• 한국멀티미디어학회논문지
• /
• 제19권9호
• /
• pp.1659-1668
• /
• 2016

Understanding 3D structure of scenes is of a great interest in various vision-related tasks. In this paper, we present a unified approach for estimating depth from a single monocular image. The key idea of our approach is to take advantages both of parametric learning and non-parametric sampling method. Using a parametric convolutional network, our approach learns the relation of various monocular cues, which make a coarse global prediction. We also leverage the local prediction to refine the global prediction. It is practically estimated in a non-parametric framework. The integration of local and global predictions is accomplished by concatenating the feature maps of the global prediction with those from local ones. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively.

• 한국정밀공학회지
• /
• 제30권6호
• /
• pp.601-606
• /
• 2013

3D scanning is a technique to measure the 3D shape information of the object. Shape information obtained by 3D scanning is expressed either as point cloud or as polygon mesh type data that can be widely used in various areas such as reverse engineering and quality inspection. 3D scanning should be performed as accurate as possible since the scanned data is highly required to detect the features on an object in order to scan the shape of the object more precisely. In this study, we propose the method on finding the location of feature more accurately, based on the extended Biplane SNAKE with global optimization. In each iteration, we project the feature lines obtained by the extended Biplane SNAKE into each image plane and move the feature lines to the features on each image. We have applied this approach to real models to verify the proposed optimization algorithm.

• 한국음향학회지
• /
• 제13권6호
• /
• pp.83-90
• /
• 1994

본 논문에서는 코호넨(Kohonen)의 SOFM (Self-Organizing Feature Map) 알고리즘의 단점을 해결하기 위한 새로운 학습 알고리즘 ASOFM(Adaptive Self-Organized Feature Map)을 제안한다. 코호넨의 학습 알고리즘은 초기화된 연결 벡터에 대하여 극소점에 빠지는 경우도 있다. 그러나 제안된 알고리즘에서는 학습과정중에 네트워크의 상태를 평가할 수 있는 목적함수(object function)을 사용하였고, 이 함수의 출력에 따라 학습의 각 시점에서 적응적으로 학습률의 재조정이 가능하였다. 이 결과, 네트워크의 상태가 최소점에 수렴함이 보증 되고 학습률의 적응성에 의해 임의의 학습패턴에 대한 학습의 일반화 능력이 보장되었다. 또한 제안된 알고리즘은 코호넨의 알고리즘보다 약 $70\%$이상의 학습시간을 단축한다.

• 한국멀티미디어학회논문지
• /
• 제12권1호
• /
• pp.50-57
• /
• 2009

본 논문은 3차원 다각형 모델에서 특징 선을 추출하기 위한 방법에 대해 제안한다. 이산 곡면으로 이루어진 다각형 모델에서 특징 선을 추출하기 위하여 기존 방법에서는 전역적인 음함수 곡면 맞춤 기법(Implicit Surface Fitting)을 이용하여 모델의 꼭지점에서 곡률과 곡률 미분 값을 측정하였다. 이러한 방법은 다각형 모델의 꼭지점에서 음함수 곡면으로 정확하게 투영할 수 있도록 사용자의 정의 파라미타를 찾아야 하며, 특징 추출을 위한 많은 계산 시간을 요구한다. 그러나 제안 방법은 지역적 음함수 곡면 맞춤 기법을 이용하여 모델의 꼭지점에 근사된 곡면을 통해 미분 정보를 측정한다. 측정된 미분 정보를 통해 쉽게 각각의 모서리에서 제로-클로싱을 통해 특징 점을 추출하고, 곡률 방향을 따라 추출된 점들을 연결하여 특징 선을 생성한다. 여러 가지 다각형 모델에서 실험을 하였고 기존 방법보다 빠르며 높은 품질의 특징 선을 추출한다.

• 한국컴퓨터정보학회논문지
• /
• 제21권4호
• /
• pp.63-71
• /
• 2016

This paper is about applying efficient data mining method which improves the score calculation and proper building performance of credit ranking score system. The main idea of this data mining technique is accomplishing such objectives by applying Correlation based Feature Selection which could also be used to verify the properness of existing rank scores quickly. This study selected 2047 manufacturing companies on KOSPI market during the period of 2009 to 2013, which have their own credit rank scores given by NICE information service agency. Regarding the relevant financial variables, total 80 variables were collected from KIS-Value and DART (Data Analysis, Retrieval and Transfer System). If correlation based feature selection could select more important variables, then required information and cost would be reduced significantly. Through analysis, this study show that the proposed correlation based feature selection method improves selection and classification process of credit rank system so that the accuracy and credibility would be increased while the cost for building system would be decreased.

• 대한전자공학회논문지SP
• /
• 제37권6호
• /
• pp.38-47
• /
• 2000

Bhattacharyya distance는 패턴 분류 문제에 있어서 클래스간 분리도 측정의 수단으로 사용되어 왔으며 특징 추출 시 유용한 정보를 제공한다. 본 논문에서는 최근 발표된 Bhattacharyya distance를 이용한 에러 예측 기법을 이용하여 예측된 분류 에러가 최소가 되는 특정 벡터를 추출하는 방법에 대하여 제안한다. 제안한 특징 추출 기법은 최적화 알고리즘인 전체탐색 및 순차탐색 방법의 적용 시 분류 에러를 직접 구하지 않고 Bhattacharyya distance를 이용하여 분류 에러를 예측하므로 고차원 데이터의 경우 고속의 특징 추출이 가능하며, 에러 예측 성질을 이용하여 패턴 분류 시 필요한 최소 특징 벡터의 수를 예측할 수 있는 장점이 있다.

• 전자공학회논문지
• /
• 제51권11호
• /
• pp.181-186
• /
• 2014

본 논문에서는 보행자 상반신 검출기의 성능을 향상하기 위한 세그먼테이션에 기반한 특징 추출 방법을 제안한다. 상반신의 부분별 색상 분포를 활용한 멀티 파트 컬러 세그먼테이션을 사용하여 국소 특징이 갖는 한계로 인해 발생하는 오검출의 감소에 효과적인 "전역적" 윤곽 특징을 추출한다. 컬러 공간과 히스토그램 분해도에 따른 성능을 분석하였으며, 자체 구축한 보행자 상반신 영상을 사용한 실험을 통해서 제안한 방법으로 추출한 특징이 국소 특징 기반 검출기의 오검출 감소에 효과적임을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• 로봇학회논문지
• /
• 제16권2호
• /
• pp.103-111
• /
• 2021

This study addresses a low-cost lidar sensor-based glass feature extraction method for an accurate map representation using statistical moments, i.e. the mean and variance. Since the low-cost lidar sensor produces range-only data without intensity and multi-echo data, there are some difficulties in detecting glass-like objects. In this study, a principle that an incidence angle of a ray emitted from the lidar with respect to a glass surface is close to zero degrees is concerned for glass detection. Besides, all sensor data are preprocessed and clustered, which is represented using statistical moments as glass feature candidates. Glass features are selected among the candidates according to several conditions based on the principle and geometric relation in the global coordinate system. The accumulated glass features are classified according to the distance, which is lastly represented on the map. Several experiments were conducted in glass environments. The results showed that the proposed method accurately extracted and represented glass windows using proper parameters. The parameters were empirically designed and carefully analyzed. In future work, we will implement and perform the conventional SLAM algorithms combined with our glass feature extraction method in glass environments.

• Asian review of World Histories
• /
• 제1권1호
• /
• pp.5-44
• /
• 2013

This essay offers a historically based critique of the idea of "alternative modernities" that has acquired popularity in scholarly discussions over the last two decades. While significant in challenging Euro/American-centered conceptualizations of modernity, the idea of "alternative modernities" (or its twin, "multiple modernities") is open to criticism in the sense in which it has acquired currency in academic and political circles. The historical experience of Asian societies suggests that the search for "alternatives" long has been a feature of responses to the challenges of Euromodernity. But whereas "alternative" was conceived earlier in systemic terms, in its most recent version since the 1980s cultural difference has become its most important marker. Adding the adjective "alternative" to modernity has important counter-hegemonic cultural implications, calling for a new understanding of modernity. It also obscures in its fetishization of difference the entrapment of most of the "alternatives" claimed--products of the reconfigurations of global power--within the hegemonic spatial, temporal and developmentalist limits of the modernity they aspire to transcend. Culturally conceived notions of alternatives ignore the common structural context of a globalized capitalism which generates but also sets limits to difference. The seeming obsession with cultural difference, a defining feature of contemporary global modernity, distracts attention from urgent structural questions of social inequality and political injustice that have been globalized with the globalization of the regime of neoliberal capitalism. Interestingly, "the cultural turn" in the problematic of modernity since the 1980s has accompanied this turn in the global political economy during the same period. To be convincing in their claims to "alterity", arguments for "alternative modernities" need to re-articulate issues of cultural difference to their structural context of global capitalism. The goal of the discussion is to work out the implications of these political issues for "revisioning" the history and historiography of modernity.