• Journal of the Society of Naval Architects of Korea
• /
• v.57 no.3
• /
• pp.140-151
• /
• 2020

It is important to identify the location of ship hull blocks with exact block identification number when scheduling the shipbuilding process. The wrong information on the location and identification number of some hull block can cause low productivity by spending time to find where the exact hull block is. In order to solve this problem, it is necessary to equip the system to track the location of the blocks and to identify the identification numbers of the blocks automatically. There were a lot of researches of location tracking system for the hull blocks on the stockyard. However there has been no research to identify the hull blocks on the stockyard. This study compares the performance of 5 Convolutional Neural Network (CNN) models with multi-view image set on the classification of the hull blocks to identify the blocks on the stockyard. The CNN models are open algorithms of ImageNet Large-Scale Visual Recognition Competition (ILSVRC). Four scaled hull block models are used to acquire the images of ship hull blocks. Learning and transfer learning of the CNN models with original training data and augmented data of the original training data were done. 20 tests and predictions in consideration of five CNN models and four cases of training conditions are performed. In order to compare the classification performance of the CNN models, accuracy and average F1-Score from confusion matrix are adopted as the performance measures. As a result of the comparison, Resnet-152v2 model shows the highest accuracy and average F1-Score with full block prediction image set and with cropped block prediction image set.

• ETRI Journal
• /
• v.44 no.1
• /
• pp.51-61
• /
• 2022

In this paper, we introduced a novel voxel-wise UV parameterization and view-dependent texture synthesis for the immersive rendering of a truncated signed distance field (TSDF) scene model. The proposed UV parameterization delegates a precomputed UV map to each voxel using the UV map lookup table and consequently, enabling efficient and high-quality texture mapping without a complex process. By leveraging the convenient UV parameterization, our view-dependent texture synthesis method extracts a set of local texture maps for each voxel from the multiview color images and separates them into a single view-independent diffuse map and a set of weight coefficients for an orthogonal specular map basis. Furthermore, the view-dependent specular maps for an arbitrary view are estimated by combining the specular weights of each source view using the location of the arbitrary and source viewpoints to generate the view-dependent textures for arbitrary views. The experimental results demonstrate that the proposed method effectively synthesizes texture for an arbitrary view, thereby enabling the visualization of view-dependent effects, such as specularity and mirror reflection.

• Journal of Sensor Science and Technology
• /
• v.16 no.3
• /
• pp.220-228
• /
• 2007

For many applications particularly in navigation system, a three-dimensional representation improves the usability of information. This paper introduces 3D Graphical User Interface (GUI) of indoor location tracking system, 3D Navigation View. The application provides users a 3D visualization of the indoor environments they are exploring, synchronized with the physical world through spatial information obtained from indoor location tracking system. It adopts widely used Virtual Reality Modeling Language (VRML) to construct, represent, distribute and render 3D world of indoor environments over Internet. Java, an all-purpose programming language is integrated to comprehend spatial information received from indoor location tracking system. Both are connected through an interface called External Authoring Interface (EAI) provided by VRML. Via EAI, Java is given the authority to access and manipulate the 3D objects inside the 3D world that facilitates the indication of user's position and viewpoint in the constructed virtual indoor environments periodically.

• Journal of Korean Society of Rural Planning
• /
• v.21 no.2
• /
• pp.63-77
• /
• 2015

Improve the rural views of the Government and the municipalities with the intention of rural landscape planning. However, rural scenery evaluation of landscape types and element categories, landscape scenes, such as the valuation of resources selected, form a coherent system and ecological point of view is not only a Visual perspective of evaluation, or evaluation is made. This study evaluates the rural landscape through the rural landscape for rurality is implemented can explain the image. Rural amenity 100 represented the rural landscape in rurality with photos of photos, and scenes, photos, location-based rural Vista rurality landscapes drawn components. Selected landscape photography scenic landscapes in the u.s. survey and image vocabularies through surveys is representative of the landscape in rurality of each Vista location-specific photos and images began extracted factors. As a result, the Distant view is a town and village in the rolling hills of the surrounding environment is an image behind the Vista Skyline, Farmland Rural village forests, Behind the hills, Individual housing roof, Housing arrangement, The number of household includes landscape components. Factor analysis 'openness', 'intimacy', 'activity', 'complexity', 'safety' was down to five factors, such as a description of the overall factors that force was 66.45 percent. Middle distance view is close to being out of town houses and village environment, an image in the skyline hills Vista, farmlands, village forests, rolling hills, behind the scenes of the housing component of the neck, the sperm will honor an individual factor analysis results are 'intimacy', 'safety', 'openness', 'specificity', 'complexity' five factors the whole description of the capacity factors compared to 67.24 percent. Close-range view is mainly in Vista village embraced the individual elements and an image of a harmonious location in the surroundings of the sperm, individual houses, fences, gates, courtyard, Garden, garage, agricultural facilities, including, but not limited to, factors assay but an 'intimacy', 'complexity', 'safety', 'activity', 'openness' five factors, such as a description of the overall factors that force was 65.29%. This research seeks to determine the extent to which rurality of rural landscape Vista by location attributes and elements and representative officer in photo selection and rurality to extract the image. To date, followed by a comprehensive study, which was presented through the readjustment could not overlook the Visual elements. The future rural development officer for the evaluation of rural landscape classification and quantitative and objective assessment will have to come up with ways to do.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.265-274
• /
• 2020

Free-viewpoint video service is a technology that allows users to watch at any angle, location and distance through interaction. In this paper, the free-viewpoint video services are defined in four viewing modes: Inward view, outward view, 3D object view and first person view. And we developed and implemented a new integrated program that plays all the suggested views. In the contents of girl band performances and basketball games, multi-view cameras suitable for each viewing mode are installed to acquire media, and data stored on the server is streamed over the network, making it available for viewing. Users can freely choose four viewing modes, space location, angle and so on, and the media data such as images and sounds are provided to them by rendering appropriately for the selected the viewpoint. Our system is expected to be a scalable free-viewpoint video service player as well as provide users with immersion and presence by combining various viewing modes.

• Journal of the Korean housing association
• /
• v.18 no.1
• /
• pp.43-51
• /
• 2007

This study examines and analyzes view hindrance factors of high-storied apartment houses at small town like 'Eup' where county office locates and it is found that hindrance factors include designation of residential area and height, length and form of main building. On recognition of view, most subjects of research considered high-storied apartment houses hindered urban view and its regulation is needed. Apartment houses at small cities become main factors of hindering urban view because they were located randomly regardless of scale of city and surrounding situation, but there is no measure to control it. Accordingly, view control through enaction of regulations is urgently needed with establishment of guidelines such as height of large buildings including high-storied apartment houses, length of main building, location and regulation of exterior design.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.9 s.102
• /
• pp.1108-1117
• /
• 2005

A robust damage detection method using short-time Fourier transform and beating phenomena is presented as an estimating tool of the healthiness of large structures. The present technique makes use of beating phenomena that manifest themselves when two signals of similar frequencies are added or subtracted. Unlike most existing methods based on vibration signals, the present approach does not require an analytic model for target structures. Furthermore, the main advantage of the proposed method compared to the competing diagnostic method using vibration data is its robustness. The proposed method is not affected by the amplitude of exciting signals and the location of exciting points. From a measuring view point. the location of sensing point have no influence on the performance of the present method. With a view to verifying the effectiveness of this method. a series of experiments are made and the results show its possibility as a robust damage diagnostic method.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.9
• /
• pp.429-434
• /
• 2006

In this paper, detection based - adaptive windowed nonlinear filter(DB-AWNF) is proposed for removing salt-pepper noise in infrared image. This filter is composed of impulse detector and window-size-variable median filters. Impulse detector checks whether current pixel is impulse or not using range function and nonlinear location estimator. If impulse is detected, current pixel is filtered according to four kinds of local masks by use of median filter. If not, current pixel is delivered to output like identity filter. In Qualitative view, the proposed could have removed heavy corrupted noise up to 30% and reserved the details of image. In quantitative view, PSNR was measured. The proposed could have about 12-31[dB] more improved performance than those of median $(3{\times}3)$ filter and 13-29[dB] more improved performance than those of median $(5{\times}5)$ filter.

• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.11-16
• /
• 2020

Deep Learning has become the most important technology in the field of artificial intelligence machine learning, with its high performance overwhelming existing methods in various applications. In this paper, an interactive window service based on object recognition technology is proposed. The main goal is to implement an object recognition technology using this deep learning technology to remove the existing eye tracking technology, which requires users to wear eye tracking devices themselves, and to implement an eye tracking technology that uses only usual cameras to track users' eye. We design an interactive system based on efficient eye detection and pupil tracking method that can verify the user's eye movement. To estimate the view-direction of user's eye, we initialize to make the reference (origin) coordinate. Then the view direction is estimated from the extracted eye pupils from the origin coordinate. Also, we propose a blink detection technique based on the eye apply ratio (EAR). With the extracted view direction and eye action, we provide some augmented information of interest without the existing complex and expensive eye-tracking systems with various service topics and situations. For verification, the user guiding service is implemented as a proto-type model with the school map to inform the location information of the desired location or building.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.1
• /
• pp.32-38
• /
• 2011

Collisions of nearby ships are reported frequently because of bad weathers. A lot of efforts, using radar warning or other navigation security devices, were given to reduce the collisions, but the number of accidents could not be reduced. The main cause is that the ship personel are not watching carefully. In the paper, we propose a novel technique estimating the locations of nearby ships from their whistle blast and delivering the location information using mobile phones. We realized the technique using LabVIEW and showed its usefulness.