李杨，金沙威尼斯欢乐娱人城，博士，副教授，硕士生导师，2000年和2003年与东南大学分别获工学学士和工学硕士学位，2006年毕业于金沙威尼斯欢乐娱人城电子科学与工程系，获工学博士学位，2012-2014年美国西北大学博士后。长期从事视觉环境感知、深度估计与重建等计算机视觉理论与应用课题研究，学科骨干教师，发表国际学术论文50余篇，获得发明专利授权10余项。获得2005年度华英文教基金青年教师奖； 2009江苏省年度优秀科技创新团队成员， 2012年度中国计算机行业发展成就优秀方案与案例。2017年度南京市高层次创新创业人才。

主要研究方向

1. 视觉深度感知与三维重建.
2. 生物图像信息学.

研究方向简介

       在计算机视觉领域。我们的研究兴趣集中利用计算机视觉技术对环境进行三维感知和对环境图像进行语义理解。我们围绕着机器人导航、自动驾驶等应用场景下的多种三维感知技术进行研究。在双目及多目立体视觉被动感知技术方面，我们首次提出了利用帧间相关性加速视频序列中的立体匹配问题，该方法在不降低视差计算精度的前提可以显著提升基于深度学习和非深度学习方法的立体匹配速度，我们在嵌入式系统中实现的双目立体视觉系统达到了国际先进水平。我们同时在激光雷达点云的语义分割、配准上也取得众多成果，利用算法优化和GPU加速我们实现在低功耗嵌入式平台上的实时三维重建。针对机器人导航、自动驾驶等应用场景，我们进一步发展和完善了双目视觉的同步定位与地图构建问题，提出并实现了利用深度图像加速地图构建。此外，我们在目标识别、图像语义分析等领域也取得若干成果，例如我们针对多模态图像中的目标识别问题提出了全新的深度网络架构和数据增强及训练方法，显著提升了算法的性能。

       在生物图像信息学领域。我们关注机器学习、计算机视觉理论在生物医学工程、生命科学等交叉学科领域的应用研究。我们发展了一系列采用计算机视觉技术对荧光显微图像中的细胞进行高通量量化分析的工具：AxonQuant，MitoQuant等，用以帮助生命科学家在微观层面对细胞的形态、动力学特征进行分析，我们首次提出了线粒体的速度空间分布动力学模型，这些方法和工具或得了领域内科学家的广泛认同和关注。我们同时开展了荧光显微图像增强及超分辨率显微成像中的单分子定位问题的研究，我们提出的移变点扩散函数模型极大的提升了真实荧光显微图像的反卷积重建结果，这个模型在单分子亚像素定位、光片显微图像增强等领域都加大的应用潜力。

      上述研究成果得以在ECCV、Optcal Express等领域内有影响力的国际期刊及会议发表，同时我们也取得了若干中国发明专利授权。

面向本科生开设《数字图像处理》课程；
面向本科生及研究生开设《计算机视觉》课程。

2023年

Jingzhao Dai, Xuejiao Hu, Ming Li, Yang Li, and Sidan Du#. 2023. 'The multi-learning for food analyses in computer vision: a survey', Multimedia Tools and Applications: 1-36.

Sheng Liu, Jianghai Shuai, Yang Li, and Sidan Du#. 2023. 'MMDA: Multi-person Marginal Distribution Awareness for Monocular 3D Pose Estimation ', IET Image Processing. (ACCEPT)

Zhiyi Zhu, Sheng Liu, Jianghai Shuai, Sidan Du, and Yang Li#. 2023. ' 3D Associative Embedding: Multi-View 3D Human Pose Estimation in Crowded Scenes ', 2023 5th International Conference on Advances in Computer Technology, Information Science and Communications. (ACCEPT)

2022年

Hanrong Wang, Ming Li, Jie Wang, Yang Li#, and Sidan Du#. 2021. A Discussion of Optimization about Stereo Image Depth Estimation Based on Multi-baseline Trinocular Camera Model. In 2021 International Conference on Computational Science and Computational Intelligence (CSCI), 1716-20. IEEE.

Jie Wang, Chenglei Peng, Ming Li, Yang Li#, and Sidan Du#. 2022. 'The study of stereo matching optimization based on multi-baseline trinocular model', Multimedia Tools and Applications, 81: 12961-72.

Jingyi Cao, Chenglei Peng, Yang Li, and Sidan Du#. 2021. A Shadow Detection Method for Retaining Key Objects in Complex Scenes. In 2021 13th International Conference on Knowledge and Smart Technology (KST), 90-95. IEEE.

Jingzhao DAI, Ming LI, Xuejiao HU, Yang LI#, and Sidan DU#. 2022. 'GazeFollowTR: A Method of Gaze Following with Reborn Mechanism', IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences.

Ming Li, Xueqian Jin, Xuejiao Hu, Jingzhao Dai, Sidan Du#, and Yang Li#. 2022. MODE: Multi-view Omnidirectional Depth Estimation with 360∘ Cameras. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXIII, 197-213. Springer.

Xuejiao Hu, Jingzhao Dai, Ming Li, Chenglei Peng, Yang Li#, and Sidan Du#. 2022. 'Online human action detection and anticipation in videos: A survey', Neurocomputing, 491: 395-413.

Zhaoxu Li, Sheng Liu, Jue Bai, Chenglei Peng, Yang Li, and Sidan Du#. 2022. A Novel Skeleton-based Model with Spine for 3D Human Pose Estimation. In 2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC), 0501-06. IEEE.

2021年

Jue Bai, Chenglei Peng#, Zhaoxu Li, Sidan Du#, and Yang Li#. 2021. A Study of General Data Improvement for Large-Angle Head Pose Estimation. In Computer Analysis of Images and Patterns: 19th International Conference, CAIP 2021, Virtual Event, September 28–30, 2021, Proceedings, Part II 19, 199-209. Springer.

Ming Li, Xuejiao Hu, Jingzhao Dai, Yang Li#, and Sidan Du#. 2021. 'Omnidirectional stereo depth estimation based on spherical deep network', Image and Vision Computing, 114: 104264.

Qi Li, Chenglei Peng, Yazhen Ma, Sidan Du, Bin Guo, and Yang Li#. 2021. Pixel-level diabetic retinopathy lesion detection using multi-scale convolutional neural network. In 2021 IEEE 3rd Global Conference on Life Sciences and Technologies (LifeTech), 438-40. IEEE.

Tong Chen, Chenzlei Peng, Ming Li, Xudong Chen, Sidan Du, and Yang Li#. 2021. A Review on Quantitative Analyzing Axonal Transport of Mitochondria. In 2021 IEEE 3rd Global Conference on Life Sciences and Technologies (LifeTech), 441-43. IEEE.

Xueqian Jin, Ming Li, Chenglei Peng, Sidan Du, and Yang Li#. 2021. 'Depth-based removal of thermal reflection with the light-field theory', JOSA A, 38: 1594-602.

Yifang Xu, Ming Li, Chenglei Peng#, Yang Li, and Sidan Du#. 2021. Dual Attention Feature Fusion Network for Monocular Depth Estimation. In Artificial Intelligence: First CAAI International Conference, CICAI 2021, Hangzhou, China, June 5–6, 2021, Proceedings, Part I 1, 456-68. Springer.

Yifang Xu, Chenglei Peng, Ming Li, Yang Li, and Sidan Du#. 2021. Pyramid feature attention network for monocular depth prediction. In 2021 IEEE International Conference on Multimedia and Expo (ICME), 1-6. IEEE.

Zihao Zhou, Yang Li, Chenglei Peng, Hanrong Wang, and Sidan Du#. 2021. Image processing: Facilitating retinanet for detecting small objects. In Journal of Physics: Conference Series, 012016. IOP Publishing.

2020年

Jie Wang, Chenglei Peng, Ming Li, Xudong Chen, Sidan Du, and Yang Li#. 2020. Stereo matching optimization with multi-baseline trinocular camera model. In 2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 1-4. IEEE.

Xudong Chen, Ming Li, Tong Chen, Sidan Du, and Yang Li#. 2020. Estimating the Binding and Unbinding Rate of Motor Protein from Mitochondrial Motion. In 2020 IEEE 2nd Global Conference on Life Sciences and Technologies (LifeTech), 226-30. IEEE.

2019年

Ming Li, Li Shi, Xudong Chen, Sidan Du#, and Yang Li#. 2019. 'Using temporal correlation to optimize stereo matching in video sequences', IEICE TRANSACTIONS on Information and Systems, 102: 1183-96.

Ming Li, Xudong Chen, Chenglei Peng, Sidan Du#, and Yang Li#. 2019. 'Modeling the occlusion problem in thermal imaging to allow seeing through mist and foliage', JOSA A, 36: A67-A76.

Sheng Lu, Tong Chen, Fan Yang, Chenglei Peng, Sidan Du, and Yang Li#. 2019. Minimal path based particle tracking in low SNR fluorescence microscopy images. In Proceedings of the 4th International Conference on Biomedical Signal and Image Processing, 93-97.

2018年

Fan Yang, Sheng Lu, Sidan Du, and Yang Li#. 2018. A Novel Training Method for Faster R-CNN based Object Detection in Multi-modal Images. In Digital Holography and Three-Dimensional Imaging, DW2F. 6. Optica Publishing Group.

Xinnian Guo, Yang Li, Jean Jiang, Chen Dong, Sidan Du, and Li Tan. 2018. 'Sparse modeling of nonlinear secondary path for nonlinear active noise control', IEEE Transactions on Instrumentation and Measurement, 67: 482-96.

Xinnian Guo, Yang Li, Jean Jiang, Chen Dong, Sidan Du, and Li Tan. 2018. 'Adaptive function expansion 3-D diagonal-structure bilinear filter for active noise control of saturation nonlinearity', IEEE Access, 6: 65139-50.

Yemeng Chen, Mengmeng Chen, Li Zhu, Jane Y Wu, Sidan Du, and Yang Li#. 2018. 'Measure and model a 3-D space-variant PSF for fluorescence microscopy image deblurring', Optics Express, 26: 14375-91.

2017年

Shuihua Wang, Sidan Du, Yang Li, Huimin Lu, Ming Yang, Bin Liu, and Yudong Zhang#. 2017. Hearing loss detection in medical multimedia data by discrete wavelet packet entropy and single-hidden layer neural network trained by adaptive learning-rate back propagation. In Advances in Neural Networks-ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part II 14, 541-49. Springer.

2016年

Mengmeng Chen, Yang Li#, Mengxue Yang, Xiaoping Chen, Yemeng Chen, Fan Yang, Sheng Lu, Shengyu Yao, Timothy Zhou, and Jianghong Liu. 2016. 'A new method for quantifying mitochondrial axonal transport', Protein & cell, 7: 804-19.

Shuihua Wang, Mengmeng Chen, Yang Li, Ying Shao, Yudong Zhang, Sidan Du, and Jane Wu. 2016. 'Morphological analysis of dendrites and spines by hybridization of ridge detection with twin support vector machine', PeerJ, 4: e2207.

Yemeng Chen, Mengmeng Chen, Jane Y. Wu, Sidan Du and Yang Li#. 2016. Space-Variant Deconvolution for Fluorescence Microscopy Image Restoration and Reconstruction. In 3rd International Conference on Light Sheet Fluorescence Microscopy.

2014年-2016年

Yang Li，Mengxue Yang，Zhuo Huang，Xiaoping Chen，Michael T. Maloney，Li Zhu, Jianghong Liu，Yanmin Yang，Sidan Du，Xinyu Jiang，Jane Y. Wu，AxonQuant: A Microfluidic Chamber: Culture-Coupled Algorithm That Allows High-Throughput Quantification of Axonal Damage.，Neurosignals，2014, (1):14-29

Yang Li，Pei Chu，Jia Liu, Sidan Du，A Novel Partitioned Light Guide Backlight LCD for Mobile Devices and Local Dimming Method With Nonuniform Backlight Compensation，Journal of Display Technology，2014，10(4): 321-328 

Jing Zhao，Yang Li#，Sidan Du，A 3-D Deconvolution Based Particle Detection Method for Wide-field Microscopy Image，8th International Symposium on Medical Information and Communication Technology，2014.4.1-2014.4.5

Qi Wang，Yang Li，Sidan Du，A Novel Resonant Tunneling Diode Based on AlGaAsP/GaAs and its Circuit Level Design，Applied Mechanics and Materials，2014，346(1):35-41