PBint (Protection, search and interoperability of multimedia content: New techniques and applications) is a research project funded by the Spanish National Science Foundation for 2012 - 2014. The contribution of GTAV to PBint consists in the development of face detection and recognition algorithms within the framework of a platform designed for the management and secure distribution of multimedia content. A watch list application is being implemented which will add an added value to the search of persons in data bases analyzed by the platform.
PBint is a joint project coordinated by the Distributed Multimedia Applications Group of the Department of Computers Architecture of UPC-BarcelonaTECH.
Image Processing in IC Reverse Engineering:
Reverse Engineering (RE) in the semiconductor industry deals with the process of obtaining the schematic diagram of an integrated circuit from its physical representation. The application of image processing in this field ease and speed up repetitive tasks that require high human efforts and hardware resources.
The GTAV collaboration with the IMB-CNM (Instituto de Microelectrónica de Barcelona del Centro Nacional de Microelectrónica-CSIC) is aided to develop a set of professional tools based on image processing algorithms to automate the reverse engineering methodology used by the ICAS (Integrated Circuits and Systems) researh group from the IMB-CNM.
Automatic Summarization of Soccer Highlights Using Audio-Visual Descriptors:
Automatic summarization generation of sports video content has been object of great interest for many years. Although semantic descriptions techniques have been proposed, many of the approaches still rely on low-level video descriptors that render quite limited results due to the complexity of the problem and to the low capability of the descriptors to represent semantic content.
BUSCAMEDIA is a research project founded by the Spanish National Science Foundation made in cooperation with TVC, the Catalan TV broadcaster whose objetive is to find an automatic system that may provide a summary of highlights of sports sequences. The approach is based on finding low-level audio-visual descriptors that are lately adequately combined to define highlights of interest in the soccer video. Once the events of interest are highlighted, a summarization of a complete soccer match is generated based on ground truth soccer summarization experiences.