University of Wollongong
Browse

Detecting People in Images: An Edge Density Approach

Download (172.05 kB)
conference contribution
posted on 2024-11-15, 15:20 authored by Son Lam PhungSon Lam Phung, Abdesselam BouzerdoumAbdesselam Bouzerdoum
In this paper, we present a new method for detecting visual objects in digital images and video. The novelty of the proposed method is that it differentiates objects from non-objects using image edge characteristics. Our approach is based on a fast object detection method developed by Viola and Jones. While Viola and Jones use Harr-like features, we propose a new image feature - the edge density - that can be computed more efficiently. When applied to the problem of detecting people and pedestrians in images, the new feature shows a very good discriminative capability compared to the Harr-like features.

History

Citation

This paper was originally published as: Phung, SL & Bouzerdoum, A, Detecting People in Images: An Edge Density Approach, IEEE International Conference on Acoustics, Speech and Signal Processing, 2007 (ICASSP 2007), Honolulu, Hawaii, USA, 15-20 April 2007, 1, I-1229-I-1232. Copyright 2007 IEEE.

Parent title

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volume

1

Language

English

RIS ID

22280

Usage metrics

    Categories

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC