Automatic estimation of crowd density using texture Export

@article{citeulike:5904743, abstract = {This paper considers the role of automatic estimation of crowd density and its importance for the automatic monitoring of areas where crowds are expected to be present. A new technique is proposed which is able to estimate densities ranging from very low to very high concentration of people, which is a difficult problem because in a crowd only parts of people's body appear. The new technique is based on the differences of texture patterns of the images of crowds. Images of low density crowds tend to present coarse textures, while images of dense crowds tend to present fine textures. The image pixels are classified in different texture classes and statistics of such classes are used to estimate the number of people. The texture classification and the estimation of people density are carried out by means of self organising neural networks. Results obtained respectively to the estimation of the number of people in a specific area of Liverpool Street Railway Station in London (UK) are presented.}, author = {Marana, A. N. and Velastin, S. A. and Costa, L. F. and Lotufo, R. A.}, citeulike-article-id = {5904743}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/S0925-7535(97)00081-7}, citeulike-linkout-1 = {http://www.ingentaconnect.com/content/els/09257535/1998/00000028/00000003/art00081}, doi = {10.1016/S0925-7535(97)00081-7}, issn = {0925-7535}, journal = {Safety Science}, keywords = {automatic\_estimation, density\_estimation, texture}, month = {April}, pages = {165--175}, posted-at = {2009-10-07 09:39:08}, priority = {0}, publisher = {Elsevier}, title = {Automatic estimation of crowd density using texture}, url = {http://dx.doi.org/10.1016/S0925-7535(97)00081-7}, year = {1998} }

TY - JOUR ID - citeulike:5904743 L3 - citeulike-article-id:5904743 N2 - This paper considers the role of automatic estimation of crowd density and its importance for the automatic monitoring of areas where crowds are expected to be present. A new technique is proposed which is able to estimate densities ranging from very low to very high concentration of people, which is a difficult problem because in a crowd only parts of people's body appear. The new technique is based on the differences of texture patterns of the images of crowds. Images of low density crowds tend to present coarse textures, while images of dense crowds tend to present fine textures. The image pixels are classified in different texture classes and statistics of such classes are used to estimate the number of people. The texture classification and the estimation of people density are carried out by means of self organising neural networks. Results obtained respectively to the estimation of the number of people in a specific area of Liverpool Street Railway Station in London (UK) are presented. JF - Safety Science SN - 0925-7535 EP - 175 TI - Automatic estimation of crowd density using texture PB - Elsevier SP - 165 KW - automatic_estimation KW - density_estimation KW - texture AU - Marana, AN AU - Velastin, SA AU - Costa, LF AU - Lotufo, RA PY - 1998/04// UR - http://dx.doi.org/10.1016/S0925-7535(97)00081-7 ER -