Dynamic management of a partial reconfigurable hardware architecture for pedestrian detection in regions of interest

Metzli Ramirez-Martinez (1) , Francisco Sanchez-Fernandez (1) , Philippe Brunet (1) , Sidi Senouci (1) , El-Bay Bourennane (2, 3)

1 DRIVE - Département de Recherche en Ingénierie des Véhicules pour l'Environnement [Nevers]
2 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]
3 Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508]

In this paper, we propose a video streaming architecture implementing an IP core design based on Histograms of Oriented Gradients (HOG) algorithm, by using a high-level synthesis workflow. Also, we present a decision algorithm for a dynamically reconfigurable architecture, applied to people detection in video over a Region Of Interest (ROI). Our method dynamically manages the resource consumption in our hardware accelerator. In the test performed with only one reconfigurable module, our method achieves a power reduction up to 7% and a speed of 51 fps, but these results could be improved according to the number of reconfigurable modules. For implementation, we used a Xilinx Zynq 7000 series platform and our experimental results are compared with other software and hardware implementations. Our hardware architecture can be used in a vast number of vision systems, including advanced driver assistance systems (ADAS).

Mots clés: Implementation; Visual-attention

Domaines: Informatique [cs]; Sciences de l'ingénieur [physics]; Sciences de l'ingénieur [physics]; Electronique

Metzli Ramirez-Martinez, Francisco Sanchez-Fernandez, Philippe Brunet, Sidi Senouci, El-Bay Bourennane. Dynamic management of a partial reconfigurable hardware architecture for pedestrian detection in regions of interest. 2017 International Conference on ReConFigurable Computing and FPGAs (ReConFig), Dec 2017, Cancun, Mexico. ⟨10.1109/RECONFIG.2017.8279787⟩. ⟨hal-01860284⟩