Title :
A kernelized Probabilistic Neural Network approach for counting pedestrians
Author :
Aik, Lim Eng ; Zainuddin, Zarita
Author_Institution :
Inst. of Eng. Mathematic, Univ. Malaysia Perlis, Arau, Malaysia
Abstract :
An improved, intelligent pedestrian counting system, using images obtained from a single video camera, is described in this paper. This system is capable of detecting and counting a group of pedestrians in the region of interest. Groups can be extracted by using the image processing method, and a kernel-induced probabilistic neural network (KPNN) employed to perform the classification, and estimate the number of pedestrians in a group. We validated the pedestrian-counting system on a pedestrian dataset, and this analysis indicates that the proposed KPNN-type classifier provides good results.
Keywords :
feature extraction; image classification; neural nets; object detection; probability; traffic engineering computing; video cameras; video signal processing; feature extraction; image classification; image processing; intelligent pedestrian counting system; kernelized probabilistic neural network; object detection; video camera; Cameras; Costs; Data mining; Feature extraction; Industrial electronics; Intelligent networks; Mathematics; Neural networks; Tellurium; Uninterruptible power systems;
Conference_Titel :
Industrial Electronics, 2009. ISIE 2009. IEEE International Symposium on
Conference_Location :
Seoul
Print_ISBN :
978-1-4244-4347-5
Electronic_ISBN :
978-1-4244-4349-9
DOI :
10.1109/ISIE.2009.5218897
