高伟，中国科学院自动化研究所研究员，硕士生导师。主要研究方向：人工智能与计算机视觉、深度学习与三维语义分析、大数据与视觉定位、机器人与SLAM技术等。目前任全国信息技术标准化技术委员会实时定位技术标准制定工作组成员，中国电子工业标准化技术协会团体标准专家委员会委员，中国卫星导航定位协会室内导航定位专业委员会委员，中国图象图形学学会机器视觉专业委员会委员，中国图象图形学学会三维视觉专业委员会委员。牵头制定国家标准1项，参与制定国家标准3项。在高水平期刊上发表论文四十余篇，申请发明专利二十余项。多次承担参与国家科研项目，包括国家重点研发计划、国家科技计划863、国家科技支撑计划、国家自然基金重点项目、国家自然基金面上项目等。
Publications
Lightweight Structured Line Map Based Visual Localization.
IEEE Robotics and Automation Letters, 9(6): 5182-5189, 2024.
Implementation and observability analysis of visual-inertial-wheel odometry with robust initialization and online extrinsic calibration.
Robotics and Autonomous Systems, 176: 104686, 2024.
Cross-Modal Learning for Event-Based Semantic Segmentation via Attention Soft Alignment.
IEEE Robotics and Automation Letters, 9(3): 2359-2366, 2024.
A large-scale dataset for indoor visual localization with high-precision ground truth.
The International Journal of Robotics Research, 41(2): 129-135, 2022.
High-quality indoor scene 3D reconstruction with RGB-D cameras: A brief review.
Computational Visual Media, 8(3): 369-393, 2022.
Bidirectional Trajectory Computation for Odometer-Aided Visual-Inertial SLAM.
IEEE International Conference on Robotics and Automation, ICRA 2021.
BSP-MonoLoc: Basic Semantic Primitives Based Monocular Localization on Roads.
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021.
Optimization-Based Visual-Inertial SLAM Tightly Coupled with Raw GNSS Measurements.
IEEE International Conference on Robotics and Automation, ICRA 2021.
Boosting Image-Based Localization Via Randomly Geometric Data Augmentation.
IEEE International Conference on Image Processing, ICIP 2020.
Color-Guided Depth Map Super-Resolution Using a Dual-Branch Multi-Scale Residual Network with Channel Interaction.
Sensors, 20(6): 1560, 2020.
Dynamic Object-Aware Monocular Visual Odometry With Local And Global Information Aggregation.
IEEE International Conference on Image Processing, ICIP 2020.
Effective Piecewise Planar Modeling Based on Sparse 3D Points and Convolutional Neural Network.
Neurocomputing, 378: 350-363, 2020.
Effective two-view line segment reconstruction based on structure priors.
Science China-Information Sciences, 63(1): 119102, 2020.
Reconstruction of lines and planes of urban buildings with angle regularization.
ISPRS Journal of Photogrammetry and Remote Sensing, 165: 54-66, 2020.
Scene-unified image translation for visual localization.
IEEE International Conference on Image Processing, ICIP 2020.
Efficient and Robust Large-Scale Structure-from-Motion via Track Selection and Camera Prioritization.
ISPRS Journal of Photogrammetry and Remote Sensing, 156: 202-214, 2019.
Effectively Modeling Piecewise Planar Urban Scenes Based on Structure Priors and CNN.
Science China-Information Sciences, 62(2): 29102, 2019.
Efficient Multi-plane Extraction from Massive 3D Points for Modeling Large-scale Urban Scenes.
The Visual Computer, 35(5): 625-638, 2019.
Optical Flow Assisted Monocular Visual Odometry.
Asian Conference on Pattern Recognition, ACPR 2019.
Visual-Inertial Odometry Tightly Coupled with Wheel Encoder Adopting Robust Initialization and Online Extrinsic Calibration.
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019.
Geometrically Stable Tracking for Depth Images Based 3D Reconstruction on Mobile Devices.
ISPRS Journal of Photogrammetry and Remote Sensing, 143: 222-232, 2018.
Progressive Large-Scale Structure-from-Motion with Orthogonal MSTs.
International Conference on 3D Vision, 3DV, 2018.
Voting-based Incremental Structure-from-Motion.
International Conference on Pattern Recognition, ICPR 2018.
Dense RGB-D SLAM with Multiple Cameras.
Sensors, 18(7), 2018.
Elaborate Scene Reconstruction with a Consumer Depth Camera.
International Journal of Automation and Computing, 15(4): 443-453, 2018.
High-Quality and Memory-Efficient Volumetric Integration of Depth Maps Using Plane Priors.
International Conference on Pattern Recognition, ICPR 2018.
Modern physiognomy: an investigation on predicting personality traits and intelligence from the human face.
Science China-Information Sciences, 61(5): 058105, 2018.
Online Temporal Calibration of Camera and IMU Using Nonlinear Optimization.
International Conference on Pattern Recognition, ICPR 2018.
Robust and Efficient CPU-Based RGB-D Scene Reconstruction.
Sensors, 18(11), 2018.
Physiognomy: Personality Traits Prediction by Learning.
International Journal of Automation and Computing, 14(4): 386-395, 2017.
Rapid and Robust Piecewise Planar Reconstruction of Urban Scenes.
Acta Automatica Sinica, 43(4): 674-684, 2017.
Robust 3D Indoor Map Building via RGB-D SLAM with Adaptive IMU Fusion on Robot.
International Conference on Image and Graphics, ICIG 2017.
Efficient Large-Scale Structure From Motion by Fusing Auxiliary Imaging Information.
IEEE Transactions on Image Processing, 24(11): 3561-3573, 2015.
Dense 3D scene reconstruction based on semantic constraint and graph cuts.
Scientia Sinica Informationis, 44(6), 774-792, 2014.
Fusion of Auxiliary Imaging Information for Robust, Scalable and Fast 3D Reconstruction.
Asian Conference on Computer Vision, ACCV 2014.
A hierarchical model for disparity computation.
Scientia Sinica Informationis, 43(9), 1111-1123, 2013.
Automatic generation of large scale true ortho-image from UAV images.
Scientia Sinica Informationis, 43(11), 1383-1397, 2013.
Batch Reconstruction from UAV Images with Prior Information.
Acta Automatica Sinica, 39(6): 834-845, 2013.