• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.793-796
• /
• 2004

이 논문에서 제안한 ICA기반 피처추출 알고리즘은 다차원 영상에서 각 픽셀의 반사도 분광영역이 서로 다른 물체타입(목표피처와 배경피처)으로 이루어진 선형 혼합 분광영역으로 가정되는 픽셀에 대한 목표피처 탐지를 목적으로 한다. Landsat ETM+ 위성영상은 다차원 데이터구조로 이루어져 있으며, 영상에는 추출하고자하는 목표피처와 여러 종류의 배경피처들이 혼재한다. 이 논문에서는 목표피처(김양식장) 주변의 배경피처(갯뻘, 바닷물 등)들을 효과적으로 제거하기 위하여 목표피처의 픽셀 분광영역을 배경피처의 픽셀 분광영역으로 직교투영하게 된다. 픽셀내의 나머지 목표피처 분광영역의 양은 배경피처의 분광영역을 제거함으로써 추정하게 된다. 이 논문에서 제안한 ICA기반의 피처추출 방법의 우수성을 확인하기 위하여 Landsat ETM+ 위성영상에서 김양식장 피처를 추출하는데 적용하였다. 또한 피처추출 후 제거되지 않고 남아 있는 잡음(noise)정도와 피처추출 정확도 측면에서 전통적으로 가장 많이 사용되고 있는 최대우도 분류방법과 비교실험을 하였다. 결과적으로 이 논문에서 제안하는 방법이 목표피처 주변의 혼합분광영역에서 배경피처를 효과적으로 제거하여 추출하고자 하는 목표피처를 추출하는데 있어 우수한 탐지 성능을 보임을 알 수 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.10B
• /
• pp.1390-1398
• /
• 2001

시선 위치 추적이란 사용자가 모니터 상의 어느 지점을 쳐다보고 있는 지를 파악해 내는 기술이다. 시선 위치를 파악하기 위해 본 논문에서는 2차원 카메라 영상으로부터 얼굴 영역 및 얼굴 특징점을 추출한다. 초기에 모니터상의 3 지점을 쳐다볼 때 얼굴 특징점들은 움직임의 변화를 나타내며, 이로부터 카메라 보정 및 매개변수 추정 방법을 이용하여 얼굴특징점의 3차원 위치를 추정한다. 이후 사용자가 모니터 상의 또 다른 지점을 쳐다볼 때 얼굴 특징점의 변화된 3차원 위치는 3차원 움직임 추정방법 및 아핀변환을 이용하여 구해낸다. 이로부터 변화된 얼굴 특징점 및 이러한 얼굴 특징점으로 구성된 얼굴평면이 구해지며, 이러한 평면의 법선으로부터 모니터 상의 시선위치를 구할 수 있다. 실험 결과 19인치 모니터를 사용하여 모니터와 사용자까지의 거리를 50∼70cm정도 유지하였을 때 약 2.08인치의 시선위치에러 성능을 얻었다. 이 결과는 Rikert의 논문에서 나타낸 시선위치추적 성능(5.08cm 에러)과 비슷한 결과를 나타낸다. 그러나 Rikert의 방법은 모니터와 사용자 얼굴까지의 거리는 항상 고정시켜야 한다는 단점이 있으며, 얼굴의 자연스러운 움직임(회전 및 이동)이 발생하는 경우 시선위치추적 에러가 증가되는 문제점이 있다. 동시에 그들의 방법은 사용자 얼굴의 뒤 배경에 복잡한 물체가 없는 것으로 제한조건을 두고 있으며 처리 시간이 상당히 오래 걸리는 문제점이 있다. 그러나 본 논문에서 제안하는 시선 위치 추적 방법은 배경이 복잡한 사무실 환경에서도 사용가능하며, 약 3초 이내의 처리 시간(200MHz Pentium PC)이 소요됨을 알 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.512-517
• /
• 2018

Improving voice quality is a major concern in telecommunications. In this paper, we propose a robust speech quality enhancement against background noise and packet loss at VoIP (Voice-over-IP) receiver. The proposed method combines network jitter estimation based on hybrid Markov chain, adaptive playout scheduling using the estimated jitter, and speech enhancement based on restoration of amplitude and phase to enhance the quality of the speech signal arriving at the VoIP receiver over IP network. The experimental results show that the proposed method removes the background noise added to the speech signal before encoding at the sender side and provides the enhanced speech quality in an unstable network environment.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.449-455
• /
• 2014

Detection of moving objects is a fundamental task in most of the computer vision applications, such as video surveillance, activity recognition and human motion analysis. This is a difficult task due to many challenges in realistic scenarios which include irregular motion in background, illumination changes, objects cast shadows, changes in scene geometry and noise, etc. In this paper, we propose an foreground extraction algorithm based on codebook, a database of information about background pixel obtained from input image sequence. Initially, we suppose a first frame as a background image and calculate difference between next input image and it to detect moving objects. The resulting difference image may contain noises as well as pure moving objects. Second, we investigate a codebook with color and brightness of a foreground pixel in the difference image. If it is matched, it is decided as a fault detected pixel and deleted from foreground. Finally, a background image is updated to process next input frame iteratively. Some pixels are estimated by input image if they are detected as background pixels. The others are duplicated from the previous background image. We apply out algorithm to PETS2009 data and compare the results with those of GMM and standard codebook algorithms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.2
• /
• pp.260-267
• /
• 2011

This paper proposes a method for segmenting objects from the background in IR(Infrared) images based on GrabCut algorithm. The GrabCut algorithm needs the window encompassing the interesting known object. This procedure is processed by user. However, to apply it for object recognition problems in image sequences. the location of window should be determined automatically. For this, we adopted the Otsu' algorithm for segmenting the interesting but unknown objects in an image coarsely. After applying the Otsu' algorithm, the window is located automatically by blob analysis. The GrabCut algorithm needs the probability distributions of both the candidate object region and the background region surrounding closely the object for estimating the Gaussian mixture models(GMMs) of the object and the background. The probability distribution of the background is computed from the background window, which has the same number of pixels within the candidate object region. Experiments for various IR images show that the proposed method is proper to segment out the interesting object in IR image sequences. To evaluate performance of proposed segmentation method, we compare other segmentation methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.10
• /
• pp.2090-2101
• /
• 2015

We propose a robust tracking method that combines the merits of ACM(active contour model) and the color-based PF(particle filter), effectively. In the proposed method, PF and ACM track the color distribution and the contour of the target, respectively, and Decision part merges the estimate results from the two trackers to determine the position and scale of the target and to update the target model. By controlling the internal energy of ACM based on the estimate of the position and scale from PF tracker, we can prevent the snake pointers from falsely converging to the background clutters. We appled the proposed method to track the head of person in video and have conducted computer experiments to analyze the errors of the estimated position and scale.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.238-244
• /
• 2013

In energy dispersive X-ray fluorescence analysis, the removal of the continuum on which the X-ray spectrum is superimposed is one of the most important processes, since it has a strong influence on the analysis result. The existing methods which have been used for it usually require tight constraints or prior information on the continuum. In this paper, an efficient background correction method is proposed for Energy Dispersive X-ray fluorescence (EDXRF) spectra. The proposed method has two steps of background modeling and background correction. It is based on the basic concept which differentiates background areas from the peak areas in a spectrum and the SNIP algorithm, one of the popular methods for background removal, is used to enhance the performance. After detecting some points which belong to the background from a spectrum, its background is modeled by a curve fitting method based on them. And then the obtained background model is subtracted from the raw spectrum. The method has been shown to give better results than some of traditional methods, while working under relatively weak constraints or prior information.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.5
• /
• pp.231-240
• /
• 2015

Medical imagery require to protect the privacy with preserving the quality of the original contents. Therefore, reversible watermarking is a solution for this purpose. Previous researches have focused on general imagery and achieved high capacity and high quality. However, they raise a distortion over entire image and hence are not applicable to medical imagery which require to preserve the quality of the objects. In this paper, we propose a novel reversible watermarking for medical imagery, which preserve the quality of the objects and achieves high capacity. First, object and background region is segmented and then predicted error histogram-based reversible watermarking is applied for each region. For the efficient watermark embedding with small distortion in the object region, the embedding level at object region is set as low while the embedding level at background region is set as high. In experiments, the proposed algorithm is compared with the previous predicted error histogram-based algorithm in aspects of embedding capacity and perceptual quality. Results support that the proposed algorithm performs well over the previous algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.15-22
• /
• 2005

This paper proposed a object tracking algorithm which can track contour of fast moving object through motion estimation. Since the proposed tracking algorithm is based on the radial representation, the motion estimation of object can be accomplished at the center of object with the low computation complexity. The motion estimation of object makes it possible to track object which move fast more than distance from center point to contour point for each frame. In addition, by introducing both gradient image and difference image into energy functions in the process of energy convergence, object tracking is more robust to the complex background. The results of experiment show that the proposed algorithm can track fast moving object in real-time and is robust under the complex background.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.5
• /
• pp.64-72
• /
• 2007

In this paper we proposed a combined active contour model and motion estimation-based object tracking technique. After assigning the initial contour, we find the object's boundary and update the initial contour by using object's motion information. In the following frames, similar snake algorithm is repeated to make continuously estimated object's region. The snake algerian plays a role in separating the object from background, while motion estimation provides object's moving direction and displacement. The proposed algorithm provides equivalently stable, robust, tracking performance with significantly reduced amount of computation, compared with the existing shape model-based algorithms.