IEICE TRANSACTIONS on Fundamentals
Using Super-Pixels and Human Probability Map for Automatic Human Subject Segmentation
Summary :
Human body segmentation has many applications in a wide variety of image processing tasks, from intelligent vehicles to entertainment. A substantial amount of research has been done in the field of segmentation and it is still one of the active research areas, resulting in introduction of many innovative methods in literature. Still, until today, a method that can overcome the human segmentation problems and adapt itself to different kinds of situations, has not been introduced. Many of methods today try to use the graph-cut framework to solve the segmentation problem. Although powerful, these methods rely on a distance penalty term (intensity difference or RGB color distance). This term does not always lead to a good separation between two regions. For example, if two regions are close in color, even if they belong to two different objects, they will be grouped together, which is not acceptable. Also, if one object has multiple parts with different colors, e.g. humans wear various clothes with different colors and patterns, each part will be segmented separately. Although this can be overcome by multiple inputs from user, the inherent problem would not be solved. In this paper, we have considered solving the problem by making use of a human probability map, super-pixels and Grab-cut framework. Using this map relives us from the need for matching the model to the actual body, thus helps to improve the segmentation accuracy. As a result, not only the accuracy has improved, but also it also became comparable to the state-of-the-art interactive methods.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E99-A No.5 pp.943-953
- Publication Date
- 2016/05/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E99.A.943
- Type of Manuscript
- PAPER
- Category
- Image
Authors
Esmaeil POURJAM
Nagoya University
Daisuke DEGUCHI
Nagoya University
Ichiro IDE
Nagoya University
Hiroshi MURASE
Nagoya University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Esmaeil POURJAM, Daisuke DEGUCHI, Ichiro IDE, Hiroshi MURASE, "Using Super-Pixels and Human Probability Map for Automatic Human Subject Segmentation" in IEICE TRANSACTIONS on Fundamentals,
vol. E99-A, no. 5, pp. 943-953, May 2016, doi: 10.1587/transfun.E99.A.943.
Abstract: Human body segmentation has many applications in a wide variety of image processing tasks, from intelligent vehicles to entertainment. A substantial amount of research has been done in the field of segmentation and it is still one of the active research areas, resulting in introduction of many innovative methods in literature. Still, until today, a method that can overcome the human segmentation problems and adapt itself to different kinds of situations, has not been introduced. Many of methods today try to use the graph-cut framework to solve the segmentation problem. Although powerful, these methods rely on a distance penalty term (intensity difference or RGB color distance). This term does not always lead to a good separation between two regions. For example, if two regions are close in color, even if they belong to two different objects, they will be grouped together, which is not acceptable. Also, if one object has multiple parts with different colors, e.g. humans wear various clothes with different colors and patterns, each part will be segmented separately. Although this can be overcome by multiple inputs from user, the inherent problem would not be solved. In this paper, we have considered solving the problem by making use of a human probability map, super-pixels and Grab-cut framework. Using this map relives us from the need for matching the model to the actual body, thus helps to improve the segmentation accuracy. As a result, not only the accuracy has improved, but also it also became comparable to the state-of-the-art interactive methods.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E99.A.943/_p
Copy
@ARTICLE{e99-a_5_943,
author={Esmaeil POURJAM, Daisuke DEGUCHI, Ichiro IDE, Hiroshi MURASE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Using Super-Pixels and Human Probability Map for Automatic Human Subject Segmentation},
year={2016},
volume={E99-A},
number={5},
pages={943-953},
abstract={Human body segmentation has many applications in a wide variety of image processing tasks, from intelligent vehicles to entertainment. A substantial amount of research has been done in the field of segmentation and it is still one of the active research areas, resulting in introduction of many innovative methods in literature. Still, until today, a method that can overcome the human segmentation problems and adapt itself to different kinds of situations, has not been introduced. Many of methods today try to use the graph-cut framework to solve the segmentation problem. Although powerful, these methods rely on a distance penalty term (intensity difference or RGB color distance). This term does not always lead to a good separation between two regions. For example, if two regions are close in color, even if they belong to two different objects, they will be grouped together, which is not acceptable. Also, if one object has multiple parts with different colors, e.g. humans wear various clothes with different colors and patterns, each part will be segmented separately. Although this can be overcome by multiple inputs from user, the inherent problem would not be solved. In this paper, we have considered solving the problem by making use of a human probability map, super-pixels and Grab-cut framework. Using this map relives us from the need for matching the model to the actual body, thus helps to improve the segmentation accuracy. As a result, not only the accuracy has improved, but also it also became comparable to the state-of-the-art interactive methods.},
keywords={},
doi={10.1587/transfun.E99.A.943},
ISSN={1745-1337},
month={May},}
Copy
TY - JOUR
TI - Using Super-Pixels and Human Probability Map for Automatic Human Subject Segmentation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 943
EP - 953
AU - Esmaeil POURJAM
AU - Daisuke DEGUCHI
AU - Ichiro IDE
AU - Hiroshi MURASE
PY - 2016
DO - 10.1587/transfun.E99.A.943
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E99-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 2016
AB - Human body segmentation has many applications in a wide variety of image processing tasks, from intelligent vehicles to entertainment. A substantial amount of research has been done in the field of segmentation and it is still one of the active research areas, resulting in introduction of many innovative methods in literature. Still, until today, a method that can overcome the human segmentation problems and adapt itself to different kinds of situations, has not been introduced. Many of methods today try to use the graph-cut framework to solve the segmentation problem. Although powerful, these methods rely on a distance penalty term (intensity difference or RGB color distance). This term does not always lead to a good separation between two regions. For example, if two regions are close in color, even if they belong to two different objects, they will be grouped together, which is not acceptable. Also, if one object has multiple parts with different colors, e.g. humans wear various clothes with different colors and patterns, each part will be segmented separately. Although this can be overcome by multiple inputs from user, the inherent problem would not be solved. In this paper, we have considered solving the problem by making use of a human probability map, super-pixels and Grab-cut framework. Using this map relives us from the need for matching the model to the actual body, thus helps to improve the segmentation accuracy. As a result, not only the accuracy has improved, but also it also became comparable to the state-of-the-art interactive methods.
ER -
English
