Title :
Gpu architecture for stationary multisensor pedestrian detection at smart intersections
Author :
Weimer, Daniel ; Köhler, Sebastian ; Hellert, Christian ; Doll, Konrad ; Brunsmann, Ulrich ; Krzikalla, Roland
Author_Institution :
Univ. of Appl. Sci. Aschaffenburg, Aschaffenburg, Germany
Abstract :
We present a real-time multisensor architecture for combined laser scanner and infra-red video-based pedestrian detection and tracking used within a road side unit for intersection assistance. In order to achieve outmost classification performance we propose a cascaded classifier using laser scanner hypothesis generation and histogram of oriented gradients (HOG) descriptors for video-based classification together with linear and Gaussian kernel support vector machines (SVM). The entire classification cascade is implemented on a graphics processing unit (GPU). Giving real-time performance top priority, we present novel compute unified device architecture (CUDA) implementations of a selective HOG-based feature extraction and background subtraction based on mixture of Gaussians (MOG). The classification cascade is managed by a multi-core CPU that further performs pedestrian tracking using a linear Kalman filter. Evaluation on an infra-red benchmark database and an experimental study on a real-world intersection used within the Ko-PER project confirm excellent classification and real-time performance around the clock without external illumination.
Keywords :
computer graphic equipment; coprocessors; image classification; infrared detectors; multiprocessing systems; object tracking; optical scanners; sensor fusion; support vector machines; traffic engineering computing; video signal processing; GPU architecture; Gaussian kernel support vector machines; Ko-PER project; cascaded classifier; compute unified device architecture; graphics processing unit; histogram of oriented gradients descriptors; infrared video based pedestrian detection; infrared video based pedestrian tracking; intersection assistance; laser scanner; laser scanner hypothesis generation; mixture of Gaussians; multicore CPU; smart intersections; stationary multisensor pedestrian detection; video based classification; Computer architecture; Finite impulse response filter; Graphics processing unit; Kernel; Real time systems; Sensors; Support vector machines;
Conference_Titel :
Intelligent Vehicles Symposium (IV), 2011 IEEE
Conference_Location :
Baden-Baden
Print_ISBN :
978-1-4577-0890-9
DOI :
10.1109/IVS.2011.5940411