[robotics-worldwide] [software] Trajectory Evaluation Toolbox for Visual(-inertial) Odometry

Davide Scaramuzza scaramuzza.davide at gmail.com
Tue Nov 6 01:50:17 PST 2018

Dear colleagues

With the explosion of visual (inertial) odometry algorithms in the last 
years, it is crucial to adopt common metrics when benchmarking different 
For this reason, we release our trajectory evaluation toolbox for 
visual(-inertial) odometry: 
which accompanies our tutorial paper on visual (-inertial) odometry 
evaluation at IROS 2018:

   Z. Zhang, D. Scaramuzza
   A Tutorial on Quantitative Trajectory Evaluation for 
Visual(-Inertial) Odometry
   IEEE/RSJ International Conference on Intelligent Robots and Systems 
(IROS), 2018.

Our toolbox includes:
* Trajectory alignment methods for different sensing modalities 
(monocular, stereo and visual-inertial)
* Commonly used error metrics: Absolute Trajectory Error and Relative 
(Odometry) Error

The toolbox is designed for easy use. Given two text files specifying 
the estimate and the groundtruth, the toolbox automatically establish 
time association, perform trajectory alignment and calculate different 
error metrics with one line of command. It can also be used to compare 
different algorithms on multiple datasets easily, such as in our recent 
paper on VIO evaluation:
   J. Delmerico, D. Scaramuzza
   A Benchmark Comparison of Monocular Visual-Inertial Odometry 
Algorithms for Flying Robots
   IEEE International Conference on Robotics and Automation (ICRA), 2018.
To make the toolbox usable with different formats, we also provide 
several scripts to convert common formats (e.g., EuRoC, rosbag) to the 
one used in the toolbox.

Best regards,
Zichao Zhang, Davide Scaramuzza


Prof. Dr. Davide Scaramuzza
Director of the Robotics and Perception Group: https://urldefense.proofpoint.com/v2/url?u=http-3A__rpg.ifi.uzh.ch_people-5Fscaramuzza.html&d=DwIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=HJcXF3-GzGwQjXqePH-eLBPPX5uiTMs27WIQPwVxC48&s=jQrHmtuCdfZYoCG6mG11ya2TBu3EFWxvh-93_7SuxoY&e=
Inst. of Informatics, University of Zurich,
Inst. of Neuroinformatics, University of Zurich and ETH Zurich
Andreasstrasse 15, AND 2.10, Zurich, Switzerland
Office: +41 44 635 24 09
YouTube Channel: https://urldefense.proofpoint.com/v2/url?u=https-3A__www.youtube.com_ailabRPG_videos&d=DwIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=HJcXF3-GzGwQjXqePH-eLBPPX5uiTMs27WIQPwVxC48&s=Tgse4tCxfPpX7vJcTtRXFpiR7rN8DkjXdjPeTsZp1ac&e=

More information about the robotics-worldwide mailing list