• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.533-540
• /
• 2021

High-resolution satellite images have high potential to acquire geospatial information over inaccessible areas such as Antarctica. Reference data are often required to increase the positional accuracy of the satellite data but the data are not available in many inland areas in Antarctica. Therefore this paper presents a multi-image RPCs (Rational Polynomial Coefficients) sensor modeling without any ground controls or reference data. Conjugate points between multi-images are extracted and used for the multi-image sensor modeling. The experiment was carried out for Kompsat-3A and showed that the significant accuracy increase was not observed but the approach has potential to suppress the maximum errors, especially the vertical errors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.543-548
• /
• 2021

The higher the resolution of the image, the higher the satisfaction of the viewers of the image, and the super-resolution imaging has a considerable increase in research value among the fields of computer vision and image processing. In this study, the main features of low-resolution image LR are extracted mainly using deep learning super-resolution models. It learns and reconstructs the extracted features, and focuses on reconstruction-based algorithms that generate high-resolution image HR. In this paper, we investigate SRCNN and VDSR in a super-resolution algorithm model based on reconstruction. The structure and algorithm process of the SRCNN and VDSR model are briefly introduced, and the multi-channel and special form are also examined in the improved performance evaluation function, and understand the performance of each algorithm through experiments. In the experiment, an experiment was performed to compare the results of the SRCNN and VDSR models with the peak signal-to-noise ratio and image structure similarity, so that the results can be easily judged.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.9
• /
• pp.943-949
• /
• 2009

Many studies for measuring vibration using image signal are suggested. These methods can measure vibration of multi-points simultaneously. However, it has the disadvantage that is very sensitive to an environment. If the measured environment is not good, image signals can be measured including much background noise. So, it is difficult to obtain accurate vibration from the measured image signals. Another problem is that camera imaging has a resolution limit. Because the resolution of the camera image is relatively much lower than that of a data acquisition system, accurate measuring vibration cannot be performed. In this paper, we proposed the enhanced technique for measuring vibration using camera signal. The key word of this paper is a curve fitting. The curve fitting can exactly detect the measurement line of interested object. So, we can measure the vibration in noisy environment. Also, it can overcome the resolution limit.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1099-1101
• /
• 2003

Change detection technology, which discovers the change information on the surface of the earth by comparing and analyzing multi-temporal satellite images, can be usefully applied to the various fields, such as environmental inspection, urban planning, forest policy, updating of geographical information and the military usage. In this paper, we introduce a change detection system that can extract and analyze change elements from high-resolution satellite imagery as well as low- or middle-resolution satellite imagery. The developed system provides not only 7 pixelbased methods that can be used to detect change from low- or middle-resolution satellite images but also a float window concept that can be used in manual change detection from highresolution satellite images. This system enables fast access to the very large image, because it is constituted by OGC grid coverage components. Also new change detection algorithms can be easily added into this system if once they are made into grid coverage components.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.814-821
• /
• 2011

The purpose of this study was to evaluate of resolution parameter and reconstitution filter in the 256 multi detector computed tomography(MDCT) by using the head phantom. We used 256 MDCT, and head phantom of philips system. We evaluated to image quality by using Extended Brilliance Workspace. The protocol were axial scan method with 120 kVp, 0.5 sec of rotation time, 5 mm of slice thickness and increment, 250 mm of field of view(FOV), $512{\times}512$ of matrix size, 1.0 of pitch, $128{\times}0.625$ mm of collimations. The resolution parameter was applied for 'Standard', 'High' and 'Ultrahigh'. The reconstitution filters were changed to seven type of 'A', 'B', 'C', 'D', 'UA', 'UB', 'UC'. The assesment factors of image quality were the uniformity, the noise, the linearity and 50% and 10% of the modulation transfer function(MTF). Finally The good image quality in 'High' resolution parameter showed at the uniformity, the linearity and 50% and 10% of MTF. The 'UA', 'UB' reconstitution filter showed at the good image quality of the uniformity and the noise and 'C' reconstitution filter showed at the same result of the linearity and 50% and 10% of MTF.

• International Journal of Internet, Broadcasting and Communication
• /
• v.7 no.1
• /
• pp.15-19
• /
• 2015

The depth information of an image is used in a variety of applications including 2D/3D conversion, multi-view extraction, modeling, depth keying, etc. There are various methods to acquire depth information, such as the method to use a stereo camera, the method to use the depth camera of flight time (TOF) method, the method to use 3D modeling software, the method to use 3D scanner and the method to use a structured light just like Microsoft's Kinect. In particular, the depth camera of TOF method measures the distance using infrared light, whereas TOF sensor depends on the sensitivity of optical light of an image sensor (CCD/CMOS). Thus, it is mandatory for the existing image sensors to get an infrared light image by bundling several pixels; these requirements generate a phenomenon to reduce the resolution of an image. This thesis proposed a measure to acquire a high-resolution image through gradual area movement while acquiring a low-resolution image through pixel bundling method. From this measure, one can obtain an effect of acquiring image information in which illumination intensity (lux) and resolution were improved without increasing the performance of an image sensor since the image resolution is not improved as resolving a low-illumination intensity (lux) in accordance with the gradual pixel bundling algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.10
• /
• pp.2943-2965
• /
• 2024

This paper proposes a fully computer assisted automated cervical cancer detection method using cervical images. This proposed system consist of six modules as Edge detector, image fusion, Gabor transform, feature computation, classification algorithm and segmentation method. The edge pixels show the contrast edge variations of each pixel in cervical image with respect to its corresponding nearby pixels. Hence, these edge pixels are detected using fuzzy logic and then the edge detected cervical images are fused using arithmetic pixel fusion algorithm. This fused cervical image having the pixels in the form of spatial resolution and hence it is need to be converted into multi-format resolution for computing the features from it. The spatial pixels in fused image are converted into multi orientation pixels using Gabor transform and then features are computed from this Gabor image. In this work, Local Binary Pattern (LBP), Grey Level Co-occurrence Matrix (GLCM) and Pixel Intensity Features (PIF) are computed from the Gabor cervical image. These features have been classified by the Cervical Features Incorporated Convolutional Neural Networks (CFICNN) classification algorithm. The modified version of the Visual Geometry Group- Convolutional Neural Networks (VGG-CNN) architecture is called as Cervical Features Incorporated CNN (CFICNN) and it is proposed in this paper for both training and classification process. Finally, the cancer pixels are segmented using morphological operations based segmentation algorithm. The Guanacaste Dataset (GD) and Kaggle Dataset (KD) are used for estimating performance efficiency.

• Journal of Broadcast Engineering
• /
• v.2 no.2
• /
• pp.216-224
• /
• 1997

In this paper, we propose a depth information extraction method for intermediate image synthesis. As stereo matching method, MBS(Multiple-Baseline Stereo) method has been proposed, in which the matching accuracy increases by using the multiple camera, but there are some inherent problems such as computational complexity, boundary overreach(BO) in depth map, and occlusion. So, we propose the modified version of MBS so called Multi-Resolution MBS(MR-MBS). Moreover, we also propose an adaptive occlusion area processing technique to improve the accuracy of the depth information in occlusion area.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.1
• /
• pp.363-371
• /
• 2014

In this paper, a new super-resolution algorithm is proposed by using successive frames for generating high-resolution frames with better quality than those generated by other conventional interpolation methods. Generally, each frame used for super-resolution must only have global translation and motions of sub-pixel unit to generate good result. However, the newly proposed MSR algorithm in this paper is exempt from such constraints. The proposed algorithm consists of three main processes; motion estimation for image registration, normalization of motion vectors, and pattern analysis of edges. The experimental results show that the proposed algorithm has better performance than other conventional algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.