• 제어로봇시스템학회논문지
• /
• 제19권12호
• /
• pp.1081-1088
• /
• 2013

Hyperspectral cameras acquire reflectance values at many different wavelength bands. Dimensions tend to increase because spectral information is stored in each pixel. Several attempts have been made to reduce dimensional problems such as the feature selection using Adaboost and dimension reduction using the Simulated Annealing technique. We propose a novel material detection method that consists of four steps: feature band selection, feature extraction, SVM (Support Vector Machine) learning, and target and specific region detection. It is a combination of the band ratio method and Simulated Annealing algorithm based on detection rate. The experimental results validate the effectiveness of the proposed feature selection and band ratio method.

• 전기전자학회논문지
• /
• 제18권2호
• /
• pp.234-239
• /
• 2014

This paper proposes a new automatic detection method to inspect mura defects on display film surface using morphological image processing and labeling. This automatic detection method for mura defects on display films comprises 3 phases of preprocessing with morphological image processing, Gabor filtering, and labeling. Since distorted results could be obtained with the presence of non-uniform illumination, preprocessing step reduces illumination components using morphological image processing. In Gabor filtering, mura images are created with binary coded mura components using Gabor filters. Subsequently, labeling is a final phase of finding the mura defect area using the difference between large mura defects and values in the periphery. To evaluate the accuracy of the proposed detection method, detection rate was assessed by applying the method in 200 display film samples. As a result, the detection rate was high at about 95.5%. Moreover, the study was able to acquire reliable results using the Semu index for luminance mura in image quality inspection.

• Journal of Electrical Engineering and Technology
• /
• 제3권2호
• /
• pp.280-284
• /
• 2008

In this paper, a best channel matrix selection scheme(BCMS) is proposed to approximate maximum likelihood(ML) detection for a multiple-input multiple-output system. For a one stage BCMS scheme, one of the transmitted symbols is selected to perform ML detection and the other symbols are detected by zero forcing(ZF). To increase the diversity of the symbols that are detected by ZF, multi-stage BCMS detection scheme is used to further improve the system performance. Simulation results show that the performance of the proposed BCMS scheme can approach that of ML detection with a significant reduction in complexity.

• 반도체디스플레이기술학회지
• /
• 제4권1호
• /
• pp.61-64
• /
• 2005

This study presents a new algorithm to detect the facial feature in a color image entered from the mobile device with complex backgrounds and undefined distance between camera's location and the face. Since skin color model with Hough transformation spent approximately 90$\%$ of running time to extract the fitting ellipse for detection of the facial feature, we have changed the approach to the simple geometric vector operation, called a TS(Triangle-Square) transformation. As the experimental results, this gives benefit of reduced run time. We have similar ratio of face detection to other methods with fast speed enough to be used on real-time identification system in mobile environments.

• 한국전기전자재료학회논문지
• /
• 제29권2호
• /
• pp.125-130
• /
• 2016

In this paper, various heat dissipation designs for a rail anchoring failure detection module were investigated by a thermal flow analysis. For the detection module with the heat dissipation design on the overall housing surface, an average temperature inside the module was lowered by $25^{\circ}C$ when compared to no heat dissipation design. In addition, an internal heat-flow blocking layer and an heat conduction layer inserted between the LED module and housing case were effective in reducing the temperature in the rail anchoring failure detection, which has a limited space for installation and little air flow. Especially, the temperature near LED module decreased below $55^{\circ}C$ when the optimal heat dissipation design was applied.

• 반도체디스플레이기술학회지
• /
• 제16권3호
• /
• pp.78-81
• /
• 2017

Augmented Reality(AR) is the core technology of the future knowledge service industry. It is expected to be used in various fields such as medical, education, entertainment etc. Briefly, augmented reality technology is a technique in which a mapped virtual object is augmented when a real-world object is viewed through a device after mapping a real-world object and a virtual object. In this paper, we implemented object detection and tracking system, which is a key technology of augmented reality. To speed up the object tracking, the ORB algorithm, which is a lightweight algorithm compared to the detection algorithm, is applied. In addition, KNN classifier, which is a machine learning algorithm, was applied to detect a single object by learning multiple images.

• 전기학회논문지
• /
• 제67권12호
• /
• pp.1671-1677
• /
• 2018

In this research, the collision detection system based on insect's visual interneuron has been designed. The lobula giant movement detector (LGMD) corresponds to the movement value that increases in direct collision process. If the collision is detected by the LGMD only, it could generate a crash warning even in a non-collision situation, resulting in a lot of false alarms. Directionally sensitive movement detectors (DSMD) are directionally sensitive algorithm based on the elementary movement detectors (EMD) in four directions (up, down, left, and right). In this paper, we propose an efficient VLSI architecture for a realtime collision detection system that is robust to the surrounding environment while improving accuracy. The proposed architecture is synthesized with Dongbu Hightech 110nm standard cell library and shows 333MHz of maximum operating frequency and requires 8400 gates with about 16.5KB of internal memories.

• 전기전자학회논문지
• /
• 제27권4호
• /
• pp.524-530
• /
• 2023

본 논문에서는 경량화된 CNN(Convolutional Neural Network)을 사용하여 CAN(Controller Area Network) 버스 상의 공격을 탐지하는 효율적인 알고리즘을 제안하고, 이를 기반으로 하는 IDS(Intrusion Detection System)를 FPGA로 설계, 구현 및 검증하였다. 제안한 IDS는 기존의 CNN 기반 IDS에 비해 CAN 버스 상의 공격을 프레임 단위로 탐지할 수 있어서 정확하고 신속한 대응이 가능하다. 또한 제안한 IDS는 기존의 CNN 기반 IDS에 비해 컨볼루션 레이어를 하나만 사용하기 때문에 하드웨어를 크게 줄일 수 있다. 시뮬레이션 및 구현 결과는 제안된 IDS가 CAN 버스 상의 다양한 공격을 효과적으로 탐지한다는 것을 보여준다.

• 전기전자학회논문지
• /
• 제24권1호
• /
• pp.132-139
• /
• 2020

공기청정기에 사용되는 이오나이저 모듈은 권선형 transformer를 사용하여 방전전극인 HV+/HV-에 3.5KV/-4KV의 고전압을 공급하여 carbon fiber brush의 전계 방사에 의해 양이온과 음이온을 발생시킨다. 기존의 MCU를 이용한 이오나이저 모듈 회로는 PCB 사이즈가 크고 가격이 비싼 단점이 있고, 기존의 ring oscillator를 이용한 게이트 구동 칩은 oscillation 주기가 PVT(Process-Voltage-Temperature) 변동에 민감하고 HV+와 GND, HV-와 GND의 단락에 의한 fault detection 기능이 없으므로 화재나 감전의 위험이 있다. 그래서 본 논문에서는 7bit binary UP counter를 이용하여 PVT 변동이 있더라도 oscillation 주기를 조절하여 HV+ 전압이 목표 전압에 도달하게 한다. 그리고 HV+와 GND 사이의 단락을 검출하기 위한 HV+ short fault detection 회로, HV-와 GND 사이의 단락을 검출하기 위한 HV- short fault detection 회로와 HV+가 과전압 이상으로 올라가는 것을 검출하기 위한 OVP(Over-Voltage Protection) 회로를 새롭게 제안하였다.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.1-9
• /
• 2022

Ship detection in synthetic aperture radar (SAR) images is an important application in marine monitoring for the military and civilian domains. Over the past decade, object detection has achieved significant progress with the development of convolutional neural networks (CNNs) and lot of labeled databases. However, due to difficulty in collecting and labeling SAR images, it is still a challenging task to solve SAR ship detection CNNs. To overcome the problem, some methods have employed conventional data augmentation techniques such as flipping, cropping, and affine transformation, but it is insufficient to achieve robust performance to handle a wide variety of types of ships. In this paper, we present a novel and effective approach for deep SAR ship detection, that exploits label-rich Electro-Optical (EO) images. The proposed method consists of two components: a data augmentation network and a ship detection network. First, we train the data augmentation network based on conditional generative adversarial network (cGAN), which aims to generate additional SAR images from EO images. Since it is trained using unpaired EO and SAR images, we impose the cycle-consistency loss to preserve the structural information while translating the characteristics of the images. After training the data augmentation network, we leverage the augmented dataset constituted with real and translated SAR images to train the ship detection network. The experimental results include qualitative evaluation of the translated SAR images and the comparison of detection performance of the networks, trained with non-augmented and augmented dataset, which demonstrates the effectiveness of the proposed framework.