• Korean Journal of Remote Sensing
• /
• v.35 no.5_1
• /
• pp.681-692
• /
• 2019

In this paper, a hybrid deep learning model, called 2D convolution with bidirectional long short-term memory (2DCBLSTM), is presented that can effectively combine both spatial and temporal features for crop classification. In the proposed model, 2D convolution operators are first applied to extract spatial features of crops and the extracted spatial features are then used as inputs for a bidirectional LSTM model that can effectively process temporal features. To evaluate the classification performance of the proposed model, a case study of crop classification was carried out using multi-temporal unmanned aerial vehicle images acquired in Anbandegi, Korea. For comparison purposes, we applied conventional deep learning models including two-dimensional convolutional neural network (CNN) using spatial features, LSTM using temporal features, and three-dimensional CNN using spatio-temporal features. Through the impact analysis of hyper-parameters on the classification performance, the use of both spatial and temporal features greatly reduced misclassification patterns of crops and the proposed hybrid model showed the best classification accuracy, compared to the conventional deep learning models that considered either spatial features or temporal features. Therefore, it is expected that the proposed model can be effectively applied to crop classification owing to its ability to consider spatio-temporal features of crops.

• Korean Journal of Cognitive Science
• /
• v.4 no.2
• /
• pp.181-200
• /
• 1994

In the learning phase of multilyer feedforword neural network,there are problems such that local minimum,learning praralysis and slow learning speed when backpropagation algorithm used.To overcome these problems, the genetic algorithm has been used as learing method in the multilayer feedforword neural network instead of backpropagation algorithm.However,because the genetic algorith, does not have any mechanism for fine-tuned local search used in backpropagation method,it takes more time that the genetic algorithm converges to a global optimal solution.In this paper,we suggest a new GA-BP method which provides a fine-tunes local search to the genetic algorithm.GA-BP method uses gradient descent method as one of genetic algorithm's operators such as mutation or crossover.To show the effciency of the developed method,we applied it to the 3-parity bit problem with analysis.

• Convergence Security Journal
• /
• v.7 no.1
• /
• pp.1-10
• /
• 2007

Surveillance system with the fixed field of view generally has an identical background and is easy to extract and segment a moving object. However, it is difficult to extract the object when the gray level of the background is varied due to illumination condition in the real circumstance. In this paper we propose the segmentation algorithm to extract effectively the object in spite of the illumination change. In order to minimize the effect of illumination, the proposed algorithm is composed of three modes according to the background generation and the illuminational change. Then the object is finally obtained by using projection and the morphological operator in post-processing. A good segmentation performance is demonstrated by the simulation result.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.4
• /
• pp.137-142
• /
• 2017

Recently, along with the development of IoT technology, technologies for wirelessly sensing various data, such as sensor nodes, RFID, CCTV, smart phones, etc., have rapidly developed, and in the field of multiple applications, to utilize sensor network related technology Have been actively pursued in various fields. Therefore, as GeoSensor utilization increases, query processing systems for efficiently processing 2D data such as spatial sensor data are actively researched. However, existing spatial query processing systems do not support a spatial-temporal data type and a spatial-temporal operator for processing spatial-temporal sensor data. Therefore, they are inadequate for processing spatial-temporal sensor data like GeoSensor. Accordingly, this paper developed a spatial-temporal query processing system, for efficient spatial-temporal query processing of spatial-temporal sensor data in a sensor network.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.53-62
• /
• 2007

In this paper, it can propose that Fuzzy Wavelet Morphology Neural Networks for the edge detection algorithm with being robustly a unclear boundary parts by brightness difference and being less sensitivity on direction to be detected the edges of images. This is applying the Fuzzy Wavelet Morphology Operator which can be simple the image robustly without the loss of data to DTCNN Structure for improving defect which carrys out a lot of operation complexly. Also, this color image can segment Y image with YCbCr space color model which has a lossless feature information of edge boundary sides effectively. This paper can offer the simulation of color images of 50ea for the performance verification of the proposal algorithm.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.6_1
• /
• pp.559-565
• /
• 2012

The purpose of the present study is to suggest the meta data of the attribute mapping for interoperability from IFC to CityGML. For this, we analyzed the interoperability issue including the neutral information model structure such as IFC, CityGML. To solve the interoperability problem between IFC and CityGML model which is the neutral GIS format, We proposed the meta data including the mapping rule. The meta data is consists of the connection information between BIM and GIS model, the mapping rule based on the perspective of the use-case, the operator and the attribute. By using this, XML to represent the meta data is defined and the information mapping system is developed.

• Computational Structural Engineering
• /
• v.7 no.4
• /
• pp.85-101
• /
• 1994

A family of variational principles governing the dynamics of laminated plate has been derived using a variationally consistent shear deformable discrete laminated plate theory with particular reference to finite element procedures. The theoretical basis for the derivation is Sandhu's generalized procedure for the variational formulation of linear coupled boundary value problem. As the bilinear mapping to write the operator matrix of the field equations in self-adjoint form, convolution product was employed. Boundary conditions, initial conditions and probable internal discontinuity were explicitly included in the governing functionals. Some interesting extensions and specializations of the general variational principle were presented, which can provide many different finite element formulations for the problem.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.285-290
• /
• 2006

본 논문에서는 출입국자 관리의 효율성과 체계적인 출입국 관리를 위하여 여권 코드를 자동으로 인식하고 위조 여권을 판별할 수 있는 여권 인식 및 얼굴 인증 방법을 제안한다. 본 논문의 구성은 여권 인식과 얼굴 인증 부분으로 구성되며, 여권 인식 부분에서는 소벨 연산자, 수평 최소값 필터 등을 적용한 후, 8 방향 윤곽선 추적 알고리즘을 적용하여 코드의 문자열 영역을 추출하고 기울기를 보정한다. 추출된 문자열은 반복 이진화 방법을 적용하여 코드의 문자열 영역을 이진화 한다. 이진화된 문자열 영역에 대해 8 방향 윤곽선 추적 알고리즘을 적용하여 개별 코드를 추출한 후에 SOM(Self-Organizing Maps) 알고리즘을 적용하여 여권 코드를 인식한다. 얼굴 인증 부분에서는 여권 사진 영역의 특징을 이용하여 얼굴 후보 영역을 추출한 후, RGB와 YCbCr 색공간에서 피부색 정보를 이용하여 얼굴 영역을 추출한다. 추출된 얼굴 영역은 PCA(Principal Component Analysis) 알고리즘을 적용하여 특징 벡터를 구하고 여권 코드가 인식된 결과를 바탕으로 여권 소지자의 데이터 베이스에 있는 얼굴 영상의 특징벡터와의 거리 값을 계산하여 사진 위조 여부를 판별한다. 제안된 여권 인식 및 얼굴 인증 방법의 성능 평가를 위하여 원본 여권의 얼굴 부분을 위조한 여권과 기울어진 여권 영상을 대상으로 실험한 결과, 제안된 방법이 여권의 코드 인식 및 얼굴 인증에 있어서 우수한 성능이 있음을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.175-176
• /
• 2020

본 논문에서는 가상 현실 기기를 이용하여 스택, 큐, 트리 등과 같은 복잡한 자료구조에 대한 학습을 도와주는 학습 지원 시스템을 제안한다. 컴퓨터 프로그래밍에서 적절한 자료구조를 선택함으로써 보다 효율적인 알고리즘을 구현할 수 있으며 프로그램 실행시간, 메모리 용량과 같은 컴퓨팅 자원을 효율적으로 사용할 수 있다. 본 논문에서 제안하는 EZ 학습 시스템은 비전공자의 자료구조 학습에 도움을 주며 특히, 스마트 폰 기반의 가상 현실 기기를 사용하여 학습자의 흥미를 유발하고자 한다. 학습자는 가상공간을 통해 정보를 보다 쉽게 받아들이고, 게임적인 요소를 통해 학습에 대한 집중도를 높일 수 있을 것으로 기대된다. EZ 학습 시스템은 스택 자료형에 대한 개념 설명, 스택 연산자 학습, 미로 탐색을 통한 스택 응용 사례를 제공한다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.6 no.1 s.11
• /
• pp.11-17
• /
• 1998

Recently, 3D GIS based on 3D geo-processing methodology and Internet environment are emerging issues in GIS fields. To design and implement 3D GIS, the strategic linkage of Java and VRML is first regarded: 3D feature format definition in the passion of conventional GIS including aspatial attributes, 3B feature indexing, 3D analytical operators such as selection, buffering, and Near, Metric operation such as distance measurement and statistical description, and 3D visualization. In 3D feature format definition, the following aspects are implemented: spatial information for 3D primitives extended from 2D primitives, multimedia data, object texture or color of VRML specification. DXF-format GIS layers with additional attributes are converted to 3D feature format and imported into this system. While, 3D analytical operators are realized in the form of 3D buffering with respect to user-defined point, line, polygon, and 3D objects, and 3D Near functions; furthermore, 'Lantern operator' is newly introduced in this 3D GIS. Because this system is implemented by Java applet, any client with Java-enable browser including VRML browser plug-in can utilize the new style of 3D GIS function in the virtual space. Conclusively, we present prototype of WWW-based 3D GIS, and this approach will be contribute to development of core modules on the stage of concept establishment and of real application model in future.