Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth Sensor

Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth Sensor

Segmentation of human bodies in images is useful for a variety of applications, including background substitution, human activity recognition, security, and video surveillance applications. However, human body segmentation has been a challenging problem, due to the complicated shape and motion of a...

Full description

Bibliographic Details
Main Authors: Jonha Lee, Dong-Wook Kim, Chee Sun Won, Seung-Won Jung
Format: Article
Language:English
Published: MDPI AG 2019-01-01
Series:Sensors
Subjects:
depth image
graph cut
human body segmentation
image segmentation
Kinect sensor
skeleton
Online Access:http://www.mdpi.com/1424-8220/19/2/393
id doaj-e6fe43564c0e4e5a8e7f210a4c1838c6
record_format Article
spelling doaj-e6fe43564c0e4e5a8e7f210a4c1838c62020-11-24T23:58:43ZengMDPI AGSensors1424-82202019-01-0119239310.3390/s19020393s19020393Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth SensorJonha Lee0Dong-Wook Kim1Chee Sun Won2Seung-Won Jung3Department of Multimedia Engineering, Dongguk University, Pildong-ro 1gil 30, Jung-gu, Seoul 100-715, KoreaDepartment of Multimedia Engineering, Dongguk University, Pildong-ro 1gil 30, Jung-gu, Seoul 100-715, KoreaDepartment of Electronics and Electrical Engineering, Dongguk University, Pildong-ro 1gil 30, Jung-gu, Seoul 100-715, KoreaDepartment of Multimedia Engineering, Dongguk University, Pildong-ro 1gil 30, Jung-gu, Seoul 100-715, KoreaSegmentation of human bodies in images is useful for a variety of applications, including background substitution, human activity recognition, security, and video surveillance applications. However, human body segmentation has been a challenging problem, due to the complicated shape and motion of a non-rigid human body. Meanwhile, depth sensors with advanced pattern recognition algorithms provide human body skeletons in real time with reasonable accuracy. In this study, we propose an algorithm that projects the human body skeleton from a depth image to a color image, where the human body region is segmented in the color image by using the projected skeleton as a segmentation cue. Experimental results using the Kinect sensor demonstrate that the proposed method provides high quality segmentation results and outperforms the conventional methods.http://www.mdpi.com/1424-8220/19/2/393depth imagegraph cuthuman body segmentationimage segmentationKinect sensorskeleton
collection DOAJ
language English
format Article
sources DOAJ
author Jonha Lee
Dong-Wook Kim
Chee Sun Won
Seung-Won Jung
spellingShingle Jonha Lee
Dong-Wook Kim
Chee Sun Won
Seung-Won Jung
Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth Sensor
Sensors
depth image
graph cut
human body segmentation
image segmentation
Kinect sensor
skeleton
author_facet Jonha Lee
Dong-Wook Kim
Chee Sun Won
Seung-Won Jung
author_sort Jonha Lee
title Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth Sensor
title_short Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth Sensor
title_full Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth Sensor
title_fullStr Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth Sensor
title_full_unstemmed Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth Sensor
title_sort graph cut-based human body segmentation in color images using skeleton information from the depth sensor
publisher MDPI AG
series Sensors
issn 1424-8220
publishDate 2019-01-01
description Segmentation of human bodies in images is useful for a variety of applications, including background substitution, human activity recognition, security, and video surveillance applications. However, human body segmentation has been a challenging problem, due to the complicated shape and motion of a non-rigid human body. Meanwhile, depth sensors with advanced pattern recognition algorithms provide human body skeletons in real time with reasonable accuracy. In this study, we propose an algorithm that projects the human body skeleton from a depth image to a color image, where the human body region is segmented in the color image by using the projected skeleton as a segmentation cue. Experimental results using the Kinect sensor demonstrate that the proposed method provides high quality segmentation results and outperforms the conventional methods.
topic depth image
graph cut
human body segmentation
image segmentation
Kinect sensor
skeleton
url http://www.mdpi.com/1424-8220/19/2/393
work_keys_str_mv AT jonhalee graphcutbasedhumanbodysegmentationincolorimagesusingskeletoninformationfromthedepthsensor
AT dongwookkim graphcutbasedhumanbodysegmentationincolorimagesusingskeletoninformationfromthedepthsensor
AT cheesunwon graphcutbasedhumanbodysegmentationincolorimagesusingskeletoninformationfromthedepthsensor
AT seungwonjung graphcutbasedhumanbodysegmentationincolorimagesusingskeletoninformationfromthedepthsensor
_version_ 1725450062889222144

Similar Items