Institut für Kognitionswissenschaft

Institute of Cognitive Science


Navigation und Suche der Universität Osnabrück


Hauptinhalt

Topinformationen

Demos / Downloads

In the area you can find selected downloads and demos.
To get more information according to downloads and video demonstrations, please visit the named project websites.

Downloads

  Description Download
Osnabrück — Synthetic Scalable Cube Dataset Osnabrück — Synthetic Scalable Cube Dataset
Voxel Based Dataset for Systematic 3D reconstruction by artificial neural networks (ANNs).
A synthetic scalable cube dataset for training, testing and validating ANNs for learning 3D reconstruction without any predefined object categories. This data set comprises 830000 different cubes captured from 12 different viewpoints.
Aim: Clarify whether and how ANNs might learn the underlying mathematical principle of multiple view geometry without object categories.
Project Website
Project Website SFN²

3x3x3 Cubes (100 000)
4x4x4 Cubes (300 000)
8x8x8 Cubes (430 000)
Osnabrück - Gaze Tracking Data Set Osnabrück - Gaze Tracking Data Set
Gaze data on video stimuli for computer vision and visual analytics.
Converted 318 video sequences from several different gaze tracking data sets with polygon based object annotation all stored in the same format; allowing to visualize these data with standard multimedia players (e.g. VLC player).
Aims:
  • visual analytics of gaze data,
  • learning gaze behavior on video with artificial neural networks,
  • gaze empowered segmentation and object detection.
 
Project Website

Real World Visual Processing
Açik et al. [A] dataset
Sundberg et al. [B] dataset
Coutrot & Guyader [C] dataset
Kurzhals et al. [K] dataset
Riche et al. [R] dataset
iSeg iSeg
iSeg - the interactive annotation and segmentation tool.
(Version: 0.0.5)
(developed by J. Schöning and P. Faion 2016)

*If iSeg.exe does not start correctly, install Visual C++ Redistributable 2013 (vcredist_x64.exe)
Project Website

Windows x64*
Linux x64
MacOS x64
Source
DeGuM DeGuM
Interactive tool for color based segmentation.(JAVA plugin necessary)
(developed in a student software project at Stuttgart University by M. Bischof, J. Kaiser, S. Müller in 2010)
DeGuM Web Application
DeGuM Download

Demos

  Description Watch now!
Visual Analytics of Gaze Data with Standard Multimedia Players Visual Analytics of Gaze Data with Standard Multimedia Players. JEMR'17
Ventral Stream-Inspired Process for Deriving 3D Models from Video Sequences Ventral Stream-Inspired Process for Deriving 3D Models from Video Sequences. ICIAP'17
Providing Video Annotations in Multimedia Containers for Visualization and Research Providing Video Annotations in Multimedia Containers for Visualization and Research. WACV'17
Exploratory Multimodal Data Analysis with Standard Multimedia Player Exploratory Multimodal Data Analysis with Standard Multimedia Player --- Multimedia Containers: a Feasible Solution to make Multimodal Research Data Accessible to the Broad Audience. VISAPP'17
Bio-Inspired Architecture for Deriving 3D Models from Video Sequences Bio-Inspired Architecture for Deriving 3D Models from Video Sequences. 3DMA@ACCV'16
Eye Tracking Data in Multimedia Containers for Instantaneous Visualizations Eye Tracking Data in Multimedia Containers for Instantaneous Visualizations. ETVIS'16
Interactive feature growing Interactive feature growing for accurate object detection in megapixel images. EPIC@ECCV'16
iSeg Demo of iSeg - the interactive annotation and segmentation tool. iSeg@ICPRAM'16
iSeg@K-CAP'15
FOREST Presentation of the ground truth annotation tool (developed in FOREST project). FOREST (en)
FOREST (de)
FOREST EuroVis
Inter-Active Learning of Ad-Hoc Classifiers for Video Visual Analytics Inter-Active Learning of Ad-Hoc Classifiers for Video Visual Analytics. VAST'12