基本信息

              

                         李垚辰

               副教授,博士生导师

              西安交通大学软件学院

联系方式

办公室:软件学院西小楼A212

电话:029-82663000-8012

地址:陕西省西安市咸宁西路28号

           西安交通大学   软件学院

邮编:710049

Email: yaochenli [At] mail.xjtu.edu.cn

新闻通知

闹钟

站点计数器

工作经历

2020年1月~至今:西安交通大学, 软件学院, 副教授

2016年10月~2019年12月:西安交通大学, 软件学院, 讲师

教育经历

联合培养博士:美国加州大学洛杉矶分校, 专业:计算机视觉

博士学位 (硕博连读) :西安交通大学, 专业:模式识别与智能系统                                                

学士学位:西安交通大学, 专业:计算机科学与技术

研究领域

计算机视觉与模式识别

人工智能与机器学习

视频图像处理

智能交通系统

科研项目

项目/课题负责人

  • 2020.08-2020.11   横向课题(编号:20200908), 智能照片分类.
  • 2019.01-2021.12   国家自然科学基金青年基金项目(编号:61803298), 道路场景视觉感知的交通要素线框模型表示与计算方法研究.
  • 2018.07-2020.07  苏州市科技计划重点产业创新前瞻性应用研究(编号:SYG201843), 交通要素时空关联的道路场景布局分析及语义建模方法研究.
  • 2018.07-2021.06  江苏省自然科学基金青年基金项目(编号:BK20180236), 多粒度视频特征融合的场景要素分析与合成方法研究.
  • 2017.01-2018.12  中国博士后科学基金面上项目(编号:2017M613142), 基于时空特征一致性的视频语义标注与建模方法研究.
  • 2017.01-2019.12  中央高校基本科研业务费综合交叉类项目(编号:xjj2017176), 基于多粒度视觉特征的场景分析建模及其在网络图像流中的应用研究.
  • 2017.09-2018.09   横向课题(编号:321100003301), 传送带商品智能检测.

参与项目

  • 2020.01-2023.12   国家自然科学基金面上项目(编号:61973245), 无人驾驶环境感知智能的测试模型与可靠性评估.(项目骨干)
  • 2019.11-2023.11   国家重点研发计划课题(编号:2018AAA0102504), 面向人机行为任务的协同决策理论与方法. (课题联系人)
  • 2014.01-2016.12   国家自然科学基金海外合作项目(编号:61328303),  运动视觉的计算模型研究.(项目骨干)
  • 2012.01-2014.12   国家自然科学基金重大研究计划培育项目(编号:91120009), 无人驾驶车辆环境认知能力评估与离线测试系统.(项目骨干)
  • 2010.01-2012.12   国家自然科学基金重大研究计划培育项目(编号:90920008), 基于选择性注意模型的可视媒体检测方法研究.(项目骨干)

发表论文

期刊论文

[9] Yaochen Li, Chuan Wu, Ling Li, Yuehu Liu and Jihua Zhu. Caption generation from road images for traffic scene modeling[J]. IEEE Transactions on Intelligent Transportation Systems, 2021. (Accepted).

[8] Zhichao Cui, Yaochen Li*, Chi Zhang, Yuehu Liu and Fuji Ren. Coarse-to-fine 3D road model rigistration for traffic video augmentation[J]. IET Image Processing, 2020, 14(12): 2690-2700. (SCI, WOS:000582146100009)

[7] Yaochen Li, Xiao Wu, Danhui Lu, Ling Li, Yuehu Liu and Li Zhu. Style transfer of urban road images using generative adversarial networks with structural details[J]. IEEE Multimedia, 2020, 27(3): 54-65. (SCI, WOS:000567430300007)(IF 2020: 4.962)

[6] Yaochen Li, Yuehu Liu, Jihua Zhu, Shiqi Ma, Zhenning Niu and Rui Guo. Spatiotemporal road scene reconstruction using superpixel-based Markov random field[J]. Information Sciences, 2020, 507: 124-142. (SCI, WOS:000489000500008)(IF 2020: 5.910)

[5] Yaochen Li, Rui Sun, Ying Liu, Yang Yang, Shuangxun Ma and Yuehu Liu. Interactive foreground segmentation and shape reconstruction from RGBD images [J]. Computers & Electrical Engineering, 2019, 79: 1-13. (SCI, WOS:000492799200006)(IF 2019: 2.189)

[4] Yaochen Li, Ying Liu, Rui Sun, Rui Guo, Li Zhu and Yong Qi. Multi-view point cloud registration with adaptive convergence threshold and its application in 3D model retrieval[J]. Multimedia Tools and Applications, 2020, 79(1): 14793-14810. (SCI)(IF 2019: 2.101)

[3] Yaochen Li, Yuehu Liu, Yuanqi Su, Gang Hua and Nanning Zheng. Three-dimensional traffic scenes simulation from road image sequences[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(4): 1121-1134. (SCI,  WOS:000373133600021; EI: 20160301821973)(IF 2019: 5.744)

[2] Yaochen Li, Yuanqi Su and Yuehu Liu. Fast two-cycle curve evolution with narrow perception of background for object tracking and contour refinement[J]. Signal Processing: Image Communication, 2016, 44: 29-43. (SCI, WOS:000376714000003; EI: 20161302174611)(IF 2019: 3.059)

[1] Yaochen Li, Yuehu Liu and Nanning Zheng. Creating Walk-Through Images from Traffic Video Sequence. UCLA Cam Report, 2013:13-82.

 

会议论文

[17] Mengtao Han, Yaochen Li*, Liangyu Zuo, Qiao Li, Chi Zhang, Yuanqi Su and Ping Li. Point cloud segmentation via edge-fused local graph learning[C]//In Proceedings of IEEE International Conference on Robotics and Automation (ICRA), Xi'an, May. 2021. (Accepted)

[16] Zikun Dong, Yaochen Li*, Haochuan Hou and Ruihao Wang. Spatiotemporal analysis of traffic scene layout using scene stages[C]//In Proceedings of International Symposium on Artificial Intelligence and Robotics (ISAIR), Fukuoka, Aug. 2021. (Accepted)

​​​​​​​[15] Ling Li, Yaochen Li*, Chuan Wu, et al. Detail Fusion GAN: High-quality translation for unpaired images with GAN-based data augmentation[C]// In Proceedings of International Conference on Pattern Recognition (ICPR), Milano, Jan. 2021.(EI)

[14] Kang Song, Yaochen Li*, Yuhui Hong, Yuting Chen, Chenming Song and Yuehu Liu. FFSSD: Improved vehicle detection with multi-scale convolution feature fusion[C]//In Proceedings of ChinaMM (ChinaMM), Qingdao, Sep. 2020.

[13] 刘荧, 李垚辰*, 刘跃虎, 付靖文, 马飞. 基于相关熵的多视角彩色点云配准[C]//第二十届全国图象图形学学术会议, 乌鲁木齐, 2020.

[12] Chuan Wu, Yaochen Li*, Ling Li, Le Wang and Yuehu Liu. Caption generation from road images for traffic scene construction[C]//In Proceedings of IEEE Intelligent Vehicles Symposium (IVS), Las Vegas, Oct. 2020.

[11] Xiao Wu, Yaochen Li*, Zelin Hao, Chuan Wu, Xiaochun Wang and Yuehu Liu. Image style transformation based on structureGAN[C]//In Proceedings of Chinese Automation Congress (CAC), Hangzhou, Nov. 2019.(EI)

[10] Chao Zhu, Yaochen Li*, Yuehu Liu, Zhiqiang Tian, Zhichao Cui, Chi Zhang and Xinyu Zhu. Road scene layout reconstruction based on CNN and its application in traffic simulation[C]//In Proceedings of IEEE Intelligent Vehicles Symposium (IVS), Paris, Jun. 2019. (EI:20193807453140)

[9] Xiao Wu, Yaochen Li*, Yuehu Liu, Shanmin Pang, Le Wang, Chuan Wu and Huihui Huo. Jointly detecting and retrieving vehicles from road image sequences based on CNN[C]//In Proceedings of IEEE Intelligent Vehicles Symposium (IVS), Paris, Jun. 2019. (EI:20193807453259)​​​​​​

[8] Yuxiao Wang, Yaochen Li*, Ming Zeng, Zikun Dong, Jian Yuan and Ziwei Wang. Bottom-up estimation of geometric layout for indoor images[C]//In Proceedings of IEEE International Conference on Unmanned Systems (ICUS), Beijing, Oct. 2019. (EI:20201008261335)

[7] Huihui Huo, Yaochen Li*, Chuan Wu, Xiao Wu, Zhiqiang Tian, and Yuehu Liu. Semantic segmentation and scene reconstruction for traffic simulation using CNN [C]//In Proceedings of 2nd China Symposium on Cognitive Computing and Hybrid Intelligence (CCHI), Xi'an, Sep. 2019. (EI:20194907772809)

[6] Huayun Pan, Yaochen Li*, Xiao Wu, Xiao Wu, Yuxiao Wang, and Yuehu Liu. Fast two-cycle level set tracking with interactive superpixel segmentation [C]//In Proceedings of 2nd China Symposium on Cognitive Computing and Hybrid Intelligence (CCHI), Xi'an, Sep. 2019. (EI:20194907772830)

[5] Jian Yuan, Yaochen Li*, Huayun Pan, Zhichao Cui and Yuehu Liu. 3D traffic scenes construction and simulation based on scene stages[C]//In Proceedings of Chinese Automation Congress (CAC), Xi'an, Dec. 2018. (Oral Paper)(EI:20191106633140)​​​​​

[4] Yaochen Li, Yuanqi Su and Yuehu Liu. Fast two-cycle level set tracking with narrow perception of background[C]//In Proceedings of IEEE International Conference on Multimedia & Expo (ICME), Turin, Jun. 2015. (Oral Paper)(EI:20154501514030)

[3] Yaochen Li, Yuehu Liu, Chi Zhang, Danchen Zhao and Nanning Zheng. The “floor-wall” traffic scenes construction for unmanned vehicle simulation evaluation[C]//In Proceedings of IEEE International Conference on Intelligent Transportation Systems (ITSC), Qingdao, Oct. 2014. (Best Student Paper Award) (EI:20152901040876)

[2] Yaochen Li, Yuehu Liu, Xiao Huang, Ming Hou and Yang Yang. Vertex Saliency Computation from 3D facial meshes[C]//In Proceedings of IEEE International Symposium on Access Spaces (ISAS), Yokohama, Jun. 2011. (EI:20113414253229)

[1] Yaochen Li, Yuehu Liu, Yuanchun Wang, Zhengwang Wu and Yang Yang. 3D facial mesh detection using geometric saliency of surface[C]//In Proceedings of IEEE International Conference on Multimedia & Expo (ICME), Barcelona, Jun. 2011.(EI:20114514487529)

 

 

合作论文

[9] Mintao Wu, Jihua Zhu, Jun Wang, Shanmin Pang and Yaochen Li. Listwise approach based on the cross-correntropy for learning to rank[J]. IET Electronic Letters, 2018, 54(14): 878-880. 

[8] Jiaxing Wang, Jihua Zhu, Shanmin Pang, Zhongyu Li, Yaochen Li and Xueming Qian. Adaptive co-weighting deep convolutional features for object retrieval[C]//In Proceedings of IEEE International Conference on Multimedia & Expo, San Diego, Jul. 2018.(EI)

[7] Zutao Jiang, Jihua Zhu, Yaochen Li and Huimin Lu. Simultaneous merging multiple grid maps using the robust motion averaging[J]. Journal of Intelligent & Robotic Systems, 2018. (Accepted)(SCI)

[6] Congcong Jin, Jihua Zhu, Yaochen Li, Shanmin Pang, Lei Chen and Jun Wang. Multi-view registration based on weighted low rand and sparse matric decomposition of motions[J]. IET Computer Vision, 2018. (Accepted)(SCI) 

[5] Siyu Xu, Jihua Zhu, Yaochen Li and Jun Wang. Effective scaling registration approach by imposing the emphasis on the scale factor[J]. IET Electronic Letters, 2018, 54(7): 422-424. (SCI)

[4] Rui Guo, Jihua Zhu, Yaochen Li, Dapeng Chen, Zhongyu Li, Yongqin Zhang. Weighted Motion Averaging for the Registration of Multi-View Range Scans[J]. Multimedia Tools and Applications, 2018, 77(9): 10651-10668. (SCI)

[3] Danchen Zhao, Yuehu Liu, Chi Zhang and Yaochen Li. Autonomous driving simulation for unmanned vehicles[C]//In Proceedings of IEEE Winter Conference on Applications of Computer Vision, Hawaii, Jan. 2015. (EI:20151300683652)

[2] Jianji Wang, Yuehu Liu, Ping Wei, Zhiqiang Tian, Yaochen Li and Nanning Zheng. Fractal image coding using SSIM[C]//In Proceedings of IEEE International Conference on Image Processing, Brussels, Sep. 2011. (EI:20120514730190)

[1] Yuanqi Su, Yaochen Li, Gang Zhou, Ping Wei and Yuehu Liu. Using selective attention for some vision tasks[J]. International Journal of Advanced Intelligence, 2011, 3(2):243-253.

发明专利

已授权专利

[4] 李垚辰,祝超,刘跃虎,一种基于深度学习的道路边界点检测方法, 专利号码:ZL201910232810.2, 授权时间:2020.11.10

[3] 李垚辰,刘跃虎,祝继华,牛振宁,郭瑞,马士琦,一种道路行驶区域的视觉检测方法, 专利号码:ZL201710437201.1, 授权时间:2019.10.18

[2] 刘跃虎,李垚辰,苏远岐,杨旸,张驰,一种道路场景视频图像序列的背景修复方法, 专利号码:ZL201410239942.5, 授权时间:2017.2.8

[1] 刘跃虎,李垚辰,苏远岐,杨旸,张驰,一种窄带背景探测的快速双循环水平集方法, 专利号码:ZL201410239863.4,  授权时间:2016.11.30

​​​​​​​

申请专利

[3] 李垚辰,袁建,董子坤,王雨潇,刘跃虎,一种基于结构化学习的道路场景布局分析方法, 专利号码:ZL202010431561.2, 申请时间:2020.5.21

[2] 李垚辰,吴潇,宋晨明,刘跃虎,一种多任务联合判别学习的车辆重识别方法, 专利号码:ZL202010432575.6, 申请时间:2020.5.20

[1] 李垚辰,王瑞豪,吴霄,陆丹卉,刘跃虎,一种基于对抗生成神经网络的图像风格迁移方法, 专利号码:ZL201910730983.7, 申请时间:2019.8.8

软件著作权

[2] 李垚辰,宋康,吴潇,宋晨明,陈雨婷, 刘敬乐, 道路场景车辆检测与检索软件[简称: xjtu-vehicle], 登记号码:2021SR0039050, 2021.2.2.

[1] 李垚辰,袁建,霍慧慧,吴霄,左良玉,三维走廊式道路场景建模软件[简称: TITV], 登记号码:2019SR0772750, 2019.6.14.