This repository is the usage page of the UrbanNav dataset. Positioning and localization in deep urban canyons using low-cost sensors is still a challenging problem. The accuracy of GNSS can be severely challenged in urban canyons due to the high-rising buildings, leading to numerous Non-line-of-sight (NLOS) receptions and multipath effects. Moreover, the excessive dynamic objects can also distort the performance of LiDAR, and camera. The UrbanNav dataset wishes to provide a challenging data source to the community to further accelerate the study of accurate and robust positioning in challenging urban canyons. The dataset includes sensor measurements from GNSS receivers, LiDAR, camera, and IMU, together with accurate ground truth from SPAN-CPT system. Different from the existing dataset, such as Waymo, KITTI, UrbanNav provide raw GNSS RINEX data. In this case, users can improve the performance of GNSS positioning via raw data. In short, the UrbanNav dataset poses a special focus on improving GNSS positioning in urban canyons but also provides sensor measurements from LiDAR, camera, and IMU. If you got any problems when using the dataset and cannot find a satisfactory solution in the issue list, please open a new issue and we will reply ASAP.
Youtube link of the webinar talk.
Slide link of the webinar talk
Key words: Positioning, Localization, GNSS Positioning, Urban Canyons, GNSS Raw Data,Dynamic Objects, GNSS/INS/LiDAR/Camera, Ground Truth
Important Notes:
Open-sourcing positioning sensor data, including GNSS, INS, LiDAR and cameras collected in Asian urban canyons;
Raising the awareness of the urgent navigation requirement in highly-urbanized areas, especially in Asian-Pacific regions;
Providing an integrated online platform for data sharing to facilitate the development of navigation solutions of the research community; and
Benchmarking positioning algorithms based on the open-sourcing data.
Contact Authors (corresponding to issues and maintenance of the currently available Hong Kong dataset): Li-Ta Hsu, Weisong Wen, Feng Huang, Hoi-Fung Ng, GuoHao Zhang, Xiwei Bai from the Intelligent Positioning and Navigation Laboratory, The Hong Kong Polytechnique University
Related Papers:
The platform for data collection in Hong Kong is a Honda Fit. The platform is equipped with the following sensors:
Total Size | Path length | Sensors | Urban Canyon | Download | 3D PointCloud | |
---|---|---|---|---|---|---|
UrbanNav-HK-Medium-Urban-1 | 33.7 GB (785s) | 3.64 Km | LiDARs/Stereo Camera/IMU/GNSS | Medium | ROS, GNSS, IMU, Ground Truth, Skymask | Medium Urban Map |
UrbanNav-HK-Deep-Urban-1 | 63.9 GB (1536s) | 4.51 Km | LiDARs/Stereo Camera/IMU/GNSS | Deep | ROS, GNSS, IMU, Ground Truth, Skymask | Deep Urban Map |
UrbanNav-HK-Harsh-Urban-1 | 147 GB (3367s) | 4.86 Km | LiDARs/Stereo Camera/IMU/GNSS | Harsh | ROS, GNSS, IMU, Ground Truth, Skymask | Harsh Urban Map |
UrbanNav-HK-Tunnel-1 | 17 GB (398s) | 3.15 Km | LiDARs/Stereo Camera/IMU/GNSS | N/A | ROS, GNSS, IMU, Ground Truth | Tunnel map |
(Pilot data) UrbanNav-HK-Data20190428 | 42.9 GB (487s) | 2.01 Km | LiDAR/Camera/IMU/GNSS | Medium | ROS, GNSS | N/A |
(Pilot data) UrbanNav-HK-Data20200314 | 27.0 GB (300s) | 1.21 Km | LiDAR/Camera/IMU/GNSS | Light | ROS, GNSS | N/A |
Dataset UrbanNav-HK-Medium-Urban-1 is collected in a typical urban canyon of Hong Kong near TST which involves high-rising buildings, numerous dynamic objects. A updated version to UrbanNav-HK-Data20190428, two loops included. The coordinates transformation between multiple sensors, and intrinsic measurements of camera can be found via Extrinsic Parameters, IMU Nosie and Intrinsic Parameters of Camera.
/velodyne_points
/left/lslidar_point_cloud
/right/velodyne_points
/zed2/camera/left/image_raw
/zed2/camera/right/image_raw
/imu/data
/novatel_data/inspvax
/time_reference
Dataset UrbanNav-HK-Deep-Urban-1 is collected in a highly urbanized area of Hong Kong which involves dense traffic, small tunnels and loops. The coordinates transformation between multiple sensors, and intrinsic measurements of camera can be found via Extrinsic Parameters, IMU Nosie and Intrinsic Parameters of Camera.
/velodyne_points
/left/lslidar_point_cloud
/right/velodyne_points
/zed2/camera/left/image_raw
/zed2/camera/right/image_raw
/imu/data
/novatel_data/inspvax
/time_reference
Dataset UrbanNav-HK-Harsh-Urban-1 is collected in an ultra-dense urban canyon of Hong Kong which involves dense vehicles, pedestrians and loops. The coordinates transformation between multiple sensors, and intrinsic measurements of camera can be found via Extrinsic Parameters, IMU Nosie and Intrinsic Parameters of Camera.
/velodyne_points
/left/lslidar_point_cloud
/right/velodyne_points
/zed2/camera/left/image_raw
/zed2/camera/right/image_raw
/imu/data
/time_reference
UrbanNav-HK-Tunnel-1 is collected in a sea tunnel of Hong Kong which involves dense vehicles and GNSS signal losses. The coordinates transformation between multiple sensors, and intrinsic measurements of camera can be found via Extrinsic Parameters, IMU Nosie and Intrinsic Parameters of Camera.
/velodyne_points
/left/lslidar_point_cloud
/right/velodyne_points
/zed2/camera/left/image_raw
/zed2/camera/right/image_raw
/imu/data
/novatel_data/inspvax
/time_reference
Brief: Dataset UrbanNav-HK-Data20190428 is collected in a typical urban canyon of Hong Kong near TST which involves high-rising buildings, numerous dynamic objects. The coordinates transformation between multiple sensors, and intrinsic measurements of camera can be found via Extrinsic Parameters, IMU Nosie and Intrinsic Parameters of Camera.
Some key features are as follows: | Date of Collection | Total Size | Path length | Sensors |
---|---|---|---|---|
2019/04/28 | 42.9 GB | 2.01 Km | GNSS/LiDAR/Camera/IMU/SPAN-CPT |
/ublox_node/fix
/velodyne_points
/camera/image_color
/imu/data
/novatel_data/inspvax
For mainland china users, please download the dataset using the Baidu Clouds Links
/ublox_node/fix
/velodyne_points
/camera/image_color
/imu/data
/novatel_data/inspvax
Brief: Dataset UrbanNav-HK-Data2020314 is collected in a low-urbanization area in Kowloon which suitable for algorithmic verification and comparison. The coordinates transformation between multiple sensors, and intrinsic measurements of camera can be found via Extrinsic Parameters, IMU Nosie and Intrinsic Parameters of Camera.
Some key features are as follows: | Date of Collection | Total Size | Path length | Sensors |
---|---|---|---|---|
2020/03/14 | 27.0 GB | 1.21 Km | LiDAR/Camera/IMU/SPAN-CPT |
/velodyne_points
/camera/image_color
/imu/data
/novatel_data/inspvax
For mainland china users, please download the dataset using the Baidu Clouds Links
/velodyne_points
/camera/image_color
/imu/data
/novatel_data/inspvax
The platform for data collection in Tokyo is a Toyota Rush. The platform is equipped with the following sensors:
Date of Collection | Total Size | Path length | Sensors |
---|---|---|---|
2018/12/19 | 4.14 GB | >10 Km | GNSS/LiDAR/IMU/Ground Truth |
/Odaiba
and /Shinjuku
.rover_ublox.obs
and rover_trimble.obs
: Rover GNSS RINEX files (5 Hz / 10 Hz)imu.csv
: CSV file which includes GPS time, Angular velocity, and acceleration, (50 Hz)lidar.bag
: ROSBAG file which includes LiDAR data /velodyne_packets
base_trimble.obs
and base.nav
: GNSS RINEX files of base station (1 Hz)reference.csv
: Ground truth from Applanix POS LV620 (10 Hz)The travel trajectory of /Odaiba
The travel trajectory of /Shinjuku
We acknowledge the help from Yihan Zhong, Jiachen Zhang, Yin-chiu Kan, Weichang Xu and Song Yang.
For any technical issues, please contact Feng Huang via email darren-f.huang@connect.polyu.hk and Weisong Wen via email welson.wen@polyu.edu.hk. For collaboration inquiries, please contact Li-Ta Hsu via email lt.hsu@polyu.edu.hk.