Search

Real-time H.264/AVC high definition video encoding represents a challenging workload to most existing programmable processors. The new technologies of programmable processors such as Graphic Processor Unit (GPU) and multicore Digital signal Processor (DSP) offer a very promising solution to overcome these constraints. In this paper, an optimized implementation of H264/AVC video encoder on a single core among the six cores of TMS320C6472 DSP for Common Intermediate Format (CIF) (352x288) resolution is presented in order to move afterwards to a multicore implementation for standard and high definitions (SD, HD). Algorithmic optimization is applied to the intra prediction module to reduce the computational time. Furthermore, based on the DSP architectural features, various structural and hardware optimizations are adopted to minimize external memory access. The parallelism between CPU processing and data transfers is fully exploited using an Enhanced Direct Memory Access controller (EDMA). Experimental results show that the whole proposed optimizations, on a single core running at 700 MHz for CIF resolution, improve the encoding speed by up to 42.91%. They allow reaching the real-time encoding 25 f/s without inducing any Peak Signal to Noise Ratio (PSNR) degradation or bit-rate increase and make possible to achieve real time implementation for SD and HD resolutions when exploiting multicore features. [ABSTRACT FROM AUTHOR]

In this work, we are concerning by the improvement of optimized static heuristic in distributed and heterogeneous architecture. Thus, in order to take into account the load-balancing criterion, a need for a dynamic model is related to the use of heuristic based on list scheduling, The greedy list algorithms are well adapted, for they help the designer to rapidly obtain an efficient implementation and so to shorten development cycle of an application. This paper presents a dynamic model based on agent concept, coupled with an off line (static) heuristic. Our model has been simulated in programming parallel environment Xpvm. We show the integration of our model in the transformations flow, that implicates a heuristic to generating a real time distributed executive. This integration will be implemented in system level CAD software tool called SynDEx which, is a seamless flow based on graphs transformations. [ABSTRACT FROM AUTHOR]

Purpose: Augmented reality (AR) is an innovative approach that could assist percutaneous procedures; by directly seeing "through" a phantom, targeting a lesion might be more intuitive than using ultrasound (US). The objective of this study was to compare the performance of experienced interventional radiologists and operators untrained in soft tissue lesion puncture using AR guidance and standard US guidance., Material and Methods: Three trained interventional radiologists with 5-10 years of experience and three untrained operators performed punctures of five targets in an abdominal phantom, with US guidance and AR guidance. Correct targeting, accuracy (defined as the Euclidean distance between the tip and the center of the target), planning time, and puncture time were documented., Results: Accuracy was higher for the trained group than the untrained group using US guidance (1 mm versus 4 mm, p = 0.001), but not when using AR guidance (4 mm vs. 4 mm, p = 0.76). All operators combined, no significant difference was found concerning accuracy between US and AR guidance (2 mm vs. 4 mm, p = 0.09), but planning time and puncture time were significantly shorter using AR (respectively, 15.1 s vs. 74 s, p < 0.001; 16.1 s vs. 59 s; p < 0.001)., Conclusion: Untrained and trained operators obtained comparable accuracy in percutaneous punctures when using AR guidance whereas US performance was better in the experienced group. All operators together, accuracy was similar between US and AR guidance, but shorter planning time, puncture time were found for AR guidance., (© 2024. Springer Science+Business Media, LLC, part of Springer Nature and the Cardiovascular and Interventional Radiological Society of Europe (CIRSE).)