欢迎访问天津理工大学视觉研究所网站!

当前位置: 首页   >   研究内容   >   正文

三维视觉与图像理解

作者:    信息来源:    发布时间: 2021-10-10

项目:

1.浙江省自然科学基金探索项目,“基于空地多源多模态主动感知的复杂环境精确重建”,9万元,2020-2022。

2.国家自然科学基金项目-面上,“动态视觉认知子空间构建与应用”,64万元,2019-2022。

3.国家自然科学基金青年基金,“面向未知环境探索的类别独立对象检测”,23万元,2014-2016。

4.浙江省科技厅公益项目,“基于实时立体视觉的智能机器人导盲系统”,10万元,2014-2016。

5.教育部博士点基金,“基于动态认知层次架构的大规模视觉类别发现”,4万元,2014-2016。

6.华电电力研究院,“基于红外双视技术的圆堆人员安全防护及自燃预警系统的研究开发”,100万元,2018-2019。

7.杭州德泽机器人科技有限公司,“断骨对接空间位姿追踪”,28万元,2018-2019。

8.新浪视觉,“基于手机视频的实时人脸追踪及姿态估计”,200万元,2015-2016。

9.《基于注意力机制的多视角人群场景下的异常行为识别和理解》,国家自然科学基金,研究经费:36万;项目批准号:61963027;研究期限:2020.01-2023.12。

10. 国家自然科学基金项目-面上,“动态视觉认知子空间构建与应用”,64万元,2019-2022,

论文:

1.Jianhua Zhang, Jingbo Chen, Jiewei Cao, Ruyu Liu*, Linjie Bian, Shengyong Chen, Dual Attention Granularity Network for Vehicle Re-Identification, Accepted by Neural Computing and Applications, 2021.

2.Zhenhua Wang, Jiajun Meng, Dongyan Guo, Jianhua Zhang*, Javen Shi, Shengyong Chen, “Consistency-Aware Graph Network for Human Interaction Understanding”, Accepte by IEEE/CVF International Conference on Computer Vision (CCF A, Oral), 2021.

3.Jie Qian, Qinying Chen, Yanhong Yang, Jianhua Zhang*, Shengyong Chen, Robust Visual-Lidar Simultaneous Localization and Mapping System for UAV, Accepted by IEEE Geoscience and Remote Sensing Letters, 2021. doi: 10.1109/LGRS.2021.3099166.

4.Jialing Liu, Ruyu Liu, Kaiqi Chen, Jianhua Zhang*, Dongyan Guo, Collaborative Visual Inertial SLAM for Multiple Smart Phones, IEEE Conference on Robotics and Automation (CCF B), 2021.

5.Jianhua Zhang, Jingbo Chen, Zhenhua Wang, Shengyong Chen, Jianwei Zhang, Detection and Segmentation of Unlearned Objects in Unknown Environment, IEEE Transactions on Industrial Informatics, 17(9): 6211-6220, 2021.

6.Jianhua Zhang, Jialing Liu, Kaiqi Chen, Zhiyang Pan,Ruyu Liu, Yanyan Wang, Thmas Yang, Shenyong Chen, Map Recovery and Fusion for Collaborative AR of Multiple Mobile Devices, IEEE Transactions on Industrial Informatics, 17(3): 2081-2089, 2021.

7.Jianhua Zhang, Jingbo Chen, Qichao Wang, Shengyong Chen, Spatiotemporal Saliency Detection Based on Maximum Consistency Superpixels Merging for Video Analysis, IEEE Transactions on Industrial Informatics, 16(1): 606-614, 2020.

8.Jianhua Zhang, Mengping Gui, Qichao Wang, Ruyu Liu, Junzhe Xu, Shengyong Chen, Hierarchical Topic Model Based Object Association for Semantic SLAM,IEEE Transactions on Visualization and Computer Graphics, 25(11): 3052 - 3062, 2019.

9.Ruyu Liu, Jianhua Zhang*, Shengyong Chen, Clemens Arth, Towards SLAM-Based Outdoor Localization using Poor GPS and 2.5D Building Models, IEEE International Symposium on Mixed and Augmented Reality (CCF B), 2019, pp. 1-7.

10.Jianhua Zhang, Ruyu Liu, Kejie Yin, Zengyuan Wang, Mengping Gui, Shengyong Chen, Intelligent Collaborative Localization among Air-Ground Robots for Industrial Environment Perception, IEEE Transactions on Industrial Electronics, 66(12): 9673-9681, 2019.

1.Jing Li, Zejin Chen, Gongfa Li, Gaoxiang Ouyang*, and Xiaoli Li, “Automatic Classification of ASD Children Using Appearance-based Features from Videos”, Neurocomputing, Accept, 2021. (SCI, JCR-2区)

2.Jing Li, Kan Jin, Dalin Zhou, Naoyuki Kubota, and Zhaojie Ju, “Attention Mechanism-based CNN for Facial Expression Recognition,” Neurocomputing, vol. 411, pp. 340-350, 2020. (SCI, JCR-2区)

3.Jing Li, Yaokai Xue, Weiqun Wang, and Gaoxiang Ouyang, “Cross-level Parallel Network for Crowd Counting,” IEEE Transactions on Industrial Informatics, vol. 16, no. 1, pp. 566-576, 2020. (SCI, JCR-1区)

4.Jing Li, Yihao Zhong, Junxia Han, Gaoxiang Ouyang, Xiaoli Li, and Honghai Liu, “Classifying ASD Children with LSTM based on Raw Videos,” Neurocomputing, vol. 390, pp. 226-238, 2020. (SCI, JCR-2区)

专利:

1.一种基于层次式主题模型的语义SLAM对象关联方法,ZL201811306327.6。

2.一种用于多传感器融合的异步在线标定方法,ZL201811265340.1。

3.一种基于精细化雷达扫描边缘点的多线激光雷达和相机联合标定方法,ZL201810939185.0。

4.一种用于视觉-惯性-激光融合的同步定位与建图方法,ZL201910297985.1。

5.一种结合GPS和雷达里程计的SLAM方法,ZL201811306455.0。

6.基于3D点云FPFH特征实时三维空间定位方法,ZL201610659484.X。

7.基于人脸简单模型的特征点插值与图像变形方法,ZL201610595699.X。

8.一种显微图像序列中癌细胞轨迹追踪与关联方法,ZL201610458726.9。

9.基于动态处理窗口及二值区域跟踪的血管分支提取方法,ZL201510703027.1。

10.结合上下信息窄带约束的腹腔主动脉瘤外轮廓分割方法,ZL201510700007.9。

11.一种基于人眼特征的视线估计方法,ZL201510675215.8。

12.融合图像灰度特征与结构化表示的图像群组配准方法,ZL201510672710.3。

13.一种面向月面导航的自适应的地标选取方法,ZL201510442396.X。

14.一种飞行器月表软着陆的实时动态选址方法,ZL201510424070.4。

15.一种通用的无人机视觉仿真平台,ZL201510415014.4。

16.一种基于多特征学习的动脉粥样硬化斑块成分分割方法,ZL201510170489.1。

17.一种基于多序列医学图像的血管配准方法,ZL201510088135.2。

18.基于形状先验和相似性约束的颈动脉内外壁自动分割方法,ZL201510088158.3。

19.基于前景和背景先验的多模态区域一致性的显著性对象检测方法,ZL201510072313.2。