The measurement method of human body bust based on Kinect depth image

2015 ◽  
pp. 231-235
Author(s):  
Y Chong ◽  
Y Wang ◽  
S Pan ◽  
Z Wang ◽  
H Dai ◽  
...  
Keyword(s):  
Human Body ◽  
Measurement Method ◽  
Depth Image

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

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 393 ◽  
Author(s):  
Jonha Lee ◽  
Dong-Wook Kim ◽  
Chee Won ◽  
Seung-Won Jung
Keyword(s):  
Human Body ◽  
Color Image ◽  
Depth Image ◽  
Body Region ◽  
Reasonable Accuracy ◽  
Depth Sensor ◽  
Complicated Shape ◽  
Depth Sensors ◽  
Body Segmentation ◽  
Human Body Segmentation

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.

A Study on Natural Interaction for Human Body Motion Using Depth Image Data

2011 ◽  
Author(s):  
Mohd Kufaisal bin Mohd Sidik ◽  
Mohd Shahrizal bin Sunar ◽  
Ismahafezi bin Ismail ◽  
Mohd Khalid bin Mokhtar ◽  
Normal binti Mat Jusoh
Keyword(s):  
Human Body ◽  
Image Data ◽  
Body Motion ◽  
Depth Image ◽  
Natural Interaction

3D Digitization of Human Body Based on Checkerboard Matching

2013 ◽  
Vol 718-720 ◽  
pp. 1108-1112
Author(s):  
Jian Li ◽  
Cheng Yan Zhang ◽  
Xue Li Xu ◽  
Hai Feng Chen
Keyword(s):  
Feature Extraction ◽  
Body Size ◽  
Human Body ◽  
Measurement Method ◽  
Stereo Matching ◽  
Low Cost ◽  
Size Measurement ◽  
Body Images ◽  
General Application ◽  
3D Digitization

A body-size measurement method based on checkerboard matching is proposed. First, calibrated cameras are used to acquire two body images after projecting chess boards on human body with projector. Then, the parallax of the two images is got by feature extraction and stereo matching. Finally, we can calculate the 3D coordinates of the human body according to the principle of binocular vision to complete the acquisition of body size. The result shows that measurement error is ± 4%. This study can measure automatically and improve precision compared with traditional methods while it has low-cost, simple operation compared with the non-contact measurement. And the results accuracy can meet its general application in practice.

scholarly journals Assessment of method for measuring clo value using human body – Assessment of method for measuring clo value that assumes human body temperature adjustment

2019 ◽  
Vol 111 ◽  
pp. 06050
Author(s):  
Yoshiaki Yamato ◽  
Yoshihito Kurazumi ◽  
Kenta Fukagawa ◽  
Kunihito Tobita ◽  
Emi Kondo
Keyword(s):  
Heat Loss ◽  
Constant Temperature ◽  
Temperature Control ◽  
Human Body ◽  
Measurement Method ◽  
Heat Dissipation ◽  
Control Method ◽  
Thermal Manikin ◽  
Constant Heat ◽  
Human Body Temperature

In order to make it possible to measure the clo value in various postures, we are studying the measurement method using the human body. Our previous researches showed that clo value measured with the human body is less than that measured with a “constant temperature control”-type thermal manikin. In our previous experiments, human body changes its skin temperature in response to the amount of clothing or changes in the temperature to maintain heat loss, while a “constant temperature control”-type thermal manikin changes its heat loss in response to the temperature or amount of clothing. Human body reaction is similar to “constant heat dissipation” -type thermal manikin. In order to improve the clo value measurement method using the human body, clo value of same clothing by thermal manikin which changed control method to “constant temperature” and “constant heat dissipation” were measured. Relational expressions of thermal insulation of clothes measured by different control methods were shown.

scholarly journals A Bayesian Framework for Human Body Pose Tracking from Depth Image Sequences

Sensors ◽  
2010 ◽  
Vol 10 (5) ◽  
pp. 5280-5293 ◽  
Author(s):  
Youding Zhu ◽  
Kikuo Fujimura
Keyword(s):  
Human Body ◽  
Bayesian Framework ◽  
Image Sequences ◽  
Depth Image ◽  
Pose Tracking

scholarly journals Human Height Estimation by Color Deep Learning and Depth 3D Conversion

2020 ◽  
Vol 10 (16) ◽  
pp. 5531
Author(s):  
Dong-seok Lee ◽  
Jong-soo Kim ◽  
Seok Chan Jeong ◽  
Soon-kak Kwon
Keyword(s):  
Deep Learning ◽  
Human Body ◽  
Real World ◽  
Human Head ◽  
Color Images ◽  
Depth Image ◽  
Body Region ◽  
Depth Information ◽  
Current Frame ◽  
Human Height

In this study, an estimation method for human height is proposed using color and depth information. Color images are used for deep learning by mask R-CNN to detect a human body and a human head separately. If color images are not available for extracting the human body region due to low light environment, then the human body region is extracted by comparing between current frame in depth video and a pre-stored background depth image. The topmost point of the human head region is extracted as the top of the head and the bottommost point of the human body region as the bottom of the foot. The depth value of the head top-point is corrected to a pixel value that has high similarity to a neighboring pixel. The position of the body bottom-point is corrected by calculating a depth gradient between vertically adjacent pixels. Two head-top and foot-bottom points are converted into 3D real-world coordinates using depth information. Two real-world coordinates estimate human height by measuring a Euclidean distance. Estimation errors for human height are corrected as the average of accumulated heights. In experiment results, we achieve that the estimated errors of human height with a standing state are 0.7% and 2.2% when the human body region is extracted by mask R-CNN and the background depth image, respectively.

Sparse auto-encoder based feature learning for human body detection in depth image

2015 ◽  
Vol 112 ◽  
pp. 43-52 ◽  
Author(s):  
Song-Zhi Su ◽  
Zhi-Hui Liu ◽  
Su-Ping Xu ◽  
Shao-Zi Li ◽  
Rongrong Ji
Keyword(s):  
Human Body ◽  
Feature Learning ◽  
Depth Image

scholarly journals Multiple Human Body Postures Detection using Kinect

2018 ◽  
Vol 10 (2) ◽  
pp. 528
Author(s):  
Rosdiyana Samad ◽  
Law Wen Yan ◽  
Mahfuzah Mustafa ◽  
Nor Rul Hasma Abdullah ◽  
Dwi Pebrianti
Keyword(s):  
Human Body ◽  
Golden Ratio ◽  
The Body ◽  
Human Detection ◽  
Depth Image ◽  
Body Proportions ◽  
Body Proportion ◽  
Body Postures ◽  
Body Joint ◽  
Average Body

<span lang="EN-US">This paper presents a method to detect multiple human body postures using Kinect sensor. In this study, a combination of shape features and body joint points are used as input features. The Kinect sensor which used infrared camera to produce a depth image is suitable to be used in an environment that has varying lighting conditions. The method for human detection is done by processing the depth image and joint data (skeleton) which able to overcome several problems such as cluttered background, various articulated poses, and change in color and illumination. Then, the body joint coordinates found on the object are used to calculate the body proportion ratio. In the experiment, the average body proportions from three body parts are obtained to verify the suitableness of golden ratio usage in this work. Finally, the measured body proportion is compared with Golden Ratio to determine whether the found object is a real human body or not. This method is tested for various scenarios, where true positive human detection is high for various postures. This method able to detect a human body in low lighting and dark room. The average body proportions obtained from the experiment show that the value is close to the golden ratio value.</span>

Sign in / Sign up

Export Citation Format

Share Document