Stereo and Neural Network-based Pedestrian Detection - Robotics Institute Carnegie Mellon University

Stereo and Neural Network-based Pedestrian Detection

Liang Zhao and Chuck Thorpe
Conference Paper, Proceedings of IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (ITSC '99), pp. 298 - 303, October, 1999

Abstract

In this paper, we present a real-time pedestrian detection system that uses a pair of moving cameras to detect both stationary and moving pedestrians in crowded environments. This is achieved through stereo-based segmentation and neural network-based recognition. Stereo-based segmentation allows us to extract objects from a changing background; neural network-based recognition allows us to identify pedestrians in various poses, shapes, sizes, clothing, occlusion status. The experiments on a large number of urban street scenes demonstrate the feasibility of the approach in terms of pedestrian detection rate and frame processing rate.

BibTeX

@conference{Zhao-1999-15039,
author = {Liang Zhao and Chuck Thorpe},
title = {Stereo and Neural Network-based Pedestrian Detection},
booktitle = {Proceedings of IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (ITSC '99)},
year = {1999},
month = {October},
pages = {298 - 303},
keywords = {Pedestrian Detection, Stereo Vision, Neural Networks, Object Recognition, Range Image Segmentation},
}