Fast pedestrian detection system with a two layer cascade of classifiers

This work presents a novel pedestrian detection system that uses Haar-like feature extraction and a covariance matrix descriptor to identify the distinctions of pedestrians. An approach that adopts an integral image is also applied to reduce the computational loads required in both the Haar-like feature extraction and evaluation of the covariance matrix descriptor. Based on the Fisher linear discriminant analysis (FLDA) classification algorithm, the proposed system can classify pedestrians efficiently. Additionally, the detection procedure of the proposed system is accelerated using a two-layer cascade of classifiers. The front end, constructed based on Haar-like features, can select candidate regions quickly wherever pedestrians may be present. Moreover, the back end, constructed based on the covariance matrix descriptor, can determine accurately whether pedestrians are positioned in candidate regions. If a region tests positive through the two-layer cascade classifiers, pedestrian images are likely captured. Test video sequences during the experiments are taken from a test set of the INRIA person database, using 30 input frames per second, each with a resolution of 320x240 pixels. Experimental results demonstrate that the proposed system can detect pedestrians efficiently and accurately, significantly contributing to efforts to develop a real time system.