Using Bounded Diameter Minimum Spanning Trees to Build Dense Active Appearance Models

被引：6

作者：

Anderson, Robert ^{[1
]}

Stenger, Bjoern ^{[2
]}

Cipolla, Roberto ^{[1
]}

机构：

[1] Univ Cambridge, Dept Engn, Cambridge CB2 1PZ, England

[2] Toshiba Res Europe Ltd, Cambridge CB4 0GZ, England

来源：

INTERNATIONAL JOURNAL OF COMPUTER VISION | 2014年 / 110卷 / 01期

关键词：

Active appearance models; Groupwise registration; Minimum spanning trees; IMAGE REGISTRATION;

D O I：

10.1007/s11263-013-0661-9

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a method for producing dense active appearance models (AAMs), suitable for video-realistic synthesis. To this end we estimate a joint alignment of all training images using a set of pairwise registrations and ensure that these pairwise registrations are only calculated between similar images. This is achieved by defining a graph on the image set whose edge weights correspond to registration errors and computing a bounded diameter minimum spanning tree. Dense optical flow is used to compute pairwise registration and a flow refinement method to align small scale texture is introduced. Further, given the registration of training images, vertices are added to the AAM to minimise the error between the observed flow fields and the flow fields interpolated between the AAM mesh points. We demonstrate a significant improvement in model compactness.

引用

页码：48 / 57

页数：10

共 32 条

[21] Segmentation of cardiac MR volume data using 3D active appearance models
Mitchell, SC
Lelieveldt, BPF
Bosch, JG
van den Geest, R
Reiber, JHC
Sonka, M
MEDICAL IMAGING 2002: IMAGE PROCESSING, VOL 1-3, 2002, 4684 : 433 - 443
[22] Automatic segmentation of the left ventricle in 3D echocardiography using active appearance models
van Stralen, M.
Leung, K. Y. E.
Voormolen, M. M.
de Jong, N.
van der Steen, A. F. W.
Reiber, J. H. C.
Bosch, J. G.
2007 IEEE ULTRASONICS SYMPOSIUM PROCEEDINGS, VOLS 1-6, 2007, : 1480 - +
[23] Automatic Lip Reading in the Dutch Language Using Active Appearance Models on High Speed Recordings
Chitu, Alin Gavril
Driel, Karin
Rothkrantz, Leon J. M.
TEXT, SPEECH AND DIALOGUE, 2010, 6231 : 259 - 266
[24] USING PARTS AND GEOMETRY MODELS TO INITIALISE ACTIVE APPEARANCE MODELS FOR AUTOMATED SEGMENTATION OF 3D MEDICAL IMAGES
Babalola, Kola
Cootes, Tim
2010 7TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, 2010, : 1069 - 1072
[25] UNSUPERVISED CLASSIFICATION OF EXTREME FACIAL EVENTS USING ACTIVE APPEARANCE MODELS TRACKING FOR SIGN LANGUAGE VIDEOS
Antonakos, Epameinondas
Pitsikalis, Vassilis
Rodomagoulakis, Isidoros
Maragos, Petros
2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012), 2012, : 1409 - 1412
[26] Anatomical Landmark Tracking for the Analysis of Animal Locomotion in X-ray Videos Using Active Appearance Models
Haase, Daniel
Denzler, Joachim
IMAGE ANALYSIS: 17TH SCANDINAVIAN CONFERENCE, SCIA 2011, 2011, 6688 : 604 - 615
[27] A novel approach for person authentication and content-based tracking in videos using kernel methods and active appearance models
Kumar, N
Abhishek, V
Gautam, G
2003 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5, CONFERENCE PROCEEDINGS, 2003, : 1384 - 1389
[28] Face recognition across pose using view based active appearance models (VBAAMs) on CMU multi-PIE dataset
Heo, Jingu
Savvides, Marios
COMPUTER VISION SYSTEMS, PROCEEDINGS, 2008, 5008 : 527 - 535
[29] Exploiting visual quasi-periodicity for real-time chewing event detection using active appearance models and support vector machines
Cadavid, Steven
Abdel-Mottaleb, Mohamed
Helal, Abdelsalam
PERSONAL AND UBIQUITOUS COMPUTING, 2012, 16 (06) : 729 - 739
[30] Exploiting visual quasi-periodicity for real-time chewing event detection using active appearance models and support vector machines
Steven Cadavid
Mohamed Abdel-Mottaleb
Abdelsalam Helal
Personal and Ubiquitous Computing, 2012, 16 : 729 - 739

← 1 2 3 4 →