Sorry, you need to enable JavaScript to visit this website.

Image/Video Processing

Object Tracking and Person Re-Identification on Manifolds


person re-identification examples

Slides from the Tutorial on Riemannian Geometry in Computer Vision, presented at the Asian Conference on Computer Vision (ACCV), Singapore, 2014.

The slides show (1) how objects can be interpreted as points on Riemannian and Grassmann manifolds, and (2) various distance measures on manifolds. Demonstrates usefulness of manifold techniques in applications such as object tracking and person re-identification.

Paper Details

Authors:
Submitted On:
23 February 2016 - 1:43pm
Short Link:
Type:

Document Files

sanderson_riemannian_geometry_tutorial_slides_accv_2014.pdf

(533 downloads)

Keywords

Subscribe

[1] , "Object Tracking and Person Re-Identification on Manifolds", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/198. Accessed: Jan. 23, 2018.
@article{198-15,
url = {http://sigport.org/198},
author = { },
publisher = {IEEE SigPort},
title = {Object Tracking and Person Re-Identification on Manifolds},
year = {2015} }
TY - EJOUR
T1 - Object Tracking and Person Re-Identification on Manifolds
AU -
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/198
ER -
. (2015). Object Tracking and Person Re-Identification on Manifolds. IEEE SigPort. http://sigport.org/198
, 2015. Object Tracking and Person Re-Identification on Manifolds. Available at: http://sigport.org/198.
. (2015). "Object Tracking and Person Re-Identification on Manifolds." Web.
1. . Object Tracking and Person Re-Identification on Manifolds [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/198

A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts


For the purposes of foreground estimation, the true background model is unavailable in many practical circumstances and needs to be estimated from cluttered image sequences. We propose a sequential technique for static background estimation in such conditions, with low computational and memory requirements. Image sequences are analysed on a block-by-block basis. For each block location a representative set is maintained which contains distinct blocks obtained along its temporal line.

Paper Details

Authors:
Vikas Reddy, Conrad Sanderson, Brian C. Lovell
Submitted On:
23 February 2016 - 1:43pm
Short Link:
Type:

Document Files

cluttered_background_estimation.pdf

(461 downloads)

Keywords

Subscribe

[1] Vikas Reddy, Conrad Sanderson, Brian C. Lovell, "A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/190. Accessed: Jan. 23, 2018.
@article{190-15,
url = {http://sigport.org/190},
author = {Vikas Reddy; Conrad Sanderson; Brian C. Lovell },
publisher = {IEEE SigPort},
title = {A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts},
year = {2015} }
TY - EJOUR
T1 - A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts
AU - Vikas Reddy; Conrad Sanderson; Brian C. Lovell
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/190
ER -
Vikas Reddy, Conrad Sanderson, Brian C. Lovell. (2015). A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts. IEEE SigPort. http://sigport.org/190
Vikas Reddy, Conrad Sanderson, Brian C. Lovell, 2015. A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts. Available at: http://sigport.org/190.
Vikas Reddy, Conrad Sanderson, Brian C. Lovell. (2015). "A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts." Web.
1. Vikas Reddy, Conrad Sanderson, Brian C. Lovell. A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/190

Bags of Affine Subspaces for Robust Object Tracking


object tracking results

We propose an adaptive tracking algorithm where the object is modelled as a continuously updated bag of affine subspaces, with each subspace constructed from the object's appearance over several consecutive frames. In contrast to linear subspaces, affine subspaces explicitly model the origin of subspaces. Furthermore, instead of using a brittle point-to-subspace distance during the search for the object in a new frame, we propose to use a subspace-to-subspace distance by representing candidate image areas also as affine subspaces.

report.pdf

PDF icon report.pdf (665 downloads)

Paper Details

Authors:
Sareh Shirazi, Conrad Sanderson, Chris McCool, Mehrtash Harandi
Submitted On:
23 February 2016 - 1:43pm
Short Link:
Type:

Document Files

report.pdf

(665 downloads)

Keywords

Subscribe

[1] Sareh Shirazi, Conrad Sanderson, Chris McCool, Mehrtash Harandi, "Bags of Affine Subspaces for Robust Object Tracking", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/185. Accessed: Jan. 23, 2018.
@article{185-15,
url = {http://sigport.org/185},
author = {Sareh Shirazi; Conrad Sanderson; Chris McCool; Mehrtash Harandi },
publisher = {IEEE SigPort},
title = {Bags of Affine Subspaces for Robust Object Tracking},
year = {2015} }
TY - EJOUR
T1 - Bags of Affine Subspaces for Robust Object Tracking
AU - Sareh Shirazi; Conrad Sanderson; Chris McCool; Mehrtash Harandi
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/185
ER -
Sareh Shirazi, Conrad Sanderson, Chris McCool, Mehrtash Harandi. (2015). Bags of Affine Subspaces for Robust Object Tracking. IEEE SigPort. http://sigport.org/185
Sareh Shirazi, Conrad Sanderson, Chris McCool, Mehrtash Harandi, 2015. Bags of Affine Subspaces for Robust Object Tracking. Available at: http://sigport.org/185.
Sareh Shirazi, Conrad Sanderson, Chris McCool, Mehrtash Harandi. (2015). "Bags of Affine Subspaces for Robust Object Tracking." Web.
1. Sareh Shirazi, Conrad Sanderson, Chris McCool, Mehrtash Harandi. Bags of Affine Subspaces for Robust Object Tracking [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/185

Pages