1,721,557 research outputs found
Southampton Gait Database
The Southampton Gait database can be used to support research in gait biometrics and in moving object analysis. It has videos of more than 100 people walking in a controlled laboratory environment.
For a description of the experiment see Seely, Richard David, Samangooei, Sina, Middleton, Lee, Carter, John and Nixon, Mark (2008) 'The University of Southampton Multi-Biometric Tunnel and introducing a novel 3D gait dataset' At Biometrics: Theory, Applications and Systems, Hyatt Regency Crystal City, Washington DC, USA, IEEE, http://eprints.soton.ac.uk/266970/
Media reports of the tunnel are available:
'It's The Way You Walk' Biometrics, BBC [TV], 2007
https://www.youtube.com/watch?v=Voygv1uTF7c
'Walk this Way' Good Morning America, ABC [TV], 13th July 2006
https://www.youtube.com/watch?v=6KuMe5n_jdQ
Bang Goes the Theory, BBC [TV], 27 July 2007
https://www.youtube.com/watch?v=PUwlNc0xAgQ
Gait Biometrics Newsnight, BBC [TV], 2015
https://www.youtube.com/watch?v=gxOB8lchYnE </span
Southampton MultiBiometric Tunnel Database
The Southampton Tunnel database is multiview synchronised video of subjects walking in a laboratory environment.
For a description of the experiment see Seely, Richard David, Samangooei, Sina, Middleton, Lee, Carter, John and Nixon, Mark (2008) 'The University of Southampton Multi-Biometric Tunnel and introducing a novel 3D gait dataset' At Biometrics: Theory, Applications and Systems, Hyatt Regency Crystal City, Washington DC, USA, IEEE, http://eprints.soton.ac.uk/266970/
Media reports of the tunnel are available:
'It's The Way You Walk' Biometrics, BBC [TV], 2007
https://www.youtube.com/watch?v=Voygv1uTF7c
'Walk this Way' Good Morning America, ABC [TV], 13th July 2006
https://www.youtube.com/watch?v=6KuMe5n_jdQ
Bang Goes the Theory, BBC [TV], 27 July 2007
https://www.youtube.com/watch?v=PUwlNc0xAgQ
Gait Biometrics Newsnight, BBC [TV], 2015
https://www.youtube.com/watch?v=gxOB8lchYnE </span
Application of the Hough transform to correct for linear variation of background illumination in images
The Hough transform has been formulated to detect areas of linear brightness variation within an image. The formulation leads to significant computational advantage involving a restricted parameter search space. Two applications are included to demonstrate the efficacy of this technique
Model-based Gait Recognition
Model-based Gait Recognition concerns identification using an underlying mathematical construct(s) representing the discriminatory gait characteristics (be they static or dynamic), with a set of parameters and a set of logical and quantitative relationships between them. These models are often simplified based on justifiable assumptions such as the system only accounts for pathologically normal gait. Such a system normally consists of gait capture, a model(s), a feature extraction scheme, a gait signature and a classifier (Figure 1). The model can be a 2- or 3-dimensional structural (or shape) model and motion model that lays the foundation for the extraction and tracking of a moving person. An alternative to a model-based approach is to analyse the motion of the human silhouette deriving recognition from the body’s shape and motion. A gait signature that is unique to each person in the database is then derived from the extracted gait characteristics. In the classification stage, many pattern classification techniques can be used, such as the k-nearest neighbour approach
Advances in Biometrics, Third IEEE/ IAPR International Conference on Biometrics ICB 2009
- …
