Visual Extraction of Motion-Based Information from Image Sequences

David Gibson; A. Sanfeliu; Campbell Neill W.; J.J. Villanueva; Colin Dalton; M. Vanrell; Thomas Barry T.; R. Alquezar; T. Huang; J. Serra

Visual Extraction of Motion-Based Information from Image Sequences

David Gibson, A. Sanfeliu, Campbell Neill W., J.J. Villanueva, Colin Dalton, M. Vanrell, Thomas Barry T., R. Alquezar, T. Huang, J. Serra

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

Abstract

We describe a system which is designed to assist in extracting high-level information from sets or sequences of images. We show that the method of principal components analysis followed by a neural network learning phase is capable of feature extraction or motion tracking, even through occlusion. Given a minimal amount of user direction for the learning phase, a wide range of features can be automatically extracted. Features discussed in this paper include information associated with human head motions and a birds wings during take off. We have quantified the results, for instance showing that with only $25$ out of $424$ frames of hand labelled information a system to track a persons nose can be trained almost as accurately as a human attempting the same task. We demonstrate a system that is powerful, flexible and, above all, easy for non-specialists to use.

Translated title of the contribution	Visual Extraction of Motion-Based Information from Image Sequences
Original language	English
Title of host publication	International Conference on Pattern Recognition
Publisher	IEEE Computer Society
Publication status	Published - 2000

Bibliographical note

Other page information: 893-896
Conference Proceedings/Title of Journal: International Conference on Pattern Recognition
Other identifier: 1000514

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=1000514

Handle.net

Persistent link

Cite this

@inproceedings{7255e579945549f7b7d34116ab3df0da,

title = "Visual Extraction of Motion-Based Information from Image Sequences",

abstract = "We describe a system which is designed to assist in extracting high-level information from sets or sequences of images. We show that the method of principal components analysis followed by a neural network learning phase is capable of feature extraction or motion tracking, even through occlusion. Given a minimal amount of user direction for the learning phase, a wide range of features can be automatically extracted. Features discussed in this paper include information associated with human head motions and a birds wings during take off. We have quantified the results, for instance showing that with only $25$ out of $424$ frames of hand labelled information a system to track a persons nose can be trained almost as accurately as a human attempting the same task. We demonstrate a system that is powerful, flexible and, above all, easy for non-specialists to use.",

author = "David Gibson and A. Sanfeliu and {Neill W.}, Campbell and J.J. Villanueva and Colin Dalton and M. Vanrell and {Barry T.}, Thomas and R. Alquezar and T. Huang and J. Serra",

note = "Other page information: 893-896 Conference Proceedings/Title of Journal: International Conference on Pattern Recognition Other identifier: 1000514",

year = "2000",

language = "English",

booktitle = "International Conference on Pattern Recognition",

publisher = "IEEE Computer Society",

address = "United States",

}

TY - GEN

T1 - Visual Extraction of Motion-Based Information from Image Sequences

AU - Gibson, David

AU - Sanfeliu, A.

AU - Neill W., Campbell

AU - Villanueva, J.J.

AU - Dalton, Colin

AU - Vanrell, M.

AU - Barry T., Thomas

AU - Alquezar, R.

AU - Huang, T.

AU - Serra, J.

N1 - Other page information: 893-896 Conference Proceedings/Title of Journal: International Conference on Pattern Recognition Other identifier: 1000514

PY - 2000

Y1 - 2000

N2 - We describe a system which is designed to assist in extracting high-level information from sets or sequences of images. We show that the method of principal components analysis followed by a neural network learning phase is capable of feature extraction or motion tracking, even through occlusion. Given a minimal amount of user direction for the learning phase, a wide range of features can be automatically extracted. Features discussed in this paper include information associated with human head motions and a birds wings during take off. We have quantified the results, for instance showing that with only $25$ out of $424$ frames of hand labelled information a system to track a persons nose can be trained almost as accurately as a human attempting the same task. We demonstrate a system that is powerful, flexible and, above all, easy for non-specialists to use.

AB - We describe a system which is designed to assist in extracting high-level information from sets or sequences of images. We show that the method of principal components analysis followed by a neural network learning phase is capable of feature extraction or motion tracking, even through occlusion. Given a minimal amount of user direction for the learning phase, a wide range of features can be automatically extracted. Features discussed in this paper include information associated with human head motions and a birds wings during take off. We have quantified the results, for instance showing that with only $25$ out of $424$ frames of hand labelled information a system to track a persons nose can be trained almost as accurately as a human attempting the same task. We demonstrate a system that is powerful, flexible and, above all, easy for non-specialists to use.

M3 - Conference Contribution (Conference Proceeding)

BT - International Conference on Pattern Recognition

PB - IEEE Computer Society

ER -

Visual Extraction of Motion-Based Information from Image Sequences

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this