• Journal of Platform Technology
• /
• v.6 no.4
• /
• pp.18-25
• /
• 2018

This paper describes a real-time human and robot tracking method in Intelligent Space with multi-camera networks. The proposed method detects candidates for humans and robots by using the histogram of oriented gradients (HOG) feature in an image. To classify humans and robots from the candidates in real time, we apply cascaded structure to constructing a strong classifier which consists of many weak classifiers as follows: a linear support vector machine (SVM) and a radial-basis function (RBF) SVM. By using the multiple view geometry, the method estimates the 3D position of humans and robots from their 2D coordinates on image coordinate system, and tracks their positions by using stochastic approach. To test the performance of the method, humans and robots are asked to move according to given rectangular and circular paths. Experimental results show that the proposed method is able to reduce the localization error and be good for a practical application of human-centered services in the Intelligent Space.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.657-664
• /
• 2003

Reliable tracking of moving humans is essential to motion estimation, video surveillance and human-computer interface. This paper presents a new approach to human motion tracking that combines appearance-based and model-based techniques. Monocular color video is processed at both pixel level and object level. At the pixel level, a Gaussian mixture model is used to train and classily individual pixel colors. At the object level, a 3D human body model projected on a 2D image plane is used to fit the image data. Our method does not use inverse kinematics due to the singularity problem. While many others use stochastic sampling for model-based motion tracking, our method is purely dependent on nonlinear programming. We convert the human motion tracking problem into a nonlinear programming problem. A cost function for parameter optimization is used to estimate the degree of the overlapping between the foreground input image silhouette and a projected 3D model body silhouette. The overlapping is computed using computational geometry by converting a set of pixels from the image domain to a polygon in the real projection plane domain. Our method is used to recognize various human motions. Motion tracking results from video sequences are very encouraging.

• 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.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.3
• /
• pp.51-57
• /
• 2007

Without human dynamics effects, the manually operated target tracking system has poor performance or instability in real environments. The tracking system is invalid when a human is added to the control loop as a real time delay, because input signals are generated by human operator to reduce the errors between target and gun. In this paper, we consider the human operator as a part of controller and modeling the human operator as a first-order model to generate the intentional force. But it is known that human modeling is not easy because of disturbance or noise of the vehicle while moving for the target. We performed a variety of experiments with real plant to identify the model's parameters and verify the proposed operator model's efficiency.

• 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 Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.42-45
• /
• 2010

This paper proposes an intelligent video surveillance system for human object tracking. The proposed system integrates the object extraction, human object recognition, face detection, and camera control. First, the object in the video signals is extracted using the background subtraction. Then, the object region is examined whether it is human or not. For this recognition, the region-based shape descriptor, angular radial transform (ART) in MPEG-7, is used to learn and train the shapes of human bodies. When it is decided that the object is human or something to be investigated, the face region is detected. Finally, the face or object region is tracked in the video, and the pan/tilt/zoom (PTZ) controllable camera tracks the moving object with the motion information of the object. This paper performs the simulation with the real CCTV cameras and their communication protocol. According to the experiments, the proposed system is able to track the moving object(human) automatically not only in the image domain but also in the real 3-D space. The proposed system reduces the human supervisors and improves the surveillance efficiency with the computer vision techniques.

• Journal of Korea Multimedia Society
• /
• v.12 no.12
• /
• pp.1728-1735
• /
• 2009

Human action tracking plays an important place in human-computer-interaction, human action tracking is a challenging task because of the exponentially increased computational complexity in terms of the degrees of freedom of the object and the severe image ambiguities incurred by frequent self-occlusions. In this paper, we will propose a novel method to track human action, in our technique, a dynamic background estimation algorithm will be applied firstly. Based on the estimated background, we then extract the human object from the video sequence, and the skeletonization method and Hough transform method will be used to detect the main structure of human body and each part rotation angle. The calculated rotation angles will be used to control a crane in the port, thus we can just control the container crane by using signalman body. And the experimental results can show that our proposed method can get a preferable result than the conventional methods such as: MIT, JPF or MFMC.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.761-765
• /
• 1997

Our study of rider's postulator stability and tracking control on a unicycle began form the observation of a human riding. The system including unicycle and human operationg his unicycle is a fuzzy intelligent biomechanical model on basis of instinct and intuition search mechanisms. We proposed a robotic unicycle with one wheel and one body as a basic mode and derived equation of motion to this model. Our works is in making out fuzzy look-up table to control robotic unicycle. Fuzzy look-up table were determined for staight line and curve under reasonable inference emulating human's instinct and intuition riding a unicyale. Simulation results show that postulator stability and tracking control on both straight line and curve were successful by using proposed each fuzzy look-up table.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.4
• /
• pp.834-848
• /
• 2013

To effectively use these functions many kinds of human-phone interface are used such as touch, voice, and gesture. However, the most important touch interface cannot be used in case of hand disabled person or busy both hands. Although eye tracking is a superb human-computer interface method, it has not been applied to smartphones because of the small screen size, the frequently changing geometric position between the user's face and phone screen, and the low resolution of the frontal cameras. In this paper, a new eye tracking method is proposed to act as a smartphone user interface. To maximize eye image resolution, a zoom lens and three infrared LEDs are adopted. Our proposed method has following novelties. Firstly, appropriate camera specification and image resolution are analyzed in order to smartphone based gaze tracking method. Secondly, facial movement is allowable in case of one eye region is included in image. Thirdly, the proposed method can be operated in case of both landscape and portrait screen modes. Fourthly, only two LED reflective positions are used in order to calculate gaze position on the basis of 2D geometric relation between reflective rectangle and screen. Fifthly, a prototype mock-up design module is made in order to confirm feasibility for applying to actual smart-phone. Experimental results showed that the gaze estimation error was about 31 pixels at a screen resolution of $480{\times}800$ and the average hit ratio of a $5{\times}4$ icon grid was 94.6%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.3
• /
• pp.202-208
• /
• 2011

Recently the technologies that control the computer system through human computer interaction(HCI) have been widely studied. Their applications usually involve the methods that locate user's positions via face detection and recognize user's gestures, but face detection performance is not good enough. In case that the applications do not locate user's position stably, user interface performance, such as gesture recognition, is significantly decreased. In this paper we propose a new stable face detection algorithm using skin color detection and cumulative distribution of face detection results, whose effectiveness was verified by experiments. The propsed algorithm can be applicable in the area of human tracking that uses correspondence matrix analysis.