VIS - Visió Artificial i Sistemes Intel·ligents
Recerca bàsica i aplicada al desenvolupament de sistemes intel•ligents capaços d'interactuar amb el món de forma autònoma i ubica. Aquests sistemes hauran de percebre, raonar, planificar, actuar i aprendre de l'experiència prèvia. El grup treballa activament en tres àrees: robòtica social i aèria ; visió per computador i reconeixement estructural de patrons. Dins de la robòtica social s’està treballant en els següents temes: Interacció robot-humà; localització i navegació social i autònoma de robots; localització i construcció simultània de mapes (SLAM); robòtica ubiqua; robòtica mòbil cooperativa; i robòtica aèria. En visió per computador es treballa en: seguiment, identificació i reconeixement de objectes; en xarxes de sensors de càmeres; fusió de dades; i percepció cooperativa. I en reconeixement estructural de patrons s'està treballant en mètodes de síntesi i coincidència de grafs i el la seva aplicació a la robòtica.
The Artificial Vision and Intelligent Systems Group (VIS) carries out basic and applied research with the aim of understanding and designing intelligent systems that are capable of interacting with the real world in an autonomous and wide-reaching manner. Such intelligent systems must perceive, reason, plan, act and learn from previous experiences. The group works on the following topics: robust colour image segmentation and labelling, pattern recognition, viewpoint invariant object learning and recognition, object tracking, face tracking, biometrics, processing and analysis of medical images for diagnosis, document analysis, mobile robot navigation, simultaneous localisation and map building, visual servoing, and human-computer interaction. The possible areas of application of the VIS?s research include the automotive and transport industry, the biomedical imaging industry, the space industry, robotics applications, security, home and office automation, the entertainment industry, and future computing enviro
The Artificial Vision and Intelligent Systems Group (VIS) carries out basic and applied research with the aim of understanding and designing intelligent systems that are capable of interacting with the real world in an autonomous and wide-reaching manner. Such intelligent systems must perceive, reason, plan, act and learn from previous experiences. The group works on the following topics: robust colour image segmentation and labelling, pattern recognition, viewpoint invariant object learning and recognition, object tracking, face tracking, biometrics, processing and analysis of medical images for diagnosis, document analysis, mobile robot navigation, simultaneous localisation and map building, visual servoing, and human-computer interaction. The possible areas of application of the VIS?s research include the automotive and transport industry, the biomedical imaging industry, the space industry, robotics applications, security, home and office automation, the entertainment industry, and future computing enviro
Collections in this community
-
Altres [2]
-
Articles de revista [133]
-
Capítols de llibre [22]
-
Presentacions [2]
-
Reports de recerca [12]
Recent Submissions
-
Single-view 3d body and cloth reconstruction under complex poses
(Scitepress, 2022)
Conference report
Open AccessRecent advances in 3D human shape reconstruction from single images have shown impressive results, leveraging on deep networks that model the so-called implicit function to learn the occupancy status of arbitrarily dense ... -
Classification of humans social relations within urban areas
(Springer, 2022)
Conference report
Open AccessThis paper presents the design of deep learning architectures which allow to classify the social relationship existing between two people who are walking in a side-by-side formation into four possible categories --colleagues, ... -
Semi-supervised wildfire smoke detection based on smoke-aware consistency
(Frontiers Media SA, 2022-11-08)
Article
Open AccessThe semi-transparency property of smoke integrates it highly with the background contextual information in the image, which results in great visual differences in different areas. In addition, the limited annotation of ... -
Context and intention for 3D human motion prediction: experimentation and user study in handover tasks
(Institute of Electrical and Electronics Engineers (IEEE), 2022)
Conference report
Open AccessIn this work we present a novel attention deep learning model that uses context and human intention for 3D human body motion prediction in handover human-robot tasks. This model uses a multi-head attention architecture ... -
Robot navigation anticipative strategies in deep reinforcement motion planning
(Springer, 2022)
Conference report
Restricted access - publisher's policyThe navigation of robots in dynamic urban environments, re-quires elaborated anticipative strategies for the robot to avoid collisions with dynamic objects, like bicycles or pedestrians, and to be human aware. ... -
A hierarchical framework for collaborative artificial intelligence
(2022-10-13)
Article
Open AccessWe propose a hierarchical framework for collaborative intelligent systems. This framework organizes research challenges based on the nature of the collaborative activity and the information that must be shared, with each ... -
Efficient hand gesture recognition for human-robot interaction
(Institute of Electrical and Electronics Engineers (IEEE), 2022)
Article
Open AccessIn this paper, we present an efficient and reliable deep-learning approach that allows users to communicate with robots via hand gesture recognition. Contrary to other works which use external devices such as gloves [1] ... -
IVO Robot: a new social robot for human-robot collaboration
(Institute of Electrical and Electronics Engineers (IEEE), 2022)
Conference lecture
Open AccessWe present a new social robot named IVO, a robot capable of collaborating with humans and solving different tasks. The robot is intended to cooperate and work with humans in a useful and socially acceptable manner to ... -
Control-oriented estimation of the exchange current density in PEM fuel cells via stochastic filtering
(2022-08)
Article
Open AccessIncreasing efficiency and durability of fuel cells can be achieved through advanced model-based optimal control of its operating conditions, and the efficient online estimation of fuel cell parameters and internal states ... -
Event-based line SLAM in real-time
(Institute of Electrical and Electronics Engineers (IEEE), 2022)
Article
Open AccessEvent-based cameras generate asynchronous streams of events, triggered proportionally to the logarithmic change of brightness in the scene. These cameras have very low latency and high dynamic range suitable to address ... -
WOLF: A modular estimation framework for robotics based on factor graphs
(Institute of Electrical and Electronics Engineers (IEEE), 2022)
Article
Open AccessThis paper introduces WOLF, a C++ estimation framework based on factor graphs and targeted at mobile robotics. WOLF can be used beyond SLAM to handle self-calibration, model identification, or the observation of dynamic ... -
Box-Jenkins autoregressive models for PEMFC operating under dynamical conditions
(2021)
Conference report
Open AccessThe objective of the present work is to explore and validate autoregressive, control oriented models models Proton Exchange Membrane Fuel Cells coperatinf under dynamic condditions. Autoregressive models have several ...