wq1989

Pinned Repositories

Benchmark-Dataset-for-Adaptive-Stride-Length-Estimation
The lack of benchmarking datasets for pedestrian stride length estimation makes it hard to pinpoint differences of published methods. Existing datasets either lack the ground-truth of each stride or are limited to small spaces with single scene or motion pattern. To fully evaluate the performance of proposed ASLE algorithm, we conducted benchmark dataset for natural pedestrian dead reckoning using smartphone sensors and FM-INS module. we leveraged the FM-INS module to provide the ground-truth of each stride with motion distance errors in 0.3% of the entire travel distance. The datasets were obtained from a group of healthy adults with natural motion patterns (fast walking, normal walking, slow walking, running, jumping). The datasets contained more than 22 km, 10000 strides of gait measurements. The datasets cover both indoor and outdoor cases, including: stairs, escalators, elevators, office environments, shopping mall, streets and metro station. To maximize compatibility, all data is published in open and simple file formats. The sensor is sampled at 100 Hz. Throughout the datasets, the users hold the phone in their hand in front of their chest. The samples hold nine degree-of-freedom sensor data and the corresponding stride number, stride length and total walking distance.
3 2 02
Fusion-DHL
Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments
Language:Python1 1 00
har-uda
An unsupervised domain adaptation approach for human activity recognition using wearable sensors
Language:Jupyter Notebook1 0 00
kalman-localization
Implementation of localization using sensor fusion of GPS/INS/compass through an error-state Kalman filter.
Language:MATLAB1 2 00
MAINSvsMAGEKF
MAINS: A Magnetic Field Aided Inertial Navigation System for Indoor Positioning
Language:MATLAB1 0 00
NeuroSLAM
NeuroSLAM: A Brain inspired SLAM System for 3D Environments
Language:MATLAB2 1 00
PDR_coupled_GNSS
PDR loose coupled with GNSS
Language:MATLAB1 1 00
Pedestrian-Dead-Reckoning-PDR
室内行人移动方位推算技术 (Pedestrian Dead Reckoning, PDR)
Language:Jupyter Notebook1 0 00
PedestrianDeadReckoning
Research on Pedestrian Dead Reckoning
Language:MATLAB1 0 00
WalkingDistanceEstimation
4 2 11

wq1989's Repositories

wq1989/MAINSvsMAGEKF
MAINS: A Magnetic Field Aided Inertial Navigation System for Indoor Positioning
Language:MATLAB1 0 00
wq1989/Pedestrian-Dead-Reckoning-PDR
室内行人移动方位推算技术 (Pedestrian Dead Reckoning, PDR)
Language:Jupyter Notebook1 0 00
wq1989/PSINS
Precise Strapdown Inertial Navigation System (PSINS) Toolbox for Matlab
Language:MATLAB1 0 0
wq1989/agrobot
Neural-Kalman GNSS/INS Navigation for Precision Agriculture
wq1989/awesome_lists
Awesome Lists for Tenure-Track Assistant Professors and PhD students. (助理教授/博士生生存指南)
Language:Python0 0
wq1989/CAGE4HAR
Language:Python0 0
wq1989/deep-speed-constrained-ins
Codes for Deep Learning Based Speed Estimation for Constraining Strapdown Inertial Navigation on Smartphones
Language:Python0 0
wq1989/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gradient (TD3) neural network, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.
wq1989/EKFMagSLAM
An extended Kalman filter for magnetic field SLAM
Language:MATLAB0 0
wq1989/GNSS_Fusing
forked from superhang
Language:Java0 0
wq1989/GnssIns-PDR
组合导航-行人航位推算算法
Language:C++0 0
wq1989/HAR-Dataset-Preprocess
Language:Python0 0
wq1989/Heterogeneous-Convolution-for-HAR
Human activity recognition using wearable sensors by heterogeneous convolution neural networks.
Language:Python0 0
wq1989/IMU-Data-Learning
Language:Python0 0
wq1989/imu-tl
Transfer Learning for Inertial-based Activity Recognition
Language:Python0 0
wq1989/IMUNet
Language:Python0 0
wq1989/IMUNet_Android
wq1989/Lightweight-Transformer-Models-For-HAR-on-Mobile-Devices
Human Activity Recognition Transformer (HART) is a transformer based architecture that has been specifically adapted for IMU sensing devices. Findings shows that HART uses fewer paremeters, FLOPs and achieves state-of-the-art results.
Language:Python0 0
wq1989/LuViRA_Dataset
Lund University Vision, Radio, and Audio (LuViRA) Dataset
wq1989/magnetic-field-odometry
Magnetic-Field aided Inertial Navigation System
wq1989/NavGPT
[AAAI 2024] Official implementation of NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models
wq1989/NeRF-SLAM-Benchmark-CVPR24
[CVPR 24'] Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM
wq1989/Pedestrian-Navigation-Activity-Recognition-Datasets
wq1989/QDeepOdo
Reproduce the paper “A Novel Deep Odometry Network for VehiclePositioning Based on Smartphone” method
Language:Python0 0
wq1989/SLAM_Code_Learning
为做NeRF-based SLAM毕设所读过的开源代码，尽量做到行行有注释。
wq1989/tinyodom
TinyOdom: Hardware-Aware Efficient Neural Inertial Navigation
wq1989/TSformer-VO
Implementation of the paper "Transformer-based model for monocular visual odometry: a video understanding approach".
Language:Python0 0
wq1989/tssearch
A Python library for time series subsequence search.
Language:Jupyter Notebook0 0
wq1989/VDRDataCollector
Language:Java0 0
wq1989/VI-SLAM2tag_app
Official implementation of "VI-SLAM2tag: Low-Effort Labeled Dataset Collection for Fingerprinting-Based Indoor Localization", to be presented at IPIN 22
Language:Java0 0