Image Noise Removal on Heterogeneous CPU-GPU Configurations

A parallel algorithm to remove impulsive noise in digital images using heterogeneous CPU/GPU computing is proposed. The parallel denoising algorithm is based on the peer group concept and uses an Euclidean metric. In order to identify the amount of pixels to be allocated in multi-core and GPUs, a performance analysis using large images is presented. A comparison of the parallel implementation in multi-core, GPUs and a combination of both is performed. Performance has been evaluated in terms of execution time and Megapixels/second. We present several optimization strategies especially effective for the multi-core environment, and demonstrate significant performance improvements. The main advantage of the proposed noise removal methodology is its computational speed, which enables efficient filtering of color images in real-time applications.

Effects of whole body vibration on strength and jumping performance in volleyball and beach volleyball players

The primary aim of this study was to examine the effects of 6-week strength training with whole body vibration (WBV) on leg strength and jumping performance in volleyball and beach volleyball players. Twenty-three sub-elite male volleyball (VB; n=12) and beach volleyball players (BVB; n=11) aged 21.2±3.0 years were divided into two groups and subjected to 6 weeks of strength training (three one-hour sessions per week): (I) 12 players (6 VB and 6 BVB players) underwent training with WBV (30-40 Hz, 1.7-2.5 mm, 3.0-5.7 g), and (II) 11 players (6 VB and 5 BVB players) underwent traditional strength training. Squat jump (SJ) and countermovement squat jump (CMJ) measurements by the Ergo Tester contact platform and maximum leg press test (1RM) were conducted. Three-factor (2 time x 2 WBV use x 2 discipline) analysis of variance for SJ, CMJ and 1RM revealed a significant time main effect (p<0.001), a WBV use effect (p<0.001) and a discipline effect (p<0.001). Significantly greater improvements in the SJ (p<0.001) and CMJ (p<0.001) and in 1RM (p<0.001) were found in the WBV training groups than in traditional training groups. Significant 3-way interaction effects (training, WBV use, discipline kind) were also found for SJ, CMJ and 1RM (p=0.001, p<0.001, p=0.001, respectively). It can be concluded that implementation of 6-week WBV training in routine practice in volleyball and beach volleyball players increases leg strength more and leads to greater improvement in jump performance than traditional strength training, but greater improvements can be expected in beach volleyball players than in volleyball players.