high performance computing on graphics processing units: hgpu.org

This paper presents a fast object class localization framework implemented on a data parallel architecture currently available in recent computers. Our case study, the implementation of Histograms of Oriented Gradients (HOG) descriptors, shows that just by using this recent programming model we can easily speed up an original CPU-only implementation by a factor of 34, making it unnecessary to use early rejection cascades that sacrifice classification performance, even in real-time conditions. Using recent techniques to program the Graphics Processing Unit (GPU) allow our method to scale up to the latest, as well as to future improvements of the hardware.