• 한국통신학회논문지
• /
• 제17권7호
• /
• pp.749-757
• /
• 1992

본 논문에서는 maneuvering 하는 이동 표적을 실시간으로 추적하기 위한 보다 효과적인 접근 방법으로, 방대한 입력 표적 영상 데이터를 몇 개의 간단한 상관신호로 변환이 가능한 광 JTC(Joint Trasform Correlator)를 이용하여 실시간 이동 표적추적 시스템을 구현하였다. 실시간 구현을 위해 고해상도를 갖는 LCD(Liquid Crystal Display) 공간 광 변조기를 사용하여 광 JTC를 구성하고, 상관 첨두치의 배경 잡음에 대한 영향을 효과적으로 감소시키기 위한 이진화 방법으로 mean 방법을 사용하였으며, maneuvering하는 이동 표적에 대한 추적 실험을통해 광 JPC를 이용한 실시간 이동 표적 추적 시스템의 구현 가능성을 제시하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.729-733
• /
• 1997

Due to the variety of disturbance, it is not ease to accomplish the in-process detection of weld line with non-contact sensor. To get around this difficulties problem develop an automatic seam tracking weld system, the reliable signal processing algorithm has been recommanded. In this research, laser displacement sensor is applied as a seam finder in the automatic tracking system. The sensor is controlled by a dc servo motor which is mounted at X-Y moving table. X-Y moving table manipulated by an ac servo motor controls the position and velocity of the welding torch. First, X-Y table moves to Y-axis to search the welding joint feature before starting the welding, and welding joint is from the scanning data and weighting factor for each other. Second, weld line is determined using proposed signal processing algorithm during welding process. Form the experimental results, we could see the possibility that laser displacement sensor with procesed algorithm can be used as a seam finder in welding process under the severe noise (spatter,arc light etc.) condition

• The Journal of Korean Physical Therapy
• /
• 제23권3호
• /
• pp.7-12
• /
• 2011

Purpose: The cane is one of the most popular assistive devices for stroke patients. Clinical complaints of sensorimotor functions on the ipsilateral upper limb were appealed in stroke patients who had used a cane for a long period. Therefore, we investigated whether cane usage for a long-term period affected sensoriomotor dysfunctions on the non-affected upper limb, in terms of pain presence, shoulder joint sense, a nine-hole pegboard test, and a tracking task. Methods: We recruited 12 stroke patients, who were divided into the cane-using (CU) group or the non-cane using (NCU) group, according to cane usage experience. We evaluated joint position sense for the integrity of proprioceptive reposition sense in the shoulder joint, used a nine-hole pegboard test for upper limb dexterity evaluation, and a tracking task for visuomotor coordination. Results: Four patients in the CU group had complained of shoulder pain none did in the NCU group. In addition, the CU group showed more reposition errors on the shoulder joint than the NCU group did. In addition, the CU group had more difficulty in proprioceptive sense perception and in performance of the nine-hole pegboard teat and tracking task, compared with the NCU group. Conclusion: Our findings suggest that cane usage for a long period in stroke patients could give rise to trigger joint pain and decrease proprioceptive sense. In addition, complex motor performance in the ipsilateral upper limb could deteriorate. In stroke patients who had used acane for long period, careful observation and proper intervention will be necessary.

• 전자공학회논문지A
• /
• 제33A권10호
• /
• pp.152-159
• /
• 1996

We have designed and implemented an optoelectronic hardware of binary phase extraction joint transform correlator (BPEJTC) which provides higher peak-to-sidelobe ratio than many other versions of JTC that has been published so far and does not produce correlation peaks due to intra-class association, to construct a multi-target tracking system. The digital processing unit controlling the entire system plays the part of modifying and binarizing the joint transform power spectrum (JTPS) and the optical processing unit is mainly used to take fourier transform operations. Some experimental results conducted by designed system along with its architecture showed the processing rate of 6 frames per second, thereby the potential applicability of the proposed system to real-time multitarget tracking system is given.

• Transactions on Control, Automation and Systems Engineering
• /
• 제2권1호
• /
• pp.56-61
• /
• 2000

Majority of industrial robots are controlled by a simple independent joint control of joint actuators rather than complex controllers based on the nonlinear dynamic model of the robot manipulator. In this independent joint control scheme, the performance of actuator control is influenced significantly by the joint disturbance torques including gravity, Coriolis and centrifugal torques, which result in the trajectory tracking error in the joint control system. The control performance of a redundant manipulator under independent joint control can be improved by minimizing this joint disturbance torque in resolving the kinematic redundancy. A 3 DOF planar robot is studied as an example, and the dynamic programming method is used to find the globally optimal joint trajectory that minimize the joint disturbance torque over the entire motion. The resulting solution is compared with the solution obtained by the conventional joint torque minimization, and it is shown that joint disturbance can be reduced using the kinematic redundancy.

• ETRI Journal
• /
• 제35권2호
• /
• pp.356-359
• /
• 2013

We present a method for tracking and interaction based on hybrid sensing for virtual environments. The proposed method is applied to motion tracking of whole areas, including the user's occlusion space, for a high-precision interaction. For real-time motion tracking surrounding a user, we estimate each joint position in the human body using a combination of a depth sensor and a wand-type physical user interface, which is necessary to convert gyroscope and acceleration values into positional data. Additionally, we construct virtual contents and evaluate the validity of results related to hybrid sensing-based whole-body tracking of human motion methods used to compensate for the occluded areas.

• 한국군사과학기술학회지
• /
• 제15권3호
• /
• pp.334-342
• /
• 2012

Data association is important technology which designate final destination in the target tracking. The joint probabilistic data association(JPDA) algorithm provides excellent ability to maintain track on multiple targets. Currently, it is not easily implemented in real time because of track coalescence & switch. The aim of this paper is to develop probabilistic filters that increase JPDA's sensitivity and decrease track coalescence & switch in a cluttered environments.

• 전기학회논문지
• /
• 제63권9호
• /
• pp.1245-1247
• /
• 2014

This paper presents a robust position tracking controller for motor-driven flexible joint manipulators using only the motor angle measurement. The control problem is not easy because the link position is hard to estimate in the presence of parameter uncertainties. The proposed controller consists of a feedback linearization controller (FLC) and two proportional-integral observers (PIOs) that estimate both system states including the link position and an equivalent disturbance for compensating the parameter uncertainties. Comparative computer simulations are conducted to demonstrate the effectiveness of the proposed control algorithm.

• International Journal of Control, Automation, and Systems
• /
• 제6권2호
• /
• pp.223-233
• /
• 2008

A new output feedback controller design approach for flexible-joint (FJ) robots via the observer dynamic surface design technique is presented. The proposed approach only requires the feedback of position states. We first design an observer to estimate the link and actuator velocity information. Then, the link position tracking controller using the observer dynamic surface design procedure is developed. Therefore, the proposed controller can be simpler than the observer backstepping controller. From the Lyapunov stability analysis, it is shown that all signals in a closed-loop system are uniformly ultimately bounded. Finally, the simulation results of a three-link FJ robot are presented to validate the good position tracking performance of the proposed control system.

• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.