Paper detail

GPU-Framework for Teamwork Action Recognition

Real time processing for teamwork action recognition is a challenge, due to complex computational models to achieve high system performance. Hence, this paper proposes a framework based on Graphical Processing Units (GPUs) to achieve a significant speed up in the performance of role based activity recognition of teamwork. The framework can be applied in various fields, especially athletic and military applications. Furthermore, the framework can be customized for many action recognition applications. The paper presents the stages of the framework where GPUs are the main tool for performance improvement. The speedup is achieved by performing video processing and Machine learning algorithms on GPU. Video processing and machine learning algorithms covers all computations involved in our framework. Video processing tasks on involves GPU implementation of Motion detection, segmentation and object tracking algorithms. In addition, our framework is integrated with GPUCV, a GPU version of OpenCV functions. Machine learning tasks are supported under our framework with GPU implementations of Support Vector Machine (SVM) for object classification and feature discretization, Hidden Marcov Model (HMM) for activity recognition phase, and ID3 algorithm for role recognition of team members. The system was tested against UC-Teamwork dataset and speedup of 20X has been achieved on NVidia 9500GT graphics card (32 500MHZ processors).