L
Laura Sellart
Researcher at Autonomous University of Barcelona
Publications - 5
Citations - 2166
Laura Sellart is an academic researcher from Autonomous University of Barcelona. The author has contributed to research in topics: Parametric statistics & Sliding mode control. The author has an hindex of 5, co-authored 5 publications receiving 1489 citations.
Papers
More filters
Proceedings ArticleDOI
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
TL;DR: This paper generates a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations, and conducts experiments with DCNNs that show how the inclusion of SYnTHIA in the training stage significantly improves performance on the semantic segmentation task.
Posted Content
Comparison of two non-linear model-based control strategies for autonomous vehicles
Eugenio Alcala,Laura Sellart,Vicenç Puig,Joseba Quevedo,Jordi Saludes,David Vazquez,Antonio M. López +6 more
TL;DR: This paper presents the comparison of two nonlinear model-based control strategies for autonomous cars using a model reference approach based on a sliding mode-control that defines a set of sliding surfaces over which the error trajectories will converge.
Journal ArticleDOI
Training my car to see using virtual worlds
Antonio M. López,Gabriel Villalonga,Laura Sellart,German Ros,David Vazquez,Jiaolong Xu,Javier Marin,Azadeh Sadat Mozafari +7 more
TL;DR: This paper summarizes a research line consisting of training visual models using photo-realistic computer graphics, especially focusing on assisted and autonomous driving, and shows how it has become a new tendency with increasing acceptance.
Proceedings ArticleDOI
Comparison of two non-linear model-based control strategies for autonomous vehicles
Eugenio Alcala,Laura Sellart,Vicenç Puig,Joseba Quevedo,Jordi Saludes,David Vazquez,Antonio M. López +6 more
TL;DR: In this article, the authors compare two nonlinear model-based control strategies for autonomous cars using a control oriented model of vehicle based on a bicycle model, using a model reference approach.
Book ChapterDOI
Semantic Segmentation of Urban Scenes via Domain Adaptation of SYNTHIA
German Ros,Laura Sellart,Gabriel Villalonga,Elias Maidanik,Francisco Molero,Marc Garcia,Adriana Cedeño,Francisco Perez,Didier Ramirez,Eduardo Escobar,José Luis Zafra Gómez,David Vazquez,Antonio M. López +12 more
TL;DR: This chapter proposes to use a combination of a virtual world to automatically generate realistic synthetic images with pixel-level annotations, and domain adaptation to transfer the models learned to correctly operate in real scenarios to address the question of how useful synthetic data can be for semantic segmentation.