• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.79-81
• /
• 2018

혈관내 초음파(Intravascular Ultrasound, IVUS)는 혈관 내벽의 단면을 보여주는 검사 방법으로 관상 동맥 내의 내강, 죽상 경화반, 그리고 혈관벽의 변화에 관한 직접적이고 구체적인 정보를 제공한다. 본 논문에서는 IVUS 영상에서 내막과 외막을 추출하고 각 막의 지름을 자동적으로 추출하는 방법을 제안한다. 제안된 방법은 IVUS 영상에 Histogram Equalization 기법을 적용하여 명암 대비를 강조한 후에 퍼지 이진화 기법과 평균 이진화 기법을 각각 적용하여 내막과 외막을 추출하기 위해 이진화한다. 이진화된 내막과 외막의 각 영역 중에서 혈관내 초음파 영상 중심에서 가장 큰 영역의 정보를 이용하여 라벨링 기법을 적용하여 내막과 외막 영역을 추출하고 각 막의 지름을 계산한다. 제안된 방법을 IVUS 영상을 대상으로 실험한 결과, 내막과 외막의 지름이 비교적 정확히 추출되는 것을 실험을 통하여 확인하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.558-568
• /
• 2000

In the paper, we propose the automatic generation method of digital elevation map based on contour map. The proposed method classifies contour data and non-contour data by thinning and labelling process of the contour line and then connects smoothly broken contour line by Bezier curve. Finally, the digital devation map is generated by the interpolation using the height data of the contour line. The proposed method can reduce vest effort, time and expense which is spend to make digital elevation map.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.183-186
• /
• 2022

최근 인공지능 기반 객체 탐지 기술이 발전함에 따라 영상 감시, 얼굴 인식, 로봇 제어, IoT, 자율주행, 제조업, 보안 등 다양한 분야에 활용되고 있다. 이에 본 논문은 발전된 객체 탐지 알고리즘을 이용하여 비전문가에겐 생소한 컴퓨터나 전기 장치 등의 '단자(terminal)' 모양을 구별하는 방법을 제안한다. 이를 위해 객체 탐지 프로그램인 You Only Look Once (YOLO) 알고리즘을 이용하여 입력한 단자들의 모양을 검출하는 알고리즘을 구성하였다. 일상에서 쉽게 볼 수 있는 단자들의 이미지(VGA, DVI, HDMI, DP, USB-A, USB-C)를 라벨링하여 데이터셋을 구축하였고, YOLOv4와 YOLOv5 두 버전의 알고리즘을 사용하여 성능을 검증하였다. 실험 결과 mean Average Precision(mAP) 기준 최대 92.9%의 정확도를 얻을 수 있었다. 전기 장치에 따라 단자의 모양이 다양하고, 그 종류 또한 많기 때문에 본 연구가 방송 기술 등의 여러 분야에 응용될 것으로 기대된다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.592-594
• /
• 2023

차량 탐지와 차량 추적 기술은 교통관리 시스템, 자율주행 자동차 시스템 및 이를 응용한 보안 감시 시스템, 군사 작전 및 안전 등 다양한 산업 분야에서 활용되고 있다. 본 논문에서는 차량 탐지는 YOLOv7 모델을, 차량 추적은 DeepSORT 알고리즘을 사용하여 도로의 차량들에 대해 탐지 및 추적을 순차적으로 진행하였다. 실험환경은 차량 탐지 데이터 셋(dataset)을 직접 라벨링(labeling) 하여 실험하였고, 차량 추적은 차량 탐지에서 학습해서 얻은 체크포인트(checkpoint) 모델을 가중치로 설정하여 실험을 진행하였다. 차량 탐지 실험결과는 validation 과 test 에서 높은 정확도를 확인할 수 있었고, 차량 추적은 Namsa 비디오 및 Seohaegyo 비디오에서도 차량 추적이 잘 되고 있음을 확인할 수 있었다.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.205-209
• /
• 2022

페르소나 대화 시스템이 상대방의 개인화된 정보에 일관된 응답을 생성하는 것은 상당히 중요하며, 이를 해결하기 위해 최근에 많은 연구들이 활발히 이루어지고 있다. 그 중, PersonaChat 데이터셋에 대해 수반/중립/모순 관계를 라벨링한 DialoguNLI 데이터셋이 제안되었으며, 일관성 측정, 페르소나 속성 추론 태스크 등 여러 분야에 활용되고 있다. 그러나, 공개적으로 이용가능한 한국어로 된 대화 추론 데이터셋은 없다. 본 연구에서는 한국어로 번역된 페르소나 대화 데이터셋과 한국어 자연어 추론 데이터셋에 학습된 모델을 이용하여 한국어 대화 추론 데이터셋(KorDialogueNLI)를 구축한다. 또한, 사전학습된 언어모델을 학습하여 한국어 대화 추론 모델 베이스라인도 구축한다. 실험을 통해 정확도 및 F1 점수 평가 지표에서 KLUE-RoBERTa 모델을 미세조정(fine-tuning)시킨 모델이 가장 높은 성능을 달성하였다. 코드 및 데이터셋은 https://github.com/passing2961/KorDialogueNLI에 공개한다.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1407-1422
• /
• 2022

This study was conducted to classify tree species and assess the classification accuracy, using SE-Inception, a classification-based deep learning model. The input images of the dataset used Worldview-3 and GeoEye-1 images, and the size of the input images was divided into 10 × 10 m, 30 × 30 m, and 50 × 50 m to compare and evaluate the accuracy of classification of tree species. The label data was divided into five tree species (Pinus densiflora, Pinus koraiensis, Larix kaempferi, Abies holophylla Maxim. and Quercus) by visually interpreting the divided image, and then labeling was performed manually. The dataset constructed a total of 2,429 images, of which about 85% was used as learning data and about 15% as verification data. As a result of classification using the deep learning model, the overall accuracy of up to 78% was achieved when using the Worldview-3 image, the accuracy of up to 84% when using the GeoEye-1 image, and the classification accuracy was high performance. In particular, Quercus showed high accuracy of more than 85% in F₁ regardless of the input image size, but trees with similar spectral characteristics such as Pinus densiflora and Pinus koraiensis had many errors. Therefore, there may be limitations in extracting feature amount only with spectral information of satellite images, and classification accuracy may be improved by using images containing various pattern information such as vegetation index and Gray-Level Co-occurrence Matrix (GLCM).

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.381-392
• /
• 2021

In this study, we perform deep learning-based object detection analysis on eight types of buildings defined by the digital map topography standard code, leveraging images taken with UAV (Unmanned Aerial Vehicle). Image labeling was done for 509 images taken by UAVs and the YOLO (You Only Look Once) v5 model was applied to proceed with learning and inference. For experiments and analysis, data were analyzed by applying an open source-based analysis platform and algorithm, and as a result of the analysis, building objects were detected with a prediction probability of 88% to 98%. In addition, the learning method and model construction method necessary for the high accuracy of building object detection in the process of constructing and repetitive learning of training data were analyzed, and a method of applying the learned model to other images was sought. Through this study, a model in which high-efficiency deep neural networks and spatial information data are fused will be proposed, and the fusion of spatial information data and deep learning technology will provide a lot of help in improving the efficiency, analysis and prediction of spatial information data construction in the future.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.4
• /
• pp.1-6
• /
• 2003

In this Paper, the moving image is detected by a collision preventive system. The noise of these images is reduced by a mean filter. In case of detecting a movement with a binary difference image the moving area is detected exactly by the labeling and the projective method. When the image move slowly with the tracking mode of the system, the center of the tracking window move to the previous tracking window. And the tracking windows are divided into a tracking mode and a coasting mode which are determine by the Contrast-Difference Correlation of the date obtained from a difference image. The coasting mode determine whether continue the tracking step or not comparing the coasting-time values to reducing the error by the disturbance. The coasting and tracking of these moving images are verified by the result of the simulation.

• Journal of Korea Multimedia Society
• /
• v.12 no.11
• /
• pp.1557-1562
• /
• 2009

In the hydraulic room of a forging press machine, a system which can detect and prevent risks at its early stage is needed because there may be a leakage due to the damage of the connection parts of the piping which can endanger human life and mechanical damage. In this paper, the system to automatically recognize a leakage of hydraulic fluid in terms of using the pan/tilt camera from a remote place is implemented. It finds the bounding boxes which are recognized with object regions in the process of labeling and detects the proper leakage regions of hydraulic fluid with the ratios of width and height of the bounding boxes and compactness of the leakage shape. Also, it performs noise removal and calibration for transition and rotation of image as a preprocessing process. The experimental results show that the proposed system has been verified to detect the leakage regions accurately in various sources of light.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.97-102
• /
• 2017

Recently deep learning techniques such as convolutional neural networks (CNN) have been introduced to classify high-resolution remote sensing data. In this paper, we investigated the possibility of applying CNN to crop classification of farmland images captured by drones. The farming area was divided into seven classes: rice field, sweet potato, red pepper, corn, sesame leaf, fruit tree, and vinyl greenhouse. We performed image pre-processing and normalization to apply CNN, and the accuracy of image classification was more than 98%. With the output of this study, it is expected that the transition from the existing image classification methods to the deep learning based image classification methods will be facilitated in a fast manner, and the possibility of success can be confirmed.