• Journal of Korea Game Society
• /
• v.7 no.4
• /
• pp.71-80
• /
• 2007

In this paper, we introduce an efficient GPU-based real-time rendering technique applicable to every kind of game. Our method, without an extra geometry, can represent terrain just with a height map. It makes it possible to freely go around in the air or on the surface, so we can directly apply it to any computer games as well as a virtual reality. Since our method is not based on any geometrical structure, it doesn't need special LOD policy and the precision of geometrical representation and visual quality absolutely depend on the resolution of height map and color map. Moreover, GPU-only technique allows the general CPU to be dedicated to more general work, and as a result, enhances the overall performance of the computer. To date, there have been many researches related to the terrain representation, but most of them rely on CPU or confmed its applications to flight simulation, Improving existing displacement mapping techniques and applying it to our terrain rendering, we completely ruled out the problems, such as cracking, poping etc, which cause in polygon-based techniques, The most important contributions are to efficiently deal with arbitrary LOS(Line Of Sight) and dramatically improve visual quality during walk-through by reconstructing a height field with curved patches. We suggest a simple and useful method for calculating ray-patch intersections. We implemented all these on GPU 100%, and got tens to hundreds of framerates with height maps a variety of resolutions$(256{\times}256\;to\;4096{\times}4096)$.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.55-61
• /
• 2021

In this paper, we proposed a DeepLabv3+ based encoder-decoder model utilizing an attention mechanism for precise semantic segmentation. The DeepLabv3+ is a semantic segmentation method based on deep learning and is mainly used in applications such as autonomous vehicles, and infrared image analysis. In the conventional DeepLabv3+, there is little use of the encoder's intermediate feature map in the decoder part, resulting in loss in restoration process. Such restoration loss causes a problem of reducing segmentation accuracy. Therefore, the proposed method firstly minimized the restoration loss by additionally using one intermediate feature map. Furthermore, we fused hierarchically from small feature map in order to effectively utilize this. Finally, we applied an attention mechanism to the decoder to maximize the decoder's ability to converge intermediate feature maps. We evaluated the proposed method on the Cityscapes dataset, which is commonly used for street scene image segmentation research. Experiment results showed that our proposed method improved segmentation results compared to the conventional DeepLabv3+. The proposed method can be used in applications that require high accuracy.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.144-159
• /
• 2014

Techniques for making a single panoramic image using multiple pictures are widely studied in many areas such as computer vision, computer graphics, etc. The panorama image can be applied to various fields like virtual reality, robot vision areas which require wide-angled shots as an useful way to overcome the limitations such as picture-angle, resolutions, and internal informations of an image taken from a single camera. It is so much meaningful in a point that a panoramic image usually provides better immersion feeling than a plain image. Although there are many ways to build a panoramic image, most of them are using the way of extracting feature points and matching points of each images for making a single panoramic image. In addition, those methods use the RANSAC(RANdom SAmple Consensus) algorithm with matching points and the Homography matrix to transform the image. The SURF(Speeded Up Robust Features) algorithm which is used in this paper to extract featuring points uses an image's black and white informations and local spatial informations. The SURF is widely being used since it is very much robust at detecting image's size, view-point changes, and additionally, faster than the SIFT(Scale Invariant Features Transform) algorithm. The SURF has a shortcoming of making an error which results in decreasing the RANSAC algorithm's performance speed when extracting image's feature points. As a result, this may increase the CPU usage occupation rate. The error of detecting matching points may role as a critical reason for disqualifying panoramic image's accuracy and lucidity. In this paper, in order to minimize errors of extracting matching points, we used $3{\times}3$ region's RGB pixel values around the matching points' coordinates to perform intermediate filtering process for removing wrong matching points. We have also presented analysis and evaluation results relating to enhanced working speed for producing a panorama image, CPU usage rate, extracted matching points' decreasing rate and accuracy.

• The KIPS Transactions:PartD
• /
• v.10D no.1
• /
• pp.1-12
• /
• 2003

Recently, there have been many indexing schemes for multimedia data such as image, video data. But recent database applications, for example data mining and multimedia database, are required to support multi-user environment. In order for indexing schemes to be useful in multi-user environment, a concurrency control algorithm is required to handle it. So we propose a concurrency control algorithm that can be applied to CBF (cell-based filtering method), which uses the signature of the cell for alleviating the dimensional curse problem. In addition, we extend the SHORE storage system of Wisconsin university in order to handle high-dimensional data. This extended SHORE storage system provides conventional storage manager functions, guarantees the integrity of high-dimensional data and is flexible to the large scale of feature vectors for preventing the usage of large main memory. Finally, we implement the web-based image retrieval system by using the extended SHORE storage system. The key feature of this system is platform-independent access to the high-dimensional data as well as functionality of efficient content-based queries. Lastly. We evaluate an average response time of point query, range query and k-nearest query in terms of the number of threads.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.3 no.1
• /
• pp.57-72
• /
• 2008

Serve and do so that graft together specialists' view application field of computer and developmental disability diagnosis estimation data to construct developmental disability diagnosis estimation system in this Paper and constructed developmental disability diagnosis estimation system. Developmental disability diagnosis estimation must supply information of specification area that specialists are having continuously. Developmental disability diagnosis estimation specialist system need multimedia data processing that is specialized little more for developmental disability classification diagnosis and decision-making and is atomized for this. Characteristic of developmental disability diagnosis estimation system that study in this paper can supply quick feedback about result, and can reduce mistake on recording and calculation as well as can shorten examination's enforcement time, and background of training is efficient system fairly in terms of nonprofessional who is not many can use easily. But, as well as when multimedia information that is essential data of system construction for developmental disability diagnosis estimation is having various kinds attribute and a person must achieve description about all developmental disability diagnosis estimation informations, great amount of work done is accompanied, technology about equal data can become different according to management. Because of these problems, applied search technology of contents base (Content-based) that search connection information by contents of edit target data for developmental disability diagnosis estimation data processing multimedia data processing technical development. In the meantime, typical access way for conversation style data processing to support fast image search, after draw special quality of data by N-dimension vector, store to database regarding this as value of N dimension and used data structure of Tree techniques to use index structure that search relevant data based on this costs. But, these are not coincided correctly in purpose of developmental disability diagnosis estimation because is developed focusing in application field that use data of low dimension such as original space DataBase or geography information system. Therefore, studied save structure and index mechanism of new way that support fast search to search bulky good physician data.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.10
• /
• pp.481-491
• /
• 2024

Digital watermarking is a technique for embedding information into digital content. Digital watermarking has attracted attention as a technique to combat piracy and identify artificially generated content, but it is still not robust in various situations. In this paper, we propose a frequency conversion-based hierarchical watermarking technique capable of attack detection, error correction, and owner identification. By embedding attack detection and error correction signatures in hierarchical watermarking, the proposed scheme maintains invisibility and outperforms the existing methods in capacity and robustness. We also proposed a framework to evaluate the performance of the image quality and error correction according to the type of error correction signature and the number of signature embeddings. We compared the visual quality and error correction performance of the conventional model without error correction signature and the conventional model with hamming and BCH signatures. We compared the quality by the number of signature embeddings and found that the quality deteriorates as the number of embeddings increases but is robust to attacks. By analyzing the quality and error correction ability by error correction signature type, we found that hamming codes showed better error correction performance than BCH codes and 41.31% better signature restoration performance than conventional methods.

• 한국가시화정보학회:학술대회논문집
• /
• 2005.04a
• /
• pp.87-112
• /
• 2005

분무를 정량적으로 측정하는 것은 노즐의 설계와 개발을 위해서 뿐만 아니라 연소 시스템 전반의 효율 및 불안정성의 제거, 공해 저감 등의 요구 조건을 만족하기 위해서 중요하다. 이를 위해 이전에는 분무장 내에 수집관을 삽입하는 기계적 패터네이터(Mechanical Patternator)와 같은 삽입식 측정 방식을 이용하여 왔으나, 최근에는 고속카메라, Malvern particle analyzer, PDPA, 광학 패터네이터(Optical Patternator)와 같은 분무장을 교란시키지 않으면서도 빠른 측정이 가능한 가시화 기술들이 적용되고 있다. 특히 광학 패터네이터는 레이저 평면광을 이용하여 분무를 측정하는 비삽입식 기술로 단시간 내에 분무장 내 액체 연료의 질량 및 액적 크기의 단면 분포를 동시에 얻어낼 수 있는 장점을 갖고 있다. 그러나 분무 액적들의 수밀도가 증가하는 경우에는 이들 액적에 의한 입사광 및 신호 감쇠, 다중산란 등에 의한 오차가 심하게 발생하여, 기존의 PDPA, PLIF 등의 광학 기법으로는 충분히 신뢰할 만한 결과를 얻기가 어렵게 된다. 이러한 분무를 정량적으로 측정하기 위해서는 입사광의 감쇠뿐만 아니라 분무장 내 액적들에 의한 신호의 감쇠 과정에 대한 고려가 필요하다. 주면 액적들의 영향을 최소한으로 줄이기 위해서는 레이저 평면광을 사용하는 광학 패터네이터와 달리 레이저 광선을 분무장에 조사하여 고압에서 나타날 수 있는 다중 산란에 의한 오차를 최소화할 수 있다. 이러한 이미지 처리 기법을 이용하는 광학 선형 패터네이터(Optical Line Patternator)를 이용하여 기존 레이저 계측기법으로 측정이 곤란하였던 고압 환경 하에서의 스월 동축형 인젝터의 분무 특성을 해석할 수가 있다. 2015(년도) 6,388, 2025(년도) 13,367, 2035(년도) 18,756, 2045(년도) 22,595, 시장점유율 증가로 인한 수출액 증가분 누적(억원) : 2015(년도) 3,411, 2025(년도) 8,847, 2035(년도) 14,433, 2045(년도) 18,005 또한 시나리오 비교평가를 실시하여 본 결과, 본 연구에서 정의한 순편익 누적(Cumulative Net Profit) 변수를 적용하면 현재 연구비 추세 대비 $30\%$ 까지 연구비를 증가 시키는 것이 효율적임을 알 수 있었다.성, 생산 용이성, 제품 디자인의 우수한 정도가 a=0.01 수준 하에서 유의적으로 추정되었다. 이들 변수들 중에서 품질경쟁력에 가장 큰 영향을 미치는 측정변수는 제품의 기본 성능, 수명(내구성), 신뢰성, 제품 디자인의 순서로 추정되었다. 이것은 한국 제조업이 아직 산업 디자인이 품질경쟁력에 크게 영향을 미치는 성숙단계에 이르지 못하였음을 의미한다. (2) 제품 디자인에게 영향을 끼치는 유의적인 변수는 연구개발력, 연구개발투자 수준, 혁신활동 수준(5S, TPM, 6Sigma 운동, QC 등)이며, 제품 디자인은 우선 품질경쟁력을 높여 간접적으로 고객만족과 고객 충성을 유발하는 것으로 추정되었다. 상기의 분석결과로부터, 본 연구는 다음과 같은 정책적 함의를 도출하였다. 첫째, 신상품 개발과 혁신을 위한 포괄적인 연구개발 프로젝트를 품질 경쟁력의 주요 결정요인(제품의 기본성능, 신뢰성, 수명(내구성) 및 제품 디자인)과 연계하여 추진해야 할 것이다. 둘째, 기업은 디자인 경영 마인드 제고와 디자인 전문인력 양성을, 대학은 디자인 현장 업무를 통하여 창의력 증진과 기획 및 마케팅 능력 교육을, 정부는 디자

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• Korean Journal of Cognitive Science
• /
• v.24 no.1
• /
• pp.49-69
• /
• 2013

While we interact with other people or objects, the brain continuously updates our own body schema to recognize the agent of observed actions. The Extrastriate Body Area (EBA) provides an initial interface for the sense of agency by integrating visual inputs of body parts with internal signals related to self-generated body movements. Less is known, however, about how the functional use of tools contributes to such processes. Here, we investigated whether tool-specific affordance would differentially affect the neural responses in the EBA depending on the agency of imaginary actions. In each trial we presented a picture of an object in a rectangular frame. Objects were either the tools typically brought towards the body (body tools; e.g., telescope, earphones) or away from the body (world tools; e.g., pen, dice; Rueschemeyer, Pfeiffer, & Bekkering, 2010). Depending on the color of the frame, participants imagined either themselves or the other person using the tool (self vs. other conditions). These four types of trials were randomly intermixed with blank trials. As results, independently localized right EBA regions of interest showed greater activation when participants imagined themselves using body tools than using world tools whereas no such differential activations were found when they imagined the other person using the tools. The postscan test revealed no significant difference in vividness of imagery between the self and other conditions. Our results suggest that the EBA incorporates functional affordance of tools into the body schema in order to enhance the sense of agency and to guide our own actions.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.375-382
• /
• 2003

Lip-reading technique based on bimodal is to enhance speech recognition rate in noisy environment. It is most important to detect the correct lip-image. But it is hard to estimate stable performance in dynamic environment, because of many factors to deteriorate Lip-reading's performance. There are illumination change, speaker's pronunciation habit, versatility of lips shape and rotation or size change of lips etc. In this paper, we propose the IIR filtering in time-domain for the stable performance. It is very proper to remove the noise of speech, to enhance performance of recognition by digital filtering in time domain. While the lip-reading technique in whole lip image makes data massive, the Principal Component Analysis of pre-process allows to reduce the data quantify by detection of feature without loss of image information. For the observation performance of speech recognition using only image information, we made an experiment on recognition after choosing 22 words in available car service. We used Hidden Markov Model by speech recognition algorithm to compare this words' recognition performance. As a result, while the recognition rate of lip-reading using PCA is 64%, Time-domain filter applied to lip-reading enhances recognition rate of 72.4%.