Unifying Panoptic Segmentation for Autonomous Driving

no code implementations • CVPR 2022 • Oliver Zendel, Matthias Schörghuber, Bernhard Rainer, Markus Murschitz, Csaba Beleznai

The dataset consists of more than 5000 unique driving scenes from all over the world with a focus on visually challenging scenes, such as diverse weather conditions, lighting situations, and camera characteristics.

Autonomous Driving Panoptic Segmentation +1

RailSem19: A Dataset for Semantic Rail Scene Understanding

no code implementations • CVPR 2019 • Oliver Zendel, Markus Murschitz, Marcel Zeilinger, Daniel Steininger, Sara Abbasi, Csaba Beleznai

In this paper, we intro-duce the first public dataset for semantic scene understand-ing for trains and trams: RailSem19.

Scene Understanding Semantic Segmentation +1

WildDash - Creating Hazard-Aware Benchmarks

no code implementations • ECCV 2018 • Oliver Zendel, Katrin Honauer, Markus Murschitz, Daniel Steininger, Gustavo Fernandez Dominguez

We have conducted a thorough risk analysis to identify situations and aspects that can reduce the output performance for these tasks.

Instance Segmentation Semantic Segmentation

Analyzing Computer Vision Data - The Good, the Bad and the Ugly

no code implementations • CVPR 2017 • Oliver Zendel, Katrin Honauer, Markus Murschitz, Martin Humenberger, Gustavo Fernandez Dominguez

However, major questions concerning quality and usefulness of test data for CV evaluation are still unanswered.

Autonomous Driving Stereo Matching +1

CV-HAZOP: Introducing Test Data Validation for Computer Vision

no code implementations • ICCV 2015 • Oliver Zendel, Markus Murschitz, Martin Humenberger, Wolfgang Herzner

This checklist can be used to evaluate existing test datasets by quantifying the amount of covered hazards.

Stereo Matching Stereo Matching Hand