• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.12
• /
• pp.3315-3337
• /
• 2012

Crowded scenes analysis is a challenging topic in computer vision field. How to detect diverse motion patterns in crowded scenarios from videos is the critical yet hard part of this problem. In this paper, we propose a novel approach to mining motion patterns by utilizing motion information during both long-term period and short interval simultaneously. To capture long-term motions effectively, we introduce Motion History Image (MHI) representation to access to the global perspective about the crowd motion. The combination of MHI and optical flow, which is used to get instant motion information, gives rise to discriminative spatial-temporal motion features. Benefitting from the robustness and efficiency of the novel motion representation, the following motion pattern mining is implemented in a completely unsupervised way. The motion vectors are clustered hierarchically through automatic hierarchical clustering algorithm building on the basis of graphic model. This method overcomes the instability of optical flow in dealing with time continuity in crowded scenes. The results of clustering reveal the situations of motion pattern distribution in current crowded videos. To validate the performance of the proposed approach, we conduct experimental evaluations on some challenging videos including vehicles and pedestrians. The reliable detection results demonstrate the effectiveness of our approach.

• Progress in Medical Physics
• /
• v.27 no.3
• /
• pp.117-124
• /
• 2016

Intrafractional motion of patients, such as respiratory motion during radiation treatment, is an important issue in image-guided radiotherapy. The accuracy of the radiation treatment decreases as the motion range increases. We developed a control system for a robotic patient immobilization system that enables to reduce the range of tumor motion by compensating the tumor motion. Fusion technology, combining robotics and mechatronics, was developed and applied in this study. First, a small-sized prototype was established for use with an industrial miniature robot. The patient immobilization system consisted of an optical tracking system, a robotic couch, a robot controller, and a control program for managing the system components. A multi speed and position control mechanism with three degrees of freedom was designed. The parameters for operating the control system, such as the coordinate transformation parameters and calibration parameters, were measured and evaluated for a prototype device. After developing the control system using the prototype device, a feasibility test on a full-scale patient immobilization system was performed, using a large industrial robot and couch. The performances of both the prototype device and the realistic device were evaluated using a respiratory motion phantom, for several patterns of respiratory motion. For all patterns of motion, the root mean squared error of the corresponding detected motion trajectories were reduced by more than 40%. The proposed system improves the accuracy of the radiation dose delivered to the target and reduces the unwanted irradiation of normal tissue.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.5
• /
• pp.467-474
• /
• 2001

When user wants to animate more than one character, some unexpected motion animation like a collision between characters may occur. Therefore, this problem must be resolved using a proper control mechanism. Therefore, this problem must be resolved using a proper control mechanism. This paper proposes an agent-based system that controls the motion animation of the character for representing animation scenario reflecting user\`s intention. This system provides a method that coordinates a type of motion and avoids collision between characters according to the moving path of a character in three-dimensional space. Agent communicates with others for motion synchronization. Agent is extended into several intelligent agents that coordinate character\`s motion. Agent system enables not only an intended motion animation, but also the scheduling of motion to an entire character animation. It designs automata model using Petri-net analysis tool for the agent\`s interaction as a method that passes the agent\`s information and infers the current state of agents. We implement this agent system to control the motion of character using agent technology and show an example of controlling the motion of human character model to prove the possiblity of motion control.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.11
• /
• pp.1130-1136
• /
• 2009

A new control algorithm for the yaw motion control of a unicycle robot has been proposed in this paper. With the increase of life quality, there are various transportation systems such as segway and unicycle robot which provide not only transportation but also amusement. In most of the unicycle robots share the same technology in that the directions of roll and pitch are controlled by the balance controllers, allowing the robots to maintain balance for a long period by continuously moving forward and backward. However, one disadvantage of this technology is that it cannot provide the capability to the robots to avoid obstacles in their path way. This research focuses to provide the yawing function to the unicycle robot and to control the yaw motion to avoid the obstacles as desired. For the control of yawing motion, the yaw angle is adjusted to the inertia generated by the velocity and torque of a yawing motor which is installed in the center axes of the unicycle robot to keep the lateral control simple. Through the real experiments, the effective and robustness of the yawing control algorithm has been demonstrated.

• Proceedings of the KIPE Conference
• /
• 2001.12a
• /
• pp.23-26
• /
• 2001

This paper presents a digital motion control system for Reluctance Synchronous Motor (RSM) drives with direct torque control (DTC). The system consists of stator flux observer, torque estimator: two hysteresis band controllers, an optimal switching look-up table, IGBT voltage source inverter(VSI), and TMS320C31 DSP controller by using fully integrated control software. The stator flux observer is based on the combined voltage and current model with stator flux feedback adaptive control of which inputs are current, voltage and actual rotor angle for wide speed range. In order to prove the suggested motion control algorithm, There are some simulation and testing at actual experimental system. The developed digitally high-performance motion control system are shown a good motion control response characteristic results and high performance features using 1.0Kw RSM.

• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.251-255
• /
• 1986

Some missiles using canards as control device adopt rollerons to reduce roll motion due to aerodynamically induced rolling moment. This paper presents equations of motion of these missiles including the gyroscopic effect of rolleron rotors. Some linearized analysis results and simulation results are shown to coincide, thus some characteristic motions of missiles and rollerons can be seen.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.5
• /
• pp.434-441
• /
• 2004

In this paper, an exoskeleton-type motion capturing system is designed and implemented. The device is designed to have 12 degree-of-freedom entirely to represent human arm motions. Forward and inverse kinematics of the device are analyzed to make sure of its singular positions. With the designed model parameters, simulation studies are conducted to verify that the designed motion capturing system is effective to represent human motions within the workspace. As a counterpart of the exoskeleton system, a mobile robot is built to follow human motion restrictively. Experimental studies of teleoperation from the exoskeleton device to control the mobile robot are carried out to show feasible application of wireless man-machine interface.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1808-1813
• /
• 2004

Recognition of human motions using their 2-D images has various applications. An eigenspace method is employed in this paper for representing and recognizing human motions. An eigenspace is created from the images taken by multiple cameras that surround a human in motion. Image streams obtained from the cameras compose the same number of curved lines in the eigenspace and they are used for recognizing a human motion in a video image. Performance of the proposed technique is shown experimentally.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.246-249
• /
• 2005

For agile production methods, manufacturing system requires development of a motion controller which has flexibility of general-purpose motion controller and productivity of specialized-purpose one. In this study we developed a flowchart programming development environment for motion language and process control. A controller designed on this environment can be used as a general purpose motion controller of a machine tool. Design of control programming based on a flowchart has the advantages such as reducing the programming time and improving intuitiveness of interface for users. We created the flowchart-based platform using OPC communication

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.05a
• /
• pp.842-847
• /
• 2002

One of the challenging problems with bicycle simulators is to deal with the inherent unstable bicycle dynamics that is coupled with rider's motion. For the bicycle dynamics calculation and the real time simulation, it is necessary to identify the control inputs from the rider as well as the virtual environments. The six control forces of the Stewart platform-based motion system are used for estimation of the rider's action force, which is one of the important control inputs, but of which the direct measurement is impractical. For the effective estimation of the rider's action force, the dynamics model of the motion system is derived incorporated with both analytical and experimental methods and the sliding mode controller with perturbation estimation is developed.