Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/420515
Title: Recovering human body configurations using pairwise constraints between parts
Authors: Ren, Xiaofeng;Berg, Alexander C.;Malik, Jitendra
subject: Science & Technology
Year: 2005
Abstract: The goal of this work is to recover human body configurations from static images. Without assuming a priori knowledge of scale, pose or appearance, this problem is extremely challenging and demands the use of all possible sources of information. We develop a framework which can incorporate arbitrary pairwise constraints between body parts, such as scale compatibility, relative position, symmetry of clothing and smooth contour connections between parts. We detect candidate body parts from bottom-up using parallelism, and use various pairwise configuration constraints to assemble them together into body configurations. To find the most probable configuration, we solve an integer quadratic programming problem with a standard technique using linear approximations. Approximate IQP allows us to incorporate much more information than the traditional dynamic programming and remains computationally efficient. 15 hand-labeled images are used to train the low-level part detector and learn the pairwise constraints. We show test results on a variety of images.
Description: 

URI: http://localhost/handle/Hannan/347458
http://localhost/handle/Hannan/420515
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL564139.pdf519.83 kBAdobe PDF
Title: Recovering human body configurations using pairwise constraints between parts
Authors: Ren, Xiaofeng;Berg, Alexander C.;Malik, Jitendra
subject: Science & Technology
Year: 2005
Abstract: The goal of this work is to recover human body configurations from static images. Without assuming a priori knowledge of scale, pose or appearance, this problem is extremely challenging and demands the use of all possible sources of information. We develop a framework which can incorporate arbitrary pairwise constraints between body parts, such as scale compatibility, relative position, symmetry of clothing and smooth contour connections between parts. We detect candidate body parts from bottom-up using parallelism, and use various pairwise configuration constraints to assemble them together into body configurations. To find the most probable configuration, we solve an integer quadratic programming problem with a standard technique using linear approximations. Approximate IQP allows us to incorporate much more information than the traditional dynamic programming and remains computationally efficient. 15 hand-labeled images are used to train the low-level part detector and learn the pairwise constraints. We show test results on a variety of images.
Description: 

URI: http://localhost/handle/Hannan/347458
http://localhost/handle/Hannan/420515
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL564139.pdf519.83 kBAdobe PDF
Title: Recovering human body configurations using pairwise constraints between parts
Authors: Ren, Xiaofeng;Berg, Alexander C.;Malik, Jitendra
subject: Science & Technology
Year: 2005
Abstract: The goal of this work is to recover human body configurations from static images. Without assuming a priori knowledge of scale, pose or appearance, this problem is extremely challenging and demands the use of all possible sources of information. We develop a framework which can incorporate arbitrary pairwise constraints between body parts, such as scale compatibility, relative position, symmetry of clothing and smooth contour connections between parts. We detect candidate body parts from bottom-up using parallelism, and use various pairwise configuration constraints to assemble them together into body configurations. To find the most probable configuration, we solve an integer quadratic programming problem with a standard technique using linear approximations. Approximate IQP allows us to incorporate much more information than the traditional dynamic programming and remains computationally efficient. 15 hand-labeled images are used to train the low-level part detector and learn the pairwise constraints. We show test results on a variety of images.
Description: 

URI: http://localhost/handle/Hannan/347458
http://localhost/handle/Hannan/420515
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL564139.pdf519.83 kBAdobe PDF