TY  - CONF
AU  - Victor Campmany
AU  - Sergio Silva
AU  - Antonio Espinosa
AU  - Juan Carlos Moure
AU  - David Vazquez
AU  - Antonio Lopez
A2  - ICCS
PY  - 2016//
TI  - GPU-based pedestrian detection for autonomous driving
BT  - 16th International Conference on Computational Science
SP  - 2377
EP  - 2381
VL  - 80
KW  - Pedestrian detection
KW  - Autonomous Driving
KW  - CUDA
N2  - We propose a real-time pedestrian detection system for the embedded Nvidia Tegra X1 GPU-CPU hybrid platform. The pipeline is composed by the following state-of-the-art algorithms: Histogram of Local Binary Patterns (LBP) and Histograms of Oriented Gradients (HOG) features extracted from the input image; Pyramidal Sliding Window technique for foreground segmentation; and Support Vector Machine (SVM) for classification. Results show a 8x speedup in the target Tegra X1 platform and a better performance/watt ratio than desktop CUDA platforms in study.
UR  - https://doi.org/10.1016/j.procs.2016.05.455
L1  - http://refbase.cvc.uab.es/files/CSE2016.pdf
N1  - ADAS; 600.085; 600.082; 600.076
ID  - Victor Campmany2016
ER  -