Cargando…
A Neural-Dynamic Architecture for Concurrent Estimation of Object Pose and Identity
Handling objects or interacting with a human user about objects on a shared tabletop requires that objects be identified after learning from a small number of views and that object pose be estimated. We present a neurally inspired architecture that learns object instances by storing features extract...
Autores principales: | Lomp, Oliver, Faubel, Christian, Schöner, Gregor |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5408094/ https://www.ncbi.nlm.nih.gov/pubmed/28503145 http://dx.doi.org/10.3389/fnbot.2017.00023 |
Ejemplares similares
-
Developing Dynamic Field Theory Architectures for Embodied Cognitive Systems with cedar
por: Lomp, Oliver, et al.
Publicado: (2016) -
Autonomous Sequence Generation for a Neural Dynamic Robot: Scene Perception, Serial Order, and Object-Oriented Movement
por: Tekülve, Jan, et al.
Publicado: (2019) -
A Neural Dynamic Architecture for Reaching and Grasping Integrates Perception and Movement Generation and Enables On-Line Updating
por: Knips, Guido, et al.
Publicado: (2017) -
Deformation-specific and deformation-invariant visual object recognition: pose vs. identity recognition of people and deforming objects
por: Webb, Tristan J., et al.
Publicado: (2014) -
Dynamic Neural Fields with Intrinsic Plasticity
por: Strub, Claudius, et al.
Publicado: (2017)