• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1250-1260
• /
• 2020

This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.

• Ocean Systems Engineering
• /
• 제10권4호
• /
• pp.415-434
• /
• 2020

Detecting objects is important for the safe operation of ships, and enables collision avoidance, risk detection, and autonomous sailing. This study proposes a ship detection method from images and videos taken at sea using one of the state-of-the-art deep neural network-based object detection algorithms. A deep learning model is trained using a public maritime dataset, and results show it can detect all types of floating objects and classify them into ten specific classes that include a ship, speedboat, and buoy. The proposed deep learning model is compared to a universal trained model that detects and classifies objects into general classes, such as a person, dog, car, and boat, and results show that the proposed model outperforms the other in the detection of maritime objects. Different deep neural network structures are then compared to obtain the best detection performance. The proposed model also shows a real-time detection speed of approximately 30 frames per second. Hence, it is expected that the proposed model can be used to detect maritime objects and reduce risks while at sea.

• 센서학회지
• /
• 제33권2호
• /
• pp.78-85
• /
• 2024

We proposed a method for visual place recognition that represents images using objects as visual words. Visual words represent the various objects present in urban environments. To detect various objects within the images, we implemented and used a zero-shot detector based on a large-scale image language model. This zero-shot detector enables the detection of various objects in urban environments without additional training. In the process of creating histograms using the proposed method, frequency-based weighting was applied to consider the importance of each object. Through experiments with open datasets, the potential of the proposed method was demonstrated by comparing it with another method, even in situations involving environmental or viewpoint changes.

• 전자공학회논문지B
• /
• 제33B권5호
• /
• pp.73-82
• /
• 1996

In this paper, an efficient algorithm for recognizing and positioning occuluded objects in a two-dimensional plane is presented. Model objects and unknown input image are approximated by polygonal boundaries, which are compactly represented by shape functions of the polygons. The input image is partitioned into measningful segments whose end points are at the locations of possible occlusion - i.e. at concave vertices. Each segment is matched against known model objects by calculating a matching measure, which is defined as the minimum euclidean distance between the shape functions. An O(mm(n+m) algorithm for computing the measure is presentd, where n and m are the number of veritces for a model and an unknown object, respectively. Match results from aprtial segments are combined based on mutual compatibility, then are verified using distance transformation and translation vector to produce the final recognition. The proposed algorithm is invariant under translation and rotation of objects, which has been shown by experimental results.

• 한국시뮬레이션학회논문지
• /
• 제9권4호
• /
• pp.25-40
• /
• 2000

The cost of simulation modeling, the expertise required, and the pains of starting a new each time are impediments to more wide spread adoption of simulation technology. In addition, one of the most critical problems in the field of computer simulation today is the lack of published models and physical objects within the World Wide Web (WWW) allowing such distribution. From the viewpoint of WWW as distributed model repositories, it can be assumed that very many simulation models exist on the web. This paper is based on the premise that WWW is a distributed repository. Design Pattern, web-oriented technology like Java and CORBA, which are especially to cope with distributed objects, are introduced and discussed in detail for integration of simulation model. In this paper an architecture of model integration is proposed, which presents the whole procedure of model integration and how the Internet technologies are connected in. The central focus of this research is on the technical realization of integrating simulation models as distributed objects

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 1999년도 추계학술대회 논문집
• /
• pp.325-330
• /
• 1999

Web-based simulation is one of the most interesting field of simulation research today. Among many research area of web-based simulation, we concern about what a effective way of building simulation model is since creating comprehensive simulation models can be expensive and time consuming. So this paper discusses how to integrate distributed simulation sub-models as objects for constructing the required simulation model which is more large and complex. We introduce two web-oriented methodologies (such as JIDL, CORBA) and the concepts of agent for assisting modelers to integrate simulation models scattered over the web. SINDBAD, which we designed, is a simulation environment which makes it possible constructing a simulation model with distributed model objects on the web and performing the parallel simulation in a distributed way. It is organized according to design patterns in the object oriented concept. Actually we are on the premise that all the distributed objects are originally composed in a CORBA-compatible way to start with our prototype of SINDBAD.

• 정보처리학회논문지D
• /
• 제10D권6호
• /
• pp.873-884
• /
• 2003

지금까지 명확하게 정의된 경계를 갖는 공간 및 시공간 객체 모델 개발에 관한 많은 연구가 수행되어 왔다. 그러나, 이들 모델은 지리 분석과 이미지 해석에 관한 많은 응용에서 식별되는 불확실한 경계를 갖는 공간 및 시공간 객체에 직접적으로 적용될 수 없다. 따라서, 이 논문에서는 불확실한 공간 및 시공간 객체에 적용할 수 있는 불확실한 시공간 데이터 모델을 제안하고, 이 모델을 기반으로 불확실한 시공간 객체간의 위상 관계에 관한 연산자를 정의하고, 연산 알고리즘을 설계하였다. 제안된 모델은 기존 모델과의 호환성을 위해 개방형 GIS 명세서를 기반으로 하는 시공간 데이터 모델을 확장하여 설계하였다. 불확실한 시공간 객체는 시간에 따라 위치와 모양이 불연속적으로 변하는 객체와 시간에 따라 위치와 모양이 연속적으로 변하는 객체로 정의하였으며, 확장된 9-IM을 사용하여 이들 객체간의 위상 관계를 정의하였다. 제안된 모델은 천연자원 관리시스템, 날씨 정보 관리 시스템, 지리 정보 관리 정보 시스템 등에 효율적으로 적용될 수 있을 것으로 기대된다.

• 한국IT서비스학회지
• /
• 제12권3호
• /
• pp.311-321
• /
• 2013

In the community of software engineering, diverse modeling languages are used for representing all relevant information in the form of models. Also many different models such as business model, business process model, product models, interface models etc. are generated through software life cycles. In this situation, models need to be integrated for enterprise integration and enhancement of software productivity. Researchers propose rebuilding models by a specific modeling language, using a intemediate modeling language and using common reference for model integration. However, in the current approach it requires a lot of cost and time to integrate models. Also it is difficult to identify common objects from several models and to update objects in the repository of common model objects. This paper proposes software model integration using metadata model based on Linked data. We verify the effectiveness of the proposed approach through a case study.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 학술대회지
• /
• pp.823-826
• /
• 2004

In this paper, A tracking of the moving objects using normalized hue distribution in HSI color model was proposed. Moving objects are detected by using difference image method and integral projection method to background image and objects image only with hue area. Hue information of the detected moving area are normalized by 24 levels from $0^{\circ}$ to $3600^{\circ}A$ distance in between normalized levels with a hue distribution chart of the normalized moving objects is used for the identity distinction feature parameters of the moving objects. To examine proposed method in this paper, image of moving cars are obtained by setting up three cameras at different places every 1 km on outer motorway. The simulation results of identity distinction show that it is possible to distinct the identity a distance in between normalization levels of a hue distribution chart without background.

• 정보학연구
• /
• 제10권4호
• /
• pp.27-39
• /
• 2007

Object tracking in a real time environment is one of challenging subjects in computer vision area during past couple of years. This paper proposes a method of object detection and tracking using adaptive background estimation in real time environment. To obtain a stable and adaptive background, we combine 3-frame differential method and running average single gaussian background model. Using this background model, we can successfully detect moving objects while minimizing false moving objects caused by noise. In the tracking phase, we propose a matching criteria where the weight of position and inner brightness distribution can be controlled by the size of objects. Also, we adopt a Kalman Filter to overcome the occlusion of tracked objects. By experiments, we can successfully detect and track objects in real time environment.