TMC is an independent, primarily volunteer organization that relies on ad revenue to cover its operating costs. Please consider whitelisting TMC on your ad blocker and becoming a Supporting Member. For more info: Support TMC

Need help: lidar vs. stereo cameras on the KITTI benchmark for odometry/SLAM

Discussion in 'Autopilot & Autonomous/FSD' started by strangecosmos, Jul 30, 2018.

  1. strangecosmos

    strangecosmos Non-Member

    May 10, 2017
    The Prime Material Plane
    I need help interpreting some data. Here is the leaderboard for the performance of different odometry/SLAM approaches, benchmarked against the KITTI Vision dataset:


    The top approach, V-LOAM, uses lidar. The fourth best approach, SOFT2, uses stereo camera images, and no lidar data. The rotation error is the same for SOFT2 and V-LOAM, and the translation error for SOFT2 is 0.05% higher.

    On the face of it, this would seem to imply that the current best stereo camera-based odometry/SLAM method is pretty close in accuracy to the current beat lidar-based method. Am I wrong? Is is a 0.05% difference actually huge? Am I otherwise misunderstanding or misinterpreting what’s going on here? Any help anyone can provide would be much appreciated. Thanks.

Share This Page

  • About Us

    Formed in 2006, Tesla Motors Club (TMC) was the first independent online Tesla community. Today it remains the largest and most dynamic community of Tesla enthusiasts. Learn more.
  • Do you value your experience at TMC? Consider becoming a Supporting Member of Tesla Motors Club. As a thank you for your contribution, you'll get nearly no ads in the Community and Groups sections. Additional perks are available depending on the level of contribution. Please visit the Account Upgrades page for more details.