徐迟_教师主页

教师主页移动版

主页 > 北京市 > 中国地质大学

徐迟

个人简历 主要从事计算机视觉、模式识别、深度学习、深度传感器人手位姿估计、机器人视觉定位与增强现实方面研究工作。研究中发现了视觉测量PnP理论中导致严重稳定性退化的“准奇异状态”并提出有效解决方法,提出了第一个完备的透视三线问题(P3L)解集分类并提供了系统的理论分析,基于Lie群代数理论建立了一般关节物体位姿估计统一框架,提出了一种新颖的人手关节链结构Hough随机森林估计方法,进行了视觉位姿估计交叉学科应用研究,取得了多项研究成果。在国内外期刊会议上发表论文20余篇,其中2012年以来以第一/通讯作者在计算机视觉与模式识别领域顶级期刊 IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI,影响因子8.329)与顶级期刊 International Journal of Computer Vision (IJCV,影响因子8.222)上发表论文4篇。研究成果应用于航空航天、机械装配、生物试验等领域,取得良好效果,并在计算机视觉顶级会议IEEE International Conference on Computer Vision(ICCV 2013)、新加坡政府公众活动(SSF 2014)等公共场合多次现场演示,反响良好。研究兴趣包括:计算机视觉,模式识别,深度学习,人手位姿估计,相机位姿估计,康复机器人,家庭服务机器人、视觉定位导航,增强现实,人机交互,机器学习等。欢迎对以上研究方向感兴趣的同学报考我的硕士 / 博士研究生。电子邮箱:  科研项目:• “融合透视投影几何与深度学习的多关节体三维位姿求解稳定性分析”,主持,国家自然科学基金(面上项目),中国地质大学(武汉)• “实时深度图像人手位姿估计方法及其稳定性分析”,主持,国家自然科学基金(面上项目),中国地质大学(武汉)• “中央高校杰出人才培育基金”,主持,中央高校基金,中国地质大学(武汉)• “卸船机无人值守系统”,主持,横向项目,中国地质大学(武汉)• “机器视觉在轨道交通装备制造过程的应用”,主持,横向项目,中国地质大学(武汉)• “基于虚拟个体行为逼近的多机器人自学习决策与协调控制一体化”,参与,国家自然科学基金(面上项目),中国地质大学(武汉)• “A Real-time Immersive Toolkit for 3D Biological Visualization and Annotation”,技术骨干,A*STAR JCO Grant,新加坡科技局• “空间机械臂视觉测量系统研究”,技术骨干,上海航天预研项目,华中科技大学。• “智能装配关键技术研究”,技术骨干,十一五基础科研项目,华中科技大学。 学术会议职务:• IEEE CVPR 2015 Workshop on Observing and understanding hands in action (HANDS 2015)程序委员会主席之一(Program Committee Chair)。会议现场演示:• ICCV 2013(计算机视觉顶级会议)现场演示,得到国际专家同行的关注与认同;• 新加坡政府公众活动“新加坡科技节2014”现场演示,向公众展示最新科技进展;• A*STAR Scientific Conference 2014最佳现场演示奖。担任以下知名国际期刊会议的审稿人:• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)• International Journal of Computer Vision (IJCV)• IEEE Transactions on Image Processing (TIP) • IEEE Transactions on Mobile Computing (TMC)• IEEE Transactions on Intelligent Transportation Systems (T-ITS)• IEEE Transactions on Cybernetics (TC)• Computer Vision and Image Understanding (CVIU)• Pattern Recognition (PR)• IEEE Conference on Computer Vision and Pattern (CVPR)• Association for the Advancement of Artificial Intelligence (AAAI)• European Conference on Computer Vision (ECCV)• British Machine Vision Conference (BMVC) 部分学术论文列表:[J1]  Chi Xu, Lakshmi Govindarajan, Yu Zhang, Li Cheng (2017), ‘Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups’, International Journal of Computer Vision (IJCV, IF:8.222), 123(3), 454–478. (SCI索引: 000403559600008)[J2]  Chi Xu, Lilian Zhang, Li Cheng, Reinhard Koch (2017), ‘Pose Estimation from Line Correspondences: A Complete Analysis and a Series of Solutions’, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, IF:8.329), 39(6), 1209–1222. (SCI检索:000401091200012)[J3]  Chi Xu, Ashwin Nanjappa, Xiaowei Zhang, Li Cheng (2015), ‘Estimate Hand Poses Efficiently from Single Depth Images’, International Journal of Computer Vision (IJCV, IF:8.222), 116(1), 21–45. (SCI检索: 000369422500002)[J4]  Shiqi Li, Chi Xu*, Ming Xie (2012), ‘A Robust O (n) Solution to the Perspective-N-Point Problem’, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, IF:8.329), 34 (7), 1444–1450. (SCI检索: 000304138300015) 通讯作者[J5]  Chi Xu, Lakshmi Govindarajan, Li Cheng (2017), ‘Hand action detection from ego-centric depth sequences with error-correcting Hough transform’, Pattern Recognition (PR, IF:4.582). (DOI: 10.1016/j.patcog.2017.08.009)[J6]  Shiqi Li, Chi Xu* (2011), ‘Efficient lookup table based camera pose estimation for augmented reality’, Computer animation and virtual worlds, 22(1), 47–58. (SCI检索: 000287820600005) 通讯作者[J7]  Shiqi Li, Chi Xu* (2011), ‘A stable direct solution of perspective-three-point problem’, International journal of pattern recognition and artificial intelligence, 25(05), 627–642. (SCI检索: 000294118300002) 通讯作者[J8]  C. Ma, A. Wang, G. Chen, Chi Xu (2018). Hand joints-based gesture recognition for noisy dataset using nested interval unscented kalman filter with LSTM network. The Visual Computer, 34(6), 1053-1063. (SCI检索)doi:10.1007/s00371-018-1556-0[J9]  Xinyu Shao, Bingang Wang, Yunqing Rao, Liang Gao, Chi Xu (2010), ‘Metaheuristic approaches to sequencing mixed-model fabrication/assembly systems with two objectives’, International Journal of Advanced Manufacturing Technology, 48(9), 1159–1171. (SCI检索: 000277795100029)[J10] Shiqi Li, Tao Peng, Junfeng Wang, Chi Xu (2009), ‘Mixed Reality-Based Interactive Technology for Aircraft Cabin Assembly’, Chinese Journal of Mechanical Engineering, 22(3): 403–409. (SCI检索: 000267310600014)[J11] Liang Wang, Yisheng Zhang, Bin Zhu, Chi Xu, Xiaowei Tian, Chao Wang, Jianhua Mo, Li Jian (2012), ’GPU accelerated parallel cholesky factorization’, Applied Mechanics and Materials, 1370–1373, (EI检索)[C1]  Chi Xu, Li Cheng (2013), ‘Efficient hand pose estimation from a single depth image’, in ‘IEEE International Conference on Computer Vision’ (ICCV, 顶级会议, CCF-A类).[C2]  Lilian Zhang, Chi Xu*, Kokmeng Lee, Reinhard Koch (2012), ‘Robust and efficient pose estimation from line correspondences’, in ‘Asian Conference on Computer Vision’ (ACCV). 通讯作者[C3]  Chi Xu, Li Cheng (2018), ‘A Flexible Method for Time-of-Flight Camera Calibration Using Random Forest’, in ‘International Conference on Smart Multimedia’ (ICSM).[C4]  Ashwin Nanjappa, Chi Xu, Li Cheng (2015), ’GHand: A GPU Algorithm for Realtime Hand Pose Estimation Using Depth Camera’, in ‘Eurographics (Posters)’ (EG)[C5]  Chi Xu, Shiqi Li, Junfeng Wang, Tao Peng, Ming Xie (2008), ‘Occlusion handling in Augmented Reality system for human-assisted assembly task’, in ‘International Conference on Intelligent Robotics and Applications’软件著作权与专利:基于增强现实的装配训练系统软件V1.0(计算机软件著作权登记号:2008SR26895)信息增强的舱体内结构智能装配系统软件V1.0(计算机软件著作权登记号:2008SR26898)用于细长腔体的视觉检测装置(发明专利号:ZL 2008 1 0048014.5) 研究方向 [1]   计算机视觉,模式识别,深度学习,人手位姿估计,相机位姿估计,康复机器人,家庭服务机器人、视觉定位导航,增强现实,人机交互,机器学习等。 联系方式 [1]  邮编: [2]  传真: [3]  通讯/办公地址: [4]  办公室电话: [5]  移动电话: [6]  邮箱: