Exploiting feature dynamics for active object recognition
This paper describes a new approach to object recognition for active vision systems that integrates information across multiple observations of an object. The approach exploits the order relationship between successive frames to derive a classifier based on the characteristic motion of local feature...
Principais autores: | Robbel, Philipp, Roy, Deb K |
---|---|
Outros Autores: | Massachusetts Institute of Technology. Media Laboratory |
Formato: | Artigo |
Idioma: | en_US |
Publicado em: |
Institute of Electrical and Electronics Engineers
2013
|
Acesso em linha: | http://hdl.handle.net/1721.1/80839 https://orcid.org/0000-0002-4333-7194 https://orcid.org/0000-0002-3315-2372 |
Registros relacionados
-
Exploiting object dynamics for recognition and control
por: Robbel, Philipp
Publicado em: (2008) -
Local multiagent control in large factored planning Problems
por: Robbel, Philipp
Publicado em: (2016) -
Exploiting stable features for iris recognition of defocused images
por: Liu, Bo, et al.
Publicado em: (2013) -
Planning to Perceive: Exploiting Mobility for Robust Object Detection
por: Velez, Javier J., et al.
Publicado em: (2013) -
Exploiting the features of deep residual network with SVM classifier for human posture recognition.
por: Irfan Kareem, et al.
Publicado em: (2024-01-01)