• Journal of Digital Contents Society
• /
• v.13 no.2
• /
• pp.255-262
• /
• 2012

Human motion tracking algorithm is receiving attention from many research areas, such as human computer interaction, video conference, surveillance analysis, and game or entertainment applications. Over the last decade, various tracking technologies for each application have been demonstrated and refined among them such of real time computer vision and image processing, advanced man-machine interface, and so on. In this paper, we introduce cost-effective and real-time human motion tracking algorithms based on depth image 3D point matching with a given superellipsoid body representation. The body representative model is made by using parametric volume modeling method based on superellipsoid and consists of 18 articulated joints. For more accurate estimation, we exploit initial inverse kinematic solution with classified body parts' information, and then, the initial pose is modified to more accurate pose by using 3D point matching algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.973-975
• /
• 2016

In this paper, we propose a selective extended Kalman filter based accurate pose estimation of the rigid body using a sensor fusion method. The pose of a rigid body can be estimated roughly by the Gauss-Newton method using the acceleration data and geomagnetic data, which can be refined with vision information and the gyro sensor information. However strong external interference noise makes the rough pose estimation difficult. In this paper, according to the measurement level of the external interference noise, the extended Kalman filter selectively uses mostly vision and gyro sensor information to increase the estimation credibility under strong interference noise environment.

• Journal of Advanced Navigation Technology
• /
• v.16 no.3
• /
• pp.545-552
• /
• 2012

In this paper, we propose Modified Multi CAMShift Algorithm based on Kalman filter and Weighted Search Windows(KWMCAMShift) that extracts skin color area and tracks several human body parts for real-time human tracking system. We propose modified CAMShift algorithm that generates background model, extracts skin area of hands and head, and tracks the body parts. Kalman filter stabilizes tracking search window of skin area due to changing skin area in consecutive frames. Each occlusion areas is avoided by using weighted window of non-search areas and main-search area. And shadows are eliminated from background model and intensity of shadow. The proposed KWMCAMShift algorithm can estimate human pose in real-time and achieves 96.82% accuracy even in the case of occlusions.

• Journal of Animal Environmental Science
• /
• v.8 no.3
• /
• pp.171-176
• /
• 2002

Physical parameters of milk cow were measured to design and build RMS(Robotic Milking System) with a tape-measurer and body parameter measurer. The parameters are very important variables to design an RMS. For the working zone space of an RMS manipulator and the movement blunting of milk cow, an interval frame was installed on the stall bottom, and then cow's behavioral reactions were tested. The results from this study is summarized as follow. 1. On the general physical condition measurement, the maximum, minimum and average body length of cow which is related to the space that the manipulator could work into the RMS were 175cm, 144cm, and 163cm respectively. It appeared that the average distance between bottom and chest was 60cm. 2. The average length between fore teats, fore and hind teats and hind teats were 178mm, 150mm and 95mm respectively. It appeared that the average length between bottom and teat attachments was 544mm, and the average length between fore teats and tail-end was 331mm. 3. Although a cow kept a some extent length between hind legs for milking, it looked a stable pose. However, the cow kept a some extent distance between front legs for milking, it looked a unstable pose. Based on results of this test, an interval frame of stall bottom should be installed around the position which was located at its hind legs.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.187-194
• /
• 2021

A person's behavioral recognition is the recognition of what a person does according to joint movements. To this end, we utilize computer vision tasks that are utilized in image processing. Human behavior recognition is a safety accident response service that combines deep learning and CCTV, and can be applied within the safety management site. Existing studies are relatively lacking in behavioral recognition studies through human joint keypoint extraction by utilizing deep learning. There were also problems that were difficult to manage workers continuously and systematically at safety management sites. In this paper, to address these problems, we propose a method to recognize risk behavior using only joint keypoints and joint motion information. AlphaPose, one of the pose estimation methods, was used to extract joint keypoints in the body part. The extracted joint keypoints were sequentially entered into the Long Short-Term Memory (LSTM) model to be learned with continuous data. After checking the behavioral recognition accuracy, it was confirmed that the accuracy of the "Lying Down" behavioral recognition results was high.

• Journal of the Korean Society of Costume
• /
• v.42
• /
• pp.69-90
• /
• 1999

Mannerism style evolved from the Renaissance style adopting the concept of grace as the ideal beauty, Having its ground on Neoplatonism the main goal of mannerism art was the realization of the invisible beauty over reality. Mannerism style in dress flourished in the sixteenth century court society, when courtly manners and courtly grace became the most important qualities in social relationship. Courtiers thought that courtly grace the ideal of beauty could be realized in the cultured and studied elegance. Mannerism style in dress evolved from the process of transforming and manipulating the Renaissance look for the abstract of beauty. The clothes of Mannerism style were against the natural movement of the human body. There was a tendency of refining and polishing the whole clothing and various technical skills were experim-ented on the mannerism style. The outstanding elements of this tendency can be found in the details like ruffs fathingale padding slashing puffing and etc. Mannerism intended to reconstruct the human body artificially to express courtly grace and novelty. During that process the new pose 'figura serpentinata' which is bizarre convoluted pose with full of flexibility was created. The expression of human body became more slender with elongated legs a torso with a long neck and a tiny head. This tendency of distorting the natural body forms were reflected in the formal characteristics of Mannerism dress style which is geometrical abstr-action unnatural elongation complex disposition and control with perfect ease.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.3
• /
• pp.229-235
• /
• 2011

To make a robust object tracking and identifying system for an intelligent robot and/or home system, heterogeneous sensor fusion between visible ray system and infrared ray system is proposed. The proposed system separates the object by combining the ROI (Region of Interest) estimated from two different images based on a heterogeneous sensor that consolidates the ordinary CCD camera and the IR (Infrared) camera. Human's body and face are detected in both images by using different algorithms, such as histogram, optical-flow, skin-color model and Haar model. Also the pose of human body is estimated from the result of body detection in IR image by using PCA algorithm along with AdaBoost algorithm. Then, the results from each detection algorithm are fused to extract the best detection result. To verify the heterogeneous sensor fusion system, few experiments were done in various environments. From the experimental results, the system seems to have good tracking and identification performance regardless of the environmental changes. The application area of the proposed system is not limited to robot or home system but the surveillance system and military system.

• The Research Journal of the Costume Culture
• /
• v.15 no.3 s.68
• /
• pp.431-445
• /
• 2007

The purpose of this study was to analyze and theorize the characteristics of femme fatale in fashion illustration since 1980. The method of this study was to analyze the documentaries for theoretical studies about femme fatale and the visual characteristics in fashion illustration works since 1980. The results of this study were as follows: Femme fatale expressed in the general realm of art was icon of fatal and seductive eroticism in late 19th century. She is composed of diverse images like mythology, exoticism, fear and sensuality. The characteristics of her image in fashion illustration were expressed into de-body image by union of animal and female body, or machine and female body, duplicity of death and sexuality, sexual decadence or abnormality and powerful masculine taste. First, de-body image by union of animal and female body, or machine and female body was expressed in transformed mythical image or bizarre and demonic image, grotesque image linked by picture of female body and painting of animal image, and cyborg image linked by machine and realistic female body by digital media. Second, duplicity of death and sexuality was expressed in juxtaposition by sexual pose, body and something metaphorical and symbolic depiction and de-constructive depiction of death. Third, sexual decadence or abnormality was expressed in fetishistic style, obscene depiction of cheap and hedonistic sexuality, masochistic depiction like antisocial and diseased sex appeal. Forth, powerful masculine taste was expressed in man's face, body, pose, masculine fashion, man's role related to crime and threatening weapon, etc. As mentioned above, femme fatale in fashion illustration was expressed in diverse images by fashion illustrator's point of view. Although she was originated by men's fantastic vision, she brings a catharsis to human being. And she is also recognized as new paradigm and positive cultural sign in our times.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.586-588
• /
• 2004

Although stable control algorithm has been implemented to the biped robot, the stability is not guaranteed because of encoder errors and/or rigid body elastics. Hence precise body pose estimation is required for more natural and long term walk. Specially pelvis sloping by gravity or uneven ground on landing place are most critical reason for undulated motion. In order to overcome these difficulties an estimation system for foot position and orientation using PSD sensors and Gyro sensors is proposed along with calibration algorithm and experimental verification.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.4
• /
• pp.65-74
• /
• 2010

At the aim of solving the problems appearing in traditional optical motion capturing systems such as the interference among multiple patches and the complexity of sensor and patch allocations, this paper proposes a new motion capturing system which is composed of a single camera and multiple motion sensors. A motion sensor is consisted of an acceleration sensor and a gyro sensor to detect the motion of a patched body and the orientation (roll, pitch, and yaw) of the motion, respectively. Although Image information provides the positions of the patches in 2D, the orientation information of the patch motions acquired by the motion sensors can generate 3D pose of the patches using simple equations. Since the proposed system uses the minimum number of sensors to detect the relative pose of a patch, it is easy to install on a moving body and can be economically used for various applications. The performance and the advantages of the proposed system have been proved by the experiments.