• 한국전자파학회:학술대회논문집
• /
• 한국전자파학회 2003년도 종합학술발표회 논문집 Vol.13 No.1
• /
• pp.403-406
• /
• 2003

In this paper, we have proposed a carrier recovery algorithm of OFDM/QPSK-DMR(Orthogonal Frequency Division Multiplexing/Quadrature Phase Shift Keying Modulation-Digital Microwave Radio)system using BL-PSF(Band Limited-Pulse Shaping Filter) and have analyzed the carrier phase MSE(Mean Square Error) performance of OFDM/QPSK and single carrier DMR systems. The existing OFDM/QPSK-DMR system using windowing requires training sequence or CP(Cyclic prefix) to synchronize a receive. carrier frequency. Because in the OFDM/QPSK-DMR system using BL-PSF there is no training sequence or CP(Cyclic Prefix), we also propose a carrier recovery useful to the system. The simulation results confirm that the proposed carrier recovery algorithm has the same carrier phase MSE(Mean Square Error) performance for the single carrier DMR system under AWGN(Additive White Gaussian Noise) environment.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권3호
• /
• pp.180-191
• /
• 2002

본 논문은 MLP와 MultiCAMShift 알고리즘을 이용한 텍스춰 기반의 영상 내 문자 추출 방법을 제안한다. MLP를 이용한 텍스춰 분석기는 별도의 특징값 추출 단계 없이 다양한 환경의 입력 영상에 대해 효과적으로 문자 확률 영상을 생성하며, 문자 확률 영상 상에서 수행되는 MultiCAMShift 알고리즘은 국소 탐색만으로 효율적으로 문자 영역을 추출할 수 있다.

• International Journal of Aeronautical and Space Sciences
• /
• 제15권3호
• /
• pp.258-266
• /
• 2014

We present a system for the real-time visual relative navigation of a fixed-wing unmanned aerial vehicle in a GPS-denied environment. An extended Kalman filter is used to construct a vision-aided navigation system by fusing the image processing results with barometer and inertial sensor measurements. Using a mean-shift object tracking algorithm, an onboard vision system provides pixel measurements to the navigation filter. The filter is slightly modified to deal with delayed measurements from the vision system. The image processing algorithm and the navigation filter are verified by flight tests. The results show that the proposed aerial system is able to maintain circling around a target without using GPS data.

• Journal of the Korean Statistical Society
• /
• 제36권4호
• /
• pp.457-469
• /
• 2007

Many procedures are available to identify a single outlier or an isolated influential point in linear regression and logistic regression. But the detection of influential points or multiple outliers is more difficult, owing to masking and swamping problems. The multiple outlier detection methods for logistic regression have not been studied from the points of direct procedure yet. In this paper we consider the direct methods for logistic regression by extending the $Pe\tilde{n}a$ and Yohai (1995) influence matrix algorithm. We define the influence matrix in logistic regression by using Cook's distance in logistic regression, and test multiple outliers by using the mean shift model. To show accuracy of the proposed multiple outlier detection algorithm, we simulate artificial data including multiple outliers with masking and swamping.

• Journal of Multimedia Information System
• /
• 제5권4호
• /
• pp.257-264
• /
• 2018

Over the years application of computer vision techniques in sports videos for analysis have garnered interest among researchers. Videos of sports games like basketball, football are available in plenty due to heavy popularity and coverage. The goal of the researchers is to extract information from sports videos for analytics which requires the tracking of the players. In this paper, we explore use of deep learning networks for player spotting and propose an algorithm for tracking using Kalman filters. We also propose an algorithm for finding distance covered by players. Experiments on sports video datasets have shown promising results when compared with standard techniques like mean shift filters.

• 제어로봇시스템학회논문지
• /
• 제13권11호
• /
• pp.1074-1081
• /
• 2007

This paper presents a method for real-time face detection and tracking which combined Adaboost and Camshift algorithm. Adaboost algorithm is a method which selects an important feature called weak classifier among many possible image features by tuning weight of each feature from learning candidates. Even though excellent performance extracting the object, computing time of the algorithm is very high with window size of multi-scale to search image region. So direct application of the method is not easy for real-time tasks such as multi-task OS, robot, and mobile environment. But CAMshift method is an improvement of Mean-shift algorithm for the video streaming environment and track the interesting object at high speed based on hue value of the target region. The detection efficiency of the method is not good for environment of dynamic illumination. We propose a combined method of Adaboost and CAMshift to improve the computing speed with good face detection performance. The method was proved for real image sequences including single and more faces.

• Smart Structures and Systems
• /
• 제13권3호
• /
• pp.389-406
• /
• 2014

Optimal sensor placement techniques play a significant role in enhancing the quality of modal data during the vibration based health monitoring of civil structures, where many degrees of freedom are available despite a limited number of sensors. The literature has shown a shift in the trends for solving such problems, from expansion or elimination approach to the employment of heuristic algorithms. Although these heuristic algorithms are capable of providing a global optimal solution, their greatest drawback is the requirement of high computational effort. Because a highly efficient optimisation method is crucial for better accuracy and wider use, this paper presents an improved simulated annealing (SA) algorithm to solve the sensor placement problem. The algorithm is developed based on the sensor locations' coordinate system to allow for the searching in additional dimensions and to increase SA's random search performance while minimising the computation efforts. The proposed method is tested on a numerical slab model that consists of two hundred sensor location candidates using three types of objective functions; the determinant of the Fisher information matrix (FIM), modal assurance criterion (MAC), and mean square error (MSE) of mode shapes. Detailed study on the effects of the sensor numbers and cooling factors on the performance of the algorithm are also investigated. The results indicate that the proposed method outperforms conventional SA and Genetic Algorithm (GA) in the search for optimal sensor placement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1121-1141
• /
• 2020

We propose a robust visual object tracking algorithm fusing a convolutional neural network tracker trained offline from a large number of video repositories and a color histogram based tracker to track objects for mixing immersive audio. Our algorithm addresses the problem of occlusion and large movements of the CNN based GOTURN generic object tracker. The key idea is the offline training of a binary classifier with the color histogram similarity values estimated via both trackers used in this method to opt appropriate tracker for target tracking and update both trackers with the predicted bounding box position of the target to continue tracking. Furthermore, a histogram similarity constraint is applied before updating the trackers to maximize the tracking accuracy. Finally, we compute the depth(z) of the target object by one of the prominent unsupervised monocular depth estimation algorithms to ensure the necessary 3D position of the tracked object to mix the immersive audio into that object. Our proposed algorithm demonstrates about 2% improved accuracy over the outperforming GOTURN algorithm in the existing VOT2014 tracking benchmark. Additionally, our tracker also works well to track multiple objects utilizing the concept of single object tracker but no demonstrations on any MOT benchmark.

• 한국콘텐츠학회논문지
• /
• 제14권3호
• /
• pp.11-21
• /
• 2014

다중 스케일 영상 분할은 영상 스타일링과 의료진단과 같은 여러 응용에서 매우 중요하다. 이 논문은 다중 스케일 구조를 확보하며 안정적이고 효율적인 MSER에 기반을 둔 새로운 알고리즘을 제안한다. 이 알고리즘은 영상에서 MSER를 수집한 후, 이것들을 특정한 순서대로 영상에 다시 그려 넣음으로써 영상을 분할한다. 영상 경계를 평활화하고 잡음을 제거하기 위한 계층적 모폴로지 연산을 제안한다. 알고리즘의 다중 스케일 특성을 보이기 위해, 여러 종류의 상세 단계 제어의 효과를 영상 스타일링에 적용한다. 제안한 기법은 이러한 효과를 시간이 많이 걸리는 다중 가우시언 평활화없이 수행한다. 분할 품질과 계산 시간 측면에서 민쉬프트-기반 Edison 시스템과 비교 결과를 제시한다.

• 한국산학기술학회논문지
• /
• 제15권8호
• /
• pp.5263-5268
• /
• 2014

본 논문은 사람 검출 알고리즘을 고해상도 CCTV 카메라에 적용할 수 있도록 빠른 사람 검출 알고리즘을 제안한다. HOG 디텍터를 이용한 사람 검출 알고리즘은 영상처리 분야의 최신 기술로 높은 성능을 보인다. 그러나 HOG 특징 추출과정에서 연산 속도가 느려 실시간 고해상도 영상에 적용하기 어렵다. 이러한 문제를 해결하기 위해 2단계 검출 방법을 제안한다. 먼저 전처리 과정으로 배경 차감법(Background subtraction)을 이용하여 사람 후보 영역을 찾는다. 이후 사람 후보영역에서만 HOG 디텍터를 이용하여 사람/비사람 구분을 수행한다. 이러한 두 단계의 실험 결과 약 2.5배의 검출 속도 향상을 보였으며, 성능 저하는 거의 없음을 확인할 수 있었다.