研究方向：

三维视觉、机器学习、模式识别、三维点云分析与场景理解

在顺德创新学院的基础科研条件：

本人及科研团队主要围绕三维视觉开展算法研究和工业应用，本人主持的科研项目有

1. 国家自然科学基金项目：时变姿态下的三维唇语行为表示及身份识别研究，No. 61906004, 主持

2. 国家重点研发计划重点专项：“汽车关键部件装配缺陷视觉检测仪”子课题——汽车发动机多种类三维缺陷视觉识别研究，No. 2018YFB2003803, 主持

3. 北京市教委科技一般项目：复杂背景下的工业零部件制造质量视觉检测算法研究，No. KM202110011012，主持

4. 中国航空发动机集团产学研合作项目：发动机外部质量数字化识别技术研究，No. HFZL2022CXY020，参研

5. 校际合作项目（横向）：航空发动机三维点云管路及关键零件细粒识别及间隙监测，主持

6. 校际合作项目（横向）：航空发动机叶片三维型面重建及关键结构参数精密测量，主持

代表性成果：

代表性学术论文：

1. Junhua Sun, Rong Guo, Jie Zhang*. Global and Uniform Point Cloud Completion with Density-Sensitive Transformer for Small-Scale 3D Object Reconstruction.  IEEE Transactions on Industrial Informatics , 2024, doi: 10.1109/TII.2024.3393565. (中科院一区，TOP)

2. J. Zhang, Z. Zhou and J. Sun, Center-Aware Instance Segmentation for Close Objects in Industrial 3-D Point Cloud Scenes,  IEEE Transactions on Industrial Informatics , vol. 20, no. 2, pp. 2812-2821, 2024. (中科院一区，TOP)

3. Jie Zhang, Jingyi Cao, Junhua Sun. Learning spatio-temporal lip point dynamics for visual voice activity detection. Biomedical Signal Processing and Control . vol. 87, Part B, 2024, 105410. (中科院二区)

4. Jie Zhang, Zitai Zhou, Junhua Sun. Three-dimensional Segmentation and Global Clearance Analysis for Free-bent Pipelines in Point Cloud Scenarios.  IEEE Transactions on Instrumentation and Measurement , vol. 72, pp. 1-12, 2023, Art no. 2511712. (中科院二区)

5. Jie Zhang, Zhengmao Sun, Junhua Sun. 3-DFineRec: Fine-Grained Recognition for Small-Scale Objects in 3-D Point Cloud Scenes. IEEE Transactions on Instrumentation and Measurement , 2022, 71, 2500711, 1-11. (中科院二区)

6. Jie Zhang, Junhua Sun. 4D Spatio-Temporal detection and modeling of free-bending pipelines in cluttered 3D point cloud.  IEEE Transactions on Instrumentation and Measurement , 2021, 70, 5017612, 1-12. (中科院二区)

7. Jie Zhang, R. B. Fisher, 3D Lip Event Detection via Interframe Motion Divergence at Multiple Temporal Resolutions,  International Conference on 3D Vision ( 3DV ), 2021, pp. 423-431. (国际三维视觉顶级会议)

8. Junhua Sun, Zhou Zhang, Jie Zhang*. Reconstructing 3-D normal section profiles of 3-D revolving structures via pose-unconstrained multiline structured-light vision.  IEEE Transactions on Instrumentation and Measurement , 70, 7001112, 1-12,2021. (中科院二区)

9. Jie Zhang, Junhua Sun, Zhou Zhang. Identifying multiple line-structured lights from images via a local-to-global graph representation.  Optics Express , 2020, 28(10), 15611-15624. (中科院二区)

10. Jie Zhang, Robert B. Fisher. 3D visual passcode: Speech-driven 3D facial dynamics for behaviometrics.  Signal Processing , 2019, 160:164-177. (中科院二区)

获奖：

1. 2023年冶金科技进步二等奖（8/15）

2. 首都挑战杯大赛一等奖指导教师