• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.56-68
• /
• 2022

In this paper, we propose a compression method for multi-resolution feature maps for VCM. The proposed compression method removes the redundancy between the channels and resolution levels of the multi-resolution feature map through PCA-based transformation. According to each characteristic, the basis vectors and mean vector used for transformation, and the transformation coefficient obtained through the transformation are compressed using a VVC-based coder and DeepCABAC. In order to evaluate performance of the proposed method, the object detection performance was measured for the OpenImageV6 and COCO 2017 validation set, and the BD-rate of MPEG-VCM anchor and feature map compression anchor proposed in this paper was compared using bpp and mAP. As a result of the experiment, the proposed method shows a 25.71% BD-rate performance improvement compared to feature map compression anchor in OpenImageV6. Furthermore, for large objects of the COCO 2017 validation set, the BD-rate performance is improved by up to 43.72% compared to the MPEG-VCM anchor.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1257-1271
• /
• 2022

Recently, many Earth observation optical satellites have been developed, as their demands were increasing. Therefore, a rapid preprocessing of satellites became one of the most important problem for an active utilization of satellite images. Satellite image matching is a technique in which two images are transformed and represented in one specific coordinate system. This technique is used for aligning different bands or correcting of relative positions error between two satellite images. In this paper, we propose an automatic image matching method among satellite images with different ground sampling distances (GSDs). Our method is based on improved feature matching and robust estimation of transformation between satellite images. The proposed method consists of five processes: calculation of overlapping area, improved feature detection, feature matching, robust estimation of transformation, and image resampling. For feature detection, we extract overlapping areas and resample them to equalize their GSDs. For feature matching, we used Oriented FAST and rotated BRIEF (ORB) to improve matching performance. We performed image registration experiments with images KOMPSAT-3A and RapidEye. The performance verification of the proposed method was checked in qualitative and quantitative methods. The reprojection errors of image matching were in the range of 1.277 to 1.608 pixels accuracy with respect to the GSD of RapidEye images. Finally, we confirmed the possibility of satellite image matching with heterogeneous GSDs through the proposed method.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.27 no.3
• /
• pp.59-65
• /
• 2004

This paper explores an image segmentation and representation method using Vector Quantization(VQ) on color and texture for content-based image retrieval system. The basic idea is a transformation from the raw pixel data to a small set of image regions which are coherent in color and texture space. These schemes are used for object-based image retrieval. Features for image retrieval are three color features from HSV color model and five texture features from Gray-level co-occurrence matrices. Once the feature extraction scheme is performed in the image, 8-dimensional feature vectors represent each pixel in the image. VQ algorithm is used to cluster each pixel data into groups. A representative feature table based on the dominant groups is obtained and used to retrieve similar images according to object within the image. The proposed method can retrieve similar images even in the case that the objects are translated, scaled, and rotated.

• Journal of the Korean Institute of Navigation
• /
• v.13 no.1
• /
• pp.11-20
• /
• 1989

Radar image data were collected through the on-line data acquisition system of A/D converter and personal computer, and the image was restorated on CRT or plotter after digital image processing of the data. The digital image processing system which was developed for this study, consisted of some kinds of software as follows : rearrangement, transformation, and enhancement of the image data in real space or frequency space by Fourier transform, edge detection of the image, compact processing, state inferential processing, and so on. Since the image of PPI radar sweeps from the center to the circumference of a circle, the image within a given period has the shape of fan. Therefore the acquired data were transformed to have the same interval as that of data in outmost concentricity. The results of various image processing methods using transformed data were better than those of the methods using original data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.1
• /
• pp.667-675
• /
• 2009

Image matching is widely applied in image application areas, such as remote sensing and GIS. In general, the initial set of matching points always includes outlier which affect the accuracy of image matching. The purpose of this paper is to develop a robust approach for outlier detection and removal in order to keep accuracy in image matching applications. In this paper we use three automatic outlier detection techniques of backward matching and affine transformation, and RANSAC(RANdom SAmple Consensus) algorithm. Moreover, we calculate overlapping apply and steps block-based processing for fast and efficient image matching in pre-processing steps. The suggested approach in this paper has been applied to real frame image pairs and the results have been analyzed in terms of the robustness and the efficiency.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.84-91
• /
• 2004

A CCD camera with a laser stripe was applied to realize the automatic weld seam tracking in GMAW. It takes relatively long time to process image on-line control using the basic Hough transformation, but it has a tendency of robustness over the noises such as spatter and arc tight. For this reason, it was complemented with adaptive Hough transformation to have an on-line processing ability for scanning specific weld points. The adaptive Hough transformation was used to extract laser stripes and to obtain specific weld points. The 3-dimensional information obtained from the vision system made it possible to generate the weld torch path and to obtain the information such as width and depth of weld line. In this study, a neural network based on the generalized delta rule algorithm was adapted for the process control of GMA, such as welding speed, arc voltage and wire feeding speed.

• Journal of Welding and Joining
• /
• v.19 no.6
• /
• pp.600-607
• /
• 2001

A CCD camera with a laser stripe was applied to realize the automatic weld seam tracking in GMAW. It takes relatively long time to process image on-line control using the basic Hough transformation, but it has a tendency of robustness over the noises such as spatter and arc light. For this reason. it was complemented with adaptive Hough transformation to have an on-line processing ability for scanning specific weld points. The adaptive Hough transformation was used to extract laser stripes and to obtain specific weld points. The 3-dimensional information obtained from the vision system made it possible to generate the weld torch path and to obtain the information such as width and depth of weld line. We controled the wire feeding rate using informations of weld line.

• Bulletin of the Korean Mathematical Society
• /
• v.56 no.3
• /
• pp.681-689
• /
• 2019

The $M{\ddot{o}}bius$ homogeneous submanifold in ${\mathbb{S}}^{n+1}$ is an orbit of a subgroup of the $M{\ddot{o}}bius$ transformation group of ${\mathbb{S}}^{n+1}$. In this note, We prove that a compact $M{\ddot{o}}bius$ homogeneous submanifold in ${\mathbb{S}}^{n+1}$ is the image of a $M{\ddot{o}}bius$ transformation of the isometric homogeneous submanifold in ${\mathbb{S}}^{n+1}$.

• Journal of the Korean Institute of Rural Architecture
• /
• v.14 no.1
• /
• pp.99-106
• /
• 2012

Transformation which is the major damage factor of living space in folk village is caused by improvement behaviors reflecting real requirements of residents who are the subjects of life. Such a process changes traditional space structure gradually and lowers preservative value of folk village. Therefore this study examines transformational conditions of living space centering around changes of spatial components and plane forms through literature and field research and analyzes characteristics of transformational phenomenon. This study examined changes of components and transformation of Seongeup folk village. While main room plane was diversified by residents' requirements, it was not harmonized with traditional image of Seongeup folk village. Transformation of living space at Seongeup Folk Village was positive from the side of residents' living requirements, but negative in that it damaged unique identity of folk village. Accordingly, it is thought that deliberation considering residents' living requirements as the field of their life with maintenance of original form for the purpose of preserving folk village and professionals' support and legal study for revision of approval system are continuously required.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.358-360
• /
• 2004

The digital images contain a significant amount of redundancy and require a large amount of data for their storage and transmission. Therefore, the image compression is necessary to treat digital images efficiently. The goal of image compression is to reduce the number of bits required for their representation. The image compression can reduce the size of image data using contractive mapping of original image. Among the compression methods, the mapping is affine transformation to find the block(called range block) which is the most similar to the original image. In this paper, we applied the neural network(SOM) in encoding. In order to improve the performance of image compression, we intend to reduce the similarities and unnecesaries comparing with the originals in the codebook. In standard image coding, the affine transform is performed with eight isometries that used to approximate domain blocks to range blocks.