• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.927-929
• /
• 2011

Since DVC (Distributed Video Coding) and FRUC (Frame Rate Up Conversion) techniques need to have an efficient motion compensated frame interpolation algorithms. Conventional works of these applications have mainly focused on the performance improvement of overall system. But, in some applications, it is necessary to evaluate how well the MCI (Motion Compensated Interpolation) frame matches the original frame. For this aim, this paper deals with the modeling methods for evaluating the block-based matching cost. First, several matching criteria, which have already been dealt with the motion compensated frame interpolation, are introduced and then combined to make estimate models for the size of MSE (Mean Square Error) noise of the MCI frame to original one. Through computer simulations, it is shown that the block-based cost evaluation models are tested and can be effectively used for estimating the MSE noise.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.91-98
• /
• 2016

Detection and classification of underwater objects in sonar imagery are challenging problems. This paper proposes a system that detects and identifies underwater objects at the sea floor level using a sonar image and image processing techniques. The identification process of underwater objects consists of two steps; detection of candidate regions and identification of underwater objects. The candidate regions of underwater objects are extracted by image registration through the detection of common feature points between the reference background image and the current scanning image. And then, underwater objects are identified as the closest pattern within the database using eigenvectors and eigenvalues as features. The proposed system is expected to be used in efficient securement of Q route in vessel navigation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.77-87
• /
• 2011

In this paper, we propose a disparity correction technique to reduce the inherent visual discomfort while watching stereoscopic videos. The visual discomfort must be solved for commercial 3D display systems to provide natural stereoscopic videos to human eyes. The proposed disparity correction technique consists of horizontal and vertical disparity corrections. The horizontal disparity correction is implemented by controlling the depth budget of stereoscopic video using the geometric relations of a stereoscopic camera system. In addition, the vertical disparity correction is implemented by using a feature-based stereo matching algorithm. Conventional vertical disparity corrections have been done by only using camera calibration parameters, which still cause systematic errors in vertical disparities. In this paper, we minimize the vertical disparity as small as possible by using a feature-based correction algorithm. Through the comparisons of conventional feature-based correction algorithms, we analyze the performance of the proposed technique.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.5
• /
• pp.509-517
• /
• 2001

Full-search algorithm requires large amount of computation which causes time delay or very complex hardware architecture for real time implementation. In this paper, we propose a fast motion estimator based on bit-plane matching, which reduce the computational complexity and the hardware cost. In the proposed motion estimator, the conventional motion estimation algorithms are applied to the binary images directly extracted from the video sequence. Furthermore, in the proposed VLSI motion estimator, we employ a Pair of processing cores that calculate the motion vector continuously By controlling the data flow in a systolic fashion using the internal shift registers in the processing cores, we avoid using SRAM (local memory) so that we remove the time overhead for accessing the local memory and adopt lower-cost fabrication technology. We modeled and tested the proposed motion estimator in VHDL, and then synthesized the whole system which has been integrated in a 0.6-$\mu$m triple-metal CMOS chip of size 8.15 X 10.84$\textrm{mm}^2$.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.482-486
• /
• 2010

Recently, gesture recognition methods based on dynamic time warping (DTW) have been actively investigated as more mobile devices have equipped the accelerometer. DTW has no additional training step since it uses given samples as the matching templates. However, it is difficult to apply the DTW on mobile environments because of its computational complexity of matching step where the input pattern has to be compared with every templates. In order to address the problem, this paper proposes a gesture recognition method based on DTW that uses localized subset of templates. Here, the k-means clustering algorithm is used to divide each class into subclasses in which the most centered sample in each subclass is employed as the localized template. It increases the recognition speed by reducing the number of matches while it minimizes the errors by preserving the diversities of the training patterns. Experimental results showed that the proposed method was about five times faster than the DTW with all training samples, and more stable than the randomly selected templates.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.316-328
• /
• 2014

In this paper, we parallelize the popular feature detection algorithms, i.e. SIFT and SURF, and its application to fast panoramic image generation on the latest embedded GPU. Parallelized algorithms are implemented using recently developed OpenCL as the embedded GPGPU software platform. We compare the implementation efficiency and speed performance of conventional OpenGL Shading Language and OpenCL. Experimental result shows that implementation on OpenCL has comparable performance with GLSL. Compared with the performance on the embedded CPU in the same application processor, the embedded GPU runs 3~4 times faster. As an example of using feature extraction, panorama image synthesis is performed on embedded GPU by applying image matching using detected features.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.24 no.4
• /
• pp.367-376
• /
• 2006

This study determines the optimum polynomial of exterior orientation parameters(EOPs) as a function of line number of linear array scanner. To estimate priori EOPs, meta data of IKONOS scene and ground control points are used. We select a first order polynomial and a constant for position elements modeling and rotation elements modeling. Positioning accuracy of the determined EOPs is compared with that of RPCs bias-corrected by the least squares adjustment. There is almost no difference between accuracies of the two methods. To obtain digital elevation model(DEM), matching line is established by the EOPs. The DEM is compared with DEM generated by ERDAS IMAGINE software, which utilizes the bias-corrected RPCs. Height differences of DEMs by the two methods are ranged within a allowable standard deviation. The produced DEM, therefore, shows accuracy similar to the verified method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.24-34
• /
• 2007

Application systems that easy to access a information have been developed by IT growth and a human life variation. In this paper, we propose a application system to register a 3D footwear model using a monocular camera. In General, a human motion analysis research to body movement. However, this system research a new method to use a foot movement. This paper present a system process and show experiment results. For projection to 2D foot plane from 3D shoe model data, we construct processes that a foot tracking, a projection expression and pose estimation process. This system divide from a 2D image analysis and a 3D pose estimation. First, for a foot tracking, we propose a method that find fixing point by a foot characteristic, and propose a geometric expression to relate 2D coordinate and 3D coordinate to use a monocular camera without a camera calibration. We make a application system, and measure distance error. Then, we confirmed a registration very well.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.401-410
• /
• 2016

3D registration is a computer vision technique of aligning multi-view range images with respect to a reference coordinate system. Various 3D registration algorithms have been introduced in the past few decades. Iterative Closest Point (ICP) is one of the widely used 3D registration algorithms, where various modifications are available nowadays. In the ICP-based algorithms, the closest points are considered as the corresponding points. However, this assumption fails to find matching points accurately when the initial pose between point clouds is not sufficiently close. In this paper, we propose a new method to solve this problem using the 6D distance (3D color space and 3D Euclidean distances). Moreover, a color segmentation-based adaptive sampling technique is used to reduce the computational time and improve the registration accuracy. Several experiments are performed to evaluate the proposed method. Experimental results show that the proposed method yields better performance compared to the conventional methods.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.7
• /
• pp.104-115
• /
• 1999

This paper proposes an efficient method for 3D modeling of a human face from trinocular images by reconstructing face surface using range data. By using a trinocular camera system, we mitigated the tradeoff between the occlusion problem and the range resolution limitation which is the critical limitation in binocular camera system. We also propose an MPC_MBS (Matching Pixel Count Multiple Baseline Stereo) area-based matching method to reduce boundary overreach phenomenon and to improve both of accuracy and precision in matching. In this method, the computing time can be reduced significantly by removing the redundancies. In the model generation sub-pixel accurate surface data are achieved by 2D interpolation of disparity values, and are sampled to make regular triangular meshes. The data size of the triangular mesh model can be controlled by merging the vertices that lie on the same plane within user defined error threshold.