杜松林，副教授，博士生导师，IEEE Senior Member。毕业于日本早稻田大学，获工学博士学位，入选东南大学“至善青年学者”A层次、江苏省科协青年科技人才托举工程、深圳市优秀科技创新人才培养项目。承担国家自然科学基金项目、江苏省基础研究计划（自然科学基金）项目、广东省基础与应用基础研究基金项目、深圳市基础研究专项（自然科学基金）项目、南京市留学人员科技创新择优资助项目、东南大学优秀青年教师科学研究资助项目、东南大学课程思政示范课改革试点项目、日本学术振兴会基础研究项目、早稻田大学特别研究课题等。在IEEE TII、IEEE TCSVT、IEEE TMM、IEEE TASE、IEEE TITS、Pattern Recognition等学术期刊和CVPR、ICCV、ECCV、AAAI等学术会议上发表论文八十余篇，出版专著Human Pose Analysis (Singapore: Springer Nature, 2024)。研究成果获ISPACS2017国际会议“最佳论文奖”、ICISIP2018国际会议“最佳报告奖”、ISIPS2018国际会议“杰出论文奖”、AIVR2019国际会议计算机视觉分会场“最佳报告奖”等学术奖项。主讲本科生“人工智能”和“模式识别与机器学习”课程、研究生“人工智能及其应用”课程。担任国家自然科学基金函评专家、教育部学位中心研究生学位论文评审专家、国家留学基金评审专家、广东省科技咨询专家、南京市科技咨询专家、航空科学基金评审专家、三星电子中国研发中心技术顾问，以及IEEE TPAMI、IEEE TIP、IEEE TII、IEEE TCSVT、IEEE TASE、IEEE TIM、IEEE TGRS、IEEE/CAA JAS、Pattern Recognition、Visual Intelligence等学术刊物审稿人。电气与电子工程师协会（IEEE）高级会员、中国图象图形学学会（CSIG）机器视觉专委会委员、中国图象图形学学会（CSIG）视觉大数据专委会委员、中国自动化学会（CAA）模式识别与机器智能专委会委员、江苏省自动化学会学术工委会秘书长。

招生计划：

每年招收博士研究生1~2名、硕士研究生3~4名，研究方向主要包括人工智能、机器视觉、模式识别与机器学习等（详见songlin.ac.cn）。

电气与电子工程师协会高级会员（IEEE Senior Member）

中国图象图形学学会（CSIG）机器视觉专委会委员

中国图象图形学学会（CSIG）视觉大数据专委会委员

中国自动化学会（CAA）模式识别与机器智能专委会委员

江苏省自动化学会（JSAA）学术工委会秘书长

本科生课程：模式识别与机器学习 (课程思政校级示范课)，自动化/机器人工程专业

研究生课程：人工智能及其应用 (课程思政校级示范课)，电子信息类专业

在计算机视觉领域，常见的相机系统通常采用二维传感器，这意味着它们捕捉到的图像是以二维数据形式呈现的。然而诸多场景下的智能体需要感知其周围的真实三维环境并确定自身的位姿，如自动驾驶、机器人导航、增强现实等，因此从二维图像恢复三维空间结构是一类重要且有挑战性的问题。欢迎同学们围绕该类问题研究和交流，例如跨视角图像匹配、运动恢复结构、相机位姿估计、目标位姿估计、人体等非刚性姿态估计等。

专著：

☐  Songlin Du and Takeshi Ikenaga, Human Pose Analysis: Deep Learning Meets Human Kinematics in Video, Springer Nature, 2024.

论文：

☐  JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba

Xiaoyong Lu and Songlin Du*

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

☐  Topology Learning for Two-view Correspondence Filtering

Ziwei Shi, Xiangyang Miao, Guobao Xiao, Songlin Du, Zheng Wang and Heng Tao Shen

IEEE Transactions on Multimedia, 2025.

☐  Skeleton-Aware Representation of Spatio-Temporal Kinematics for 3D Human Motion Prediction

Songlin Du*, Zhihan Zhuang, Zenghui Wang, Yuan Li, Takeshi Ikenaga

IEEE Transactions on Automation Science and Engineering, 2025.

☐  Bi-Pose: Bidirectional 2D-3D Transformation for Human Pose Estimation from a Monocular Camera

Songlin Du*, Hao Wang, Zhiwei Yuan, Takeshi Ikenaga

IEEE Transactions on Automation Science and Engineering, vol. 21, no. 3, pp. 3483-3496, 2024.

☐  ContextMatcher: Detector-Free Feature Matching with Cross-Modality Context

Dongyue Li and Songlin Du*

IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 9, pp. 7922-7934, 2024.

☐  AnatPose: Bidirectionally Learning Anatomy-Aware Heatmaps for Human Pose Estimation

Songlin Du*, Zhiwen Zhang, and Takeshi Ikenaga

Pattern Recognition, vol. 155, pp. 110654:1-110654:14, 2024.

☐  Kinematics-Aware Spatial-Temporal Feature Transform for 3D Human Pose Estimation

Songlin Du*, Zhiwei Yuan, Takeshi Ikenaga

Pattern Recognition, vol. 150, pp. 110316:1-110316:10, 2024.

☐  Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching

Xiaoyong Lu and Songlin Du*

European Conference on Computer Vision (ECCV), pp.  256-273, 2024.

☐  Toward Better Generalization: Shape Feature-Enhanced Fastener Defect Detection with Diffusion Model

Shixiang Su, Songlin Du, Dezhou Wang, and Xiaobo Lu*

IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1-13, 2024.

☐  JoyPose: Jointly Learning Evolutionary Data Augmentation and Anatomy-Aware Global-Local Representation for 3D Human Pose Estimation

Songlin Du*, Zhiwei Yuan, Takeshi Ikenaga

Pattern Recognition, vol. 147, pp. 110116:1-110116:12, 2024.

☐  Fine-grained Recognition via Submodular Optimization Regulated Progressive Training

Bin Kang, Songlin Du*, Dong Liang, Fan Wu, and Xin Li

Pattern Recognition, vol. 156, pp. 110849:1-110849:9, 2024.

☐  Straight-Line Detection within 1 Millisecond per Frame for Ultra-High-Speed Industrial Automation

Songlin Du*, Ziwei Dong, Yuan Li, Takeshi Ikenaga

IEEE Transactions on Industrial Informatics, vol. 19, no. 4, pp. 5965-5975, 2023.

☐  RFS-Net: Railway Track Fastener Segmentation Network with Shape Guidance

Shixiang Su, Songlin Du, Xuan Wei, Xiaobo Lu*

IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 3, pp. 1398-1412, 2023.

☐  Scene-aware Feature Matching

Xiaoyong Lu, Yaping Yan, Tong Wei, Songlin Du*

IEEE/CVF International Conference on Computer Vision (ICCV), pp. 3681-3690, 2023.

☐  ParaFormer: Parallel Attention Transformer for Efficient Feature Match

Xiaoyong Lu, Yaping Yan, Bin Kang, Songlin Du*

AAAI Conference on Artificial Intelligence (AAAI), pp. 1853-1860, 2023.

☐  Automatic Foreground Detection at 784 FPS for Ultra-High-Speed Human-Machine Interactions

Songlin Du*, Peikun Cai, Tingting Hu, Takeshi Ikenaga

IEEE Transactions on Automation Science and Engineering, vol. 19, no. 4, pp. 3587-3600, 2022.

☐  Subpixel Displacement Measurement at 784 FPS: From Algorithm to Hardware System

Songlin Du*, Kaidong Gu, Takeshi Ikenaga

IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 5008310:1-5008310:10, 2022.

☐  Geometric Constraint and Image Inpainting Based Railway Track Fastener Sample Generation for Improving Defect Inspection

Shixiang Su, Songlin Du, Xiaobo Lu*

IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 12, pp. 23883-23895, 2022.

☐  Highly-Parallel Hardwired Deep Convolutional Neural Network for 1-ms Dual-Hand Tracking

Peiqi Zhang, Tingting Hu, Dingli Luo, Songlin Du, Takeshi Ikenaga*

IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 12, pp. 8192-8203, 2022.