Change Detection Algorithm on Wavelet and Markov Random Field

Song Hongxun,Wang Weixing,Zhang Tingting,Yu Tianchao,Song Junfang 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.4

In this study, the algorithm that applies Wavelet and multi-scale analysis to remote sensing images is proposed for region variation detection on Markov random field. First of all, the Wavelet transform is adopted to decompose an original image into several sub-images, then the Mahalanobis distance decision function is used to detect the changes in different scale images, and finally the Markov random field is applied to fuse the change detection results at different scales. Since the Markov random field fusion method takes full account of the correlation between the adjacent pixels and the links of the change detection results at different scales, the fusion results are accurate and practical. The testing results prove that the studied algorithm is effective and robust.

피라미드 구조와 베이지안 접근법을 이용한 Markove Random Field의 효율적 모델링

정명희 ( Myung Hee Jung ),홍의석 ( Eui Seok Hong ) 대한원격탐사학회 1999 대한원격탐사학회지 Vol.15 No.2

Remote sensing technique has offered better understanding of our environment for the decades by providing useful level of information on the landcover. In many applications using the remotely sensed data, digital image processing methodology has been usefully employed to characterize the features in the data and develop the models. Random field models, especially Markov Random Field (MRF) models exploiting spatial relationships, are successfully utilized in many problems such as texture modeling, region labeling and so on. Usually, remotely sensed imagery are very large in nature and the data increase greatly in the problem requiring temporal data over time period. The time required to process increasing larger images is not linear. In this study, the methodology to reduce the computational cost is investigated in the utilization of the Markov Random Field. For this, multiresolution framework is explored which provides convenient and efficient structures for the transition between the local and global features. The computational requirements for parameter estimation of the MRF model also become excessive as image size increases. A Bayesian approach is investigated as an alternative estimation method to reduce the computational burden in estimation of the parameters of large images.

세미-마르코프 조건 랜덤 필드 기반의 수화 적출

조성식(Seong-Sik Cho),이성환(Seong-Whan Lee) 한국정보과학회 2009 정보과학회논문지 : 소프트웨어 및 응용 Vol.36 No.12

수화 적출이란 연속된 영상에서 수화의 시작과 끝점을 찾고, 이를 사전에 정의된 수화 단어로 인식하는 방법을 말한다. 수화는 매우 다양한 손의 움직임과 모양으로 구성되어 있고, 그 변화가 다양하여 적출에 많은 어려움이 있다. 특히, 다양한 길이의 궤적 정보로 구성된 수화는 길이가 긴 수화에 대해 짧은 길이를 갖는 수화가 인식에 필요한 정보를 추출하기 어려운 문제점 있다. 본 논문에서는 다양한 길이를 갖는 입력 데이터의 특징을 반영할 수 있는 Semi-Markov Conditional Random Field에 기반하여 다양한 수화의 길이에 강인하게 수화를 적출하는 방법을 제안한다. 성능 평가를 위해 미국 수화와 한국 수화 데이터베이스를 사용하여 연속된 수화 영상에서의 수화 적출 성능을 평가하였고, 실험 결과 기존의 Hidden Markov Model과 Conditional Random Field보다 뛰어난 성능을 보였다. Sign language spotting is the task of detecting the start and end points of signs from continuous data and recognizing the detected signs in the predefined vocabulary. The difficulty with sign language spotting is that instances of signs vary in both motion and shape. Moreover, signs have variable motion in terms of both trajectory and length. Especially, variable sign lengths result in problems with spotting signs in a video sequence, because short signs involve less information and fewer changes than long signs. In this paper, we propose a method for spotting variable lengths signs based on semi-CRF (semi-Markov Conditional Random Field). We performed experiments with ASL (American Sign Language) and KSL (Korean Sign Language) dataset of continuous sign sentences to demonstrate the efficiency of the proposed method. Experimental results show that the proposed method outperforms both HMM and CRF.

Local Autoencoding for Parameter Estimation in a Hidden Potts-Markov Random Field

Sanming Song,Bailu Si,Herrmann, J. Michael,Xisheng Feng IEEE 2016 IEEE TRANSACTIONS ON IMAGE PROCESSING - Vol.25 No.5

<P>A local-autoencoding (LAE) method is proposed for the parameter estimation in a Hidden Potts-Markov random field model. Due to sampling cost, Markov chain Monte Carlo methods are rarely used in real-time applications. Like other heuristic methods, LAE is based on a conditional independence assumption. It adapts, however, the parameters in a block-by-block style with a simple Hebbian learning rule. Experiments with given label fields show that the LAE is able to converge in far less time than required for a scan. It is also possible to derive an estimate for LAE based on a Cramer-Rao bound that is similar to the classical maximum pseudolikelihood method. As a general algorithm, LAE can be used to estimate the parameters in anisotropic label fields. Furthermore, LAE is not limited to the classical Potts model and can be applied to other types of Potts models by simple label field transformations and straightforward learning rule extensions. Experimental results on image segmentations demonstrate the efficiency and generality of the LAE algorithm.</P>

클러스터링과 마르코프 랜덤 필드를 이용한 배경 모델링 기법 제안

한희일(Hee-il Hahn),박수빈(Soobin Park) 大韓電子工學會 2011 電子工學會論文誌-SP (Signal processing) Vol.48 No.1

본 논문에서는 마르코프 랜덤 필드(Markov random fields: MRF) 기반으로 배경을 모델링하는 방식과 함께 관련 파라미터들을 추정하는 알고리즘을 제안한다. 화소 기반의 배경 모델링 기법은 인근 화소 간의 연관성을 고려하지 않고 화소 단위의 시간적 변화에 대한 통계적 특성에 주로 의존하므로 판정 오류를 줄이는데 한계가 있다. 제안 알고리즘은 화소 기반으로 배경모델을 일차적으로 수행한 다음 MRF를 이용하여 시공간적으로 인근한 화소 간의 상호 의존성을 활용하여 배경모델의 정확도를 향상시키는데 그 목적을 두고 있다. MRF는 기본적으로 파라미터의 크기에 매우 민감하므로 기존의 MRF 기반 알고리즘은 이미지에 따라 적절한 값을 사전에 구하여 적용하고 있다. 제안한 방식은 초기에 임의의 파라미터로 배경/전경 상태변수를 구한 후에 이의 통계적 특성을 이용하여 파라미터들을 추정하고 추정된 파라미터를 적용하여 상태변수를 재차 구하는 과정을 반복함으로써 최적의 파라미터에 적응적으로 수렴하도록 조정한다. 실내외의 다양한 환경에서 촬영한 비디오를 이용하여 제안한 방식 성능을 확인한다. It is challenging to detect foreground objects when background includes an illumination variation, shadow or structural variation due to its motion. Basically pixel-based background models including codebook-based modeling suffer from statistical randomness of each pixel. This paper proposes an algorithm that incorporates Markov random field model into pixel-based background modeling to achieve more accurate foreground detection. Under the assumptions the distance between the pixel on the input image and the corresponding background model and the difference between the scene estimates of the spatio-temporally neighboring pixels are exponentially distributed, a recursive approach for estimating the MRF regularizing parameters is proposed. The proposed method alternates between estimating the parameters with the intermediate foreground detection and estimating the foreground detection with the estimated parameters, after computing it with random initial parameters. Extensive experiment is conducted with several videos recorded both indoors and outdoors to compare the proposed method with the standard codebook-based algorithm.

분산 유전자 알고리즘을 이용한 동영상 분할

김은이,박세현 건국대학교 산업기술연구원 2004 건국기술연구논문지 Vol.29 No.-

This paper presents a Bayesian framework for simultaneous motion segmentation and estimation using genetic algorithms (GAs). The segmentation label and motion field are modeled by Markov random fields (MRFs), and a MAP estimate is used to identify the optimal label and motion field. In this paper, the motion segmentation and estimation problems are formalized as optimization problems of the energy function. And, the process for optimization of energy function is performed by iterating motion segmentation and estimation using a genetic algorithm, which is robust and effective to deal with combinatorial problems. The computation is distributed into chromosomes that evolve by distributed genetic algorithms (DGAs). Experimental results shows that our proposed method estimates an accurate motion field and segments a satisfactory label fields.

A Bayesian Wavelet Threshold Approach for Image Denoising

Ahn, Yun-Kee,Park, Il-Su,Rhee, Sung-Suk The Korean Statistical Society 2001 Communications for statistical applications and me Vol.8 No.1

Wavelet coefficients are known to have decorrelating properties, since wavelet is orthonormal transformation. but empirically, those wavelet coefficients of images, like edges, are not statistically independent. Jansen and Bultheel(1999) developed the empirical Bayes approach to improve the classical threshold algorithm using local characterization in Markov random field. They consider the clustering of significant wavelet coefficients with uniform distribution. In this paper, we developed wavelet thresholding algorithm using Laplacian distribution which is more realistic model.

Hotelling's T²-검정통계량을 이용한 다채널 영상의 에지검출 -동시다중검정기법적 접근법-

김승구 한국자료분석학회 2008 Journal of the Korean Data Analysis Society Vol.10 No.6

Multichannel images prevail in practice more than single channel images. Edge detection of the multichannel images is usually performed by edge detection of an one dimensional image which they are transformed into, or it is performed from the logical add-operating after separate channel-wise edge detections. However, both are not resonable because they neglect the structure of covariance between channels of the image. This paper suggests using Hotelling's T²-test statistic to evaluate the edge strength of pixel of a multichannel image. The normal scores for p-values of these evaluates are used to fit the HMRF-NMM(hidden Markov random field-normal mixture model) in order to implement the multiple test of many single edge tests with spatially correlated data. 실용에서 접하는 대부분의 영상은 단일채널 영상보다는 다채널 영상이다. 그러나 다채널 영상에 대한 전통적 에지 결정은 단일채널로 변환한 후 얻은 단변량 영상으로부터 이루어지거나 채널별로 에지를 검출 한 후 논리합으로 통합된 결과로 에지를 결정하는 방식을 하는 것이 보통이다. 이는 채널 사이의 상관성 정보를 무시하는 방법으로서 정보적이라 할 수 없다. 본 논문에서는 다채널 영상의 에지검출을 위한 (정규화 변환된) 동시다중기법적 방법론을 제시한다. D-채널 영상에 대한 Hotelling's T² 에지검출 통계량 관측값의 유의확률들의 정규화점수들을 K-변량 은닉 마코프 랜덤 필드로 가정하여 정규혼합모형을 적합하며, 이를 바탕으로 공간적 종속성을 가진 화소자료의 개별 에지 검정에 대응한 다중검정기법적 접근법을 제공한다.

Hyper-Parameter in Hidden Markov Random Field

임요한,유동현,변경숙 한국통계학회 2011 응용통계연구 Vol.24 No.1

Hidden Markov random field(HMRF) is one of the most common model for image segmentation which is an important preprocessing in many imaging devices. The HMRF has unknown hyper-parameters on Markov random field to be estimated in segmenting testing images. However, in practice, due to computational complexity, it is often assumed to be a fixed constant. In this paper, we numerically show that the segmentation results very depending on the fixed hyper-parameter, and, if the parameter is misspecified, they further depend on the choice of the class-labelling algorithm. In contrast, the HMRF with estimated hyper-parameter provides consistent segmentation results regardless of the choice of class labelling and the estimation method. Thus, we recommend practitioners estimate the hyper-parameter even though it is computationally complex.

Broadband Spectrum Sensing of Distributed Modulated Wideband Converter Based on Markov Random Field

Zhi Li,Jiawei Zhu,Ziyong Xu,Wei Hua 한국전자통신연구원 2018 ETRI Journal Vol.40 No.2

The Distributed Modulated Wideband Converter (DMWC) is a networking system developed from the Modulated Wideband Converter, which converts all sampling channels into sensing nodes with number variables to implement signal undersampling. When the number of sparse subbands changes, the number of nodes can be adjusted flexibly to improve the reconstruction rate. Owing to the different attenuations of distributed nodes in different locations, it is worthwhile to find out how to select the optimal sensing node as the sampling channel. This paper proposes the spectrum sensing of DMWC based on a Markov random field (MRF) to select the ideal node, which is compared to the image edge segmentation. The attenuation of the candidate nodes is estimated based on the attenuation of the neighboring nodes that have participated in the DMWC system. Theoretical analysis and numerical simulations show that neighboring attenuation plays an important role in determining the node selection, and selecting the node using MRF can avoid serious transmission attenuation. Furthermore, DMWC can greatly improve recovery performance by using a Markov random field compared with random selection.