• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1224-1235
• /
• 2017

Recently, augmented reality technology has received much attention in many fields. This paper presents an augmented reality system using Rubiks' Cube which can augment various 3D objects depending on patterns of a Rubiks' cube. The system first detects a cube from an image using partitional clustering and strongly connected graph. Thereafter, the system detects the top side of the cube and finds a proper pattern to determine which object should be augmented. An object corresponding to the pattern is finally augmented according to the camera viewpoint. Experimental results show that the proposed system successfully augments various virtual objects in real time.

• 한국주거학회:학술대회논문집
• /
• 한국주거학회 2002년도 추계학술발표대회
• /
• pp.179-182
• /
• 2002

Today, augmentation of industrial wastes with industrial development demands diminution and recycling technical development for industrial wastes reduction. A statistical research of industry and constructional wastes as a request of the times can achieve the conservation of resource and the protection of environment. The ultimate object of the study is not only diminution and recycling of industrial wastes but also the degree of self-sufficiency in resource and the attainment of comfortable life environment, which can the accomplish the resource circulation system and make progress into the environmentally advanced country. The object of this investigation is industrial classification, a waste discharge quantity, a waste sort, waste disposal of industrial wastes in Yeung-nam area. The investigation of special quality in industrial wastes can be used to establish a wastes management policy and a disposition method .

• 전기학회논문지
• /
• 제68권2호
• /
• pp.359-363
• /
• 2019

As commercial drones have been widely used, concerns for collision accidents with people and invading secured properties are emerging. The detection of drone is a challenging problem. The deep learning based object detection techniques for detecting drones have been applied, but limited to the specific cases such as detection of drones from bird and/or background. We have tried not only detection of drones, but classification of different drones with an end-to-end model. YOLOv2 is used as an object detection model. In order to supplement insufficient data by shooting drones, data augmentation from collected images is executed. Also transfer learning from ImageNet for YOLOv2 darknet framework is performed. The experimental results for drone detection with average IoU and recall are compared and analysed.

• 한국측량학회지
• /
• 제1권2호
• /
• pp.23-29
• /
• 1983

Degradation of image caused by relative motion between the object and the imaging system (like a camera with its platform) is detrimental to precision photogrammetry. Principal modes of relative motion are identified. The discussion is, however, concentrated on the systematic motions, translatory and rotatory. Various analogical approaches of compensating for the image motion are cited. An analytical-computational approach is presented. This one considers the relationship of transformation bet ween the image and the object, known as the collinearity condition. The standard forms of collinearity condition equations are presented. Augmentation of these equations with regard to both translatory and rotatory motions are expounded. With ever increasing use of high speed computers (as well as analytical plotters in the realm of photogrammetry), this approach seems to be more costeffective and seems to yield better precision in the long run than other approaches that concentrate on analogical corrections to the image itself.

• 한국융합학회논문지
• /
• 제9권12호
• /
• pp.47-52
• /
• 2018

개체명 인식(Named Entity Recognition)시스템은 문서로부터 고유한 의미를 가질 수 있는 인명(PS), 지명(LC), 기관명(OG) 등의 개체명을 추출하고 추출된 개체명의 범주를 결정하는 시스템이다. 최근 딥러닝 방식을 이용한 개체명 인식 연구에서 입력 데이터의 앞, 뒤 방향을 고려한 LSTM 기반의 Bi-LSTM 모델로부터 출력 데이터 간의 전이 확률을 이용한 CRF를 결합한 방식의 Bi-LSTM-CRF가 우수한 성능을 보이고, 문자 및 단어 단위의 효율적인 임베딩 벡터생성에 관한 연구와 CNN, LSTM을 활용한 모델에서도 좋은 성능을 보여주고 있다. 본 연구에서는 한국어 개체명 인식시스템 성능 향상을 위해 자질을 보강한 Bi-LSTM-CNN-CRF 모델에 관해 기술하고 전통문화 말뭉치구축 방식에 대해 제안한다. 그리고 구축한 말뭉치를 한국어 개체명 인식 성능 향상을 위한 자질 보강 모델 Bi-LSTM-CNN-CRF로 학습한 결과에 대해 제안한다.

• 스마트미디어저널
• /
• 제12권9호
• /
• pp.159-170
• /
• 2023

실종자 수색은 많은 시간과 인력이 필요하다. 그 해결책의 일환으로 YOLO 기반 모델을 활용하여 실종자 수색 AI 시스템을 구현하였다. 객 객체 탐지 모델을 훈련하기 위해 AI-Hub에서 드론 이동체 인지 영상(도로 고정)을 수집하고 모델을 학습하였다. 또한, 훈련 데이터 세트와 상이한 환경에서의 성능을 평가하기 위해 산악 환경 데이터 세트를 추가 수집하였다. 실종자 수색 AI 시스템의 최적화를 위해 모델 크기 및 하이퍼파라미터에 따른 성능평가, 과대적합 우려에 대한 추가 성능평가를 시행하였다. 성능평가 결과 YOLOv5-L 모델이 우수한 성능을 보이는 것을 확인할 수 있었으며 데이터 증강 기법을 적용함에 따라 모델의 성능이 보다 향상되었다. 이후 웹 서비스에는 데이터 증강 기법을 적용한 YOLOv5-L 모델을 적용하여 실종자 수색의 효율성을 높였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권2호
• /
• pp.47-54
• /
• 2022

For safe driving of autonomous vehicles, road damage detection is very important to lower the potential risk. In order to ensure safety while an autonomous vehicle is driving on the road, technology that can cope with various obstacles is required. Among them, technology that recognizes static obstacles such as poor road conditions as well as dynamic obstacles that may be encountered while driving, such as crosswalks, manholes, hollows, and speed bumps, is a priority. In this paper, we propose a method to extract similarity of images and find damaged road images using OpenCV image processing and CNN algorithm. To implement this, we trained a CNN model using 280 training datasheets and 70 test datasheets out of 350 image data. As a result of training, the object recognition processing speed and recognition speed of 100 images were tested, and the average processing speed was 45.9 ms, the average recognition speed was 66.78 ms, and the average object accuracy was 92%. In the future, it is expected that the driving safety of autonomous vehicles will be improved by using technology that detects road obstacles encountered while driving.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.685-686
• /
• 2006

Recently, various AR-based product design methodologies have been introduced. In this paper, we propose technologies for enhancing robust augmentation and immersive realization of virtual objects. A robust augmentation technology is developed for various lighting conditions and a partial solution is proposed for the hand occlusion problem that occurs when the virtual objects overlay the user' hands. It provides more immersive or natural images to the users. Finally, vibratory haptic cues by page motors as well as button clicking force feedback by modulating pneumatic pressures are proposed while interacting with virtual widgets. Also our system reduces gabs between modeling spaces and user spaces. An immersive game-phone model is selected to demonstrate that the users can control the direction of the car in the racing game by tilting a tangible object with the proposed augmented haptic and robust non-occluded visual feedback. The proposed methodologies will be contributed to the immersive realization of the conventional AR system.

• International Journal of Automotive Technology
• /
• 제6권5호
• /
• pp.545-554
• /
• 2005

Passive velocity field control (PVFC) was previously developed for fully mechanical systems, in which the motion task was specified by behaviors in terms of a velocity field and the closed-loop was passive with respect to the supply rate given by the environment input. However, the PVFC was only applied to a single manipulator. The proposed control law was derived geometrically and the geometric and robustness properties of the closed-loop system were also analyzed. In this paper, we propose a virtual passivity-based algorithm to apply decentralized control to multiple 3­wheeled mobile robotic systems whose subsystems are under nonholonomic constraints and convey a common rigid object in a horizontal plain. Moreover, it is shown that multiple robot systems ensure stability and the velocities of augmented systems converge to a scaled multiple of each desired velocity field for cooperative mobile robot systems. Finally, the application of proposed virtual passivity-based decentralized algorithm via system augmentation is applied to trace a circle and the simulation results is presented in order to show effectiveness for the decentralized control algorithm proposed in this research.

• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.468-474
• /
• 2022

본 논문에서는 딥러닝을 이용하여 실시간 화재경보 시스템을 구현하는 방법을 제안한다. 화재경보를 위한 딥러닝 학습 이미지 데이터셋은 인터넷을 통하여 1500장을 취득하였다. 일상적인 환경에서 취득된 다양한 이미지를 그대로 학습하게 되면 학습 정확도가 높지 않은 단점이 있다. 본 논문에서는 학습 정확도 향상을 위해 화재 이미지 데이터 확장 방법을 제안한다. 데이터증강 방법은 밝기 조절, 블러링, 불꽃사진 합성을 이용해 학습 데이터 600장을 추가해 총 2100장을 학습했다. 불꽃 이미지 합성방법을 이용하여 확장된 데이터는 정확도 향상에 큰 영향을 주었다. 실시간 화재탐지 시스템은 영상 데이터에 딥러닝을 적용하여 화재를 탐지하고 사용자에게 알림을 전송하는 시스템이다. Edge AI시스템에 적합한 YOLO V4 TINY 모델을 custom 학습한 모델을 이용해 실시간으로 영상을 분석해 화재를 탐지하고 그 결과를 사용자에게 알리는 웹을 개발하였다. 제안한 데이터를 사용하였을 때 기존 방법에 비하여 약 10%의 정확도 향상을 얻을 수 있다.