The Computer Vision and Robotics Laboratory, where the following research took place, in 21 years has graduated more than 40 Master and Ph.D. students. It currently accommodates seven professors and more than 45 graduate and undergraduate students. [source]
We intend to tackle the problem of Scene Understanding. In other words, given the image of a scene, the objective is to extract highly semantic information, for instance, the class it belongs to (e.g., bathroom, church, library). A scene consists in places where humans can act within or navigate. Therefore the capacity to sense the environment in a more meaningful way is highly relevant for most applications that intend to operate in the real world. [source]
The following video is a short clip with parts of a presentation of the extended abstract entitled "Anomaly detection in indoor scenes based on contextual modeling" at the Student Consortium 2017 - 22nd Ibero American Congress on Pattern Recognition.
SILVA, C. L.; NACIMENTO, E. R. . Representing Indoor Scenes as a Sparse Composition of Feature Segments. In: WiP SIBGRAPI 2017 - 30th Conference on Graphics, Patterns and Images, 2017, Niterói. 30th Conference on Graphics, Patterns and Images (SIBGRAPI), 2017.
NASCIMENTO, G. ; LARANJEIRA, C. ; BRAZ, V. ; LACERDA, A. ; NACIMENTO, E. R. . A Robust Indoor Scene Recognition Method based on Sparse Representation. In: 22nd Iberoamerican Congress on Pattern Recognition (CIARP), 2017, Valparaíso. 22nd Iberoamerican Congress on Pattern Recognition (CIARP), 2017.
LARANJEIRA, C.; NASCIMENTO, E.R.. Anomaly detection in indoor scenes based on contextual modeling. In: Student Consortium, 22nd Iberoamerican Congress on Pattern Recognition (StuCon2017 CIARP), Valparaíso, 2017.
See all publications here.