• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 1999년도 추계학술대회 발표요약문
• /
• pp.47-51
• /
• 1999

Geo-features play a key role in object-oriented or feature-based geo-processing system. So the strategy for how-to-model and how-to-manage the geo-features builds the main architecture of the entire system and also supports the efficiency and functionality of the system. Unlike the conventional 2D geo-processing system, geo-features in 3D GIS have lots to be considered to model regarding the efficient manipulation and analysis and visualization. When the system is running on the Web, it should also be considered that how to leverage the level of detail and the level of automation of modeling in addition to the support for client side data interoperability. We built a set of 3D geo-features, and each geo-feature contains a set of aspatial data and 3D geo-primitives. The 3D geo-primitives contain the fundamental modeling data such as the height of building and the burial depth of gas pipeline. We separated the additional modeling data on the geometry and appearance of the model from the fundamental modeling data to make the table in database more concise and to allow the users more freedom to represent the geo-object. To get the users to build and exchange their own data, we devised a fie format called VGFF 2.0 which stands for Virtual GIS File Format. It is to describe the three dimensional geo-information in XML(extensible Markup Language). The DTD(Document Type Definition) of VGFF 2.0 is parsed using the DOM(Document Object Model). We also developed the authoring tools for users can make their own 3D geo-features and model and save the data to VGFF 2.0 format. We are now expecting the VGFF 2.0 evolve to the 3D version of SVG(Scalable Vector Graphics) especially for 3D GIS on the Web.

• 방송공학회논문지
• /
• 제26권7호
• /
• pp.868-876
• /
• 2021

Deploying deep neural network model training performs remarkable performance in the fields of Object detection and Instance segmentation. To train these models, features are first extracted from the input image using a backbone network. The extracted features can be reused by various tasks. Research has been actively conducted to serve various tasks by using these learned features. In this process, standardization discussions about encoding, decoding, and transmission methods are proceeding actively. In this scenario, it is necessary to analyze the response characteristics of features against various distortions that may occur in the data transmission or data compression process. In this paper, experiment was conducted to inject various distortions into the feature in the object recognition task. And analyze the mAP (mean Average Precision) metric between the predicted value output from the neural network and the target value as the intensity of various distortions was increased. Experiments have shown that features are more robust to distortion than images. And this points out that using the feature as transmission means can prevent the loss of information against the various distortions during data transmission and compression process.

• 대한전자공학회논문지SP
• /
• 제43권2호
• /
• pp.57-64
• /
• 2006

본 논문에서는 해마신경망(HCNN:HippoCampal Neural Network)을 이용하여 사용자 친화적인 객체 기반 멀티미디어 검색시스템을 제안한다. 내용 기반 검색(Content-based Retrieval)에 관한 대부분의 기존의 질의 방법은 입력 영상에 의한 질의 또는 컬러(color), 형태(shape), 질감(texture)등과 같은 low-level의 특징을 사용한다. 본 논문에서 제안하는 방법은 MPEG 기반의 압축 비디오 스트림으로부터 장면 전환 검출을 수행하여 샷을 검출한다. 이 샷 프레임에서 컬러 객체의 자동 추출을 위하여 similar colorization과 ACE(Adaptive Circular filter and Edge) 알고리즘을 사용한다. 그리고 이렇게 추출된 특징을 해마 신경망을 통하여 학습한 후 멀티미디어 검색 시스템을 구성한다. 제안하는 해마 신경망은 호감도 조정에 의해서 입력되는 영상패턴의 특징들을 흥분학습과 억제학습을 이용하여 불필요한 특징은 억제시키고 중요한 특징은 흥분학습을 통해 장기기억 시켜서 적응성 있는 실시간 검색 시스템을 구현한다.

• 전기전자학회논문지
• /
• 제14권3호
• /
• pp.224-231
• /
• 2010

이미지에서의 자동 객체 인식은 컴퓨터 비젼 및 패턴 분석을 포함한 많은 분야에서 아주 중요한 이슈중의 하나이다. 특히, 최근 스마트폰과 같은 개인용 이동형 단말기가 빠르게 보급되면서, 그러한 기술들을 지원할 필요성이 커지게 되었다. 이러한 단말기들은 대개 카메라, GPS, 가속도 센서 등과 같은 장치들을 갖추고 있으며 사용자들에게 다양한 서비스를 편리한 인터페이스를 통해 제공하고 있다. 하지만 제한된 시스템 자원 때문에 처리속도가 비교적 느리다는 문제점을 가지고 있다. 본 논문에서 우리는 전처리 과정과 단순 지역 특징을 기반으로 한 객체 인식 성능 향상 기법을 제안한다. 전처리 단계에서는, 우선 객체 종류별 이미지로부터 각 객체의 특징이라고 생각되는 부분을 자동으로 판별하고 비슷한 부분끼리 분류한 다음 이들의 특징을 추출하고 학습한다. 질의 영상에 대해 우선 지역 특징 후보들을 파악한 다음 전처리 과정에서 학습된 정보와 비교하여 객체인식을 하게 된다. 실험을 통하여 제안된 기법의 객체 인식 성능을 보인다.

• 한국정보처리학회논문지
• /
• 제2권5호
• /
• pp.645-654
• /
• 1995

분산 DBMS는 네트워크의 각 사이트에서 서로 다른 사용자에 의해 독립적으로 설 계, 관리, 유지보수되고 있는 지역 스키마들을 통합하여 전역 가상 스키마를 제공하 며, 특정 사이트의 사용자가 다른 사이트의 지역 데이타베이스를 투명하게 이용할 수 있는 환경을 지원한다. 또한 각 지역 스키마에 부여된 스키마 구성 엔티티들의 보안 성질이 통합된 스키마에서도 유지되도록 해야 한다. 그러나 분산 DBMS에서 지역 스키 마의 보안성질을 유지할 수 있는 통합에 대한 연구는 거의 이루어지지 않았다. 본 논 문은 분산 DBMS 환경에서 각 사이트의 지역 스키마 정의를 위한 모델로서 객체지향 모 델을 확장한 다단계 보안 객체지향 데이타베이스 모델을 사용하였으며, 지역 스키마를 통합하는데 있어서 본래의 보안성질을 유지할 수 있는 통합 방법을 객체클래스, 객체 클래스사이의 관계를 중심으로 각각 8가지로 구분하여 제안하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.

• 한국정보처리학회논문지
• /
• 제7권7호
• /
• pp.1997-2007
• /
• 2000

This paper presents a new benchmark for object-relational database systems, which are regarded as the next-generation database system. This benchmark has been developed to evaluate system performance peculiar to object-relational database systems. The design philosophy, test databases, an test queries of the benchmark are presented. This benchmark features scaleability, use of a synthesized database only, and a query-oriented evaluation. We have implemented his benchmark with two commerical object-relational database systems and the experimental results are also reported.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.448-451
• /
• 1999

In this paper, we propose a new object representation method and matching algorithm for object recognition using a 3-fingered robot hand. Each finger tip can measure normal vector and shapes of a contacting surface. Object is represented by the inter-surface description table where the features of a surface are described in the diagonal and the relations between two surfaces are in the upper diagonal. Based on this table, a fast and the efficient matching algorithm has been proposed. This algorithm can be applied to natural quadric objects.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.306-308
• /
• 2006

We propose an attention based object recognition system, to recognize object fast and robustly. For this we calculate visual stimulus degrees and make saliency maps. Through this map we find a strongly attentive part of image by stimulus degrees, where local features are extracted to recognize objects.

• 디지털산업정보학회논문지
• /
• 제15권3호
• /
• pp.37-44
• /
• 2019

In this study, we propose the automatic extraction method of Rescue Requests from Drone Images. A central object is extracted from each image by using central object extraction method[7] before classification. A central object in an images are defined as a set of regions that is lined around center of the image and has significant texture distribution against its surrounding. In this case of artificial objects, edge of straight line is often found, and texture is regular and directive. However, natural object's case is not. Such characteristics are extracted using Edge direction histogram energy and texture Gabor energy. The Edge direction histogram energy calculated based on the direction of only non-circular edges. The texture Gabor energy is calculated based on the 24-dimension Gebor filter bank. Maximum and minimum energy along direction in Gabor filter dictionary is selected. Finally, the extracted rescue requestor object areas using the dominant features of the objects. Through experiments, we obtain accuracy of more than 75% for extraction method using each features.