• 전기학회논문지P
• /
• 제58권3호
• /
• pp.297-302
• /
• 2009

In this paper, we propose advanced screen detector as a tool for selecting the object for tracking and estimating its distance from a screen using fuzzy logic in vision based pointing device. Our system classifies the line component of the input image into horizontal and vertical lines and applies the fuzzy rule to obtain the best line pair which constitute peripheral framework of the screen. The proposed system improves the detection ratio for detecting the screen in relative to the detector used in the previous works for hand-held type vision based pointing device. Also it allows to detect the screen even though a small part of it may be hidden behind other object.

• 전자공학회논문지A
• /
• 제33A권11호
• /
• pp.60-69
• /
• 1996

In this study, when the coherent detector has been developed and manufactured in the receiver of radar system, we have suggested and realized the 'Frequecny-Feedback correction (FFC)' that extracts its errors affecting the performance of radar, such as amplitude imbalances (k), phase imbalance ($\varphi$) between channels and offset votlages and corrects them to improve radar performances. Applying the FFC proposed, we analyzed sthe properties of the coherent detector and compared its perfomances after and before correction procdure. After the correction sequence, the amplitude imbalance was improved upt o 2dB and the phase imbalance over 9$^{\circ}$. The image rejection ratio (IRR), one of the figures of merit of radar system, was made better above 9 dB after correcting the coherent detector which possessed 23 dB before.

• Journal of electromagnetic engineering and science
• /
• 제15권1호
• /
• pp.59-61
• /
• 2015

A wideband H-band detector operating near 300 GHz has been developed based on SiGe HBT technology. The detector consists of an on-chip antenna and a HBT differential pair for square-law detection. It showed responsivity of more than 1,700 V/W and noise equivalent power (NEP) smaller than $180pW/Hz^{0.5}$ for the measured frequency range of 250-350 GHz. The maximum responsivity and the minimum NEP were 5,155 V/W and $57pW/Hz^{0.5}$, respectively; both were obtained at 330 GHz with DC power dissipation at 9.1 W.

• 한국의학물리학회:학술대회논문집
• /
• 한국의학물리학회 2002년도 Proceedings
• /
• pp.373-375
• /
• 2002

4D CT is a dynamic volume imaging system of moving organs with an image quality comparable to conventional CT, and is realized with continuous and high-speed cone-beam CT. In order to realize 4D CT, we have developed a novel 2D detector on the basis of the present CT technology, and mounted it on the gantry frame of the state-of-the-art CT-scanner. In the present report we describe the design of the first model of 4D CT-scanner as well as the early results of performance test. The x-ray detector for the 4D CT-scanner is a discrete pixel detector in which pixel data are measured by an independent detector element. The numbers of elements are 912 (channels) ${\times}$ 256 (segments) and the element size is approximately 1mm ${\times}$ 1mm. Data sampling rate is 900views(frames)/sec, and dynamic range of A/D converter is 16bits. The rotation speed of the gantry is l.0sec/rotation. Data transfer system between rotating and stationary parts in the gantry consists of laser diode and photodiode pairs, and achieves net transfer speed of 5Gbps. Volume data of 512${\times}$512${\times}$256 voxels are reconstructed with FDK algorithm by parallel use of 128 microprocessors. Normal volunteers and several phantoms were scanned with the scanner to demonstrate high image quality.

• 대한의용생체공학회:의공학회지
• /
• 제26권1호
• /
• pp.43-47
• /
• 2005

We have developed a small bore x-ray CT for small animal imaging with a linear x-ray detector array and small-scale slip rings. The linear x-ray detector array consists of 1024 elements of 400□m×400□m with a gadolinium oxysulfide (GOS) scintillator on top of them. To avoid use of expensive large diameter slip rings for projection data transmission from the X­ray detector to the image reconstruction system, we used the wireless LAN technology. The projection data are temporally stored in the data acquisition system residing on the rotating gantry during the scan and they are transmitted to the image reconstruction system after the scan. With the wireless LAN technology, we only needed to use small-scale slip rings to deliver the AC electric power to the X-ray generator and the power supply on the rotating gantry. The performances of the small animal CT system, such as SNR, contrast, and spatial resolution, have been evaluated through experiments using various phantoms. It has been experimentally found that the SNR is almost linearly proportional to the tube current and tube voltage, and the minimum resolvable contrast is less than 30 CT numbers at 40kVp/3.0㎃. The spatial resolution of the small animal CT system has been found to be about 0.9Ip/㎜. Postmortem images of a piglet is also presented.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권1호
• /
• pp.29-34
• /
• 2022

모바일 디바이스 화면상의 클릭 가능한 객체를 인지하기 위한 데이터셋을 구축하고 새로운 네트워크 구조를 제안한다. 모바일 디바이스 화면에서 클릭 가능한 객체를 기준으로 다양한 해상도를 가진 디바이스에서 여러 애플리케이션을 대상으로 데이터를 수집하였다. 총 24,937개의 annotation data를 text, edit text, image, button, region, status bar, navigation bar의 7개 카테고리로 세분화하였다. 해당 데이터셋을 학습하기 위한 모델 구조는 Deconvolution Single Shot Detector를 베이스라인으로, backbone network는 기존 ResNet에 Squeeze-and-Excitation block을 추가한 Squeeze-and-Excitation networks를 사용하고, Single shot detector layers와 Deconvolution module을 Feature pyramid networks 형태로 쌓아 올려 header와 연결한다. 또한, 기존 input resolution의 1:1 비율에서 오는 특징의 손실을 최소화하기 위해 모바일 디바이스 화면과 유사한 1:2 비율로 변경하였다. 해당 모델을 구축한 데이터셋에 대하여 실험한 결과 베이스라인에 대비하여 mean average precision이 최대 101% 개선되었다.

• 반도체공학회 논문지
• /
• 제2권1호
• /
• pp.17-20
• /
• 2024

본 논문은 전통적인 자원 집약적인 컴퓨터 비전 모델의 한계를 해결하기 위해 저전력 엣지 장치에 최적화된 새로운 경량 객체 검출 모델을 제안합니다. 제안된 검출기는 Single Shot Detector (SSD)에 기반하여 소형이면서도 견고한 네트워크를 설계하였고, 작은 객체를 효율적으로 감지하는 데 있어 효율성을 크게 향상시키도록 모델을 구성하였다. 이 모델은 주로 두 가지 구성요소로 구성되어 있습니다: Depthwise 와 Pointwise Convolution 레이어를 사용하여 효율적인 특징 추출을 위한 Light_Block, 그리고 작은 객체의 향상된 감지를 위한 Enhancer_Block 으로 나누었다. 우리의 모델은 300x480 의 이미지 크기를 가진 Udacity 주석이 달린 데이터셋에서 처음부터 훈련되었으며, 사전 훈련된 분류 가중치의 필요성을 제거하였다. 약 0.43M 의 파라미터로 5.5MB 만의 무게를 가진 우리의 검출기는 평균 정밀도 (mAP) 27.7%와 140 FPS 의 처리 속도를 달성하여, 정밀도와 효율성 모두에서 기존 모델을 능가하였다. 따라서, 본 논문은 추론의 정확성을 손상시키지 않으면서 엣지 장치를 위한 객체 검출에서의 효과적인 경량화를 보여주고 있다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제22권1호
• /
• pp.5-11
• /
• 1999

This paper reviews recent major activities on instrumentation and methodology of PET. The performance of the PET instrumentation can be expressed by four physical characteristics, 1) spatial resolution, 2) coincidence resolving time, 3) energy resolution, and 4) detection efficiency. The physical and technical aspects of PET systems are briefly discussed along with these characteristics. Toward high resolution PET the recent trend has been to design multiple rings of densely packed detector arrays with scintillators. In order to satisfy the sampling requirement in reconstruction, continuous detector units has been developed. Iterative image reconstruction algorithms have received considerable attention for improvement of both the sampling requirement and image quality toward the stationary PET. Better resolving time improves the maximum true coincidence rate, which is also increased with more detectors placed in coincidence with each other. It suggests that volume PET is promising for enhancement of detection efficiency. The scattered coincidence event rate may be reduced by using detectors with better energy resolution. The use of interplane septa, however, takes over improvement of energy resolution in 2D PET. Energy resolution becomes an important factor for image quality under the condition of septa removal such as volume PET. Toward full utilization of emitting photons, 3D reconstruction incorporating oblique rays has been studied, and volume reconstruction algorithms have been developed. Practical volume PET systems impose heavy burden not only to detector sets and coincidence circuits, but also to computers in the memory requirements and the data processing. In conclusion, there have been many ingenious methods in development of PET instrumentation, which are based on unique capability of PET. They will be expected to overcome technical limitations, and to approach the fundamental limits.

• 한국콘텐츠학회논문지
• /
• 제13권10호
• /
• pp.54-61
• /
• 2013

본 논문에서는 하드웨어 기반의 영상 신호 윤곽선 검출을 위한 하드웨어기반의 알고리즘으로 CMOS 이미지 센서의 인접픽셀과 아날로그 상관기로 구성되는 윤곽선 검출기를 제안한다. 제안하는 이미지 윤곽 검출기는 각 열(column)마다 비교기를 공유하고, 비교기는 기준전압과 비교를 통해 대상 픽셀의 윤곽선 여부를 판별한다. 이미지 센서와 직접적으로 연결된 윤곽선 검출 회로는 기존의 연구와 비교하여 면적은 4배, 그리고 전력소모는 20 % 감소하는 결과를 보였다. 또한 외부에서 기준전압을 제어할 수 있어, 윤곽선 검출의 민감도를 조절하기에 유용한 장점을 가진다. 0.18 ${\mu}m$ CMOS 공정에서 제작된 칩은 34%의 fill factor를 가지며, 픽셀 당 0.9 ${\mu}W$의 전력소모를 가진다.

• 유통과학연구
• /
• 제18권1호
• /
• pp.15-26
• /
• 2020

Purpose: This study is to analyze the image classification using Convolution Neural Network and Transfer Learning for Jeju Island and to suggest related implications. As the biggest tourist destination in Korea, Jeju Island encounters environmental issues frequently caused by marine debris along the seaside. The ever-increasing volume of plastic waste requires multidirectional management and protection. Research design, data and methodology: In this study, the deep learning CNN algorithm was used to train a number of images from Jeju clean and polluted beaches. In the process of validating and testing pre-processed images, we attempted to explore their applicability to coastal tourism applications through probabilities of classifying images and predicting clean shores. Results: We transformed and augmented 194 small image dataset into 3,880 image data. The results of the pre-trained test set were 85%, 70% and 86%, and then its accuracy has increased through the process. We finally obtained a rapid convergence of 97.73% and 100% (20/20) in the actual training and validation sets. Conclusions: The tested algorithms are expected to implement in applications for tourism service distribution aimed at reducing coastal waste or in CCTVs as a detector or indicator for residents and tourists to protect clean beaches on Jeju Island.