• Journal of Korea Multimedia Society
• /
• v.19 no.9
• /
• 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.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.6
• /
• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.6
• /
• pp.83-90
• /
• 1994

In this paper, we propose a new learning algorithm, ASOFM(Adaptive Self Organizing Feature Map), to solve the defects of Kohonen's Self Organiaing Feature Map. Kohonen's algorithm is sometimes stranded on local minima for the initial weights. The proposed algorithm uses an object function which can evaluate the state of network in learning and adjusts the learning rate adaptively according to the evaluation of the object function. As a result, it is always guaranteed that the state of network is converged to the global minimum value and it has a capacity of generalized learning by adaptively. It is reduce that the learning time of our algorithm is about $30\%$ of Kohonen's.

• Journal of Korea Multimedia Society
• /
• v.12 no.1
• /
• pp.50-57
• /
• 2009

This paper proposes a extraction of feature lines on a polygonal model using local implicit surface fitting technique. To extract feature lines on a polygonal model, the previous technique addressed to compute the curvature and their derivatives at mesh vertices via global implicit surface fitting. It needs a user-specified precision parameter for finding an accurate projection of the mesh vertices onto an approximating implicit surface and requires high-time consumption. But we use a local implicit surface fitting technique to estimate the local differential information near a vertex by means of an approximating surface. Feature vertices are easily detected as zero-crossings, and can then be connected along the direction of principal curvature. Our method, demonstrated on several large polygonal models, produces a good fit which leads to improved visualization.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.4
• /
• 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.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.38-47
• /
• 2000

In pattern classification, the Bhattacharyya distance has been used as a class separability measure. Furthemore, it is recently reported that the Bhattacharyya distance can be used to estimate error of Gaussian ML classifier within 1-2% margin. In this paper, we propose a feature extraction method utilizing the Bhattacharyya distance. In the proposed method, we first predict the classification error with the error estimation equation based on the Bhauacharyya distance. Then we find the feature vector that minimizes the classification error using two search algorithms: sequential search and global search. Experimental reslts show that the proposed method compares favorably with conventional feature extraction methods. In addition, it is possible to determine how man, feature vectors arc needed for achieving the same classification accuracy as in the original space.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.181-186
• /
• 2014

The paper proposes a new method of segmentation-based feature extraction to improve performance in pedestrian upper-body detection. General pedestrian detectors that use local features are often plagued by false positives due to the locality. Color information of multi parts of the upper body is utilized in figure-ground segmentation scheme to extract an salient, "global" shape feature capable of reducing the false positives. The performance of the multi-part color segmentation-based feature is evaluated by changing color spaces and the parameters of color histogram. The experimental result from an upper-body dataset shows that the proposed feature is effective in reducing the false positives of local feature-based detectors.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• 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.

• The Journal of Korea Robotics Society
• /
• v.16 no.2
• /
• 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
• /
• v.1 no.1
• /
• 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.