• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.161-170
• /
• 2012

This paper presents an efficient and robust approach for determining the correspondence between unbalanced stereo images. The disparity vectors were used instead of feature points, such as corners, to calculate a correspondence relationship. For a faster and optimal estimation, the vectors were classified into several regions, and the homography of each region was calculated using the RANSAC algorithm. The correspondence image was calculated from the images transformed by each homography. Although it provided good results under normal conditions, it was difficult to obtain reliable results in an unbalanced stereo pair. Therefore, a balancing method is also proposed to minimize the unbalance effects using the histogram specification and structural similarity index. The experimental results showed that the proposed approach outperformed the baseline algorithms with respect to the speed and peak-signal-to-noise ratio. This work can be applied to practical fields including 3D depth map acquisition, fast stereo coding, 2D-to-3D conversion, etc.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.11a
• /
• pp.311-314
• /
• 2010

최근 3D 영상에 대한 대중화가 급속히 진행되고 있음에도 불구하고 한 번 만들어진 영상/비디오를 재사용하거나 조작하여 다양한 형태의 콘텐츠를 만들지 못하고 있다. 본 논문에서는 깊이영상과 양안(스테레오) 영상 또는 깊이영상과 단안 영상이 주어졌다고 가정하고 깊이영상을 조작하여 양안 시차(parallax)를 변화시키는 방법을 제안한다. 시차변화의 대상은 부분영상이며, 특정 개체를 추출하여 깊이정보를 수정하고, 이를 바탕으로 스테레오 영상을 재구성한다. 본 논문에서는 정지영상만을 대상으로 하며, 동일한 방법을 동영상에 적용하면 동영상 또한 시차를 변화시킨 결과를 얻을 수 있다. 실험은 Middlebury의 테스트 영상들을 대상으로 제안한 방법을 적용하여 자연스러운 스테레오 영상을 얻을 수 있음을 보인다.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.12 no.2
• /
• pp.8-17
• /
• 2008

Objectives: For the traditional pulse diagnosis in Oriental Medicine, not only the pulse shape in time domain, but the width, length and depth of arterial pulse also should be measured. However, conventional pulse diagnostic systems have failed to measure the spatial parameters of the arterial pulse e.g. effective length of arterial pulse in the wrist. In fact, there are many ways to measure that kind of spatial features in arterial pulsation, but among them, the method using image sensor provides relatively cheap and simple way, therefore I tested feasibility of measuring 2-dimensional pressure distribution by imaging devices. Methods: Using widely used PC cameras and dotted balloons, the subtle oscillation of skin over the radial artery was recorded continuously, and then the displacement of every dot was calculated. Consequently, the time course of that displacements shows arterial pulse wave. Results: By the proposed method I could get pressure distribution map with 30Hz sampling rate, 21steps quantization resolution, and approximately 1mm spatial resolution. With reduced quantization resolution, $3cm{\times}4cm$ view angle could be achieved. Conclusion: Although this method has some limitations, it would be useful method for detecting 2-dimensional features of arterial pulse, and accordingly, this method provides a novel way to detect 'narrow pulse', 'wide pulse', 'long pulse', 'short pulse', and their derivatives.

• Journal of Korean Society of societal Security
• /
• v.2 no.3
• /
• pp.39-46
• /
• 2009

A small loop-loop multi-frequency electromagnetic(EM) induction method is a useful technique to map a resistivity distribution efficiently and non-destructively. However, for quantitative interpretation and depth sounding, the quality of measured data is crucial. In this paper, we propose a bias correction of measured data by using background noise measurements to obtain reliable data, and propose an evaluation technique of apparent that can provide a resistivity image easily. We have performed small loop-loop EM measurements to detect water saturation in a man-made test site. The application of our proposed techniques to the measured data was successful.

• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1552-1559
• /
• 2021

Convolution neural networks (CNNs) show notable performance in image processing and are used as representative core models. CNNs extract and learn features from large amounts of train dataset. In general, it has a structure in which a convolution layer and a fully connected layer are stacked. The core of CNN is the convolution layer. The size of the kernel used for feature extraction and the number that affect the depth of the feature map determine the amount of weight parameters of the CNN that can be learned. These parameters are the main causes of increasing the computational complexity and memory usage of the entire neural network. The most computationally expensive components in CNNs are fully connected and spatial convolution computations. In this paper, we propose a Fourier Convolution Neural Network that performs the operation of the convolution layer in the Fourier domain. We work on modifying and improving the amount of computation by applying the fast fourier transform method. Using the MNIST dataset, the performance was similar to that of the general CNN in terms of accuracy. In terms of operation speed, 7.2% faster operation speed was achieved. An average of 19% faster speed was achieved in experiments using 1024x1024 images and various sizes of kernels.

• Journal of Navigation and Port Research
• /
• v.32 no.5
• /
• pp.355-361
• /
• 2008

Stereo matching is one of the most active research areas in computer vision. In this paper, we propose a stereo matching scheme using genetic algorithm for object depth recognition. The proposed approach considers the matching environment as an optimization problem and finds the optimal solution by using an evolutionary strategy. Accordingly, genetic operators are adapted for the circumstances of stereo matching. An individual is a disparity set. Horizontal pixel line of image is considered as a chromosome. A cost function is composed of certain constraints which are commonly used in stereo matching. Since the cost function consists of intensity, similarity and disparity smoothness, the matching process is considered at the same time in each generation. The LoG(Laplacian of Gaussian) edge is extracted and used in the determination of the chromosome. We validate our approach with experimental results on stereo images.

• Journal of Korea Multimedia Society
• /
• v.16 no.1
• /
• pp.11-18
• /
• 2013

This paper presents a SFF(shape from focus) algorithm using a new focus measure based on higher order statistics for the exact depth estimation. Since conventional SFF-based 3D depth reconstruction algorithms used SML(sum of modified Laplacian) as the focus measure, their performance is strongly depended on the image characteristics. These are efficient only for the rich texture and well focused images. Therefore, this paper adopts a new focus measure using HOS(higher order statistics), in order to extract the focus value for relatively poor texture and focused images. The initial best focus area map is generated by the measure. Thereafter, the area refinement, thinning, and corner detection methods are successively applied for the extraction of the locally best focus points. Finally, a 3D model from the carefully selected points is reconstructed by Delaunay triangulation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.707-716
• /
• 2017

The advances in image display devices necessitate display images suitable for the user's purpose. The display devices should be able to provide object-based image information when a depthmap is required. In this paper, we represent the algorithm using a histogram-based image segmentation method for depthmap generation. In the conventional K-means clustering algorithm, the number of centroids is parameterized, so existing K-means algorithms cannot adaptively determine the number of clusters. Further, the problem of K-means algorithm tends to sink into the local minima, which causes over-segmentation. On the other hand, the proposed algorithm is adaptively able to select centroids and can stand on the basis of the histogram-based algorithm considering the amount of computational complexity. It is designed to show object-based results by preventing the existing algorithm from falling into the local minimum point. Finally, we remove the over-segmentation components through connected-component labeling algorithm. The results of proposed algorithm show object-based results and better segmentation results of 0.017 and 0.051, compared to the benchmark method in terms of Probabilistic Rand Index(PRI) and Segmentation Covering(SC), respectively.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.162-170
• /
• 2013

In recent years, the interests and needs of the Pedestrian Protection System (PPS), which is mounted on the vehicle for the purpose of traffic safety improvement is increasing. In this paper, we propose a pedestrian candidate window extraction and unit cell histogram based HOG descriptor calculation methods. At pedestrian detection candidate windows extraction stage, the bright ratio of pedestrian and its circumference region, vertical edge projection, edge factor, and PCA reconstruction image are used. Dalal's HOG requires pixel based histogram calculation by Gaussian weights and trilinear interpolation on overlapping blocks, But our method performs Gaussian down-weight and computes histogram on a per-cell basis, and then the histogram is combined with the adjacent cell, so our method can be calculated faster than Dalal's method. Our PCA reconstruction error based pedestrian detection candidate window extraction method efficiently classifies background based on the difference between pedestrian's head and shoulder area. The proposed method improves detection speed compared to the conventional HOG just using image without any prior information from camera calibration or depth map obtained from stereo cameras.

• Journal of Broadcast Engineering
• /
• v.9 no.4 s.25
• /
• pp.402-410
• /
• 2004

Recently, there has been much interest in realistic broadcasting that is a new field following HDTV and 3DTV. In general. the realistic broadcasting is composed of diverse components such as aquisition, authoring, compression, transmission and display, posing many challenging tasks. It is necessary that the types of realistic contents need to be defined prior to the development of realistic broadcasting systems. Based upon them, other components need to be designed and developed. In this paper, we propose some realistic contents suitable to the realistic broadcasting as well as techniques of generating them. Our proposed contents consist of stereoscopic multiview sequences, object-based stereoscopic images, depth map-based image compositing and the composition of stereoscopic real and graphics images. Content generation techniques and their associated software modules are presented with realistic images produced from our experiments. Those contents are produced to deliver stereoscopic perception, immersion and realism to the users as shown in our experimental results.