• 대한원격탐사학회지
• /
• 제28권1호
• /
• pp.55-67
• /
• 2012

멀티센서 시스템으로부터 취득된 영상을 이용하여 공간정보를 신속하게 생성하기 위해서 영상의 실시간 지오레퍼런싱이 요구된다. 위치/자세 센서의 성능을 보완하며 실시간 처리가 가능하려면 연속 추정 알고리즘을 활용한 온라인 항공삼각측량이 수행되어야 한다. 본 연구는 연속적으로 취득되는 영상의 실시간 지오레퍼런싱을 위한 효율적인 온라인 항공삼각측량 방법론을 도출하고자 한다. 기존의 기븐스 변환 갱신 알고리즘과 최근 개발된 관측값 분류에 기반한 정규행렬 역행렬 갱신 알고리즘을 활용하여 온라인 항공삼각 측량을 구현하였다. 정확도와 연산 속도 측면에서 두 알고리즘의 성능을 비교 검증하기 위하여 항공 멀티센서 시스템으로부터 취득된 센서 데이터를 모의 생성하고 이를 적용하였다. 적용 결과, 관측값 분류에 기반한 정규행렬 역행렬 갱신에 의한 온라인 항공삼각측량이 기븐스 변환에 의한 방법보다 추정된 지상점 좌표에 대하여 40 % 이상 높은 정확도를 보이고, 8배 이상의 빠른 처리 속도를 나타내었다. 따라서, 영상의 실시간 지오레퍼런싱을 위하여 정규행렬 역행렬 갱신에 의한 온라인 항공삼각측량이 더 적합한 것으로 판단되었다.

• 대한의용생체공학회:의공학회지
• /
• 제16권3호
• /
• pp.271-278
• /
• 1995

An ECG data compression algorithM using max-min slope update is proposed and a real time 3 channel ECG transmission system is implemented using the proposed algorithm. In order to effectively compress ECG data, we compare a threshold value with the max-min slope difference (MMSD) which is updated at each sample values. If this MMSD value is smaller than the threshold value, then the data is compressed. Conversely, when the MMSD value is larger than threshold value, the data is transmitted after storing the value and the length between the data which is beyond previous threshold level. As a result, it can accurately compress both the region of QRS, P, and T wave that has fast-changing and the region of the base line that slope is changing slow. Therefore, it Is possible to enhance the compression rate and the percent roms difference. In addition, because of the simplicity, this algorithm is more suitable for real-time implementation.

• Journal of information and communication convergence engineering
• /
• 제13권1호
• /
• pp.42-49
• /
• 2015

In laser pointer interaction systems, laser spot detection is one of the most important technologies, and most of the challenges in this area are related to the varying backgrounds, and the real-time performance of the interaction system. In this paper, we present a robust dictionary construction and update algorithm based on a sparse model of background subtraction. In order to control dynamic backgrounds, first, we determine whether there is a change in the backgrounds; if this is true, the new background can be directly added to the dictionary configurations; otherwise, we run an online cumulative average on the backgrounds to update the dictionary. The proposed dictionary construction and update algorithm for laser spot detection, is robust to the varying backgrounds and noises, and can be implemented in real time. A large number of experimental results have confirmed the superior performance of the proposed method in terms of the detection error and real-time implementation.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.20-27
• /
• 2020

Sound event detection in real-world environments suffers from the interference of non-stationary and time-varying noise. This paper presents an adaptive noise reduction method for sound event detection based on non-negative matrix factorization (NMF). In this paper, we proposed a deep learning model that integrates Convolution Neural Network (CNN) with Non-Negative Matrix Factorization (NMF). To improve the separation quality of the NMF, it includes noise update technique that learns and adapts the characteristics of the current noise in real time. The noise update technique analyzes the sparsity and activity of the noise bias at the present time and decides the update training based on the noise candidate group obtained every frame in the previous noise reduction stage. Noise bias ranks selected as candidates for update training are updated in real time with discrimination NMF training. This NMF was applied to CNN and Hidden Markov Model(HMM) to achieve improvement for performance of sound event detection. Since CNN has a more obvious performance improvement effect, it can be widely used in sound source based CNN algorithm.

• International Journal of Internet, Broadcasting and Communication
• /
• 제9권1호
• /
• pp.9-17
• /
• 2017

This paper describes a process of developing commercial real time image recognition system with company. In this paper we will make a system that is combining an empirical kernel map method and conjugate least squares support vector machine in order to represent images in a low-dimensional subspace for real time image recognition. In the traditional approach calculating these eigenspace models, known as traditional PCA method, model must capture all the images needed to build the internal representation. Updating of the existing eigenspace is only possible when all the images must be kept in order to update the eigenspace, requiring a lot of storage capability. Proposed method allows discarding the acquired images immediately after the update. By experimental results we can show that empirical kernel map has similar accuracy compare to traditional batch way eigenspace method and more efficient in memory requirement than traditional one. This experimental result shows that proposed model is suitable for commercial real time image recognition system.

• 한국ITS학회 논문지
• /
• 제20권1호
• /
• pp.193-202
• /
• 2021

고정밀 지도의 갱신은 정사영상 또는 점군 데이터 등을 원천 자료로 하여 기하 정보를 우선적으로 수정한 이후 지도를 구성하는 공간객체들 간의 연관관계를 재정립하는 방식으로 진행된다. 이러한 일련의 과정들은 기하 정보를 처리하는 데에 많은 시간을 소요하므로 차량의 실시간 경로 계획(Real-time route planning)에 빠르게 적용되기 어렵다. 따라서 이 연구에서는 그래프 구조를 활용하여 경로 계획을 위한 도로 연결구조를 우선적으로 업데이트 하는 방식 및 도로 네트워크의 특징을 고려한 그래프 구조의 저장 유형을 제안하였다. 또한 제안된 방법을 실제 도로 자료에 적용해 봄으로써 실시간 경로 정보 전송 시의 활용 가능성에 대해 검토하였다.

• 한국생산제조학회지
• /
• 제23권4호
• /
• pp.337-344
• /
• 2014

While implicit integration methods such as Newton's method have excellent stability for the analysis of stiff and constrained mechanical systems, they have the drawback that the evaluation and LU-factorization of the system Jacobian matrix required at every time step are time-consuming. This paper proposes a Jacobian update-free Newton's method in order to overcome these defects. Because the motions of all bodies in a vehicle model are limited with respect to the chassis body, the equations are formulated with respect to the moving chassis-body reference frame instead of the fixed inertial reference frame. This makes the system Jacobian remain nearly constant, and thus allows the Newton's method to be free from the Jacobian update. Consequently, the proposed method significantly decreases the computational cost of the vehicle dynamic simulation. This paper provides detailed generalized formulation procedures for the equations of motion, constraint equations, and generalized forces of the proposed method.

• 대한전자공학회논문지
• /
• 제26권11호
• /
• pp.1857-1866
• /
• 1989

In this paper, an algorithm to update a codebook using a neural network in consecutive images, is proposed. With the Kohonen's self-organizing feature map, we adopt the iterative technique to update a centroid of each cluster instead of the unsupervised learning technique. Because the performance of this neural model is comparable to that of the LBG algorithm, it is possible to update the codebooks of consecutive frames sequentially in TV and to realize the hardwadre on the real-time implementation basis.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.588-591
• /
• 2009

유비쿼터스 컴퓨팅 환경의 GIS 서비스는 모바일 기기를 이용하여 언제 어디서나 공간데이터를 이용할 수 있다. GIS 서비스는 최적의 서비스를 제공하기 위해 주기적으로 공간데이터를 최신의 데이터로 갱신한다. 모바일 환경에서는 이를 위해 변경데이터를 CD로 배포하거나 유선 네트워크를 이용한 업데이트 서비스를 제공한다. 그러나 이러한 배포방식은 실제 세계의 변경이 사용자에게 전달되기까지 오랜 시간이 소모되는 문제가 있다. 이 논문에서는 사용자까지 변경 데이터가 도달하는 시간을 최소화 하기위한 동기화 시스템을 제안한다. 이 동기화 시스템은 모바일 기기를 이용하여 현장에서 변경된 데이터를 수집하고, 수집된 데이터를 무선네트워크를 이용하여 실시간으로 서버와 동기화한다. 이를 위하여 무선 네트워크 모듈과 변경 데이터를 갱신하는 동기화 모듈을 설계 및 구현하였다.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2007년도 춘계학술발표회 논문집
• /
• pp.289-293
• /
• 2007

Because the current numerical value map and update system in use do not reflect rapidly enough the transformation of topography, their usage are gradually in decrease. Therefore, there is an increasing demand for reception update system of numerical value map which can guarantee the accuracy and up-to-dateness of data. While rapid detection of topographical transformation is essential for rapid updating, the existing research based on remote investigation or direct measurement was difficult to apply efficiently in terms of cost and accuracy. Thereupon, this research aims to present efficient methods of detecting topographical transformations for a frequent real time updating of numerical value map using the topographical transformation and related data inputted in real time into the administrative information system.