Vehicle tracking and classification in challenging scenarios via slice sampling
Egileak: Marcos Nieto and Luis Unzueta and Javier Barandiaran and Andoni Cortés and Oihana Otaegui and Pedro Sánchez
Data: 27.10.2011
EURASIP Journal on Advances in Signal Processing
Abstract
This article introduces a 3D vehicle tracking system in a traffic surveillance environment devised for shadow tolling applications. It has been specially designed to operate in real time with high correct detection and classification rates. The system is capable of providing accurate and robust results in challenging road scenarios, with rain, traffic jams, casted shadows in sunny days at sunrise and sunset times, etc. A Bayesian inference method has been designed to generate estimates of multiple variable objects entering and exiting the scene. This framework allows easily mixing different nature information, gathering in a single step observation models, calibration, motion priors and interaction models. The inference of results is carried out with a novel optimization procedure that generates estimates of the maxima of the posterior distribution combining concepts from Gibbs and slice sampling. Experimental tests have shown excellent results for traffic-flow video surveillance applications that can be used to classify vehicles according to their length, width, and height. Therefore, this vision-based system can be seen as a good substitute to existing inductive loop detectors.
BIB_text
@Article {
author = {Marcos Nieto and Luis Unzueta and Javier Barandiaran and Andoni Cortés and Oihana Otaegui and Pedro Sánchez},
title = {Vehicle tracking and classification in challenging scenarios via slice sampling},
journal = {EURASIP Journal on Advances in Signal Processing},
pages = {ene-36},
volume = {October 2011},
keywds = {
vehicle tracking; Bayesian inference; MRF; particle filter; shadow tolling; ILD; slice sampling; real time
}
abstract = {
This article introduces a 3D vehicle tracking system in a traffic surveillance environment devised for shadow tolling applications. It has been specially designed to operate in real time with high correct detection and classification rates. The system is capable of providing accurate and robust results in challenging road scenarios, with rain, traffic jams, casted shadows in sunny days at sunrise and sunset times, etc. A Bayesian inference method has been designed to generate estimates of multiple variable objects entering and exiting the scene. This framework allows easily mixing different nature information, gathering in a single step observation models, calibration, motion priors and interaction models. The inference of results is carried out with a novel optimization procedure that generates estimates of the maxima of the posterior distribution combining concepts from Gibbs and slice sampling. Experimental tests have shown excellent results for traffic-flow video surveillance applications that can be used to classify vehicles according to their length, width, and height. Therefore, this vision-based system can be seen as a good substitute to existing inductive loop detectors.
}
date = {2011-10-27},
year = {2011},
}
author = {Marcos Nieto and Luis Unzueta and Javier Barandiaran and Andoni Cortés and Oihana Otaegui and Pedro Sánchez},
title = {Vehicle tracking and classification in challenging scenarios via slice sampling},
journal = {EURASIP Journal on Advances in Signal Processing},
pages = {ene-36},
volume = {October 2011},
keywds = {
vehicle tracking; Bayesian inference; MRF; particle filter; shadow tolling; ILD; slice sampling; real time
}
abstract = {
This article introduces a 3D vehicle tracking system in a traffic surveillance environment devised for shadow tolling applications. It has been specially designed to operate in real time with high correct detection and classification rates. The system is capable of providing accurate and robust results in challenging road scenarios, with rain, traffic jams, casted shadows in sunny days at sunrise and sunset times, etc. A Bayesian inference method has been designed to generate estimates of multiple variable objects entering and exiting the scene. This framework allows easily mixing different nature information, gathering in a single step observation models, calibration, motion priors and interaction models. The inference of results is carried out with a novel optimization procedure that generates estimates of the maxima of the posterior distribution combining concepts from Gibbs and slice sampling. Experimental tests have shown excellent results for traffic-flow video surveillance applications that can be used to classify vehicles according to their length, width, and height. Therefore, this vision-based system can be seen as a good substitute to existing inductive loop detectors.
}
date = {2011-10-27},
year = {2011},
}
