• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.88-95
• /
• 2011

Stereo matching is the research area that regarding the estimation of the distance between objects and camera using different view points and it still needs lot of improvements in aspects of speed and accuracy. This paper presents a fast stereo matching algorithm based on plane-converging belief propagation that uses message passing convergence in hierarchical belief propagation. Also, stereo matching technique is developed using GPU and it is available for real-time applications. The error rate of proposed Plane-converging Belief Propagation algorithm is similar to the conventional Hierarchical Belief Propagation algorithm, while speed-up factor reaches 2.7 times.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.5
• /
• pp.54-63
• /
• 2007

The purpose of this study is to present a new energy minimization method for image completion with hierarchical approach. The goal of image completion is to fill in missing part in a possibly large region of an image so that a visually plausible outcome is obtained. An exemplar-based Markov Random Field Modeling(MRF) is proposed in this paper. This model can deal with following problems; detection of global features, flexibility on environmental changes, reduction of computational cost, and generic extension to other related domains such as image inpainting. We use the Priority Belief Propagation(Priority-BP) which is a kind of Belief propagation(BP) algorithms for the optimization of MRF. We propose the hierarchical Priority-BP that reduces the number of nodes in MRF and to apply hierarchical propagation of messages for image completion. We show that our approach which uses hierarchical Priority-BP algorithm in image completion works well on a number of examples.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.119-122
• /
• 2011

The Stereo vision using belief propagation algorithm that has been studied recently yields good performance in disparity extraction. In this paper, BP algorithm is proved theoretically to high precision for a stereo matching algorithm. We derive disparity map from stereo image by using Belief Propagation (BP) algorithm and area-based matching algorithm. Two algorithms are compared using stereo images provided by Middlebury web site. Disparity map error rate decreased from 52.3% to 2.3%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.7 no.4
• /
• pp.223-228
• /
• 2014

It is known that a belief propagation algorithm is a fast decoding scheme for LT codes but it require a large overhead, especially for a short block length LT codes. In this paper an improved belief decoding algorithm using searching method for degree-1 packets is proposed for a small overhead. The proposed decoding scheme shows the desirable performance in terms of overhead while guaranteeing the same computational complexity with respect to the conventional BP decoding scheme.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.256-261
• /
• 2007

본 논문은 이미지 완성(Image Completion)을 위한 근사적 에너지 최적화 알고리즘을 제안한다. 이미지 완성이란 이미지의 특정영역이 지워진 상태에서, 그 지워진 부분을 나머지 부분과 시각적으로 어울리도록 완성시키는 기법을 말한다. 본 논문에서 이미지 완성은 유사-확률적(pseudo-probabilistic) 시스템인 Markov Random Field로 모델링된다. MRF로 모델링된 이미지 완성 시스템에서 사후 확률(posterior probability)을 최대로 만드는 MAP(Maximum A Posterior) 문제는 결국 시스템의 전체 에너지를 낮추는 에너지 최적화 문제와 동일하다. 본 논문에서는 MRF의 최적화 알고리즘들 중에서 Belief Propagation 알고리즘을 이용한다. BP 알고리즘이 이미지 완성 분야에 적용될 때 다음 두 가지가 계산시간을 증가시키는 요인이 된다. 첫 번째는 완성시킬 영역이 넓어 MRF를 구성하는 정점의 수가 증가할 때이다. 두 번째는 비교할 후보 이미지 조각의 수가 증가할 때이다. 기존에 제안된 Priority-Belief Propagation 알고리즘은 우선순위가 높은 정점부터 메시지를 전파하고 불필요한 후보 이미지 조각의 수를 제거함으로써 이를 해결하였다. 하지만 우선순위를 정점에 할당하기 위한 최초 메시지 전파의 경우 Belief Propagation의 단점은 그대로 남아있다. 이를 개선하기 위해 본 논문에서는 이미지 완성을 위한 MRF 모델을 피라미드 구조와 같이 층위로 나누어 정점의 수를 줄이고, 계층적으로 메시지를 전파하여 시스템의 적합성(fitness)을 정교화 해나가는 Hierarchical Priority Belief Propagation 알고리즘을 제안한다.

• ETRI Journal
• /
• v.26 no.5
• /
• pp.432-436
• /
• 2004

In this paper, we propose the modified uniformly most powerful (UMP) belief-propagation (BP)-based decoding algorithm which utilizes multiplicative and additive factors to diminish the errors introduced by the approximation of the soft values given by a previously proposed UMP BP-based algorithm. This modified UMP BP-based algorithm shows better performance than that of the normalized UMP BP-based algorithm, i.e., it has an error performance closer to BP than that of the normalized UMP BP-based algorithm on the additive white Gaussian noise channel for low density parity check codes. Also, this algorithm has the same complexity in its implementation as the normalized UMP BP-based algorithm.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.3
• /
• pp.45-51
• /
• 2015

In this paper, we discuss the belief propagation decoding algorithm for polar codes. The performance of Polar codes for shorter lengths is not satisfactory. Motivated by this, we propose a novel technique to improve its performance at short lengths. We showed that the probability of messages passed along the factor graph of polar codes, can be increased by multiplying the current message of nodes with their previous message. This is like a feedback path in which the present signal is updated by multiplying with its previous signal. Thus the experimental results show that performance of belief propagation polar decoder can be improved using this proposed technique. Simulation results in binary-input additive white Gaussian noise channel (BI-AWGNC) show that the proposed belief propagation polar decoder can provide significant gain of 2 dB over the original belief propagation polar decoder with code rate 0.5 and code length 128 at the bit error rate (BER) of $10^{-4}$.

• Journal of the Semiconductor & Display Technology
• /
• v.9 no.2
• /
• pp.123-126
• /
• 2010

An implementation of modified stereo matching using efficient belief propagation (BP) algorithm is presented in this paper. We do recommend the use of the simple sobel, prewitt edge operator. The application of B band sobel edge operator over image demonstrates result with somewhat noisy (distinct border). When we adopt the only MRF + BP algorithm, however, borders cannot be distinguished due to that the message functions in the BP algorithm is just the mechanism which passes energy data to the only large gap of each Message functions In order to address the abovementioned disadvantageous phenomenon, we use the sobel edge operator + MRF + BP algorithm to distinguish the border that is located between the similar message data. Using edge information, the result shows that our proposed process diminishes the propagation of wrong probabilistic information. The enhanced result is due to that our proposed method effectively reduced errors incurred by ambiguous scene properties.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.281-282
• /
• 2008

Turbo equalizers which use MAP (maximum a posteriori probability) equalizer or MMSE (minimum mean square error) equalizer have shown high performance and adoptability [1], [2]. In this paper, we show that the BP (belief propagation) algorithm can also be applied in equalizer and when it is connected with channel code, it can replace the MAP equalizer with similar complexity and performance.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.11a
• /
• pp.52-53
• /
• 2012

Belief propagation (BP) is a commonly used global energy minimization algorithm for solving stereo matching problem in 3D reconstruction. However, it requires large memory bandwidth and data size. In this paper, we propose a novel memory-efficient algorithm of BP in stereo matching on the Graphics Processing Units (GPU). The data size and transfer bandwidth are significantly reduced by storing only a part of the whole message. In order to maintain the accuracy of the matching result, the local messages are reconstructed using shared memory available in GPU. Experimental result shows that there is almost an order of reduction in the global memory consumption, and 21 to 46% saving in memory bandwidth when compared to the conventional algorithm. The implementation result on a recent GPU shows that we can obtain 22.8 times speedup in execution time compared to the execution on CPU.