Detecting background and foreground with a laser array system

Teresa Hernández-Díaz, Alberto Vázquez-Cervantes, José Joel Gonzalez-Barboza, Leonardo Barriga-Rodríguez, Ana M. Herrera-Navarro, Leonardo Aurelio Baldenegro-Pérez, Hugo Jiménez-Hernández

Research output: Contribution to journalArticle

Abstract

© 2014 Elsevier Ltd. All rights reserved. Ranging Laser Sensors are typically used as method for extracting tridimensional information on the environment. This information takes the sensor's location as reference, obtaining a points cloud which corresponds to the relative distances of the surrounding surfaces, which are related to the objects around the reference. However, in outdoor scenarios, a great diversity of non-controllable events makes difficult to analyze the dynamic objects. Consequently, an efficient criterion to discriminate which information corresponds to fixed zones and which information corresponds to dynamic zones is complicated to define, due to a wide variety of involved situations. This work presents a stochastic approach for modeling a tridimensional environment. This approach is used to estimate the foreground and background using information obtained from a Laser Imaging Detection and Ranging (LiDAR) sensor. It represents an extension of the background subtraction approach, using a Mixture of Gaussians (MoG) on the image sequences. The environment is visualized using a laser array system, which acquires the distance of every surrounding surface in a radius of 120 m. The obtained data are set into an array of parametric form and spherical discretized notation to model every interval as a Mixture of Gaussians. The Expectation Maximization (EM) technique is used to estimate the parameters of every MoG. Finally, this new algorithm allows characterizing objects according to the distance between their surfaces and the laser array system. Furthermore, as a consequence of the technique itself, it also eliminates noise and obtains a trust level of the implemented method.
Original languageAmerican English
Pages (from-to)195-206
Number of pages174
JournalMeasurement: Journal of the International Measurement Confederation
DOIs
StatePublished - 1 Jan 2015

Fingerprint

laser arrays
Lasers
Sensors
sensors
laser ranging
Noise
estimates
subtraction
Imaging techniques
coding
intervals
radii
lasers

Cite this

Hernández-Díaz, T., Vázquez-Cervantes, A., Gonzalez-Barboza, J. J., Barriga-Rodríguez, L., Herrera-Navarro, A. M., Baldenegro-Pérez, L. A., & Jiménez-Hernández, H. (2015). Detecting background and foreground with a laser array system. Measurement: Journal of the International Measurement Confederation, 195-206. https://doi.org/10.1016/j.measurement.2014.12.004
Hernández-Díaz, Teresa ; Vázquez-Cervantes, Alberto ; Gonzalez-Barboza, José Joel ; Barriga-Rodríguez, Leonardo ; Herrera-Navarro, Ana M. ; Baldenegro-Pérez, Leonardo Aurelio ; Jiménez-Hernández, Hugo. / Detecting background and foreground with a laser array system. In: Measurement: Journal of the International Measurement Confederation. 2015 ; pp. 195-206.
@article{14e1cea41f4545c398502b4a0d12db69,
title = "Detecting background and foreground with a laser array system",
abstract = "{\circledC} 2014 Elsevier Ltd. All rights reserved. Ranging Laser Sensors are typically used as method for extracting tridimensional information on the environment. This information takes the sensor's location as reference, obtaining a points cloud which corresponds to the relative distances of the surrounding surfaces, which are related to the objects around the reference. However, in outdoor scenarios, a great diversity of non-controllable events makes difficult to analyze the dynamic objects. Consequently, an efficient criterion to discriminate which information corresponds to fixed zones and which information corresponds to dynamic zones is complicated to define, due to a wide variety of involved situations. This work presents a stochastic approach for modeling a tridimensional environment. This approach is used to estimate the foreground and background using information obtained from a Laser Imaging Detection and Ranging (LiDAR) sensor. It represents an extension of the background subtraction approach, using a Mixture of Gaussians (MoG) on the image sequences. The environment is visualized using a laser array system, which acquires the distance of every surrounding surface in a radius of 120 m. The obtained data are set into an array of parametric form and spherical discretized notation to model every interval as a Mixture of Gaussians. The Expectation Maximization (EM) technique is used to estimate the parameters of every MoG. Finally, this new algorithm allows characterizing objects according to the distance between their surfaces and the laser array system. Furthermore, as a consequence of the technique itself, it also eliminates noise and obtains a trust level of the implemented method.",
author = "Teresa Hern{\'a}ndez-D{\'i}az and Alberto V{\'a}zquez-Cervantes and Gonzalez-Barboza, {Jos{\'e} Joel} and Leonardo Barriga-Rodr{\'i}guez and Herrera-Navarro, {Ana M.} and Baldenegro-P{\'e}rez, {Leonardo Aurelio} and Hugo Jim{\'e}nez-Hern{\'a}ndez",
year = "2015",
month = "1",
day = "1",
doi = "10.1016/j.measurement.2014.12.004",
language = "American English",
pages = "195--206",
journal = "Measurement: Journal of the International Measurement Confederation",
issn = "0263-2241",
publisher = "Elsevier",

}

Hernández-Díaz, T, Vázquez-Cervantes, A, Gonzalez-Barboza, JJ, Barriga-Rodríguez, L, Herrera-Navarro, AM, Baldenegro-Pérez, LA & Jiménez-Hernández, H 2015, 'Detecting background and foreground with a laser array system', Measurement: Journal of the International Measurement Confederation, pp. 195-206. https://doi.org/10.1016/j.measurement.2014.12.004

Detecting background and foreground with a laser array system. / Hernández-Díaz, Teresa; Vázquez-Cervantes, Alberto; Gonzalez-Barboza, José Joel; Barriga-Rodríguez, Leonardo; Herrera-Navarro, Ana M.; Baldenegro-Pérez, Leonardo Aurelio; Jiménez-Hernández, Hugo.

In: Measurement: Journal of the International Measurement Confederation, 01.01.2015, p. 195-206.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detecting background and foreground with a laser array system

AU - Hernández-Díaz, Teresa

AU - Vázquez-Cervantes, Alberto

AU - Gonzalez-Barboza, José Joel

AU - Barriga-Rodríguez, Leonardo

AU - Herrera-Navarro, Ana M.

AU - Baldenegro-Pérez, Leonardo Aurelio

AU - Jiménez-Hernández, Hugo

PY - 2015/1/1

Y1 - 2015/1/1

N2 - © 2014 Elsevier Ltd. All rights reserved. Ranging Laser Sensors are typically used as method for extracting tridimensional information on the environment. This information takes the sensor's location as reference, obtaining a points cloud which corresponds to the relative distances of the surrounding surfaces, which are related to the objects around the reference. However, in outdoor scenarios, a great diversity of non-controllable events makes difficult to analyze the dynamic objects. Consequently, an efficient criterion to discriminate which information corresponds to fixed zones and which information corresponds to dynamic zones is complicated to define, due to a wide variety of involved situations. This work presents a stochastic approach for modeling a tridimensional environment. This approach is used to estimate the foreground and background using information obtained from a Laser Imaging Detection and Ranging (LiDAR) sensor. It represents an extension of the background subtraction approach, using a Mixture of Gaussians (MoG) on the image sequences. The environment is visualized using a laser array system, which acquires the distance of every surrounding surface in a radius of 120 m. The obtained data are set into an array of parametric form and spherical discretized notation to model every interval as a Mixture of Gaussians. The Expectation Maximization (EM) technique is used to estimate the parameters of every MoG. Finally, this new algorithm allows characterizing objects according to the distance between their surfaces and the laser array system. Furthermore, as a consequence of the technique itself, it also eliminates noise and obtains a trust level of the implemented method.

AB - © 2014 Elsevier Ltd. All rights reserved. Ranging Laser Sensors are typically used as method for extracting tridimensional information on the environment. This information takes the sensor's location as reference, obtaining a points cloud which corresponds to the relative distances of the surrounding surfaces, which are related to the objects around the reference. However, in outdoor scenarios, a great diversity of non-controllable events makes difficult to analyze the dynamic objects. Consequently, an efficient criterion to discriminate which information corresponds to fixed zones and which information corresponds to dynamic zones is complicated to define, due to a wide variety of involved situations. This work presents a stochastic approach for modeling a tridimensional environment. This approach is used to estimate the foreground and background using information obtained from a Laser Imaging Detection and Ranging (LiDAR) sensor. It represents an extension of the background subtraction approach, using a Mixture of Gaussians (MoG) on the image sequences. The environment is visualized using a laser array system, which acquires the distance of every surrounding surface in a radius of 120 m. The obtained data are set into an array of parametric form and spherical discretized notation to model every interval as a Mixture of Gaussians. The Expectation Maximization (EM) technique is used to estimate the parameters of every MoG. Finally, this new algorithm allows characterizing objects according to the distance between their surfaces and the laser array system. Furthermore, as a consequence of the technique itself, it also eliminates noise and obtains a trust level of the implemented method.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84919924599&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84919924599&origin=inward

U2 - 10.1016/j.measurement.2014.12.004

DO - 10.1016/j.measurement.2014.12.004

M3 - Article

SP - 195

EP - 206

JO - Measurement: Journal of the International Measurement Confederation

JF - Measurement: Journal of the International Measurement Confederation

SN - 0263-2241

ER -

Hernández-Díaz T, Vázquez-Cervantes A, Gonzalez-Barboza JJ, Barriga-Rodríguez L, Herrera-Navarro AM, Baldenegro-Pérez LA et al. Detecting background and foreground with a laser array system. Measurement: Journal of the International Measurement Confederation. 2015 Jan 1;195-206. https://doi.org/10.1016/j.measurement.2014.12.004