DYNAMIC MINVIP
Dynamic Minimal prior knowledge for model based Computer Vision and Scene Analysis
| Coordinatore | GOTTFRIED WILHELM LEIBNIZ UNIVERSITAET HANNOVER
Spiacenti, non ci sono informazioni su questo coordinatore. Contattare Fabio per maggiori infomrazioni, grazie. |
| Nazionalità Coordinatore | Germany [DE] |
| Totale costo | 1˙430˙000 € |
| EC contributo | 1˙430˙000 € |
| Programma | FP7-IDEAS-ERC
Specific programme: "Ideas" implementing the Seventh Framework Programme of the European Community for research, technological development and demonstration activities (2007 to 2013) |
| Code Call | ERC-2011-StG_20101014 |
| Funding Scheme | ERC-SG |
| Anno di inizio | 2011 |
| Periodo (anno-mese-giorno) | 2011-10-01 - 2016-09-30 |
Partecipanti
| # | ||||
|---|---|---|---|---|
| 1 |
GOTTFRIED WILHELM LEIBNIZ UNIVERSITAET HANNOVER
Organization address
address: Welfengarten 1 contact info |
DE (HANNOVER) | hostInstitution | 1˙430˙000.00 |
| 2 |
GOTTFRIED WILHELM LEIBNIZ UNIVERSITAET HANNOVER
Organization address
address: Welfengarten 1 contact info |
DE (HANNOVER) | hostInstitution | 1˙430˙000.00 |
Mappa
Word cloud
Esplora la "nuvola delle parole (Word Cloud) per avere un'idea di massima del progetto.
Obiettivo del progetto (Objective)
'Efficient solutions for open problems in computer vision are often achieved with the help of suitable prior knowledge, e.g. stemming from labeled databases, physical simulation or geometric invariances. Yet it has been largely neglected to analyse the minimal amount of prior knowledge, needed to satisfactory solve computer vision tasks. Even more important, there is need to steer the amount of priors in a dynamic fashion. Especially for scene analysis, database knowledge can become so large and complex, that it cannot be integrated efficiently for optimization. On the other hand, there exist geometric priors which are efficient and compact, but they have to be integrated and exploited explicitly in vision systems. As a consequence there is need to develop methods to conclude from (statistical) database knowledge to geometric prior knowledge and therefore to achieve compressed priors which contain the relevant information from a given database. Besides the efficient regularization during scene analysis, specific tasks require to treat the amount of priors dynamically, e.g. to maintain individualities of patterns or to avoid a bias from a given database. Our beyond state-of-the art research will focus on answering the following questions:
1) How to limit statistical prior knowledge to geometric priors for solving markerless Motion Capture dynamically with sufficient accuracy ? 2) How to stabilize tracking without introducing a database bias, or to enforce individuality ? 3) How to extract (geometric) motion characteristics for individual motion transfer and interpretation ?
Advancing minimal dynamic prior knowledge means to seek for the essence and granularity of priors. This will have a profound impact well beyond computer vision (e.g. for cognitive sciences or robotics). We strongly believe that we have the necessary competence to pursue this project. Preliminary results have been well received by the community'