Vés al contingut (premeu Retorn)

Interactive multiple object learning with scanty human supervision

Villamizar, M.A.; Garrell, A.; Sanfeliu, A.; Moreno-Noguer, F.
Tipus d'activitat
Article en revista
Computer vision and image understanding
Data de publicació
Pàgina inicial
Pàgina final
DOI Obrir en finestra nova
Projecte finançador
Aerial robotic system integrating multiple arms and advanced manipulation capabilities for inspection and maintenance
FP7-ICT2009-6-269959 - IntellAct: Intelligent observation and execution of Actions and manipulations ViSen: Visual Sense, Tagging visual data with semantic descriptions
Interacción, aprendizaje y cooperación robot-humano en areas urbanas
RobInstruct: Instructing robots using natural communication skills - TIN2014-58178-R
Robot-Int-Coop: Robot-Human Interaction, Cooperation and Learning in Urban Areas
Repositori Obrir en finestra nova
URL Obrir en finestra nova
We present a fast and online human-robot interaction approach that progressively learns multiple object classifiers using scanty human supervision. Given an input video stream recorded during the human robot interaction, the user just needs to annotate a small fraction of frames to compute object specific classifiers based on random ferns which share the same features. The resulting methodology is fast (in a few seconds, complex object appearances can be learned), versatile (it can be applied to...
Villamizar, M.A., Garrell, A., Sanfeliu, A., Moreno-Noguer, F. Interactive multiple object learning with scanty human supervision. "Computer vision and image understanding", Agost 2016, vol. 149, p. 51-64.
Paraules clau
Human-robot interaction, Interactive learning, Object recognition, Online classifier, human-robot interaction, recognition
Grup de recerca
ROBiri - Grup de Robòtica de l'IRI
VIS - Visió Artificial i Sistemes Intel.ligents