<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Juan F. Vazquez</style></author><author><style face="normal" font="default" size="100%">Jose L. Lazaro</style></author><author><style face="normal" font="default" size="100%">Manuel Mazo</style></author><author><style face="normal" font="default" size="100%">Carlos Andres Luna</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Sensor for object detection in railway environment</style></title><secondary-title><style face="normal" font="default" size="100%">Sensor Letters</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">adaptive threshold</style></keyword><keyword><style  face="normal" font="default" size="100%">background subtraction</style></keyword><keyword><style  face="normal" font="default" size="100%">object detection</style></keyword><keyword><style  face="normal" font="default" size="100%">principal component analysis</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2008</style></year><pub-dates><date><style  face="normal" font="default" size="100%">10/2008</style></date></pub-dates></dates><publisher><style face="normal" font="default" size="100%">American Scientific Publishers</style></publisher><pub-location><style face="normal" font="default" size="100%">USA</style></pub-location><volume><style face="normal" font="default" size="100%">6</style></volume><pages><style face="normal" font="default" size="100%">690-698</style></pages><language><style face="normal" font="default" size="100%">English</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;In this paper, a solution for object detection in railway environment is presented. This solution is based on a background subtraction technique and adaptive threshold. The captured scene by a fixed camera is compared with a background model created by means of standard principal component analysis (PCA). The result of this comparison is a matrix of distances, from which a binary image, representing the background and objects, is obtained, using the adaptive threshold proposed. The histogram of the matrix of distances and the variance of a mean image is used to obtain the adaptive proposed threshold. This thresholding method was compared with the methods of Kittler and Kapur. The error rate in the detection of false-negatives with our algorithm was, at the worst, 1.3% (with Kittler's algorithm, it was 7.8% and with Kapur's algorithm, it was 6.9%). The low error rate of our thresholding method in the varied illumination and weather conditions show the validity and robustness of this alternative, which is also observed in comparison with other algorithms&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">5</style></issue><accession-num><style face="normal" font="default" size="100%">1.587</style></accession-num><call-num><style face="normal" font="default" size="100%">INSTRUMENTS &amp; INSTRUMENT</style></call-num></record></records></xml>