PRCV VSLAM Challenge 2022 Save

The FusionPortable-VSLAM Challenge 2022

Project README

The FusionPortable-VSLAM Challenge


For more information, we can visit the following websits:


Sensor Characteristics
3D LiDAR (not provided) Ouster OS1-128, 128 channels, 120m range
Frame Camera * 2 FILR BFS-U3-31S4C, resolution: 1024 × 768
Event Camera * 2 DAVIS346, resolution: 346 × 240,2 built-in imu
IMU (body_imu) STIM300
Ground Truth Leica BLK 360
  • This visual SLAM benchmark is based on the FusionPortable dataset, which covers a variety of environments in The Hong Kong University of Science and Technology campus by utilizing multiple platforms for data collection. It provides a large range of difficult scenarios for Simultaneous Localization and Mapping (SLAM).
  • All these sequences are characterized by structure-less areas and varying illumination conditions to best represent the real-world scenarios and pose great challenges to the SLAM algorithms which were verified in confined lab environments.

Latest News

  • [08.07]: calibration dataset released.
  • [08.01]: challenge data sequences released.



  • The submission will be ranked based on the completeness and frequency of the trajectory as well as on the position accuracy (ATE). The score is based on the ATE of individual points on the trajectory. Points with the error smaller than a distance threshold are added to your final score. This evaluation scheme is inspired by HILTI Challenge.

  • Output trajectories should be transformed into the body_imu frame, We will align the trajectory with the dense ground truth points using a rigid transformation. Then the Absolute Trajectory Error (ATE) of a set of discrete point is computed. At each ground truth point, extra penalty points are added to the final score depending on the amount of error at this point:

    Error Score (points)
    <= 5cm 10
    <= 30cm 6
    <= 50cm 3
    <= 100cm 1
    > 100cm 0
  • Each sequence will be evaluated over a maximum of 200 points, which leads to a maximum of $N\times 200$ points being evaluated among $N$ sequences.

Given an example:


Sign up for an account and submit your results in the evaluation system, the live leaderboard will update your ranking.


Submission Guidelines

  • Trajectory Results

    • Please upload a .zip file consisting of a list of text files named as the sequence name shown as follows:
    • These text files should put in a folder of "traj", and then compress as a *.zip file, such as ""
    • The text files should have the following contents(TUM format):
    1644928761.036623716 0.0 0.0 0.0 0.0 0.0 0.0 1.0

    Each row contains timestamp_s tx ty tz qx qy qz qw. The timestamps are in the unit of second which are used to establish temporal correspondences with the groundtruth. The first pose should be no later than the starting time specified above, and only poses after the starting time will be used for evaluation.

    • The poses should specify the poses of the body IMU in the world frame. If the estimated poses are in the frame of other sensors, one should transform these poses into the world frame of the body IMU as T_bodyw_body = T_body_sensor * T_sensorw_sensor * T_body_sensor^(-1);.
  • Do not publicly release your trajectory estimates, as we might re-use some of the datasets for future competitions.


We provide the compressed rosbag data, remember to execute the following command to decompress them.

# example: 20220216_garden_day_ref_compressed
rosbag decompress 20220216_garden_day.bag

Calibration files

Yaml Files Describtion Link
body_imu extrinsics and intrinsics of the STIM300 body_imu.yaml
event_cam00 extrinsics and intrinsics of the left event camera event_cam00.yaml
event_cam00_imu extrinsics and intrinsics of the left event camera imu event_cam00_imu.yaml
event_cam01 extrinsics and intrinsics of the right event camera event_cam01.yaml
event_cam01_imu extrinsics and intrinsics of the right event camera imu event_cam01_imu.yaml
frame_cam00 extrinsics and intrinsics of the left flir camera frame_cam00.yaml
frame_cam01 extrinsics and intrinsics of the right flir camera frame_cam01.yaml

Test Sequences

Platform Sequence Compressed Bag
Handheld Garden 20220216_garden_day 20.4GB

Calibration Sequences

Platform Sequence Compressed Bag
Handheld Motion Capture Room 20220209_StaticTarget_SmallCheckerBoard_9X12_30mm 6.7GB
Handheld Motion Capture Room 20220215_DynamicTarget_BigCheckerBoard_7X10_68mm 2.3GB
Handheld Motion Capture Room 20220209_Static_IMUs_3h20mins 894MB

Challenge Sequences

Platform Sequence Compressed Bag
Handheld Canteen 20220216_canteen_night 15.9GB
20220216_canteen_day 17.0GB
Garden 20220215_garden_night 8.5GB
20220216_garden_day 20.4GB
Canteen 20220216_corridor_day 27.4GB
Canteen 20220216_escalator_day 31.7GB
Buliding 20220225_building_day 37.5GB
Motion Capture Room 20220216_MCR_slow 3.5GB
20220216_MCR_normal 2.2GB
20220216_MCR_fast 1.7GB
Quadruped Robot MCR_slow_00 20220219_MCR_slow_00 9.7GB
20220219_MCR_slow_01 8.4GB
20220219_MCR_normal_00 7.1GB
20220219_MCR_normal_01 6.5GB
20220219_MCR_fast_00 7.6GB
20220219_MCR_fast_01 8.5GB
Apollo Vehicle Campus Road 20220226_campus_road 72.3GB


  • How are the frames defined on the sensor setup?

The picture below is a schematic illustration of the reference frames (red = x, green = y, blue = z):


  • How are the results scored?

The results submitted by each team will be scored based on the completeness and ATE accuracy of the trajectories. All the results will be displayed in the live leaderboard. Each trajectory will be scored based on the standard evaluation points, the accumulation of the scores of all these evaluation points is normalized to 200 points to get the final score of the sequence. Each evaluation point can get 0-10 points according to its accuracy.

  • Will the organizer provide the calibration datasets of the IMU and camera?

Of course, we will provide the calibration data of IMU and cameras.

  • Is the ground truth available?

We will provide some sample datasets along with their ground truth collected with the same sensor kit, but the ground truth for the challenge sequences is not available. However, you can submit your own results in the website evaluation system for evaluation.


A team can only register one account. Quota can only be obtained by joining the WeChat group.

In order to prevent the problem of a team registering multiple accounts, this competition requires all members of the participating team to join the WeChat group. If the QR code is invalid, we will update it in time. And the old account cannot be used, you need to re-register a new account.



[1] Jianhao Jiao, Hexiang Wei, Tianshuai Hu, Xiangcheng Hu, etc., Lujia Wang, Ming Liu, FusionPortable: A Multi-Sensor Campus-Scene Dataset for Evaluation of Localization and Mapping Accuracy on Diverse Platforms, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, Kyoto, Japan.)

[2] HILTI Challenge.

Open Source Agenda is not affiliated with "PRCV VSLAM Challenge 2022" Project. README Source: JokerJohn/PRCV-VSLAM-Challenge-2022

Open Source Agenda Badge

Open Source Agenda Rating