D
Daniel Kondermann
Researcher at Heidelberg University
Publications - 48
Citations - 1758
Daniel Kondermann is an academic researcher from Heidelberg University. The author has contributed to research in topics: Optical flow & Ground truth. The author has an hindex of 18, co-authored 47 publications receiving 1428 citations. Previous affiliations of Daniel Kondermann include Saarland University & Interdisciplinary Center for Scientific Computing.
Papers
More filters
Book ChapterDOI
A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields
TL;DR: In computer vision communities such as stereo, optical flow, or visual tracking, commonly accepted and widely used benchmarks have enabled objective comparison and boosted scientific progress.
Journal ArticleDOI
Horn-schunck optical flow with a multi-scale strategy
TL;DR: This work describes an implementation of the original Horn and Schunck method and introduces a multi-scale strategy in order to deal with larger displacements and creates a pyramidal structure of downsampled images and changes the optical flow constraint equation with a nonlinear formulation.
Proceedings ArticleDOI
The HCI Benchmark Suite: Stereo and Flow Ground Truth with Uncertainties for Urban Autonomous Driving
Daniel Kondermann,Rahul Nair,Katrin Honauer,Karsten Krispin,Jonas Andrulis,Alexander Brock,Burkhard Gussefeld,Mohsen Rahimimoghaddam,Sabine Hofmann,Claus Brenner,Bernd Jähne +10 more
TL;DR: A new stereo and optical flow dataset is presented to complement existing benchmarks, specifically designed to be representative for urban autonomous driving, including realistic, systematically varied radiometric and geometric challenges which were previously unavailable.
Proceedings ArticleDOI
Ensemble Learning for Confidence Measures in Stereo Vision
TL;DR: This work applies the random decision forest framework to a large set of diverse stereo confidence measures and obtains consistently improved area under curve values of sparsification measures in comparison to best performing single stereoconfidence measures where numbers of stereo errors are large.
Proceedings ArticleDOI
Blood Vessel Classification into Arteries and Veins in Retinal Images
TL;DR: In this paper, the authors compared two feature extraction methods and two classification methods based on support vector machines and neural networks to detect diabetic retinopathy (DR) and achieved 95.32% correctly classified vessel pixels.