A Neural Network Approach to Pedestrian Detection

The paper presents an original approach for pedestrian detection using the neural network classifier called Concurrent Self-Organizing Maps (CSOM), previously introduced by first author; it represents a winner-takes-all collection of neural modules. The algorithm has the following stages: (a) feature selection using one of the three candidate techniques Histogram of Oriented Gradients (HOG)/1D Haar transform/2D Haar transform; (b) classification using a CSOM classifier with two concurrent neural modules, where first module is trained with pedestrian images and the second one is trained with non-pedestrian images. We present the experimental results obtained by computer simulation of our model. For training and testing the neural classifier, we have used INRIA Person Dataset. One obtains the best Total Success Rate (TSR) of 99.7 %. Key-Words: pedestrian detection, neural network classifier, Concurrent Self-Organizing Maps, Histogram of Oriented Gradients, Haar transform.