This document gives an overview of the most advanced research topics presently under investigatio... more This document gives an overview of the most advanced research topics presently under investigation at Advanced System Technology Group of STMicroelectronics, a corporate research organization focused on R&D at system level. The paper cover unprecedented technologies/ findings about tailored streaming, the necessary advanced codec capable to serve these needs, as well a seamless connectivity for user terminals and others technologies connected to multimedia information processing and distribution. Most of those researches like content adaptation/personalization, semantic description/ content retrieval, multiview/3DTV codecs, peer-to-peer multimedia delivery systems and augmented reality are fully on line with the priorities outlined by NEM and are actively investigated, both in house and within the frameworks of currently existing sponsored projects. 1 INTRODUCTION Microelectronics technologies, with a continuous strive for increased performances coupled with low consumption, are pav...
2009 Digest of Technical Papers International Conference on Consumer Electronics, 2009
I. INTRODUCTION Modern mobile and consumer embedded devices are increasingly including 3D and Vec... more I. INTRODUCTION Modern mobile and consumer embedded devices are increasingly including 3D and Vector graphics capabilities. These devices are flexible enough that it becomes convenient and important to use them for other purposes than graphics rendering, thus increasing the ...
2013 IEEE Third International Conference on Consumer Electronics ¿ Berlin (ICCE-Berlin), 2013
ABSTRACT Embedded application processors have evolved dramatically over the past years, offering ... more ABSTRACT Embedded application processors have evolved dramatically over the past years, offering ever increasing computation power and hardware support for critical features such as 3D Graphics with programmable OpenGL ES-capable GPUs [1]. Games, User Interfaces or Augmented Reality applications can now render complex and interactive 3D assets in real-time on portable or embedded devices. Such applications often use their own proprietary format for encoding and distributing 3D assets, in response to very particular use-cases or IP protection issues for example. However, in many cases, an open, compact, streaming-friendly format would be preferred. In this paper, we concentrate our attention to the 3D Graphics Compression (3DGC) standard [2] developed by MPEG as part of MPEG-4, which intends to provide an open solution for encoding, compressing and streaming animated 3D assets. We used 3DGC as a basis for our developments and extended it to support modern shader-based GPU techniques on embedded platforms for the real-time rendering of complex 3D models, with pre-computed or user-controlled animation.
ABSTRACT Singular Value Decomposition is widely used in many different engineering applications l... more ABSTRACT Singular Value Decomposition is widely used in many different engineering applications like Image Processing, Image Compression, Principle Component Analysis etc. It is also very useful in statistical analysis for Least Squares Approximations, and Data Clustering for reducing data dimensionality. Its power consists in its capability to serve as a single method for analysing several features in a matrix. Its computation involves a sequence of vector kind operations which makes it computationally intensive. This paper addresses optimisations of computation of Singular Value Decomposition as implemented in LAPACK library by parallelizing on the Graphics Processing Unit architecture using OpenCL. Its programmable architecture suits well because of its flexibility and native support for vector operations and OpenCL is a key enabler for making the implementation platform independent and portable.
2012 IEEE Second International Conference on Consumer Electronics - Berlin (ICCE-Berlin), 2012
ABSTRACT Visual search for mobile devices relies on transmitting wirelessly image descriptors to ... more ABSTRACT Visual search for mobile devices relies on transmitting wirelessly image descriptors to a remote server. Hence, descriptors needs to be compressed to reduce bandwidth occupancy and network latency. In this paper, we investigate on the compression ratio versus accuracy of two low complexity coding schemes, based on Arithmetic and Type coding, applied to SIFT local descriptors
2012 IEEE Second International Conference on Consumer Electronics - Berlin (ICCE-Berlin), 2012
ABSTRACT Many-core architectures are becoming increasingly popular due to advances in open progra... more ABSTRACT Many-core architectures are becoming increasingly popular due to advances in open programming environments. Typical architectures are Graphics Processing Units (GPUs) and Homogenous Computing Fabrics, offering high computing parallelism in order to decrease execution time of computationally intensive algorithms, for example in Computer Vision. In this paper, a low complexity interest point detector has been written in OpenCL language and executed on different desktop and embedded computing platforms. The algorithm performs interest point detection in an image, around which there is enough distinctive information to enable further description. The algorithm has been optimized on the targeted platforms and performance and accuracy comparison has been performed
2013 IEEE Third International Conference on Consumer Electronics ¿ Berlin (ICCE-Berlin), 2013
ABSTRACT Visual search has seen many improvements over the years, but its application on video co... more ABSTRACT Visual search has seen many improvements over the years, but its application on video content is still an open research problem and it is often limited to still images. Based on the tools devised by the standardization group MPEG CDVS, we developed a processing flow that processes at nearly real-time a video acquired with a low cost imager and performs content search and retrieval of the top match from a local database. To allow efficient interest point detection, we used a GPU accelerated SIFT library. To process the video frames efficiently, we developed a new dataflow processing which allows switching between object searching, retrieving and tracking in order to keep at minimum the number of queries sent to the database. A search into a local database is performed only when no object has been recognized, and once a good match has been found, the algorithm switches to tracking mode.
With few exceptions, complex applications do not ex-hibit a constantly predominant type of parall... more With few exceptions, complex applications do not ex-hibit a constantly predominant type of parallelism through-out the set of programs on which they are based. This fact limits the efficiency of highly parallel architectures when executing such an application. This is the reason for the ...
The full search motion estimation algorithm for video coding is a procedure of high computational... more The full search motion estimation algorithm for video coding is a procedure of high computational cost. For this reason, in real-time low-power applications, low-cost motion estimation algorithms are viable solutions. A novel reduced complexity motion estimation algorithm is presented. It conjugates the reduction of computational load with good encoding efficiency. It exploits the past history of the motion field to predict the current motion field. A successive refinement phase gives the final motion field. This approach leads to a sensible reduction in the number of motion vector that have to be tested. The complexity is lower than any other algorithm algorithms known to the authors, in the literature, it is constant as there is no recursivity in the algorithm and independent of any search window area size. Experimental evaluations have shown the robustness of the algorithm when applied on a wide set of video sequences--a good performance compared to other reduced complexity algorithms and negligible loss of efficiency versus the full search algorithm.
This document gives an overview of the most advanced research topics presently under investigatio... more This document gives an overview of the most advanced research topics presently under investigation at Advanced System Technology Group of STMicroelectronics, a corporate research organization focused on R&D at system level. The paper cover unprecedented technologies/ findings about tailored streaming, the necessary advanced codec capable to serve these needs, as well a seamless connectivity for user terminals and others technologies connected to multimedia information processing and distribution. Most of those researches like content adaptation/personalization, semantic description/ content retrieval, multiview/3DTV codecs, peer-to-peer multimedia delivery systems and augmented reality are fully on line with the priorities outlined by NEM and are actively investigated, both in house and within the frameworks of currently existing sponsored projects. 1 INTRODUCTION Microelectronics technologies, with a continuous strive for increased performances coupled with low consumption, are pav...
2009 Digest of Technical Papers International Conference on Consumer Electronics, 2009
I. INTRODUCTION Modern mobile and consumer embedded devices are increasingly including 3D and Vec... more I. INTRODUCTION Modern mobile and consumer embedded devices are increasingly including 3D and Vector graphics capabilities. These devices are flexible enough that it becomes convenient and important to use them for other purposes than graphics rendering, thus increasing the ...
2013 IEEE Third International Conference on Consumer Electronics ¿ Berlin (ICCE-Berlin), 2013
ABSTRACT Embedded application processors have evolved dramatically over the past years, offering ... more ABSTRACT Embedded application processors have evolved dramatically over the past years, offering ever increasing computation power and hardware support for critical features such as 3D Graphics with programmable OpenGL ES-capable GPUs [1]. Games, User Interfaces or Augmented Reality applications can now render complex and interactive 3D assets in real-time on portable or embedded devices. Such applications often use their own proprietary format for encoding and distributing 3D assets, in response to very particular use-cases or IP protection issues for example. However, in many cases, an open, compact, streaming-friendly format would be preferred. In this paper, we concentrate our attention to the 3D Graphics Compression (3DGC) standard [2] developed by MPEG as part of MPEG-4, which intends to provide an open solution for encoding, compressing and streaming animated 3D assets. We used 3DGC as a basis for our developments and extended it to support modern shader-based GPU techniques on embedded platforms for the real-time rendering of complex 3D models, with pre-computed or user-controlled animation.
ABSTRACT Singular Value Decomposition is widely used in many different engineering applications l... more ABSTRACT Singular Value Decomposition is widely used in many different engineering applications like Image Processing, Image Compression, Principle Component Analysis etc. It is also very useful in statistical analysis for Least Squares Approximations, and Data Clustering for reducing data dimensionality. Its power consists in its capability to serve as a single method for analysing several features in a matrix. Its computation involves a sequence of vector kind operations which makes it computationally intensive. This paper addresses optimisations of computation of Singular Value Decomposition as implemented in LAPACK library by parallelizing on the Graphics Processing Unit architecture using OpenCL. Its programmable architecture suits well because of its flexibility and native support for vector operations and OpenCL is a key enabler for making the implementation platform independent and portable.
2012 IEEE Second International Conference on Consumer Electronics - Berlin (ICCE-Berlin), 2012
ABSTRACT Visual search for mobile devices relies on transmitting wirelessly image descriptors to ... more ABSTRACT Visual search for mobile devices relies on transmitting wirelessly image descriptors to a remote server. Hence, descriptors needs to be compressed to reduce bandwidth occupancy and network latency. In this paper, we investigate on the compression ratio versus accuracy of two low complexity coding schemes, based on Arithmetic and Type coding, applied to SIFT local descriptors
2012 IEEE Second International Conference on Consumer Electronics - Berlin (ICCE-Berlin), 2012
ABSTRACT Many-core architectures are becoming increasingly popular due to advances in open progra... more ABSTRACT Many-core architectures are becoming increasingly popular due to advances in open programming environments. Typical architectures are Graphics Processing Units (GPUs) and Homogenous Computing Fabrics, offering high computing parallelism in order to decrease execution time of computationally intensive algorithms, for example in Computer Vision. In this paper, a low complexity interest point detector has been written in OpenCL language and executed on different desktop and embedded computing platforms. The algorithm performs interest point detection in an image, around which there is enough distinctive information to enable further description. The algorithm has been optimized on the targeted platforms and performance and accuracy comparison has been performed
2013 IEEE Third International Conference on Consumer Electronics ¿ Berlin (ICCE-Berlin), 2013
ABSTRACT Visual search has seen many improvements over the years, but its application on video co... more ABSTRACT Visual search has seen many improvements over the years, but its application on video content is still an open research problem and it is often limited to still images. Based on the tools devised by the standardization group MPEG CDVS, we developed a processing flow that processes at nearly real-time a video acquired with a low cost imager and performs content search and retrieval of the top match from a local database. To allow efficient interest point detection, we used a GPU accelerated SIFT library. To process the video frames efficiently, we developed a new dataflow processing which allows switching between object searching, retrieving and tracking in order to keep at minimum the number of queries sent to the database. A search into a local database is performed only when no object has been recognized, and once a good match has been found, the algorithm switches to tracking mode.
With few exceptions, complex applications do not ex-hibit a constantly predominant type of parall... more With few exceptions, complex applications do not ex-hibit a constantly predominant type of parallelism through-out the set of programs on which they are based. This fact limits the efficiency of highly parallel architectures when executing such an application. This is the reason for the ...
The full search motion estimation algorithm for video coding is a procedure of high computational... more The full search motion estimation algorithm for video coding is a procedure of high computational cost. For this reason, in real-time low-power applications, low-cost motion estimation algorithms are viable solutions. A novel reduced complexity motion estimation algorithm is presented. It conjugates the reduction of computational load with good encoding efficiency. It exploits the past history of the motion field to predict the current motion field. A successive refinement phase gives the final motion field. This approach leads to a sensible reduction in the number of motion vector that have to be tested. The complexity is lower than any other algorithm algorithms known to the authors, in the literature, it is constant as there is no recursivity in the algorithm and independent of any search window area size. Experimental evaluations have shown the robustness of the algorithm when applied on a wide set of video sequences--a good performance compared to other reduced complexity algorithms and negligible loss of efficiency versus the full search algorithm.
Uploads