Fast-coding robust motion estimation model in a GPU

摘要: Nowadays vision systems are used with countless purposes. Moreover, the motion estimation is a discipline that allow to extract relevant information as pattern segmentation, 3D structure or tracking objects. However, the real-time requirements in most applications has limited its consolidation, considering adoption of high performance meet response times. With emergence so-called highly parallel devices known as accelerators this gap narrowed. Two extreme endpoints spectrum common accelerators Field Programmable Gate Array (FPGA) and Graphics Processing Systems (GPU), which usually offer higher rates than general propose processors. use GPUs involves efficient exploitation any parallelism target application. This task not easy because performance rates affected by many aspects programmers should overcome. In paper, we evaluate OpenACC standard, programming model directives favors porting code GPU context The results confirm paradigm suitable for image processing achieving very satisfactory acceleration convolution based problems well-known Lucas & Kanade method.