• 한국자동차공학회논문집
• /
• 제21권4호
• /
• pp.33-42
• /
• 2013

This paper describes a multiple vehicle tracking algorithm using an integrated probabilistic data association filter (IPDAF) in urban environments. The algorithm consists of two parts; a pre-processing stage and an IPDA tracker. In the pre-processing stage, measurements are generated by a feature extraction method that manipulates raw data into predefined geometric features of vehicles as lines and boxes. After that, the measurements are divided into two different objects, dynamic and static objects, by using information of ego-vehicle motion. The IPDA tracker estimates not only states of tracks but also existence probability recursively. The existence probability greatly assists reliable initiation and termination of track in cluttered environment. The algorithm was validated by using experimental data which is collected in urban environment by using single laser scanner.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1994년도 봄 학술발표회 논문집
• /
• pp.25-32
• /
• 1994

The pre-processor for finite to element structural analysis considering the user-friendly device is developed by using GUI. This can be used on WINDOWS' environment which is realized the multi-tasking and the concurrency by object-oriented paradigm. Data input can be done easily through menu, dialog box, automatic stepwise input and concurrent representation with the structural geometry on multiple windows. It in designed to control integratedly the pre-processing, execution and the post-processing of the finite element structural analysis program on multiple windows, and input data can be seen with result outputs at the same time. In addition, the object-oriented programming environment makes convenient revision and addition of the program components for expanding the scope of analysis and making better user environment.

• 한국산업융합학회 논문집
• /
• 제2권2호
• /
• pp.41-49
• /
• 1999

In general, FORTRAN is used for numerical analysis and OPS5 or LISP is used for expert systems, This causes problems at the interface because the various applications require different computing languages or environments. This paper describes the approach used to take AutoCAD as a user-interface for an existing finite element structural analysis package. Some principles concerning database management related to data-exchange interface of pre- and post-processing system for FORTRAN structural analysis program are discussed, and numerical examples demonstrate the power of the combination of these programs.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.11-16
• /
• 1997

This paper describes the grenade counting system developed for DPICM submunition analysis using the infrared video streams, and its some video stream processing technique. The video stream data processing procedure consists of four sequences; Analog infrared video stream recording, video stream capture, video stream pre-processing, and video stream analysis including the grenade counting. Some applications of this algorithms to real bursting test has shown the possibility of automation for submunition counting.

• 문화기술의 융합
• /
• 제10권2호
• /
• pp.453-458
• /
• 2024

광학 문자 인식(Optical Character Recognition, OCR)은 이미지 내의 문자를 인식하여 디지털 포맷(Digital Format)의 텍스트로 변환하는 기술이다. 딥러닝(Deep Learning) 기반의 OCR이 높은 인식률을 보여줌에 따라 대량의 기록 자료를 보유한 많은 산업 분야에서 OCR을 활용하고 있다. 특히, 의료 산업 분야는 의료 서비스 향상을 위해 딥러닝 기반의 OCR을 적극 도입하였다. 본 논문에서는 딥러닝 기반 OCR 엔진(Engine) 및 의료 데이터에 특화된 OCR의 동향을 살펴보고, 의료 OCR의 발전 방향에 대해 제시한다. 현재의 의료 OCR은 검출한 문자 데이터를 자연어 처리(Natural Language Processing, NLP)하여 인식률을 개선하였다. 그러나, 정형화되지 않은 손글씨(Handwriting)나 변형된 문자에서는 여전히 인식 정확도에 한계를 보였다. 의료 데이터의 데이터베이스(Database)화, 이미지 전처리(Pre-processing), 특화된 자연어 처리를 통해 더욱 고도화된 의료 OCR을 발전시키는 것이 필요하다.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 동계 학술대회 논문집
• /
• pp.451-456
• /
• 2000

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 춘계학술발표회 논문집
• /
• pp.271-276
• /
• 2003

The Moderate Resolution Imaging Spectroradiometer (MODIS) on the Earth Observing System (EOS) of Terra and Aqua satellites, launched in December 1999 and May 2002, has been directly received by Korea Aerospace Research Institute (KARI) ground station facility from July 2002. MODIS scans a swath width of 2330 km that is sufficiently wide to cover Korean peninsular, Yellow and East Sea at once. The MODIS has 36 spectral bands between 0.415 $\mu\textrm{m}$ and 14.235 $\mu\textrm{m}$, i.e., through the visible into the thermal infrared. MODIS has been observed active fires, floods, smoke transport, dust storms, severe storms since February of 2000. The satellite imagery obtained through the MODIS will be utilized for many application such as national territorial management, agriculture, natural environment, atmosphere and ocean, etc. In this study is to introduce various application field of MODIS imagery and data processing system.

• Journal of Information Processing Systems
• /
• 제16권4호
• /
• pp.795-808
• /
• 2020

Due to the poor evaluation indexes such as detection accuracy and recall rate when Yolov3 network detects aircraft in remote sensing images, in this paper, we propose a remote sensing image aircraft detection method based on machine vision. In order to improve the target detection effect, the Inception module was introduced into the Yolov3 network structure, and then the data set was cluster analyzed using the k-means algorithm. In order to obtain the best aircraft detection model, on the basis of our proposed method, we adjusted the network parameters in the pre-training model and improved the resolution of the input image. Finally, our method adopted multi-scale training model. In this paper, we used remote sensing aircraft dataset of RSOD-Dataset to do experiments, and finally proved that our method improved some evaluation indicators. The experiment of this paper proves that our method also has good detection and recognition ability in other ground objects.

• 한국산업정보학회논문지
• /
• 제29권3호
• /
• pp.79-87
• /
• 2024

최근 텍스트분류, 감성분석, 질의응답 등의 자연어 처리를 위해서 사전학습언어모델(Pre-trained Language Model, PLM)의 중요성은 날로 강조되고 있다. 한국어 PLM은 범용적인 도메인의 자연어 처리에서 높은 성능을 보이나 금융, 제조, 법률, 의료 등의 특화된 도메인에서는 성능이 미약하다. 본 연구는 금융도메인 뿐만 아니라 범용도메인에서도 우수한 성능을 보이는 금융특화 언어모델의 구축을 위해 언어모델의 학습과정과 미세조정 방법을 제안하는 것이 주요 목표이다. 금융도메인 특화언어모델을 구축하는 과정은 (1) 금융데이터 수집 및 전처리, (2) PLM 또는 파운데이션 모델 등 모델 아키텍처 선정, (3) 도메인 데이터 학습과 인스트럭션 튜닝, (4) 모델 검증 및 평가, (5) 모델 배포 및 활용 등으로 구성된다. 이를 통해 금융도메인의 특성을 살린 사전학습 데이터 구축방안과 효율적인 LLM 훈련방법인 적응학습과 인스트럭션 튜닝기법을 제안하였다.