Share Email Print
cover

Proceedings Paper

Estimating the number of people in crowded scenes
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper presents a method to estimate the number of people in crowded scenes without using explicit object segmentation or tracking. The proposed method consists of three steps as follows: (1) extracting space-time interest points using eigenvalues of the local spatio-temporal gradient matrix, (2) generating crowd regions based on space-time interest points, and (3) estimating the crowd density based on the multiple regression. In experimental results, the efficiency and robustness of our proposed method are demonstrated by using PETS 2009 dataset.

Paper Details

Date Published: 31 January 2011
PDF: 8 pages
Proc. SPIE 7882, Visual Information Processing and Communication II, 78820L (31 January 2011); doi: 10.1117/12.872493
Show Author Affiliations
Minjin Kim, Korea Advanced Institute of Science and Technology (Korea, Republic of)
Wonjun Kim, Korea Advanced Institute of Science and Technology (Korea, Republic of)
Changick Kim, Korea Advanced Institute of Science and Technology (Korea, Republic of)


Published in SPIE Proceedings Vol. 7882:
Visual Information Processing and Communication II
Amir Said; Onur G. Guleryuz; Robert L. Stevenson, Editor(s)

© SPIE. Terms of Use
Back to Top