Extraction of Motion Data from Image Sequences to Assist Animators

David Gibson; M. Mirmehdi; Neill Campbell; Thomas B.; Colin Dalton; Thomas Barry T.

Extraction of Motion Data from Image Sequences to Assist Animators

David Gibson, M. Mirmehdi, Neill Campbell, Thomas B., Colin Dalton, Thomas Barry T.

Research output: Contribution to journal › Article (Academic Journal)

Abstract

We describe a system which is designed to assist animators in extracting high-level information from sequences of images. The system is not meant to replace animators, but to be a tool to assist them in creating the first `rough-cut' of a sequence quickly and easily. Using the system, short animations have been created in a very short space of time. We show that the method of principal components analysis followed by a neural network learning phase is capable of motion tracking (even through occlusion), feature-extraction and gait classification. We quantify the results, and demonstrate the system tracking horses, birds and actors in a film. We demonstrate a system that is powerful, flexible and, above all, easy for non-specialists to use.

Translated title of the contribution	Extraction of Motion Data from Image Sequences to Assist Animators
Original language	English
Pages (from-to)	302-311
Journal	Proceedings of the British Machine Vision Conference 2000
Publication status	Published - 2000

Bibliographical note

ISBN: 1901725138
Publisher: BMVA
Name and Venue of Conference: Proceedings of the British Machine Vision Conference 2000
Other identifier: 1000515

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=1000515

Fingerprint Dive into the research topics of 'Extraction of Motion Data from Image Sequences to Assist Animators'. Together they form a unique fingerprint.

Cite this

@article{4bd3fad83f2e40c3b3cbeee3efaf4f28,

title = "Extraction of Motion Data from Image Sequences to Assist Animators",

abstract = "We describe a system which is designed to assist animators in extracting high-level information from sequences of images. The system is not meant to replace animators, but to be a tool to assist them in creating the first `rough-cut' of a sequence quickly and easily. Using the system, short animations have been created in a very short space of time. We show that the method of principal components analysis followed by a neural network learning phase is capable of motion tracking (even through occlusion), feature-extraction and gait classification. We quantify the results, and demonstrate the system tracking horses, birds and actors in a film. We demonstrate a system that is powerful, flexible and, above all, easy for non-specialists to use.",

author = "David Gibson and M. Mirmehdi and Neill Campbell and Thomas B. and Colin Dalton and {Barry T.}, Thomas",

note = "ISBN: 1901725138 Publisher: BMVA Name and Venue of Conference: Proceedings of the British Machine Vision Conference 2000 Other identifier: 1000515",

year = "2000",

language = "English",

pages = "302--311",

journal = "Proceedings of the British Machine Vision Conference 2000",

}

TY - JOUR

T1 - Extraction of Motion Data from Image Sequences to Assist Animators

AU - Gibson, David

AU - Mirmehdi, M.

AU - Campbell, Neill

AU - B., Thomas

AU - Dalton, Colin

AU - Barry T., Thomas

N1 - ISBN: 1901725138 Publisher: BMVA Name and Venue of Conference: Proceedings of the British Machine Vision Conference 2000 Other identifier: 1000515

PY - 2000

Y1 - 2000

N2 - We describe a system which is designed to assist animators in extracting high-level information from sequences of images. The system is not meant to replace animators, but to be a tool to assist them in creating the first `rough-cut' of a sequence quickly and easily. Using the system, short animations have been created in a very short space of time. We show that the method of principal components analysis followed by a neural network learning phase is capable of motion tracking (even through occlusion), feature-extraction and gait classification. We quantify the results, and demonstrate the system tracking horses, birds and actors in a film. 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 animators in extracting high-level information from sequences of images. The system is not meant to replace animators, but to be a tool to assist them in creating the first `rough-cut' of a sequence quickly and easily. Using the system, short animations have been created in a very short space of time. We show that the method of principal components analysis followed by a neural network learning phase is capable of motion tracking (even through occlusion), feature-extraction and gait classification. We quantify the results, and demonstrate the system tracking horses, birds and actors in a film. We demonstrate a system that is powerful, flexible and, above all, easy for non-specialists to use.

M3 - Article (Academic Journal)

SP - 302

EP - 311

JO - Proceedings of the British Machine Vision Conference 2000

JF - Proceedings of the British Machine Vision Conference 2000

ER -