2019-04-12T14:04:39 n19664

ACRV Robotic Vision Challenge 1 Validation Data

Viewed: 1632

This is the validation data for the first Australian Centre for Robotic Vision (ACRV) Robotic Vision Challenge. It consists of 4 rendered video sequences in which participants must detect objects, with both spatial and semantic uncertainty. This validation data also contains pixel-level ground-truth annotations for the 30 classes of object to be detected.

For more details, see https://competitions.codalab.org/competitions/21727

The sequence contains synthetic data generated using Unreal Engine 4. For more details on its generation, see the workshop paper: https://arxiv.org/abs/1903.07840.

Data files consist of a single zip file, containing the frames and ground-truth data for 4 video sequences. The frames folder within the zip file contains a separate folder of .png images for each of the 4 video sequences. The ground_truth folder within the zip file contains a seperate folder containing mask .png images and a single labels.json file for each video sequence.

For information on how to read the ground-truth format and use it for evaluation, see https://github.com/jskinn/rvchallenge-evaluation.

Contact: contact@roboticvisionchallenge.org.

Geographical area of data collection



Probabilistic Object Detection: Definition and Evaluation by David Hall, Feras Dayoub, John Skinner, Haoyang Zhang, Dimity Miller, Peter Corke, Gustavo Carneiro, Anelia Angelova, Niko Sünderhauf. 10 April 2019 https://arxiv.org/abs/1811.10800v3
The Probabilistic Object Detection Challenge by John Skinner, David Hall, Haoyang Zhang, Feras Dayoub, Niko Sunderhauf. 19 March 2019. https://arxiv.org/abs/1903.07840

Research areas

Control Systems, Robotics and Automation
Computer Vision
Simulation and Modelling

Cite this collection

ARC Centre of Excellence in Robotic Vision (2019): ACRV Robotic Vision Challenge 1 Validation Data. Queensland University of Technology. (Dataset) https://doi.org/10.25912/5cae736bc8f51

Related information

Further challenge information http://www.roboticvisionchallenge.org/

Data file types

Data files consist of 18 zip files, each containing a video sequence made up of multiple .png images.


Creative Commons Attribution 4.0 (CC-BY)


© ARC Centre of Excellence in Robotic Vision, 2019.

Dates of data collection

From 20-02-2019 to 21-02-2019


Has association with
David Hall  (Researcher)
Dr Feras Dayoub  (Researcher)
Dr Haoyang Zhang  (Researcher)
John Skinner  (Researcher)
Niko Suenderhauf  (Researcher)


Name: Dr Niko Sünderhauf
Phone: +61 7 3138 9971


Date record created:
Date record modified:
Record status:
Published - Open Access