• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2839-2852
• /
• 2013

Context-awareness is an essential part of ubiquitous computing, and over the past decade video based activity recognition (VAR) has emerged as an important component to identify user's context for automatic service delivery in context-aware applications. The accuracy of VAR significantly depends on the performance of the employed human body segmentation algorithm. Previous human body segmentation algorithms often engage modeling of the human body that normally requires bulky amount of training data and cannot competently handle changes over time. Recently, active contours have emerged as a successful segmentation technique in still images. In this paper, an active contour model with the integration of Chan Vese (CV) energy and Bhattacharya distance functions are adapted for automatic human body segmentation using depth cameras for VAR. The proposed technique not only outperforms existing segmentation methods in normal scenarios but it is also more robust to noise. Moreover, it is unsupervised, i.e., no prior human body model is needed. The performance of the proposed segmentation technique is compared against conventional CV Active Contour (AC) model using a depth-camera and obtained much better performance over it.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2006.11a
• /
• pp.420-425
• /
• 2006

Measurements results of flow-structure-interactions (FSI) of an air-lifted body are introduced. An adaptive stereoscopic-PIV system has been constructed for the measurements of the air-lifted body. The measurement system consists of two cameras and optical sensors. The flow characteristics around a lifted cylinder body(length=60mmm, diameter =10mm, polystyrene) in the swirling flow field in a vertical pipe (length=600mm, inner diameter=) are investigated by the use of the constructed adaptive stereoscopic-PIV system. The images of the two cameras were used for the analysis of the flow fields around the floated cylinder body. The images of the cylinder body captured by the two cameras were used for the analyses of its motions. Four optical sensors (LED) were used for the detection of the postures of the freely-lifted cylinder body. The FSI analyses have been carried out to find the physical conditions at which the floating body is stabilized with its upright postures.

• Korean Journal of Community Nutrition
• /
• v.16 no.4
• /
• pp.454-465
• /
• 2011

This study was carried out to investigate distribution of obesity, body composition, weight control and dietary behaviors, and to analyze the relationship between Body Mass Index (BMI) and physical characteristics, body composition and dietary behaviors by anthropmetric measurement and questionnaires. The 199 study subjects were divided into 3 age groups; 30's (78), 40's (77) and 50's (44) and 4 groups by BMI ; under weight (4.5%), normal (51.3%), over weight (26.1%) and obese (18.1%). Amount of skeletal muscle, body water, mineral and body fat were significantly increased with BMI. There were especially significant increase skeletal muscle 5.3 kg ($19.1\;{\rightarrow}\;23.5\;kg$), body water 5.3 kg ($26.3\;{\rightarrow}\;31.6\;kg$) and fat 15.2 kg ($11.2\;{\rightarrow}\;26.4\;kg$) from under weight to obesity group, respectively (p < 0.01). There were significantly decreased in the ratio of body water (10.3%), protein (2.7%) and body mineral (1.1%) from under weight to obesity, but significant increase 14.1% in body fat (p < 0.001). About 44.4% of under weight group and 40.1% of normal group and 50% of over and obesity group had dissatisfaction on their body images. Most of the women were concerned about their body images and experienced weight control. Dietary behavior scores of obesity group were significant lower than the other four groups (p < 0.001). There were significant positive correlation between BMI and body water (r = 0.62), protein (r = 0.52), skeletal muscle (r = 0.63), body fat (r = 0.91) and WH ratio (r = 0.91), respectively (p < 0.001). The correlation between BMI and body fat and WH ratio were much higher than the correlation between weight and fat and WH ratio.

• Journal of Biosystems Engineering
• /
• v.28 no.1
• /
• pp.65-76
• /
• 2003

The analysis of cow body parameters is important to provide some useful information fur cow management and cow evaluation. Present methods give many stresses to cows because they are invasive and constrain cow postures during measurement of body parameters. This study was conducted to develop the stereo vision system fur non-invasive analysis of cow body features. Body feature parameters of 16 heads at two farms(A, B) were measured using scales and nineteen stereo images of them with walking postures were captured under outdoor illumination. In this study, the camera calibration and inverse perspective transformation technique was established fer the stereo vision system. Two calibration results were presented for farm A and fm B, respectively because setup distances from camera to cow were 510 cm at farm A and 630cm at farm B. Calibration error values fer the stereo vision system were within 2 cm for farm A and less than 4.9 cm for farm B. Eleven feature points of cow body were extracted on stereo images interactively and five assistant points were determined by computer program. 3D world coordinates for these 15 points were calculated by computer program and also used for calculation of cow body parameters such as withers height. pelvic arch height. body length. slope body length. chest depth and chest width. Measured errors for body parameters were less than 10% for most cows. For a few cow. measured errors for slope body length and chest width were more than 10% due to searching errors fer their feature points at inside-body positions. Equation for chest girth estimated by chest depth and chest width was presented. Maximum of estimated error fur chest girth was within 10% of real values and mean value of estimated error was 8.2cm. The analysis of cow body parameters using stereo vision system were successful although body shape on the binocular stereo image was distorted due to cow movements.

• Investigative Magnetic Resonance Imaging
• /
• v.9 no.2
• /
• pp.117-133
• /
• 2005

For identifying the pathological findings in magnetic resonance images (MRIs), normal anatomical structures in MRIs should be identified in advance. For studying the anatomical structures in MRIs, a learning tool that includes the followings is necessary. First, MRIs of the entire body; second, horizontal, coronal, and sagittal MRIs; third, segmented images corresponding to the MRIs; fourth, three dimensional (3D) images of the anatomical structures in the MRIs; fifth, software incorporating the MRIs, segmented images, and 3D images. Such a learning tool, however, is hard to obtain. Therefore, in this research, such a learning tool which helps medical students and doctors study the normal anatomical structures in MRIs was made as follows. A healthy young Korean male adult with standard body shape was selected. Six hundred thirteen MRIs of the entire body were scanned (slice thickness 3 mm, interslice gap 0 mm, field of view 480 mm${\times}$480 mm, resolution 512${\times}$512, T1 weighted), and transferred to the personal computer. Sixty anatomical structures in the MRIs were segmented to make segmented images. Coronal, sagittal MRIs and coronal, sagittal segmented images were made. On the basis of the segmented images, forty-seven anatomical structures 3D images were made by manual surface reconstruction method. Software incorporating the MRIs, segmented images, and 3D images was composed. This learning tool that includes horizontal, coronal, sagittal MRIs of the entire body, corresponding segmented images, 3D images of the anatomical structures in the MRIs, and software is expected to help medical students and doctors study the normal anatomical structures in MRIs. This learning tool will be presented worldwide through Internet or CD titles.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.37 no.6
• /
• pp.799-808
• /
• 2013

Previous research reported that body size measured as Body Mass Index (BMI) and body shape measured as waist-hip-ratio (WHR) are two essential factors that form the perceptions of body attractiveness. However, the debate on the importance of BMI versus WHR is ongoing. In addition, scholarly articles, that focus on the role of geographic and cultural variability on perceptions of attractiveness, report inconsistent results. Some suggested that according to globalization and the rise of mass media, geographic variability of perceptions of attractiveness have been altered, while others believed that it remains. This study cross-regionally investigates the role of body size and body shape on the perceptions of female attractiveness. Samples were composed of 107 female college students in Alabama and 107 female college students in California. Participants viewed 27 three-dimensional body scan images of women in three body shapes (pear, hourglass, and rectangle) and three body sizes (underweight, normal weight, and overweight) and rated their perceptions of attractiveness. Images were shown to students in a random order with an overhead projector and Microsoft Office PowerPoint software. A three-way mixed-ANOVA was conducted to analyze the data. The results of the study showed that some regional differences exist between the two sample groups. However, regardless of the regional difference, hourglass shapes were perceived to be the most attractive shape and underweight sizes were perceived to be the most attractive size for both samples.

• The Journal of the Korea Contents Association
• /
• v.11 no.4
• /
• pp.215-224
• /
• 2011

There have been studying many researches to detect human body and to track one with increasing interest on human and computer interaction. In this paper, we propose the algorithm that automatically extracts joints, linked points of human body, using the ratio of human body under single camera and tracks object. The proposed method gets the difference images of the grayscale images and ones of the hue images between input image and background image. Then the proposed method composes the results, splits background and foreground, and extracts objects. Also we standardize the ratio of human body using face' length and the measurement of human body and automatically extract joints of the object using the ratio and the corner points of the silhouette of object. After then, we tract the joints' movement using block-matching algorithm. The proposed method is applied to test video to be acquired through a camera and the result shows that the proposed method automatically extracts joints and effectively tracks the detected joints.

• Journal of Fashion Business
• /
• v.16 no.4
• /
• pp.107-122
• /
• 2012

This thesis takes it an aim to analyze and compare the visual images which results from attaching the voluminous changes of the waist gathering to the basic Sarrouel pants, one of the Islamic costume, and also from the three body type influenced by these changes. The method of the investigation was to select basic designs of the Sarrouel pants, then the three pieces of the experimental clothes called pattern 1(50%), pattern 2(100%), and pattern 3(150%) were made respectively. The 3 types of the adult women were selected as models in a way to represent the S(S1), M(S2), L(S3) the female body indices of the K. S. The models wearing the 3 types of experimental clothes were taken pictures from the front, side and back, which the pictures were used for the evaluations for the visual effects. For the evaluation, the questionaire from 12 to 18, associated with the body types and images respectively were completed and collected in an investigative way. The visual effects by the waist gathering and body size are composed body and image emerged the four factors. Conclusively, the volume of the waist gathering gives a benefit only in terms of the appropriateness in which the voluminous gatherings compensate for the defects of the body type while too much gathering leads to the negative effects. The visual effects from the increased gathering gives the impressions of the more activity with the snugness as it decreases the feminine effects. The evaluation indices like the stiffness or the masculine images might be more or less predominant in this case. This might be ascribed to the fact that the Sarrouel pants were originated from the men's trousers in a real sense.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.4
• /
• pp.259-266
• /
• 2016

Recently, CCTV cameras are emplaced actively to reinforce security and intelligent surveillance systems have been under development for detecting and monitoring of the objects in the video. In this study, we propose a method for detection of upper body in intelligent surveillance system using FCM-based RBFNN classifier realized with the aid of HOG features. Firstly, HOG features that have been originally proposed to detect the pedestrian are adopted to train the unique gradient features about upper body. However, HOG features typically exhibit a very high dimension of which is proportional to the size of the input image, it is necessary to reduce the dimension of inputs of the RBFNN classifier. Thus the well-known PCA algorithm is applied prior to the RBFNN classification step. In the computer simulation experiments, the RBFNN classifier was trained using pre-classified upper body images and non-person images and then the performance of the proposed classifier for upper body detection is evaluated by using test images and video sequences.

• Fashion & Textile Research Journal
• /
• v.7 no.2
• /
• pp.225-230
• /
• 2005

This research was undertaken to compare basic bodice prototypes for Internet shopping customer, and to select a profitable fit vacant space quantity between clothing and body. A total one hundred of eighteen outfits (4 types of pattern ${\times}$ 9 subjects ${\times}$5 body areas) were constructed with basic bodice drafting method of Japan Bunka Women's University according to nine male body types. Fifty-two experts analysis of the different prototypes as five body area and evaluate the most appropriate ease amount and stabilization of the simulation images on the computer. The experiments with automated methods using simulation image are based on AZ program of TORAY, Japan. Data was analyzed using percentiles, frequency and $X^2$. Taken together, the present result of vacant space quantity and stability evaluation through images shows that there is a significant difference in the size variation of the chest circumference, shoulder slope and waist circumference. In case of ease amount, chest area, shoulder slope, waist area and armhole except neckline area were shown more appropriate on the basic bodice pattern without size change. In case of stabilization, the chest area, shoulder slope and armhole except waist area and neckline area was shown the best on the basic bodice pattern without size change. However the waist area was shown on the basic bodice pattern plus 2 cm, neckline was shown more appropriate on the basic bodice pattern plus 1cm.