ACRV Robotic Vision Challenge

Datasets for the ACRV Robotic Vision Challenge (http://www.roboticvisionchallenge.org ). Our probabilistic object detection challenge requires participants to detect objects in video data from high-fidelity simulation. As a novelty, our evaluation metric rewards accurate estimates of spatial and semantic uncertainty using probabilistic bounding boxes.

You can participate in the challenge here: https://competitions.codalab.org/competitions/21727