We present a discriminative key pose-based approach for moves recognition and segmentation of training sequences for high performance sports. Compared to daily human gestures, moves in high performance sports are faster and have low inter-class variability, which produce noisy features and ambiguity. Our approach combines a robust filtering strategy to select frames composed of discriminative poses (key poses) and the discriminative Latent-Dynamic Conditional Random Fields (LDCRF) model to predict a label for each frame from the training sequence. We evaluate our approach on unsegmented sequences of Taekwondo training. Experimental results indicate that our methodology outperforms the Decision Forests method in terms of efficiency and accuracy. Our average recognition rate was equal to 74.72% while Decision Forests achieves 58.29%. The experiments also show that our approach was able to recognize and segment high speed moves like roundhouse kicks, which can reach peak linear speeds up to 26 m/s.

The increasing interest on the possibility of accessing information anytime, anywhere, associated with the development of modern portable equipments, is stimulating the mobile network evolution. This is a gradual evolution, from the firt mobile network generation, 1G, towards the fourth generation, 4G, passing through 2G, 2.5G, and 3G. Higher video, voice and image transmission capacities are reached on each generation. GSM (Global System for Mobile Communications) is a 2G technology, while GPRS (General Packet Radio Services) is a 2.5G technology. This work compares the capacity of both GSM and GPRS networks. Experimental results obtained through simulation are described, in which the number of mobile stations as well as the traffic generation rate are varied. The main results show that with the GPRS there is a greater number of mobile stations transmitting simultaneously, as it allows a multi-slot allocation. There is also an performance analysis of the GPRS environment. The delay, jitter and throughput are the performance parameters analyzed. The GPRS ideal empirical release time is indicated.