• Journal of Broadcast Engineering
• /
• v.11 no.4 s.33
• /
• pp.396-406
• /
• 2006

This paper proposes an omni-directional image generation algorithm with parametric image compensation. The algorithm generates an omni-directional image by transforming each planar image to the spherical image on spherical coordinate. Parametric image compensation method is presented in order to compensate vignetting and illumination distortions caused by properties of a camera system and lighting condition. The proposed algorithm can generates realistic and seamless omni-directional video and synthesize any point of view from the stitched omni-directional image on the spherical image. Experimental results show that the proposed omni-directional system with vignetting and illumination compensation is approximately $1{\sim}4dB$ better than that which does not consider the said effects.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• 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.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06b
• /
• 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
• /
• v.8 no.1
• /
• 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.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.5
• /
• 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.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• 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
• /
• v.36 no.3
• /
• 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
• /
• v.10 no.1
• /
• 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)
• /
• v.11 no.11
• /
• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• 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.