Toronto Robotics and Artificial Intelligence Laboratory’s Post

Announcing our second #ICRA2024 paper (2/3): Numerous multi-object tracking methods blindly trust incoming object detections with no sense of their associated uncertainty. This lack of uncertainty awareness poses a problem in safety-critical tasks such as autonomous driving. To that end, we introduce UncertaintyTrack, a collection of extensions that can be applied to existing trackers to account for localization uncertainty estimates from probabilistic object detectors. Take a look at our #ICRA2024 paper: "UncertaintyTrack: Exploiting Detection and Localization Uncertainty in Multi-Object Tracking" by Chang Won (John) Lee and Steven Lake Waslander from the University of Toronto. Paper: https://lnkd.in/gzEW_8ZJ Video: https://lnkd.in/gG7aaktj #ICRA24 #uncertainty #robotics #autonomousdriving #objectdetection #tracking

  • No alternative text description for this image
  • No alternative text description for this image

To view or add a comment, sign in

Explore topics