• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.5
• /
• pp.1225-1233
• /
• 2008

In this paper, the 2D/3D converting algorithm is proposed. The single frame of 2D image is used fur the real-time processing of the proposed algorithm. The proposed algorithm creates a 3D image with the depth map by using the vertical position information of a object in a single frame. In order to real-time processing and improve the hardware complexity, it performs the generation of a depth map using the image sampling, the object segmentation with the luminance standardization and the boundary scan. It might be suitable to a still image and a moving image, and it can provide a good 3D effect on a image such as a long distance image, a landscape, or a panorama photo because it uses a vertical position information. The proposed algorithm can adapt a 3D effect to a image without the restrictions of the direction, velocity or scene change of an object. It has been evaluated with the visual test and the comparing to the MTD(Modified Time Difference) method using the APD(Absolute Parallax Difference).

• Journal of Korea Multimedia Society
• /
• v.17 no.1
• /
• pp.26-33
• /
• 2014

Video retrieval and indexing are performed by comparing feature similarities between key frames in shot after detecting a scene change and extracting key frames from the shot. Typical image features such as color, shape, and texture are used in content-based video and image retrieval. Many approaches for integrating these features have been studied. However, the issue of these approaches is how to appropriately assign weighting of key frame features at query time. Therefore, we propose a new video retrieval method using adaptively weighted image features. We performed computer simulations in test databases which consist of various kinds of key frames. The experimental results show that the proposed method has better performance than previous works in respect to several performance evaluations such as precision vs. recall, retrieval efficiency, and ranking measure.

• Journal of Intelligence and Information Systems
• /
• v.10 no.1
• /
• pp.1-11
• /
• 2004

It is very important part of pre-processing for get better results by image processing that get emphasized image by processing of source image. Emphasized image is not only good looking image but clear and sharp image. Emphasized images are used very useful data at contour extraction and image recognition in image processing. It have different image recognition by how much represent a origin scene in row quality image. Present algorithms that get emphasized premier image do not get clear picture of degree that want in various kind of images and there is shortcoming that need much process times being proportional size of picture quality or accumulation degree of histogram. In this paper, we propose method to change distribution chart that pixels occupy in histogram as subsequentness in reflex of various kinds as well as that picture quality reflex method to emphasize so that is suitable in practical use purpose originally of premier. Proposed algorithm re-allot histogram distribution by reverse tracking histogram. Experimental images are same result and take less processing time than histogram equalization.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.65-76
• /
• 2005

A digital video is a very long data that requires large-capacity storage space. As such, prior to watching a long original video, video watchers want to watch a summarized version of the video. In the field of sports, in particular, highlights videos are frequently watched. In short, a highlights video allows a video watcher to determine whether the highlights video is well worth watching. This paper proposes a scheme for creating soccer video highlights using the structural features of captions in terms of time and space. Such structural features are used to extract caption frame intervals and caption keyframes. A highlights video is created through resetting shots for caption keyframes, by means of logical indexing, and through the use of the rule for creating highlights. Finally, highlights videos and video segments can be searched and browsed in a way that allows the video watcher to select his/her desired items from the browser.

• Journal of Korea Game Society
• /
• v.13 no.3
• /
• pp.85-94
• /
• 2013

In this paper, we propose a scheme to reduce the number of shadow tests conducted during rendering of ray tracing. The shadow test is a very important process in ray tracing to generate photo-realistic images. In the rendering phase, the ray tracer determines whether to cull the shadow test based on information calculated from a shadow test conducted on the kd-tree in the preprocessing phase. In conventional rendering process, the proposed method can be used with little modification. The proposed method is suitable for a static scene, in which the geometry and light source does not change in the same manner as it does in the conventional method. The validity of the proposed scheme is verified and its performance is evaluated during cycle-accurate simulation. Through experiment results, we found that we could reduce up to 17% of the shadow test.

• Fire Science and Engineering
• /
• v.25 no.5
• /
• pp.108-118
• /
• 2011

In this study, strengths related with fire investigation of fire stations are analyzed and methods for the capacity building of their fire cause investigation are suggested. The methods for capacity building of fire cause investigation suggested are focused on using potential and strengths of current fire fighting and enhancing internal capacity rather than reinforcing investigation personnel, organization, and equipment and ensuring investigation power. The methods suggested in this study are as follows. 1) Because fire investigation results are the basis of fire administration, fire marshals should change their awareness of the need of fire investigation; 2) A fire investigation system should be established to ensure statements of people concerned systematically; 3) A substantial system of fire cause investigation should be established to investigate fire scenes more than twice; 4) A substantial system of fire cause investigation should be established to use such materials as CCTV; 5) Extinguishing should be made in consideration of fire cause investigation and a scene preservation system after extinguishing should be established; 6) A fire investigation system should be established in connection with 119 first-aid and rescue teams and 7) Steps to raise the morale of fire investigation staff should be taken.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.8 no.2
• /
• pp.71-78
• /
• 2002

For the first Maritime Accident Inquiry System in Korea, Central Marine Accidents Inquiry Committee were founded in Seoul and District Marine Accidents Inquiry Committee in Busan city In 1963 to determine the circumstances of the accidents and causes. At the present day, it was settled as Maritime Safety Tribunal tough several revision of the Law and regulations regarding the Maritime Accident Inquiry System. In Korea, there occurred about m cases of marine accident, and as a result, about 200 people were lost human lives in average per year. In accordance with the change of circumstances such as traffic increasing and being bigger in size, being faster in speed, etc., the causes of the marine accidents become complicated year by year. Accordingly, in this moment, it is meaningful that the introduction of the Research Official who assists the Judges probing the cases fair and square. In this Paper, with the consideration of the several kinds of Research Official System, such as the Research Official of the Korean Supreme Court, the Supreme Public Prosecutors' Office and the Constitutional Court, Japanese Supreme Court, Law Clerk in USA, etc., the selection, numbers, duty of the Research Official were studied. The results of the study are as follows; 1. The Research Official to be appointed among the person having long enough career as a Judge, Investigator engaged in the Maritime Safety Tribunal due to he sho띨d have capability to confirm perfectly logical judgement and to collect enough material for the conclusion of the causes of the case. The one who understands the foreign language is preferred for the study of the foreign cases; 2. It will be logical to post 3 joint Research Officials in Korea Maritime Safety Tribunal in Seoul after due consideration the cases treated a year; 3. It will be logical for the Research Official to perform the collection of material and inspection of the scene for the trial and inquiry of the cases, to attend the cases filed suit to the Supreme Court, to make commentarial papers regarding the judged cases, to collect statistics of marine accidents and to devise a reform measure through in-depth analysis of the accidents frequently occurred, to study for the improvement of the Maritime Accident Inquiry System;

• Journal of Digital Contents Society
• /
• v.19 no.8
• /
• pp.1555-1564
• /
• 2018

In recent years, In recent years, research on geo-tagged image contents has defined a view frustum based on filming location and direction data and has studied indexes and various query search techniques for efficient search. The existing view frustum model has a limit of using the static visible distance and provides a simple service that displays the huge image contents on the digital map. We show a method to acquire filming location and attitude data and propose a view frustum model that can change the visible distance using geospatial object data. In addition, we describe the augmented reality service that combines the image matching technique so that it can be mapped in the scene where the image contents are captured.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.1
• /
• pp.94-98
• /
• 2015

Recently, with the rapid advancement in information and computer vision technology, a CCTV system using object recognition and tracking has been studied in a variety of fields. However, it is difficult to recognize a precise object outdoors due to varying pixel values by moving background elements such as shadows, lighting change, and moving elements of the scene. In order to adapt the background outdoors, this paper presents to analyze a variety of background models and proposed background update algorithms based on the weight factor. The experimental results show that the accuracy of object detection is maintained, and the number of misrecognized objects are reduced compared to previous study by using the proposed algorithm.

• Journal of Korea Multimedia Society
• /
• v.11 no.9
• /
• pp.1286-1295
• /
• 2008

Colors of 2D animation characters are generally assigned by art directors' subjective color sense. Even same characters should be colored differently according to the mood of animation scenes. In this study, we introduce the model for automatic color transformation of characters by using neural network. It can not only create automatically colors of characters which are good matched with 2D animation scenes but also reproduce art directors' subjective color sense. Specifically, this neural network model is initially made to learn the patterns of color change between basic colors of characters and colors of characters in various scene. Then if you know basic colors of some characters, you can derive colors of characters under other light source environments using the learned neural network. Subjective ratings(which is adopted to verify the proposed model) by color experts on the automatically transformed colors showed that the colors created by the model tended to be evaluated natural.