• Journal of the Korea Society of Computer and Information
• /
• v.20 no.6
• /
• pp.87-97
• /
• 2015

An Aerial video summarization is not only the key to effective browsing video within a limited time, but also an embedded cue to efficiently congregative situation awareness acquired by unmanned aerial vehicle. Different with previous works, we utilize sensor operation mode of unmanned aerial vehicle, which is global, local, and focused surveillance mode in order for accurately summarizing the aerial video considering flight and surveillance/reconnaissance environments. In focused mode, we propose the moving-react tracking method which utilizes the partitioning motion vector and spatiotemporal saliency map to detect and track the interest moving object continuously. In our simulation result, the key frames are correctly detected for aerial video summarization according to the sensor operation mode of aerial vehicle and finally, we verify the efficiency of video summarization using the proposed mothed.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.6
• /
• pp.254-259
• /
• 2013

A newly developed fall recognition algorithm using gravity weighted 3-axis accelerometer data as the input of HMM (Hidden Markov Model) is introduced. Five types of fall feature parameters including the sum vector magnitude(SVM) and a newly-defined gravity-weighted sum vector magnitude(GSVM) are applied to a HMM to evaluate the accuracy of fall recognition. A GSVM parameter shows the best accuracy of falls which is 100% of sensitivity and 97.96% of specificity, and comparing with SVM, the results archive more improved recognition rate, 5.2% of sensitivity and 4.5% of specificity. GSVM shows higher recognition rate than SVM due to expressing falls characteristics well, whereas SVM expresses the only momentum.

• Journal of Sensor Science and Technology
• /
• v.8 no.2
• /
• pp.124-132
• /
• 1999

In this paper, we propose interband vector quantization of remotely sensed satellite image using edge region compensation. This method classifies each pixel vector considering spectral reflection characteristics of satellite image data. For each class, we perform classified intraband VQ and classified interband VQ to remove intraband and interband redundancies, respectively. In edge region case, edge region is compensated using class information of neighboring blocks and gray value of quantized reference band. Then we perform classified interband VQ to remove interband, redundancy using compensated class information, effectively. Experiments on remotely sensed satellite image show that coding efficiency of the proposed method is better than that of the conventional method.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.6 no.1
• /
• pp.57-63
• /
• 2001

The wound rotor type induction motor(WRIM) control system which is widely used in the industry has many maintenance problem because of external resistors and magnetic contactors. In this paper, the simple sensorless vector control algorithm for WRIM is proposed without any additional devices except detecting rotor currents. Because the external resistors are disconnectd and the rotor slip rings are shorten, the power loss due to external resistors is removed and the maintenance problem is improved remarkably. Also, the vector control performance becomes better because the proposed sensorless vector control algorithm does not use the rotor resistance which is usually used to estimate the slip frequency in case of indirect vector control scheme. The proposed algorithm is verified by the digital simulation and the experiment.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.576-578
• /
• 1999

본 연구의 목적은 자계방향 기준 벡터제어 이론에 기초하여 속도 센스리스 벡터제어를 구현하는 것이다. 속도센스리스 벡터제어에서 속도추정 방법은 관측기에서 얻은 상태량을 취하는 MRAS 방법이 제안되고 있지만 이득정수의 조정을 행하여야 하는 결점을 가지고 있다. 본 논문에서는 속도추정은 관측기 이론에 기초하여 2차자속 관측기와 전류센스에서 검출한 전류 값으로 행하는 새로운 속도 추정법을 이용한 제어 알고리즘을 제안한다. 그리고 제안한 방법이 본 연구에 있어서 사용한 자계방향 벡터제어시스템의 실현에 가능성이 있음을 시뮬레이션으로 검토하고 실제로 시스템을 구현하여 센스리스 속도제어를 달성하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.4
• /
• pp.414-421
• /
• 2024

In this paper, we design and verify a system that can detect piping leakage noise in an environment with significant reverberation and reflection using a multi-channel acoustic sensor module as a technology to prevent major plant accidents caused by leakage. Four-channel microphones arranged in a tetrahedron are designed as a single sensor module to measure three-dimensional sound intensity vectors. In an environment with large effects of reverberation and reflection, the measurement error of each sensor module increases on average, so after placing multiple sensor modules in the field, measurement results showing locations with large errors due to effects such as reflection are excluded. Using the intersection between three-dimensional vectors obtained from several pairs of sensor modules, the coordinates where the sound source is located are estimated, and outliers (e.g., positions estimated to be outside the site, positions estimated to be far from the average position) are detected and excluded among the points. For achieving aforementioned goal, an excluding algorithm by deciding the outliers among the estimated positions was proposed. By visualizing the estimated location coordinates of the leakage sound on the site drawing within 1 second, we construct and verify a system that can detect the location of the leakage sound in real time and enable immediate response. This study is expected to contribute to improving accident response capabilities and ensuring safety in large plants.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.808-811
• /
• 2002

The stability for a speed sensorless vector control of an induction machine has been studied. These studies show that the sensorless control is apt to be more unstable than the control with sensor on the variation for stator resistance, rotor resistance and system parameters of the machine. First, this paper investigates the speed characteristics when the inertia, J, changes and the rotor resistance, R$_{r}$ changes respectively for a step change of a speed reference, $\omega$. Then, the new speed estimation algorithms with no effects on the parameters variation of the machine and the system is proposed. The proposed method is to implement the observer using voltage, current and constant of the machine. The results are verified by simulation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.8
• /
• pp.1820-1826
• /
• 2013

Heterogeneous field sensor network between sensor to sensor is designed the CAN method to bus type structure in most using at industry. This Network is supporting a distance vector routing protocol on a characteristic structural a bus type. Also This network support to convert as making separate routing table in heterogeneous network. However distance vector routing protocol make a problem of decrease efficiency because of restriction of network expandability and low transmission process. We propose new CAN routing protocol to support network expandability and high transmission process of industry network. New CAN routing protocol structure addition priority and optional function field based on RIPv2. We established heterogeneous field sensor network, we measure data Throughput(bits/sec) for confirm new CAN routing protocol to increase efficient in industry.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.10 no.4
• /
• pp.78-84
• /
• 1996

In this study, 3-D object recognition and restoration independent of the object translation for automotive kind recognition in parking administration system using an ultrasonic sensor array, neural networks and invariant moments are presented. Using invariant moment vectors of the acquired data 16$\times$8 pixels, 3-D objects could be classified by SCL (Simple Competitive Learning) neural networks. Modified SCL neural networks using the 16$\times$8 low resolution image was used for object restoration of 32$\times$32 high resolution image. Invariant moment vectors kept constant independent of the object translation. The recognition rates for the training and the testing data were 98[%] and 95[%], respectively. The experimental results have shown that ultrasonic sensor array with the neural networks could be applied for the detection of the automobiles and classification of the automotive kind.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.4
• /
• pp.230-237
• /
• 2005

The angle-tracking of maneuvering targets is required to the state estimation and classification of targets in underwater acoustic systems. The Problem of angle-tracking multiple closed and crossing targets has been studied by various authors. Sword et al. Proposed a multiple target an91e-tracking algorithm using angular innovations of the targets during a sampling Period are estimated in the least square sense using the most recent estimate of the sensor output covariance matrix. This algorithm has attractive features of simple structure and avoidance of data association problem. Ryu et al. recently Proposed an effective multiple target angle-tracking algorithm which can obtain the angular innovations of the targets from a signal subspace instead of the sensor output covariance matrix. Hwang et al. improved the computational performance of a multiple target angle-tracking algorithm based on the fact that the steering vector and the noise subspace are orthogonal. These algorithms. however. are ineffective when a subset of the incident sources are coherent. In this Paper, we proposed a new multiple target angle-tracking algorithm for coherent and incoherent sources. The proposed algorithm uses the relationship between source steering vectors and the signal eigenvectors which are multiplied noise covariance matrix. The computer simulation results demonstrate the improved Performance of the Proposed algorithm.