ABOUT ME
José Elías Herrero ha dedicado su carrera de investigación en el ámbito de la visión por computador y redes neuronales desde 2001. Iniciando su doctorado en la Universidad de Zaragoza (España) tras una etapa de trabajo como ingeniero en la planta de Opel España en Figueruelas (Zaragoza).
En 2001 obtuvo una beca de investigación financiada por un proyecto del Ministerio de Educación y Ciencia, y obtuvo posteriormente un contrato como Profesor Ayudante en la Universidad de Zaragoza desde 2002 a 2006. Durante este etapa como ayudante cofundó junto con Carlos Orrite Uruñuela el grupo de Investigación extinto CVLAB, convirtiéndose años después en grupo consolidado DGA.
En 2006 obtuvo la plaza de Profesor Colaborador y empezó a participar como IP en diversos proyectos de investigación. En la parte más dedicada a la investigación, se ha centrado en el ámbito del análisis del movimiento humano. Tanto en la fase de detección, en la fase de seguimiento, o en la fase de reconocimiento. En 2013 se integró como coordinador de la iniciativa Smart Vehicle en el I3A (Instituto Universitario de Investigación en Ingeniería de Aragón).
En 2017 entró como Profesor Contratado Doctor dentro de la Universidad de Zaragoza, y en su CV entra la dirección de 15 Trabajos Fin de Grado, 7 Trabajos Fin de Máster, y 2 Direcciones de Tesis.
Hitos más destacados:
- 10 publicaciones en revistas indexadas (3 Q1, 5 Q2 y 2 Q3), 8 lecture notes, 4 capítulos de libros y 18 comunicaciones a congresos.
- Publicación en revistas relevantes, tales como Computer Vision and Image Understanding o Journal of Mathematical Imaging and Vision.
- En proyectos de investigación ha sido promotor y el investigador principal de 12 nacionales con un presupuesto total de alrededor de
- 600.000; y ha participado en 7 regionales, 11 nacionales y 2 Europeos.
- Derivado de la investigación llevada a cabo en colaboración con empresas privadas (17 contratos), el investigador es co-inventor de 1 patente.
PUBLICATIONS
2019
Orrite, Carlos; Herrero, Elias; Valencia, Mauricio
From Features to Attribute Graphs for Point Set Registration Proceedings Article
En: Morales, Aythami; Fierrez, Julian; Sánchez, José Salvador; Ribeiro, Bernardete (Ed.): Pattern Recognition and Image Analysis, pp. 437–448, Springer International Publishing, Cham, 2019, ISBN: 978-3-030-31332-6.
@inproceedings{10.1007/978-3-030-31332-6_38,
title = {From Features to Attribute Graphs for Point Set Registration},
author = {Carlos Orrite and Elias Herrero and Mauricio Valencia},
editor = {Aythami Morales and Julian Fierrez and José Salvador Sánchez and Bernardete Ribeiro},
isbn = {978-3-030-31332-6},
year = {2019},
date = {2019-01-01},
booktitle = {Pattern Recognition and Image Analysis},
pages = {437–448},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {The traditional approach for point set registration is based on matching feature descriptors between the target object and the query image and then the fundamental matrix is calculated robustly using RANSAC to align the target in the image. However, this approach can easily fail in the presence of occlusion, background clutter and changes in scale and camera viewpoint, being the RANSAC algorithm unable to filter out many outliers. In our proposal the target is represented by an attribute graph, where its vertices represent salient features describing the target object and its edges encode their spatial relationships. The matched keypoints between the attribute graph and the descriptors in the query image are filtered taking into account features such as orientation and scale, as well as the structure of the graph. Preliminary results using the Stanford Mobile Visual search data set and the Stanford Streaming Mobile Augmented Reality Dataset show the best behaviour of our proposal in valid matches and lower computational cost in relation to the standard approach based on RANSAC.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2015
Rodriguez, Mario; Medrano, Carlos; Herrero, Elias; Orrite, Carlos
Spectral Clustering Using Friendship Path Similarity Proceedings Article
En: Iberian Conference on Pattern Recognition and Image Analysis, pp. 319–326, Springer 2015.
@inproceedings{rodriguez2015spectral,
title = {Spectral Clustering Using Friendship Path Similarity},
author = {Mario Rodriguez and Carlos Medrano and Elias Herrero and Carlos Orrite},
year = {2015},
date = {2015-01-01},
booktitle = {Iberian Conference on Pattern Recognition and Image Analysis},
pages = {319–326},
organization = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2014
Orrite, Carlos; Rodriguez, Mario; Herrero, Elias; Rogez, Gregory; Velastin, Sergio A
Automatic segmentation and recognition of human actions in monocular sequences Proceedings Article
En: 2014 22nd International Conference on Pattern Recognition, pp. 4218–4223, IEEE 2014.
@inproceedings{orrite2014automatic,
title = {Automatic segmentation and recognition of human actions in monocular sequences},
author = {Carlos Orrite and Mario Rodriguez and Elias Herrero and Gregory Rogez and Sergio A Velastin},
year = {2014},
date = {2014-01-01},
booktitle = {2014 22nd International Conference on Pattern Recognition},
pages = {4218–4223},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2013
Rodríguez, Mario; Medrano, Carlos; Herrero, Elias; Orrite, Carlos
Transfer learning of human poses for action recognition Proceedings Article
En: International Workshop on Human Behavior Understanding, pp. 89–101, Springer 2013.
@inproceedings{rodriguez2013transfer,
title = {Transfer learning of human poses for action recognition},
author = {Mario Rodríguez and Carlos Medrano and Elias Herrero and Carlos Orrite},
year = {2013},
date = {2013-01-01},
booktitle = {International Workshop on Human Behavior Understanding},
pages = {89–101},
organization = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Orrite, Carlos; Monforte, Pedro; Rodriguez, Mario; Herrero, Elías
Human action recognition under partial occlusions Proceedings Article
En: Iberian Conference on Pattern Recognition and Image Analysis, pp. 398–405, Springer 2013.
@inproceedings{orrite2013human,
title = {Human action recognition under partial occlusions},
author = {Carlos Orrite and Pedro Monforte and Mario Rodriguez and Elías Herrero},
year = {2013},
date = {2013-01-01},
booktitle = {Iberian Conference on Pattern Recognition and Image Analysis},
pages = {398–405},
organization = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}