• 한국전자통신학회논문지
• /
• 제9권2호
• /
• pp.149-154
• /
• 2014

실외에서 영상기반의 화재감지는 시간, 날씨 변화에 따른 조도와 그림자 등에 의하여 성능에 영향을 받는다. 본 논문에서는 주간에 화재감지를 위하여 외부조명 변화에 강건한 배경추정 알고리즘과 결합된 연기검출 방법을 제안한다. 혼합 가우스 모델(mixture Gaussian model)을 배경추정에 적용하고 분리된 후보영역에 대하여 연기의 통계적 특성을 적용하여 연기를 검출한다. 주간 야외에서 획득한 영상에 대하여 제안하는 방법이 실외 연기검출에 유용한 것을 확인한다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제28권2호
• /
• pp.285-291
• /
• 2004

Early detection of an internal malfunction of machinery plays a very important part in all condition monitoring programs. Sensors to detect amplitude. velocity and acceleration are widely used in vibration detection and control. Piezoceramic materials are largely used in sensors and actuators for vibration monitoring and control due to their relatively large output from an induced strain and their arguable self powering characteristics. In this paper a cheap and yet reliable sensors/actuators were developed to detect vibration. The results show that low cost PZT can be designed for optimum detection of bearing vibration. This paper presents the experimental results of a number of piezoceramics characteristics in terms of resonant frequencies and variation of PZT constants with temperature.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.437-440
• /
• 2022

현대 사회는 4차 산업 혁명과 IoT 기술 등의 발전으로 영상 처리 분야의 활용이 급증하고 있다. 특히, 에지 검출은 이미지 분류, 객체 검출 등 영상 처리 응용에서 필수적인 전처리 과정으로 여러 분야에서 널리 사용되고 있다. 에지를 검출하기 위한 기존의 방법에는 소벨 필터(Sobel edge detection filter), 로버츠 필터(Roberts edge detection filter), 프리윗 필터(Prewitt edge detection filter), LoG(Laplacian of Gaussian) 등이 있다. 하지만 기존의 방법들은 명암도가 낮은 저조도 환경에서 에지 검출 특성이 다소 미흡한 성능을 보인다는 단점이 있다. 따라서 본 논문에서는 저조도 환경에서도 에지 검출 특성을 높이기 위해 명암도 분석에 기반한 에지 검출 알고리즘을 제안한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.136-138
• /
• 2022

에지 검출은 영상에 대하여 물체의 모양, 위치, 크기 및 재질 등과 같은 정보를 포함하고 있으며, 영상의 특징을 분석할 때 매우 중요한 요소이다. 기존의 에지 검출 방법에는 1차 미분을 이용한 소벨 필터(Sobel edge detection filter), 로버츠 필터(Roberts edge detection filter), 프리윗 필터(Prewitt edge detect ion filter) 등이 있으며, 2차 미분을 이용한 LoG(Laplacian of Gaussian) 등이 있다. 하지만 이러한 방법들은 전체 영상 영역에 대해 고정된 가중치 마스크를 적용하기 때문에 에지 검출 결과가 다소 미흡하다는 단점이 있다. 따라서 본 논문에서는 마스크 내의 중심 화소를 고려하여 에지 검출 특성을 높이는 에지 검출 알고리즘을 제안한다. 또한 제안한 에지 검출 성능을 확인하기 위하여 시뮬레이션 결과 영상을 통해 비교하였다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.265-271
• /
• 2015

This study proposes an algorithm for recognizing apple trees in images and detecting apples to measure the number of apples on the trees. The proposed algorithm explores whether there are apple trees or not based on the number of image block-unit edges, and then it detects apple areas. In order to extract colors appropriate for apple areas, the CIE $L^*a^*b^*$ color space is used. In order to extract apple characteristics strong against illumination changes, modified census transform (MCT) is used. Then, using the AdaBoost learning algorithm, characteristics data on the apples are learned and generated. With the generated data, the detection of apple areas is made. The proposed algorithm has a higher detection rate than existing pixel-based image processing algorithms and minimizes false detection.

• 한국컴퓨터정보학회논문지
• /
• 제22권6호
• /
• pp.131-140
• /
• 2017

As video equipments such as CCTV are used for various purposes in fields of society, digital video data processing technology such as automatic motion detection is essential. In this paper, we proposed and implemented a more stable and accurate motion detection system based on background subtraction technique. We could improve the accuracy and stability of motion detection over existing methods by efficiently processing color information of digital image data. We divided the procedure of color information processing into each components of color information : brightness component, color component of color information and merge them. We can process each component's characteristics with maximum consideration. Our color information processing provides more efficient color information in motion detection than the existing methods. We improved the success rate of motion detection by our background update process that analyzed the characteristics of the moving background in the natural environment and reflected it to the background image.

• 한국식품과학회지
• /
• 제33권2호
• /
• pp.195-199
• /
• 2001

Amylograph를 이용하여 방사선 조사된 검은후추가루의 amylograph characteristics의 변화를 검사하고, 변화된 amylograph characteristics에 의해서 검은후추가루의 검지가 가능한지를 알아보기 위하여 본 실험은 수행되었다. Initial pasting temperatures, maximum viscosity temperatures는 조사선량의 증가에 따른 유의적인 변화가 관찰되지 않았다. Maximum viscosity(P), $93^{\circ}C$ viscosity, $93^{\circ}C$에서 15분 후의 viscosity(H), $45^{\circ}C$ viscosity(C), $45^{\circ}C$에서 30분 후의 viscosity, $45^{\circ}C$에서 60분 후의 viscosity는 조사선량이 증가할수록 감소하는 경향을 보여주었으며, p<0.05의 수준에서 통계적인 유의성이 관찰되었다. 그러나 breakdown(P-H), setback(C-P), 그리고 consistency(C-H)는 조사선량의 증가에 따른 명확한 차이가 관찰되지 않았다. breakdown(P-H)이 0.75, setback(C-P)이 0.88, consistency(C-H)가 0.31의 $R^2$ 값을 보인 것을 제외하고는 모든 amylograph characteristics 의 $R^2$ 값은 0.97 이상의 높은 상관성을 보여 주었다. 따라서 amylograph characteristics에 의해서 검은후추가루의 방사선 조사여부 확인이 가능하였다.

• 한국안전학회지
• /
• 제37권3호
• /
• pp.16-23
• /
• 2022

This study aims to provide a fundamental material for identifying fire and no-fire signals using the detection signal characteristics of IoT-based fire-detection systems. Unlike analog automatic fire-detection equipment, IoT-based fire-detection systems employ wireless digital communication and are connected to a server. If a detection signal exceeds a threshold value, the measured values are saved to a server within seconds. This study was conducted with the detection data saved from seven fire accidents that took place in traditional markets from 2020 to 2021, in addition to 233 fire alarm data that have been saved in the K institute from 2016 to 2020. The saved values demonstrated variable and continuous VC-Signals. Additionally, we discovered that the detection signals of two fire accidents in the K institution had a VC-Signal. In the 233 fire alarms that took place over the span of 5 years, 31% of smoke alarms and 30% of temperature alarms demonstrated a VC-Signal. Therefore, if we selectively recognize VC-Signals as fire signals, we can reduce about 70% of false alarms.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제12권1호
• /
• pp.258-269
• /
• 2020

This paper proposes Snapping Shrimp Noise (SSN) detection and corrupted Orthogonal Frequency Division Multiplexing (OFDM) reconstruction methods to increase Bit Error Rate (BER) performance when OFDM transmitted signal is corrupted by impulsive SSNs in underwater acoustic communications. The proposed detection method utilizes multilayer wavelet packet decomposition for detecting impulsive and irregularly concentrated and SSN energy in specific frequency bands of SSN, and the proposed reconstruction scheme uses iterative decision directed-subcarrier reconstruction to recover corrupted OFDM signals using multiple carrier characteristics. Computer simulations were executed to show receiver operating characteristics curve for the detection performance and BER for the reconstruction. The practical ocean experiment of SAVEX 15 demonstrated that the proposed method exhibits a better detection performance compared with conventional detection method and improves BER by 250% and 1230% for uncoded and coded data, respectively, compared with the conventional reconstruction scheme.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3712-3729
• /
• 2020

Smoke detection is helpful for early fire detection. With its large coverage area and low cost, vision-based smoke detection technology is the main research direction of outdoor smoke detection. We propose a two-stage smoke detection method combined with block Deep Normalization and Convolutional Neural Network (DNCNN) and visual change image. In the first stage, each suspected smoke region is detected from each frame of the images by using block DNCNN. According to the physical characteristics of smoke diffusion, a concept of visual change image is put forward in this paper, which is constructed by the video motion change state of the suspected smoke regions, and can describe the physical diffusion characteristics of smoke in the time and space domains. In the second stage, the Support Vector Machine (SVM) classifier is used to classify the Histogram of Oriented Gradients (HOG) features of visual change images of the suspected smoke regions, in this way to reduce the false alarm caused by the smoke-like objects such as cloud and fog. Simulation experiments are carried out on two public datasets of smoke. Results show that the accuracy and recall rate of smoke detection are high, and the false alarm rate is much lower than that of other comparison methods.