A5084697744- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- 3D Surveying and Cultural Heritage
- Inertial Sensor and Navigation
- Indoor and Outdoor Localization Technologies
- GNSS positioning and interference
- Structural Health Monitoring Techniques
- Geophysics and Gravity Measurements
- Advanced Image and Video Retrieval Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Sensor Technology and Measurement Systems
- Seismic Waves and Analysis
- Robotic Path Planning Algorithms
- Ionosphere and magnetosphere dynamics
- Geophysics and Sensor Technology
- Autonomous Vehicle Technology and Safety
- Optical measurement and interference techniques
- Image Retrieval and Classification Techniques
- Video Surveillance and Tracking Methods
- Remote Sensing and LiDAR Applications
- Soil Moisture and Remote Sensing
- Human-Automation Interaction and Safety
Wuhan University
2022-2024
Nowadays, the low-cost MEMS-based Inertial Measurement Units (IMU) and LiDARs are commercially available in vehicle systems usually integrated to achieve robust ego-motion estimation due their excellent complementary properties. In this case, accurate inter-sensor spatial transformation, i.e. extrinsic parameters, is a fundamental prerequisite for combined application of LiDAR IMU. However, current LiDAR-IMU calibration methods rely on specially-designed artificial targets or facilities,...
Most existing visual-inertial navigation system (VINS) simply rejects dynamic object features to improve performance, rendering the loss of motion information. Whereas some emerging applications, such as autonomous driving, need accurately perceive movement surrounding objects for making decisions. Aiming at performing accurate pose estimations both ego vehicle and objects, we propose a tightly-coupled estimator multi-object tracking, called VIMOT. The proposed directly utilizes 3D bounding...
Nowadays, portable cameras and LiDARs are widely applied in robotic applications for environment perception, path planning, high precision navigation. In such cases, accurate inter-sensor spatial transformation is critical to fuse these sensors seamlessly. However, the feasible efficient extrinsic calibration of LiDAR-camera sensor pair still challenging as it hard establish common feature correspondence between sparse LiDAR point clouds monocular images. this contribution, we design a novel...
High-precision and continuous positioning is a fundamental requirement for intelligent navigation applications. Nowadays, the global satellite system (GNSS) real-time kinematic (RTK) technique recognized as feasible solution to provide precise services, but its accuracy susceptible signal attenuation will deteriorate drastically in urban environments. Fortunately, low-cost inertial measurement units (IMU) light detection ranging (LiDAR) are available modern vehicle systems could be...
The visual-inertial navigation system (VINS) is a low-cost sensor suite that utilizes inertial measurement unit (IMU) and camera data for vehicle ego-motion estimation environmental perception. For VINS, the accurate calibration of inter-sensor (IMU-camera, camera-camera) extrinsic parameters prerequisite optimal information fusion. Currently, modern vehicles are usually equipped with global satellite (GNSS) devices, which provide driftless position could be utilized to enhance calibration....
Accurate and real-time tracking of multiple moving objects in 3-D space is critical for intelligent transportation applications such as autonomous driving traffic monitoring. However, performance often hindered by difficulties occlusion or distant objects. To this end, we present a novel 3-D-light detection ranging (LiDAR) multiobject (MOT) system based on factor graph optimization (FGO) that simultaneously tracks reconstructs their models. First, develop object dynamic motion model combines...
In recent years, it is increasingly prevalent to integrate global navigation satellite system (GNSS) with visual-inertial systems (VINS) provide high-precision and continuous solutions. However, its accuracy robustness are challenged by GNSS signal blockages, inertial (INS) error accumulation, noisy visual measurements, especially in severe environments such as urban downtowns. To achieve accurate consistent pose estimation complex scenarios, we innovatively propose a filter-based...
Pose estimation is a crucial problem in simultaneous localization and mapping (SLAM). However, developing robust consistent state estimator remains significant challenge, as the traditional extended Kalman filter (EKF) struggles to handle model nonlinearity, especially for inertial measurement unit (IMU) light detection ranging (LiDAR). To provide efficient solution of pose estimation, we propose Eq-LIO, tightly coupled LIO systems based on an equivariant (EqF). Compared with invariant...
For high-level geo-spatial applications and intelligent robotics, accurate global pose information is of crucial importance. Map-aided localization an important universal approach to overcome the limitations navigation satellite system (GNSS) in challenging environments. However, current solutions face challenges terms mapping flexibility, storage burden re-localization performance. In this work, we present SF-Loc, a lightweight visual map-aided system, whose core idea map representation...
Visual–inertial systems suffer from the issue of error accumulation, which limits their application to small-scale and short-duration scenarios. To enhance applicability visual–inertial odometry (VIO), we propose T-VIO, a filter-based estimator that tightly integrates visual, inertial, time-differenced carrier phase (TDCP) measurements for low-drift high-precision local pose estimation. The introduction TDCP suppresses accumulation provides absolute heading observability. On this basis,...