• Fire Science and Engineering
• /
• v.30 no.6
• /
• pp.92-98
• /
• 2016

This study evaluated thermal image real-time estimation and fire alarm using by a CCD camera, which has been a seamless feature-point analysis method, according to the angle and position and image fusion by a vector coordinate point set-up of equal shape. The system has higher accuracy, fixing data value of temperature sensing and fire image of 0~255, and sensor output-value of 0~5,000. The operation time of a flame specimen within 500 m, 1000 m, and 1500 m from the test report specimen took 7 s, 26 s, and 62 s, respectively, and image creation was proven. A diagnosis of fire accident was designated to 3 steps: Caution/Alarm/Fire. Therefore, a series of process and the transmission of SNS were identified. A light bulb and fluorescent bulb were also tested for a false alarm test, but no false alarm occurred. The possibility that an unwanted alarm will be reduced was verified through a forecast of the fire progress or real-time estimation of a thermal image by the change in the image of a time-based flame and an analysis of the diffusion velocity.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.2E
• /
• pp.58-67
• /
• 1994

Hidden Markov Model (HMM)-based algorithms have been used successfully in many speech recognition systems, especially large vocabulary systems. Although general purpose processors can be employed for the system, they inevitably suffer from the computational complexity and enormous data. Therefore, it is essential for real-time speech recognition to develop specialized hardware to accelerate the recognition steps. This paper concerns with a real-time implementation of an isolated word recognition system based on HMM. The speech recognition system consists of a host computer (PC), a DSP board, and a prototype Viterbi scoring board. The DSP board extracts feature vectors of speech signal. The Viterbi scoring board has been implemented using three field-programmable gate array chips. It employs a hardware-efficient Viterbi scoring architecture and performs the Viterbi algorithm for HMM-based speech recognition. At the clock rate of 10 MHz, the system can update about 100,000 states within a single frame of 10ms.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.158-162
• /
• 1996

본 논문에서는 문자출력이 가능한 무선호출기에 음성인식 기술을 접목한, 특성화된 한 음성인식 시스템에 대하여 설명하고자 한다. 시스템 동작 과정은, 일단 호출자가 음성인식 서버와 접속하게 되면 서버는 호출자의 자연스런 입력음성을 인식, 그 결과를 문장 형태로 피호출자의 호출기 단말기에 출력시키는 방식으로 되어 있다. 본 시스템에서는 통계적 음성인식 기법을 도입하여, 각 단어를 연속 HMM으로 모델링하였다. 가우시안 혼합 확률밀도함수를 사용하는 각 모델은 전통적인 HMM 학습법들 중의 하나인 Baum-Welch 알고리듬에 의해 학습되고 인식시에는 이들에 비터비 빔 탐색을 적용하여 최선의 결과를 얻도록 한다. MFCC와 파워를 혼용한 26 차원 특징벡터를 각 프레임으로부터 추출하여, 최종적으로, 83 개의 도메인 어휘들 및 무음과 같은 특수어휘들에 대한 모델링을 완성하게 된다. 여기에 구문론적 기능과 의미론적 기능을 함께 수행하는 FSN을 결합시켜 자연발화음성에 대한 연속음성인식 시스템을 구성한다. 본문에서는 이상의 사항들 외에도 음성 데이터베이스, 레이블링 등과 갈이 시스템 성능과 직결되는 시스템의 외적 요소들에 대해 고찰하고, 시스템에 구현되어 있는 다양한 특성들에 대해 밝히며, 실험 결과 및 앞으로의 개선 방향 등에 대해 논의하기로 한다.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.4
• /
• pp.21-27
• /
• 2018

In this paper, we propose a real-time interaction method using user's mouth wind in mobile device. In mobile and virtual reality, user interaction technology is important, but various user interface methods is still lacking. Most of the interaction technologies are hand touch screen touch or motion recognition. In this study, we propose an interface technology that can interact with real time using user's mouth wind. The direction of the wind is determined by using the angle and the position between the user and the mobile device, and the size of the wind is calculated by using the magnitude of user's mouth wind. To show the superiority of the proposed technique, we show the result of visualizing the flow of the vector field in real time by integrating the mouth-wind interface into the Navier-Stokes equations. We show the results of the paper on mobile devices, but can be applied in the Agumented reality(AR) and Virtual reality(VR) fields requiring interface technology.

• Journal of Korea Multimedia Society
• /
• v.10 no.3
• /
• pp.391-400
• /
• 2007

According to the recent advances in multimedia computing, storage and searching technology have made large volume of music contents become prevalent. Also there has been increasing needs for the study on efficient categorization and searching technique for music contents management. In this paper, a new classifying method using the local information of music content and music tone feature is proposed. While the conventional classifying algorithms are based on entire information of music content, the algorithm proposed in this paper focuses on only the specific local information, which can drastically reduce the computing time without losing classifying accuracy. In order to improve the classifying accuracy, it uses a new classification feature based on music tone. The proposed method has been implemented as a part of MuSE (Music Search/Classification Engine) which was installed on various systems including commercial PDAs and PCs.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.897-900
• /
• 2007

This paper presents a study on the DSP controller and IGBT inverter driver design for the power-by-wire(PBW) system using BLDC servo motor. This BLDC servo motor system was realized with DSP(Digital Signal Processor) and IGBT inveter module. The PBW system needs speed control of servo motor for linear thrust action. This paper implements a servo controller with vector control and min-max PWM technique. As CPU of controller, TMS320F2812 DSP was adopted because it has PWM(Pulse Width Modulation) waveform generator, A/D(Analog to Digital) converter, SPI( Serial Peripheral Interface) port and many input/output port etc.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.742-749
• /
• 2020

This paper proposes a method for recognizing both phoneme and emotion using a common neural network and a multi-task training method for the common neural network. The common neural network performs the same function for both recognition tasks, which corresponds to the structure of multi-information recognition of human using a single auditory system. The multi-task training conducts a feature modeling that is commonly applicable to multiple information and provides generalized training, which enables to improve the performance by reducing an overfitting occurred in the conventional individual training for each information. A method for increasing phoneme recognition performance is also proposed that applies weight to the phoneme in the multi-task training. When using the same feature vector and neural network, it is confirmed that the proposed common neural network with multi-task training provides higher performance than the individual one trained for each task.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2A
• /
• pp.147-156
• /
• 2004

This paper presents an implementation and performance analysis of an access channel decoder which exploits a diversity gain due to the independent magnitude of received signals energy at each of antenna elements of a smart antenna BTS (Base-station Transceiver Subsystem) operating in CDMA2000 1X signal environment. Proposed access channel decoder consists of a searcher supporting 4 fingers, Walsh demodulator, and demodulator controller. They have been implemented with 5 of 1 million-gate FPGA's (Field Programmable Gate Array) Altera's APEX EP20K1000EBC652 and TMS320C6203 DSP (digital signal processing). The objective of the proposed access channel decoders is to enhance the data retrieval at co]1-site during the access period, for which the optimal weight vector of the smart antenna BTS is not available. Through experimental tests, we confirmed that the proposed access channel decoder exploitng the diversity technique outperforms the conventional one, which is based on a single antenna channel, in terms of detection probability of access probe, access channel failure probability, and $E_{b/}$ $N_{o}$ in Walsh demodulator.r.r.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.15 no.1
• /
• pp.43-51
• /
• 2010

This paper proposes an analysis of voltage delay and compensation for current control in H-Bridge Multi-Level (HBML) inverters for a medium voltage motor drive with vector control. It is shown that the expansion and modularization capability of the HBML inverter is improved in case of using Phase-Shifted Pulse Width Modulation (PSPWM) since individual inverter modules operate more independently. But, the PSPWM of HBML has a phase difference between reference voltage and real voltage, which can cause instability in the current regulator at high speed where the ratio of the sampling frequency to the output frequency is insufficient. This instability of the current regulator is removed by adding a proposed method which compensate a phase difference between reference voltage and real voltage. The proposed method is suitable for HBML inverter controlled by PSPWM with low switching frequency and high speed motor drive. The validity of the proposed method is verified experimentally on 6,600[V] 1,400[kW] induction motor fed by an 13-level HBML inverter.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.116-123
• /
• 2009

Feature point matching, which is finding the corresponding points from two images with different viewpoint, has been used in various vision-based applications and the demand for the real-time operation of the matching is increasing these days. This paper presents a real-time feature point matching method by using a local descriptor derived by Zernike moments. From an input image, we find a set of feature points by using an existing fast corner detection algorithm and compute a local descriptor derived by Zernike moments at each feature point. The local descriptor based on Zernike moments represents the properties of the image patch around the feature points efficiently and is robust to rotation and illumination changes. In order to speed up the computation of Zernike moments, we compute the Zernike basis functions with fixed size in advance and store them in lookup tables. The initial matching results are acquired by an Approximate Nearest Neighbor (ANN) method and false matchings are eliminated by a RANSAC algorithm. In the experiments we confirmed that the proposed method matches the feature points in images with various transformations in real-time and outperforms existing methods.