• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.364-380
• /
• 2016

The most popular approach in object classification is based on the bag of visual-words model, which has several fundamental problems that restricting the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification based on weakly supervised E2LSH and saliency map weighting is proposed. Firstly, E2LSH (Exact Euclidean Locality Sensitive Hashing) is employed to generate a group of weakly randomized visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, graph-based visual saliency (GBVS) algorithm is applied to detect the saliency map of different images and weight the visual words according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results datasets of Pascal 2007 and Caltech-256 indicate that the distinguishability of objects is effectively improved and our method is superior to the state-of-the-art object classification methods.

• Convergence Security Journal
• /
• v.7 no.1
• /
• pp.1-10
• /
• 2007

Surveillance system with the fixed field of view generally has an identical background and is easy to extract and segment a moving object. However, it is difficult to extract the object when the gray level of the background is varied due to illumination condition in the real circumstance. In this paper we propose the segmentation algorithm to extract effectively the object in spite of the illumination change. In order to minimize the effect of illumination, the proposed algorithm is composed of three modes according to the background generation and the illuminational change. Then the object is finally obtained by using projection and the morphological operator in post-processing. A good segmentation performance is demonstrated by the simulation result.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.23 no.11 s.170
• /
• pp.1929-1939
• /
• 1999

This paper presents a neural network approach, which was named PRONET, to 3D object recognition and pose calculation. 3D objects are represented using a set of centroidal profile patterns that describe the boundary of the 2D views taken from evenly distributed view points. PRONET consists of the training stage and the execution stage. In the training stage, a three-layer feed-forward neural network is trained with the centroidal profile patterns using an error back-propagation method. In the execution stage, by matching a centroidal profile pattern of the given image with the best fitting centroidal profile pattern using the neural network, the identity and approximate orientation of the real object, such as a workpiece in arbitrary pose, are obtained. In the matching procedure, line-to-line correspondence between image features and 3D CAD features are also obtained. An iterative model posing method then calculates the more exact pose of the object based on initial orientation and correspondence.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.11
• /
• pp.1551-1558
• /
• 2014

We propose a multi-rate sensor fusion of vision and radar using Kalman filter to solve problems of asynchronized and multi-rate sampling periods in object vehicle tracking. A model based prediction of object vehicles is performed with a decentralized multi-rate Kalman filter for each sensor (vision and radar sensors.) To obtain the improvement in the performance of position prediction, different weighting is applied to each sensor's predicted object position from the multi-rate Kalman filter. The proposed method can provide estimated position of the object vehicles at every sampling time of ECU. The Mahalanobis distance is used to make correspondence among the measured and predicted objects. Through the experimental results, we validate that the post-processed fusion data give us improved tracking performance. The proposed method obtained two times improvement in the object tracking performance compared to single sensor method (camera or radar sensor) in the view point of roots mean square error.

• Journal of the Korean Institute of Rural Architecture
• /
• v.13 no.1
• /
• pp.9-20
• /
• 2011

This study is designed to examine characteristics and types of basic landscape design established by 7 local governments in Jeollanam-do and its availability as the index of landscape administration and present a guideline with view landscape plan of local governments. The results of this study are described below. In case of view landscape, while Korean cities have not many historical assets like landmark, they have locational characteristics with mountain or coast in the center or surroundings of downtown. Therefore, since view landscape has many cases of restricting individual property rights as well as having a value as public property of city which makes recognition of sharing city, it is very sensitive problem and establishing guideline of it is needed. But, it was found that view landscape plan of local governments established location of view spot with the nature of relief viewing downtown or coast from high spot. Selection of viewing objects in view plan require deciding an object as the public property of city and big cities require selection from the zone and small cities must select 1~2 spots from the viewpoint of whole downtown. 3~4 view spots of middle and distant views which makes city community centering around the subject of view must be selected through enough discussion and in case of natural landscape, View shaft or visible rays require setting of range that 30% of viewing objects is seen. View spot or viewing objects should be selected over twice as extra spots through public hearing and civil participation as the process.

• Korean Institute of Interior Design Journal
• /
• no.13
• /
• pp.11-17
• /
• 1997

The purpose of this study is to research the phychological determinant factors of window design and the relationshiops between preferences over those factors. Field surveys and questionnaires, focused on residents in apartment houses, were used to research the residents' preferences. Sunlight inflow, view privacy, and spaciousness can be assumed as major environmental psychological factors related to windows. But some difficulties in applying all those factors' requirements in a window design lie in the fundamental mutual contradiction such as providing both optimum privacy and openness. Those difficulties can be solved to a certain degree through the process of comparison between those factors based on residents' preference tendency in a specific space. Other results of this research are as follows: 1) The preference research shows that sunlight inflow stands first in living room, and followed by view, privacy, and spaciousness: privacy ranks first in bedroom and followed by sunlight inflow, view, and spaciousness: the elderly over sixties prefer the sunlight inflow first both in the living room and the bedroom. 2) Satisfaction degrees on sunlight inflow, privacy, spaciousness are increasing along with the dwelling height, while the view is not showing any relationship with the dwelling height. 3) Natural elements, as the object of view, are preferred to artificial elements such as buildings and roads. 4) Windowsill heights in bedrooms have relevance to the state of satisfaction with sunlight inflow, privacy, and view, while they show no relationship with spaciousness.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.7
• /
• pp.53-61
• /
• 1998

In this paper, we propose an efficient multi-view images coding algorithm to find the optimal depth and texture from the set of multi-view images. The proposed algorithm consists of two consecutive steps, i) the depth estraction step, and ii) the texture extraction step, comparedwith the traditional algorithem which finds the depth and texture concurrently. The X-Y plane of the normalized object space is divided into traingular paatches and the Z value of the node is determined in the first step and then the texture of the each patch is extracted in the second step. In the depth extraction step, the depth of the node is determined by applying the block based disparity compensation method to the windowed area centered at the node. In the second step, the texture of the traingular patches is extracted from the multi-view images by applying the affine transformation based disparity compensation method to the traingular pateches with the depth extracted from the first step. Experimental results show that the SNR(Singnal-to- Noise Ratio) of images enconded by our algorithm is better than that of images encoded by the traditional algorithm by the amount about 4dB for for the test sets of multi-view images called dragon, kid, city and santa.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.3
• /
• pp.1023-1033
• /
• 2014

In this paper, performance improved hole-filling algorithm which includes the boundary noise removing pre-process that can be used for an arbitrary virtual view synthesis has been proposed. Boundary noise occurs due to the boundary mismatch between depth and texture images during the 3D warping process and it usually causes unusual defects in a generated virtual view. Common-hole is impossible to recover by using only a given original view as a reference and most of the conventional algorithms generate unnatural views that include constrained parts of the texture. To remove the boundary noise, we first find occlusion regions and expand these regions to the common-hole region in the synthesized view. Then, we fill the common-hole using the spiral weighted average algorithm and the gradient searching algorithm. The spiral weighted average algorithm keeps the boundary of each object well by using depth information and the gradient searching algorithm preserves the details. We tried to combine strong points of both the spiral weighted average algorithm and the gradient searching algorithm. We also tried to reduce the flickering defect that exists around the filled common-hole region by using a probability mask. The experimental results show that the proposed algorithm performs much better than the conventional algorithms.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.9
• /
• pp.2857-2866
• /
• 2000

As software technology has made progress, object-oriented CASE tools have become more important. This paper presents the process and similarity in design and implementation of OODesigner, an object-oriented CASE tool, on three platfonns and outlines a kind of generic architecture for the design and the implementation of CASE tools. OODesigner is a tool that was initially developed to support OMT. An initial Unix version has been developed since 1994. In 1997, after the completion of the Unix version, we began developing a Java version and a Windows version supporting UML. The development of a CASE tool is a typical application of the Model-View-ControllerO'vIVC) paradigm. Thus, we obtained a common design pattern among the versions in the MVC point of views. This design similarity can be used to develop several kinds of CASE tools with the corresponding design notations.

• Journal of the Korean Society of Costume
• /
• v.51 no.1
• /
• pp.163-174
• /
• 2001

The purpose of this study is to review the features of eroticism expressed in men's fashion, to explain psychological and social contexts which engender eroticism and to analyze in what way eroticism is portrayed in men s fashion in this context. Eroticism as the metonymy of forbidden sexual desire, has been embodied mostly in visual forms such as picture and photo. From a psychoanalytic view, the context in which eroticism is formed can be explained by primary narcissism and fetishism. Primary narcissism is the feeling of satisfaction with the self in which the subject who is admiring and the object of admiration are one and the same. Accordingly, in order to give rise to eroticism, both subject and object have to exist. Fetishism, the metonymy of castrated penis, is also one of the factors to produce eroticism. Metaphorically seen as a woman who has a penis, a man who dresses in the same manner as a woman dresses can be a source of eroticism to gays. From a sociological view, the context in which eroticism is fostered depends on the dynamic relations among social powers. In these relations, who is a subject or who is an object has been continuously changing. In the Post-modern culture appearing in the late 20th century, power begins to take various forms, and gays and women who had never been subjects begin to make man an object of eroticism. The other point is that social morality, ignoring desire itself, objectifies sexual desire and seeks to remove It by exchanging it for objectified symbols. The design elements provoking eroticism in men s fashion are exposure and decoration. In particular, models in exposure and decorative fashion have been objectified through the methods of fragmentation rather than showing the whole figure or removing a person s individuality or will,.