SGR09 - Processament de Video Multicamera
Type | Start | End |
---|---|---|
National | Oct 2009 | Dec 2013 |
Responsible | URL |
---|---|
Josep R. Casas | Image Processing Group |
Reference
Multicamera Video Processing.
Ref. SGR2009-01534, Generalitat de Catalunya, Departament d'Innovació, Universitats i Empresa, Direcció General de Recerca.
Description
The GPI is a Consolidated Research Group of the Catalan Government continuously since 1999 (Calls: 1999-2001, 2002-2005, 2005-2008, 2009-2013). SGR09 - Multicamera Video Processing is the present GPI project in the last call.
This is a baseline project integrating research lines of the GPI group both in Video Analysis (mono- and multi-sensor) and Video Representation (coding and video indexing). Multi-camera strategies pose significant challenges for the visual analysis of the scene, with increased robustness to occlusions and conveying additional depth information. Volumetric analysis are possible for object recognition and precise tracking and recognition of human body movements in the 3D domain. For the compression of multiple correlated video sequences from the different views, frame prediction is possible not only along the time but also accross views of the same scene.
Publications
Region-based Particle Filter Leveraged with a Hierarchical Co-clustering . Signal Theory and Communications Department. 2016 . | .
Stochastic optimization and interactive machine learning for human motion analysis . Signal Theory and Communications. 2014 . (17.16 MB) | .
Hierarchical information representation and efficient classification of gene expression microarray data . TSC. 2014 ;PhD Thesis:150. (2.76 MB) | .
Monocular Depth Estimation in Images and Sequences using Occlusion Cues . Signal Theory and Communications. 2014 ;PhD:250. (107.61 MB) | .
Image Segmentation Evaluation and Its Application to Object Detection . 2014 . (48.44 MB) | .
Human body analysis using depth data . 2013 . (10.67 MB) | .
Can our TV robustly understand human gestures? Real-Time Gesture Localization in Range Data. In: Conference on Visual Media Production. Conference on Visual Media Production. London, UK: ACM; 2012. (5.62 MB) | .
Articulated Models for Human Motion Analysis . 2012 . (2.47 MB) | .