Thesis icon

Thesis

Human layout estimation using structured output learning

Abstract:

In this thesis, we investigate the problem of human layout estimation in unconstrained still images. This involves predicting the spatial configuration of body parts.

We start our investigation with pictorial structure models and propose an efficient method of model fitting using skin regions. To detect the skin, we learn a colour model locally from the image by detecting the facial region. The resulting skin detections are also used for hand localisation.

Our next contribution...

Expand abstract

Actions


Access Document


Files:
  • (Dissemination version, pdf, 46.1MB)

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Research group:
Visual Geometry Group
Oxford college:
Brasenose College
Role:
Author

Contributors

Division:
MPLS
Department:
Engineering Science
Role:
Supervisor
Division:
MPLS
Department:
Engineering Science
Role:
Supervisor
Publication date:
2012
Type of award:
DPhil
Level of award:
Doctoral
Awarding institution:
University of Oxford
UUID:
uuid:bb290cfd-5216-42d7-b3d2-c2b4b01614bc
Local pid:
ora:6591

Terms of use


Metrics


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP