Multiple Pedestrians Recognition using Hybrid GA for Driving Assistance System

H. Suzuki and M. Minami (Japan)

Keywords

Intelligent Transport Systems, Genetic Algorithm, Pedes trians, RealTime Recognition, Carmounted Camera

Abstract

This study proposes a method of recognizing multiple pedestrians in real time using a car-mounted camera, as a basic technology for the driving assistance system. We em ployed a hybrid GA (Genetic Algorithm) based on selec tive attention, which is the human visual function used to reduce processing load, to search for the position of pedes trians in input image. The hybrid GA used random search ing as a rough, preliminary search of the area, then used an improved GA to carefully search the target possibili ties. A real-time experiment on the recognition of mul tiple pedestrians in dynamic images obtained from a car mounted camera was used to verify the effectiveness of the proposed method.

Important Links:



Go Back