Marc Leny

Statistical motion vector analysis for object tracking in compressed video streams

Compressed video is the digital raw material provided by video-surveillance systems and used for archiving and indexing purposes. Multimedia standards have therefore a direct impact on such systems. If MPEG-2 used to be the coding standard, MPEG-4 (part 2) has now replaced it in most installations, and MPEG-4 AVC/H.264 solutions are now being released. Finely analysing the complex and rich MPEG-4 streams is a challenging issue addressed in that paper. The system we designed is based on five modules: low-resolution decoder, motion estimation generator, object motion filtering, low-resolution object segmentation, and cooperative decision. Our contributions refer to as the statistical analysis of the spatial distribution of the motion vectors, the computation of DCT-based confidence maps, the automatic motion activity detection in the compressed file and a rough indexation by dedicated descriptors. The robustness and accuracy of the system are evaluated on a large corpus (hundreds of hours of in-and outdoor videos with pedestrians and vehicles). The objective benchmarking of the performances is achieved with respect to five metrics allowing to estimate the error part due to each module and for different implementations. This evaluation establishes that our system analyses up to 200 frames (720x288) per second (2.66 GHz CPU).

Enhancing the audience experience during sport events: real-time processing of multiple stereoscopic cameras

From video acquisition to 3D rendering, most of the hardware and software modules required for stereoscopy are currently available in academic or industrial R&D laboratories. Some are even features of open-source libraries. However, designing a stereoscopic architecture able to perform this acquisition followed by geometrical calibration and colour correction, disparity maps computation, multi-view coding and transmission for several cameras into one dedicated server remains a challenge. This was achieved for the SkyMedia project which aimed at providing an enhanced experience for the audience, organising staff and performers of an event. Compromises were required, from lower-resolution depth estimation to limited MultiView Coding predictions, but in the end the project system was fit to the task and delivered contents to the various people evolving around the 2012 Turin Marathon.

Field test of SkyMedia HD/3D content augmentation system for immersive media experiences

This paper presents the field test results of the novel SkyMedia 3D/HD system in a marathon race setup. The augmentation system is tailored for immersive media experiences such as public live events in which people can interact together in order to improve users experience. The paper reports the first public demonstration of the HD/3D content augmentation system conducted in the Turin Marathon race setup. A large set of SkyMedia Multimedia Service Platform (MSP) building blocks has been tested and validated in a real environment.