upgrade for Ultrasound Image Blind Super-resolution. JEEE Journal of Biomedical and Health Informatics, 2022, 26(9): 4390 – 4401.

[10] Rui Wang#, Feng Chen#, Jun Tang*, Pu Yan. Adaptive Camera Margin for Mask-guided Domain Adaptive Person Re-identification. In: Proceedings of the 30th ACM International Conference on Multimedia (MM ’22), October 10–14, 2022, Lisboa, Portugal. ACM, New York, NY, USA, doi: 10.1145/3503161.3548216

[11] Yuezhong Chu, Yunan Qiao, Heng Liu* et al. Dual Attention with the Self-Attention Alignment for Efficient Video Super-resolution. Cognitive Computation, 2022, 14:1140–1151.

[12] Zhen Tang, S. Mahmoodi, A. Darekar, and B. Vollmer, 2022. Hypoxic-Ischaemic Encephalopathy Prognosis using Susceptibility Weighted Image Analysis based on Histogram Orientation Gradient. In: Proceedings of 15th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 4: BIOSIGNALS, ISBN 978-989-758-552-4, ISSN 2184-4305, pages 57-62.

[13] Feng Chen, Tongtong Zhang, Heng Liu*. Face image inpainting via latent features reconstruction and mask awareness[J]. Computers and Electrical Engineering, 2022, 103: 108282.

[14] Jie Wang, Yongzhen Wang, Yidan Feng, et al. Contrastive Semantic-Guided Image Smoothing Network[J]. Computer Graphics Forum, 2022, 41(7): 335-346.

[15] Yiyang Shen, Yongzhen Wang, Mingqiang Wei, et al. Semi-MoreGAN: Semi-supervised Generative Adversarial Network for Mixture of Rain Removal[J]. Computer Graphics Forum, 2022, 41(7): 443-454.

[16] 熊佳梅, 王永振, 燕雪峰等. 一种基于语义引导和对比学习的战场图像去烟算法[J]. 兵工学报, 2022: 1-12.

[17] 范益华, 王永振, 燕雪峰等. 人脸识别任务驱动的低光照图像增强算法[J]. 图学学报, 2022, 43(06): 1170-1181.

[18] Heng Liu, Jianyong Liu, Shudong Hou, et al. Perception consistency ultrasound image super-resolution via selfsupervised CycleGAN. Neural computing and applications, 2021, https://doi.org/10.1007/s00521-020-05687-9. (高被引论文).

[19] Yongzhen Wang, Xuefeng Yan, and Junan Zhang. Research on GPU parallel algorithm for direct numerical solution of two-dimensional compressible flows [J]. Journal of Supercomputing, 2021, 77(10): 10921-10941.

[20] Zhen Tang, S. Mahmoodi, A. Darekar and B. Vollmer, 2023. Automatic veins analysis of susceptibility weighted image in hypoxic-ischaemic encephalopathy. Magnetic Resonance Imaging，98，pp.83-96.

[21] Feng Chen, Nian Wang, Jun Tang*, Dong Liang. A Negative Transfer Approach to Person Re-identification via Domain Augmentation[J], Information Sciences, 2021, 549:1-12.

[22] Feng Chen, Nian Wang, Jun Tang*, Fan Zhu. A Feature Disentangling Approach for Person Re-identification via Self-supervised Data Augmentation[J], Applied Soft Computing, 2021, 100: 106939.

[23] Feng Chen, Nian Wang, Jun Tang*, Dong Liang, Hao Feng. Self-supervised Data Augmentation for Person Re-identification[J], Neurocomputing, 2020, 415:48-59.

[24] Heng Liu, Jiajun Qin, Zilin Fu, et al. Fast simultaneous image super-resolution and motion deblurring with decoupled cooperative learning, Journal of Real-Time Image Processing, 2020, 17(6): 1787-1800.

[25] Heng Liu, Ziling Fu, Jungong Han, Single Image Super-Resolution Using Multi-Scale Deep Encoder-Decoder with Phase Congruency Edge Map Guidance. Information Sciences, 2019, 473:44-58.

[26] Xianglin Guo, et.al. Robust Low-Rank Subspace Segmentation with Finite Mixture Noise, Pattern Recognition 93 : 55-67 (2019)

[27] Xianglin Guo, et.al. Mesh Defiltering via Cascaded Geometry Recovery, Computer Graphics Forum 38(7): 591-605 (2019)

[28] Shudong Hou, Heng Liu, Quansen Sun. Sparse regularized discriminative canonical correlation analysis for multi-view semi-supervised learning, Neural Computing & Applications, 31: 7351-7359 (2019)

[29] Xingyu Xie, Xianglin Guo, Guangcan Liu, Jun Wang. Implicit Block Diagonal Low-Rank Representation. IEEE Trans. Image Processing, 2018, 27(1) : 477-489

[30] Heng Liu, Ziling Fu, Jungong Han, Ling Shao, Single Satellite Imagery Simultaneous Super-resolution and Colorization using Multi-task Deep Neural Networks. Journal of Visual Communication and Image Representation, 2018, 53:20-30.

[31] 侯书东，孙权森. 稀疏保持典型相关分析及在特征融合中的应用,自动化学报，2012, 38(4): 659-665.

获奖：

1. 2022 安徽省研究生教学名师

2. 2021 全讯600cc大白菜研究生高水平导师

3. 2018-2020连续三年获安徽省计算机学会优秀硕士学位论文指导教师奖

4. 2020年度第五届全国计算机类课程实验教学案例设计竞赛（人工智能类）二等奖

5. 指导员工获 2022全国老员工电子商务电子商务“创新、创意及创业”大赛省级一等奖

6. 指导员工获2022全国互联网+创新创业大赛省赛银奖

近年主要专利：

1. 一种基于对称深度网络的单幅图像超分辨率重建方法, ZL201610528420.6

2. 一种基于多任务深度神经网络的卫星图像同时超分辨和着色方法, ZL201711224807.3

3. 一种基于特征迁移学习的转换手势识别到身份识别的方法, ZL2018107628857

4. 一种隔空动态手势用户身份认证方法及装置, ZL201611087785.6

5. 一种基于深度学习的2D+3D大型飞机外形缺陷检测与分析方法, ZL201911321821.4

6. 一种智能电视的播放控制方法及装置，ZL201310617514.7。

7. 一种运动物体的高度检测方法和装置，ZL201410437736.5。

8. 基于方向运动历史图及竞争机制的手挥运动方向判定方法，ZL201210190678.1

招生信息：

本团队每年招录研究生10-12名，欢迎对模式识别、机器学习、计算机视觉、深度学习等研究方向感兴趣的优秀员工报考我们研究团队。基本要求：基础扎实，态度端正，踏实有责任心，勤奋上进。