• 방송공학회논문지
• /
• 제11권4호
• /
• pp.396-406
• /
• 2006

본 논문에서는 변수화된 영상 보정을 통한 전방향 영상 (Omni-directional image) 생성 방법을 제안한다. 제안한 방법은 모든 방향의 영상을 포함하고 영상 합성 시에 발생하는 왜곡과 에러를 최소화하는 전방향 영상을 생성하기 위해, 원형 좌표계를 기반으로 평면 영상을 원형 영상으로 변환한다. 카메라로 획득한 각각의 영상은 카메라의 시스템과 외부 환경 조건에 따라 발생하는 비그네이팅 효과와 조명 변화를 포함하고 있으므로, 최적의 비그네이팅 및 조명 변수를 추출하여 자연스러운 전방향 영상 생성을 위한 영상 보정 과정을 수행한다. 실험 결과에서는 제안한 방법에 따라 생성된 전방향 영상을 확인하고 비그네이팅 효과 및 조명 변화를 고려하지 않은 방법과 제안한 방법의 성능을 비교, 분석하여 제안한 방법이 $1{\sim}4dB$ 정도 더 효과적임을 보인다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.991-994
• /
• 2002

Photon mapping is an efficient global illumination technique for realistic image synthesis that has been developed in computer graphics. In this paper, an adaptive photon mapping in the use of automatic differentiation is proposed. Since the automatic differentiation is used when photons emit from the light sources through the scene, we can check the variation of surrounding shape. Therefore, we can decrease the number of photons and generate an image in relatively low computational cost.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1996년도 Proceedings International Workshop on New Video Media Technology
• /
• pp.83-87
• /
• 1996

A virtual reality system using video image is designed and implemented. A participant having 2{{{{ { 1} over { 2} }}}}DOF can interact with the computer-generated virtual object using her/his full body posture and gesture in the 3D virtual environment. The system extracts the necessary participant-related information by video-based sensing, and simulates the realistic interaction such as collision detection in the virtual environment. The resulting scene obtained by compositing video image of the participant and virtual environment is updated in near real time.

• Communications for Statistical Applications and Methods
• /
• 제8권1호
• /
• pp.109-115
• /
• 2001

Wavelet coefficients are known to have decorrelating properties, since wavelet is orthonormal transformation. but empirically, those wavelet coefficients of images, like edges, are not statistically independent. Jansen and Bultheel(1999) developed the empirical Bayes approach to improve the classical threshold algorithm using local characterization in Markov random field. They consider the clustering of significant wavelet coefficients with uniform distribution. In this paper, we developed wavelet thresholding algorithm using Laplacian distribution which is more realistic model.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권5호
• /
• pp.226-232
• /
• 2001

The ability to efficiently and robustly recover accurate 3D terrain models from sets of stereoscopic images is important to many civilian and military applications. To develop an effective and practical terrain modeling system, we propose a new multi-image stereo method which detect unreliable elevations in DEM(Digital Elevation Map), and fuse several DEMs from multiple sources into an accurate and reliable results. This paper focuses on two key factors for generating robust 3D terrain models: the ability to detect unreliable elevation estimates and the ability to fuse the reliable elevations into a single optimal terrain model. We apply the self-consistency methodology to reconstruct accurate DEM from multi-image and show the method is more effective than the conventional stereo image 3D reconstruction method. Using photo-realistic simulator, four synthetic image are generated from ground truth DEM and orthoimage to evaluate the accuracy of the proposed method quantitatively.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1239-1242
• /
• 1998

In television stereo system, to produce a realistic sound effect is very difficult because the distance between stereo speakers is very narrow. Many signal processing methods of widening the sound image for spatial impression have been studied. One of the methods of widening the sound image is using the Precedence Effect by reflected sound. However, this method does not work effectively in lower frequencies because of directivity of a speaker. In this paper, we propose an effective method of expanding stereo image using Precedence Effect and Phase Shifting method to produce a whole band frequency sound expansion. In experiments, we confirm the usefulness of the proposed stereo sound image expansion system.

• ETRI Journal
• /
• 제36권3호
• /
• pp.450-459
• /
• 2014

In this paper, we present a new, easy-to-generate system that is capable of creating virtual 3D tree models and simulating a variety of growth processes of a tree from a single, real tree image. We not only construct various tree models with the same trunk through our proposed digital image matting method and skeleton-based abstraction of branches, but we also animate the visual growth of the constructed 3D tree model through usage of the branch age information combined with a scaling factor. To control the simulation of a tree growth process, we consider tree-growing attributes, such as branching orders, branch width, tree size, and branch self-bending effect, at the same time. Other invisible branches and leaves are automatically attached to the tree by employing parametric branch libraries under the conventional procedural assumption of structure having a local self-similarity. Simulations with a real image confirm that our system makes it possible to achieve realistic tree models and growth processes with ease.

• International Journal of Aeronautical and Space Sciences
• /
• 제10권1호
• /
• pp.83-90
• /
• 2009

A new IRF (Impulse Response Function) analysis technique in high resolution SAR image is presented by taking into account the real clutter environment. In order to investigate the realistic effect of clutter background on the impulse response function of SAR image, an ideally generated impulse response function is superimposed with a large number of background clutter data which are extracted from the various regions of an actual SAR image. As a performance measure, PSLR (Peak Sidelobe Ratio) of the clutter-contained IRF is presented in the various groups of clutter background, and finally the results are compared with the stochastic model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5506-5521
• /
• 2017

Three-dimensional video (3DV), as the new generation of video format standard, can provide the viewers with a vivid screen sense and a realistic stereo impression. Meanwhile the view synthesis has become an important issue for 3DV application. Differently from the conventional methods based on depth, in this paper we propose a new view synthesis algorithm, which can employ the correlation among views and warp in the image domain only. There are mainly two contributions. One is the incorporation of sobel edge points into feature extraction and matching, which can obtain a better stable homography and then a visual comfortable synthesis view compared to SIFT points only. The other is a novel image blending method proposed to obtain a better synthesis image. Experimental results demonstrate that the proposed method can improve the synthesis quality both in subjectivity and objectivity.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.401-403
• /
• 2019

In this paper, we propose a generative adversarial networks (GAN) based text-to-image generating method. In many natural language processing tasks, which word expressions are determined by their term frequency -inverse document frequency scores. Word2Vec is a type of neural network model that, in the case of an unlabeled corpus, produces a vector that expresses semantics for words in the corpus and an image is generated by GAN training according to the obtained vector. Thanks to the understanding of the word we can generate higher and more realistic images. Our GAN structure is based on deep convolution neural networks and pixel recurrent neural networks. Comparing the generated image with the real image, we get about 88% similarity on the Oxford-102 flowers dataset.