Car detection with omnidirectional cameras using haar-like features and cascaded boosting

Abstract

This paper presents an approach to detects cars in omnidirectional images. We first go through the conventional method of using Haar-like features and cascaded boosting for conventional camera images. Then, to apply this method for omnidirectional cameras, we generate panoramic images from omnidirectional ones. In this way we perform car detection on a single image without generating numerous perspective images from the omnidirectional view. We also discuss two different ways of panoramic image generation and conclude that spherical profile panoramas are more convenient than cylindrical panoramas. We present our car detection experiments on real omnidirectional images.