机器人导航与定位、视觉定位、SLAM

   

081104-模式识别与智能系统
081101-控制理论与控制工程

计算机视觉
智能机器人

计算机视觉
数字图像处理
计算机视觉秋季
机器人视觉导航
机器人视觉定位导航
机器人视觉感知和行为规划
计算机视觉 II

[1] Wang, Zengmao, Hu, Jianhua, Tang, Qifei, Gao, Wei. COAL: Robust Contrastive Learning-Based Visual Navigation Framework. JOURNAL OF FIELD ROBOTICS[J]. 2025, 第 4 作者  通讯作者  http://dx.doi.org/10.1002/rob.22508.
[2] Xie, Chuyun, Gao, Wei, Guo, Ren. Cross-Modal Learning for Event-Based Semantic Segmentation via Attention Soft Alignment. IEEE ROBOTICS AND AUTOMATION LETTERS[J]. 2024, 第 2 作者  通讯作者  9(3): 2359-2366, 
[3] Jinxu Liu, Gao, Wei, Xie Chuyun, Hu, Zhanyi. Implementation and observability analysis of visual-inertial-wheel odometry with robust initialization and online extrinsic calibration. Robotics and Autonomous Systems[J]. 2024, 第 2 作者  通讯作者  176: 
[4] Liu, Hongmin, Cao, Chengyang, Ye, Hanqiao, Cui, Hainan, Gao, Wei, Wang, Xing, Shen, Shuhan. Lightweight Structured Line Map Based Visual Localization. IEEE ROBOTICS AND AUTOMATION LETTERS[J]. 2024, 第 5 作者9(6): 5182-5189, http://dx.doi.org/10.1109/LRA.2024.3387137.
[5] Han, Sheng, Gao, Wei, Hu, Zhanyi. Why You Cannot Rank First: Modifications for Benchmarking Six-Degree-of-Freedom Visual Localization Algorithms. SENSORS[J]. 2023, 第 2 作者  通讯作者  23(23): http://dx.doi.org/10.3390/s23239580.
[6] Li, Jianwei, Gao, Wei, Wu, Yihong, Liu, Yangdong, Shen, Yanfei. High-quality indoor scene 3D reconstruction with RGB-D cameras: A brief review. COMPUTATIONAL VISUAL MEDIA. 2022, 第 2 作者8(3): 369-393, http://sciencechina.cn/gw.jsp?action=detail.jsp&internal_id=7371625&detailType=1.
[7] Liu, Yuchen, Gao, Wei, Hu, Zhanyi. A large-scale dataset for indoor visual localization with high-precision ground truth. INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH[J]. 2022, 第 2 作者  通讯作者  41(2): 129-135, 
[8] Heping Li, Changliang Xue, Feng Wen, Hongbo Zhang, Wei Gao. BSP-MonoLoc: Basic Semantic Primitives based Monocular Localization on Roads. 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)[J]. 2021, 第 5 作者5470-5475, 
[9] Liu, Jinxu, Gao, Wei, Hu, Zhanyi. Bidirectional Trajectory Computation for Odometer-Aided Visual-Inertial SLAM. IEEE ROBOTICS AND AUTOMATION LETTERS[J]. 2021, 第 2 作者  通讯作者  6(2): 1670-1677, https://www.webofscience.com/wos/woscc/full-record/WOS:000626509300001.
[10] Liu, Jinxu, Gao, Wei, Hu, Zhanyi. Optimization-Based Visual-Inertial SLAM Tightly Coupled with Raw GNSS Measurements. 2021 IEEE International Conference on Robotics and Automation (ICRA). 2021, 第 2 作者  通讯作者  11612-11618, https://ieeexplore.ieee.org/document/9562013.
[11] Wang, Wei, Gao, Wei, Hu, Zhanyi. Effective piecewise planar modeling based on sparse 3D points and convolutional neural network. NEUROCOMPUTING[J]. 2020, 第 2 作者378: 350-363, https://www.webofscience.com/wos/woscc/full-record/WOS:000506202200031.
[12] Han, Sheng, Gao, Wei, Wan, Yiming, Wu, Yihong. SCENE-UNIFIED IMAGE TRANSLATION FOR VISUAL LOCALIZATION. IEEE International Conference on Image Processing (ICIP). 2020, 第 2 作者  通讯作者  2266-2270, 
[13] Wang, Wei, Gao, Wei, Cui, Hainan, Hu, Zhanyi. Reconstruction of lines and planes of urban buildings with angle regularization. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING[J]. 2020, 第 2 作者  通讯作者  165: 54-66, 
[14] Wan, Yiming, Gao, Wei, Han, Sheng, Wu, Yihong, IEEE. DYNAMIC OBJECT-AWARE MONOCULAR VISUAL ODOMETRY WITH LOCAL AND GLOBAL INFORMATION AGGREGATION. 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)[J]. 2020, 第 2 作者  通讯作者  603-607, 
[15] Wan, Yiming, Gao, Wei, Han, Sheng, Wu, Yihong, IEEE. BOOSTING IMAGE-BASED LOCALIZATION VIA RANDOMLY GEOMETRIC DATA AUGMENTATION. 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)[J]. 2020, 第 2 作者  通讯作者  688-692, 
[16] Chen, Ruijin, Gao, Wei. Color-Guided Depth Map Super-Resolution Using a Dual-Branch Multi-Scale Residual Network with Channel Interaction. SENSORS[J]. 2020, 第 2 作者  通讯作者  20(6): https://doaj.org/article/406ffd20a77547da99a0e8f79eadf7e5.
[17] Yiming Wan, Wei Gao, Yihong Wu. Optical Flow Assisted Monocular Visual Odometry. Pattern recognition : Part I /[J]. 2020, 第 2 作者  通讯作者  366-377, http://dx.doi.org/10.1007/978-3-030-41404-7_26.
[18] Wang, Wei, Cui Hainan, Gao, Wei, Hu, Zhanyi. Effective two-view line segment reconstruction based on structure priors. SCIENCE CHINA-INFORMATION SCIENCES[J]. 2020, 第 3 作者63(1): 
[19] Wang, Wei, Gao, Wei, Hu, Zhanyi. Effectively modeling piecewise planar urban scenes based on structure priors and CNN. SCIENCE CHINA-INFORMATION SCIENCES[J]. 2019, 第 2 作者62(2): 199-201, http://lib.cqvip.com/Qikan/Article/Detail?id=7001631097.
[20] Cui, Hainan, Shen, Shuhan, Gao, Wei, Liu, Hongmin, Wang, Zhiheng. Efficient and robust large-scale structure-from-motion via track selection and camera prioritization. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING[J]. 2019, 第 3 作者156: 202-214, 
[21] Wang, Wei, Gao, Wei. Efficient multi-plane extraction from massive 3D points for modeling large-scale urban scenes. VISUAL COMPUTER[J]. 2019, 第 2 作者35(5): 625-638, http://ir.ia.ac.cn/handle/173211/24175.
[22] Liu, Yangdong, Gao, Wei, Hu, Zhanyi. 3D Scanning of High Dynamic Scenes Using an RGB-D Sensor and an IMU on a Mobile Device. IEEE ACCESS[J]. 2019, 第 2 作者  通讯作者  7(7): 24057-24070, https://doaj.org/article/626807dfaf8c4055810f3a2874ffa2ba.
[23] Liu, Jinxu, Gao, Wei, Hu, Zhanyi. Visual-Inertial Odometry Tightly Coupled with Wheel Encoder Adopting Robust Initialization and Online Extrinsic Calibration. 2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)[J]. 2019, 第 2 作者  通讯作者  5391-5397, 
[24] Li, Jianwei, Gao, Wei, Wu, Yihong. High-Quality 3D Reconstruction With Depth Super-Resolution and Completion. IEEE ACCESS[J]. 2019, 第 2 作者  通讯作者  7(1): 19370-19381, https://doaj.org/article/5738a550df054452b45a001fd9b2be4a.
[25] Liu, Yangdong, Gao, Wei, Hu, Zhanyi. Geometrically stable tracking for depth images based 3D reconstruction on mobile devices. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING[J]. 2018, 第 2 作者  通讯作者  143: 222-232, http://dx.doi.org/10.1016/j.isprsjprs.2018.03.009.
[26] Cui Hainan, Shen Shuhan, Gao Wei. Voting-based Incremental Structure-from-Motion. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)[J]. 2018, 第 3 作者1929-1934, 
[27] Liu Yangdong, Gao Wei, Hu Zhanyi. High-Quality and Memory-Efficient Volumetric Integration of Depth Maps Using Plane Priors. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)[J]. 2018, 第 2 作者  通讯作者  1749-1754, 
[28] Jian-Wei Li, Wei Gao, Yi-Hong Wu. Elaborate Scene Reconstruction with a Consumer Depth Camera. 国际自动化与计算杂志英文版[J]. 2018, 第 2 作者  通讯作者  15(4): 443-453, http://lib.cqvip.com/Qikan/Article/Detail?id=675656986.
[29] Cui Hainan, Shen Shuhan, Gao Wei, Wang Zhiheng. Progressive Large-Scale Structure-from-Motion with Orthogonal MSTs. 6th International Conference on 3D Vision (3DV). 2018, 第 3 作者79-88, 
[30] Cui Hainan, Shen Shuhan, Gao Wei, IEEE. Voting-based Incremental Structure-from-Motion. 24th International Conference on Pattern Recognition (ICPR). 2018, 第 3 作者1929-1934, 
[31] Li, JianWei, Gao, Wei, Wu, YiHong. Elaborate Scene Reconstruction with a Consumer Depth Camera. INTERNATIONAL JOURNAL OF AUTOMATION AND COMPUTING[J]. 2018, 第 2 作者  通讯作者  15(4): 443-453, http://lib.cqvip.com/Qikan/Article/Detail?id=675656986.
[32] Rizhen QIN, Wei GAO, Huarong XU, Zhanyi HU. Modern physiognomy: an investigation on predicting personality traits and intelligence from the human face. SCIENCE CHINA Information Sciences[J]. 2018, 第 2 作者61(5): https://www.sciengine.com/doi/10.1007/s11432-016-9174-0.
[33] Li, Jianwei, Gao, Wei, Li, Heping, Tang, Fulin, Wu, Yihong. Robust and Efficient CPU-Based RGB-D Scene Reconstruction. SENSORS[J]. 2018, 第 2 作者  通讯作者  18(11): http://ir.ia.ac.cn/handle/173211/23360.
[34] 孟馨蕊, 高伟, 胡占义. Robust 3D Indoor Map Building via RGB-D SLAM with Adaptive IMU Fusion on Robot. 2018, 第 2 作者  通讯作者  454-465, http://ir.ia.ac.cn/handle/173211/20948.
[35] Meng, Xinrui, Gao, Wei, Hu, Zhanyi. Dense RGB-D SLAM with Multiple Cameras. SENSORS[J]. 2018, 第 2 作者  通讯作者  18(7): https://doaj.org/article/d13cdde1daae4f51a9d98d7e92b28c4f.
[36] Liu Jinxu, Gao Wei, Hu Zhanyi. Online Temporal Calibration of Camera and IMU using Nonlinear Optimization. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)[J]. 2018, 第 2 作者  通讯作者  1761-1766, 
[37] 王伟, 高伟, 朱海, 胡占义. 快速鲁棒的城市场景分段平面重建. 自动化学报[J]. 2017, 第 2 作者43(4): 674-684, 
[38] Meng, Xinrui, Gao, Wei, Hu, Zhanyi, Zhao, Y, Kong, X, Taubman, D. Robust 3D Indoor Map Building via RGB-D SLAM with Adaptive IMU Fusion on Robot. IMAGE AND GRAPHICS (ICIG 2017), PT I[J]. 2017, 第 2 作者  通讯作者  10666: 454-465, 
[39] Zhang, Ting, Qin, RiZhen, Dong, QiuLei, Gao, Wei, Xu, HuaRong, Hu, ZhanYi. Physiognomy: Personality Traits Prediction by Learning. INTERNATIONAL JOURNAL OF AUTOMATION AND COMPUTING[J]. 2017, 第 4 作者14(4): 386-395, 
[40] 贾奋励, 王光霞, 李霖, 徐连明, 高伟. 互联网全息位置地图迭加协议与建模制图技术. 科技资讯[J]. 2016, 第 5 作者14(25): 183-184, http://lib.cqvip.com/Qikan/Article/Detail?id=670629498.
[41] Cui, Hainan, Shen, Shuhan, Gao, Wei, Hu, Zhanyi. Efficient Large-Scale Structure From Motion by Fusing Auxiliary Imaging Information. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2015, 第 3 作者24(11): 
[42] Cui Hainan, Shen Shuhan, Gao Wei, Hu Zhanyi, Cremers D, Reid I, Saito H, Yang MH. Fusion of Auxiliary Imaging Information for Robust, Scalable and Fast 3D Reconstruction. COMPUTER VISION - ACCV 2014, PT I. 2015, 第 3 作者9003: 227-242, 
[43] 王伟, 高伟, 胡占义. 基于语义约束与Graph Cuts的稠密三维场景重建. 中国科学 信息科学[J]. 2014, 第 2 作者44(6): 774-792, 
[44] 郭复胜, 高伟. 基于辅助信息的无人机图像批处理三维重建方法. 自动化学报[J]. 2013, 第 2 作者39(6): 834-845, 
[45] 孔庆群, 高伟. 视差计算的层级模型. 中国科学: 信息科学[J]. 2013, 第 2 作者43(9): 1111-1123, https://www.sciengine.com/doi/10.1360/112012-642.
[46] 郭复胜, 许华荣, 高伟, 胡占义. 利用相机辅助信息的分组三维场景重建. 计算机科学与探索[J]. 2013, 第 3 作者7(9): 783-799, http://lib.cqvip.com/Qikan/Article/Detail?id=46943742.
[47] 郭复胜, 高伟, 胡占义. 无人机图像全自动生成大比例尺真正射影像方法. 中国科学 信息科学[J]. 2013, 第 2 作者43(11): 1383-1397, 
[48] Hainan Cui, Shuhan Shen, Wei Gao, Zhanyi Hu. Fusion of Auxiliary Imaging Information for Robust, Scalable and Fast 3D Reconstruction. 12th Asian Conference on Computer Vision,. 2012, 第 3 作者227-242, 
[49] Liu, Xin, Gao, Wei, Hu, ZhanYi. Hybrid Parallel Bundle Adjustment for 3D Scene Reconstruction with Massive Points. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY[J]. 2012, 第 2 作者27(6): 1269-1280, https://www.webofscience.com/wos/woscc/full-record/WOS:000311264700018.
[50] 史利民, 郭复胜, 高伟, 胡占义. 基于语义交互的三维重建. 计算机辅助设计与图形学学报[J]. 2011, 第 3 作者23(5): 839-848, http://lib.cqvip.com/Qikan/Article/Detail?id=37684957.
[51] 高伟, 王志衡, 赵训坡, 孙凤梅. 基于HSI颜色空间的棉花杂质高速实时检测方法. 自动化学报[J]. 2008, 第 1 作者  通讯作者  34(7): 729-735, http://lib.cqvip.com/Qikan/Article/Detail?id=27758368.
[52] Gao, Wei, Wang, Liang, Hu, Zhanyi. Flexible method for structured light system calibration. OPTICAL ENGINEERING[J]. 2008, 第 1 作者  通讯作者  47(8): http://ir.ia.ac.cn/handle/173211/9564.
[53] GAO Wei, Wang Liang, HU ZhanYi. Flexible Calibration of a Portable Structured Light System through Surface Plane. ACTA AUTOMATICA SINICA[J]. 2008, 第 1 作者  通讯作者  34(11): 1358-1362, 

   

（ 1 ） 基于草图CAD模型智能生成, 负责人, 国家任务, 2022-11--2025-10
（ 2 ） 基于弱监督学习和图神经网络的大型建筑室内视觉定位技术研究, 负责人, 国家任务, 2022-01--2025-12
（ 3 ） 基于控制的三维综合测试系统, 负责人, 境内委托项目, 2020-01--2021-12
（ 4 ） 室内服务机器人定位导航系统, 负责人, 境内委托项目, 2019-05--2021-12
（ 5 ） 几何与语义相结合的复杂室内场景三维重建技术研究, 负责人, 国家任务, 2019-01--2022-12
（ 6 ） 室外场景SLAM技术研究, 负责人, 境内委托项目, 2018-01--2018-12
（ 7 ） 室外街景图像三维重建技术研究, 负责人, 境内委托项目, 2018-01--2018-12
（ 8 ） 基于古建的三维重建系统研究, 负责人, 境内委托项目, 2018-01--2018-12
（ 9 ） 室内地标特征匹配与位姿精密估计, 负责人, 国家任务, 2016-07--2020-12
（ 10 ） 深度相机三维建模, 负责人, 境内委托项目, 2015-01--2016-09
（ 11 ） 三维重建中POI提取技术, 负责人, 国家任务, 2015-01--2017-12
（ 12 ） 基于微型旋翼无人飞行器的古代建筑影像获取与三维重建方法研究, 负责人, 国家任务, 2015-01--2018-12
（ 13 ） 文博考古三维重建, 负责人, 境内委托项目, 2013-01--2016-12
（ 14 ） 针对中国古代建筑的结构与图像相融合的三维重建方法研究, 负责人, 国家任务, 2013-01--2015-12
（ 15 ） 全息地图实时生成和快速更新, 负责人, 国家任务, 2013-01--2015-12