• 한국멀티미디어학회논문지
• /
• 제25권3호
• /
• pp.546-557
• /
• 2022

Recently, the demand to interpret image data with artificial intelligence in various fields is rapidly increasing. Object recognition and detection techniques using deep learning are mainly used, and video integration analysis to determine unstructured object recognition is a particularly important problem. In the case of natural disasters or social disasters, there is a limit to the object recognition structure alone because it has an unstructured shape. In this paper, we propose intelligent video integration analysis system that can recognize unstructured objects based on video turning point and object detection. We also introduce a method to apply and evaluate object recognition using virtual augmented images from 2D to 3D through GAN.

• International Journal of Advanced Culture Technology
• /
• 제10권4호
• /
• pp.536-546
• /
• 2022

A society will lose a lot of something in this field when the forest fire broke out. If a forest fire can be detected in advance, damage caused by the spread of forest fires can be prevented early. So, we studied how to detect forest fires using CCTV currently installed. In this paper, we present a deep learning-based model through efficient image data construction for monitoring forest fire smoke, which is unstructured data, based on the deep learning model YOLOv5. Through this study, we conducted a study to accurately detect forest fire smoke, one of the amorphous objects of various forms, in YOLOv5. In this paper, we introduce a method of self-learning by producing insufficient data on its own to increase accuracy for unstructured object recognition. The method presented in this paper constructs a dataset with a fixed labelling position for images containing objects that can be extracted from the original image, through the original image and a model that learned from it. In addition, by training the deep learning model, the performance(mAP) was improved, and the errors occurred by detecting objects other than the learning object were reduced, compared to the model in which only the original image was learned.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.22-28
• /
• 1992

The need for intelligent systems that can operate in an unstructured, dynamic environment has created a growing demand for the use of multiple, distributed sensors. While most research in multisensor fusion has revolved around applications in object recognition-including military applications for automatic target recognition-developments in microsensor technology are encouraging more research in affordable, highly-redundant sensor networks. Three trends that are described at length are the increasing use of microsensors, the techniques that are used in the handling of partial or uncertain data, and the application of neural network techniques for sensor fusion.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 춘계학술대회
• /
• pp.309-311
• /
• 2014

최근, 산재된 비정형 데이터 분석 등을 통한 빅데이터 활용에 대한 요구들이 증가하고 있으나, 아직까지 이에 대한 연구들이 부족한 실정이다. 따라서 본 연구에서는 수집된 웹 정보에서 개체들을 추출하여 이들 간의 관계를 집단지성 기술과 언어처리 기술을 통해 자동 분석해 냄으로써 문장단위의 의미기반 분석을 할 수 있는 기법을 제시한다. 이를 위해, 수집된 정보를 DBMS에 정형화된 형태로 저장한 후 형태소와 자질정보를 분석한다. 획득한 형태소 중 관심개체, 주변개체, 비관심 개체를 분류하고 개체간 속성인식기법을 이용하여 각 개체간의 관계를 정도, 범위, 성격 등으로 분석한다. 그 결과, 긍정 부정의 판단이 가능한 개체간의 관계성 도출기법을 제시함으로써, 특정 키워드를 대상으로 분석된 정보들의 연관도를 분석할 수 있었다. 이 연구를 통해, 최근 실시간 대용량 처리 시스템에 적합한 시스템을 설계하여 이를 부가가치가 높은 서비스에 적용할 수 있는 방법을 제시하였다.