• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.3
• /
• pp.1264-1286
• /
• 2018

In this paper, a novel background prior-based salient object detection framework is proposed to deal with images those are more complicated. We take the superpixels located in four borders into consideration and exploit a mechanism based on image boundary information to remove the foreground noises, which are used to form the background prior. Afterward, an initial foreground prior is obtained by selecting superpixels that are the most dissimilar to the background prior. To determine the regions of foreground and background based on the prior of them, a threshold is needed in this process. According to a fixed threshold, the remaining superpixels are iteratively assigned based on their proximity to the foreground or background prior. As the threshold changes, different foreground priors generate multiple different partitions that are assigned a likelihood of being foreground. Last, all segments are combined into a saliency map based on the idea of similarity voting. Experiments on five benchmark databases demonstrate the proposed method performs well when it compares with the state-of-the-art methods in terms of accuracy and robustness.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.5 s.311
• /
• pp.12-21
• /
• 2006

In this paper, we propose a technique for extracting attentive objects in images using feature maps, regardless of the complexity of images and the position of objects. The proposed method uses feature maps with edge and color information in order to extract attentive objects. We also propose a reference map which is created by integrating feature maps. In order to create a reference map, feature maps which represent visually attentive regions in images are constructed. Three feature maps including edge map, CbCr map and H map are utilized. These maps contain the information about boundary regions by the difference of intensity or colors. Then the combination map which represents the meaningful boundary is created by integrating the reference map and feature maps. Since the combination map simply represents the boundary of objects we extract the candidate object regions including meaningful boundaries from the combination map. In order to extract candidate object regions, we use the convex hull algorithm. By applying a segmentation algorithm to the area of candidate regions to separate object regions and background regions, real object regions are extracted from the candidate object regions. Experiment results show that the proposed method extracts the attentive regions and attentive objects efficiently, with 84.3% Precision rate and 81.3% recall rate.

• Spatial Information Research
• /
• v.23 no.4
• /
• pp.57-66
• /
• 2015

At these day, owing to functional limitations and cost issues, used image map in web service have a problem which can not make exactly meet the user needs. This study aims to create an individual map for user suitable purposes using HTML5 technology that implement the vector map creation and its functions with services. The results of this study, the invisible problems of the tilting and rotation functions in image-based map utilizing the existing web environment were solved in HTML5 vector map. And to access the map information, by implementing the function of expressing the background and name data to selectively derive, various results were expressed in the map. Also, as a result of a comparison of performance the time required was measured at 0.88sec which comes in the range of the first loading time between 0.78sec and 7.56sec in a commercial map service, which showed the possibility of its commercialization. compared to 180GB of image maps for the production of a national map index system, the volume to produce a vector map was 2.5GB, a decrease by over 90%, which solved the issue of costs for a storage space. As a result, this study of HTML5 vector map design and implementation presented a plan for providing information suitable for the requirements of the users who use spatial information through utilizing a variety of information and expanding functions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.5
• /
• pp.1155-1163
• /
• 2011

In this paper, we propose a new pre-processing algorithm applied to depth map to improve the coding efficiency. Now, 3DV/FTV group in the MPEG is working for standard of 3DVC(3D video coding), but compression method for depth map images are not confirmed yet. In the proposed algorithm, after dividing the histogram distribution of a given depth map by EM clustering method based on GMM, we classify the depth map into several layered images. Then, we apply different mean shift filter to each classified image according to the existence of background or foreground in it. In other words, we try to maximize the coding efficiency while keeping the boundary of each object and taking average operation toward inner field of the boundary. The experiments are performed with many test images and the results show that the proposed algorithm achieves bits reduction of 19% ~ 20% and computation time is also reduced.

• The Bulletin of The Korean Astronomical Society
• /
• v.43 no.1
• /
• pp.60.2-60.2
• /
• 2018

We present the near infrared JHK photometric properties and the spatial distribution of red supergiants(RSGs) of NGC 3623, NGC 3627 and NGC 3628 in the Leo Triplet system using the data obtained with 3.8m UKIRT(United Kingdom Infra-Red Telescope) at Hawaii. We checked interaction between the three galaxies by making a spatial density map of RSGs. From (J-K,K)0 Color-Magnitude Diagram which include resolved stars in three galaxy and control field with PARSEC isochrone, we figured out the RSG candidates of the Leo triplet are at 0.9<(J-K)0<1.2, mK<17.5 and separated them from background and foreground sources. Using gaussian kernel density estimation, we drew spatial density map of RSGs in the Leo triplet with an assumption that all RSGs are an identical population. The density map shows extended features of NGC 3628 to NGC 3627 along the declination direction. The asymmetries between NGC 3627 and NGC 3628 might be evidence for that the distribution of actual star components(RSGs) follows the neutral hydrogen distribution and also for interaction between two galaxies. And the extended features along the right ascension direction might be a supporting evidence for the existence of a TDG(Tidal Dwarf Galaxy). In case of NGC 3623, we could not see any sign of interaction in density map.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.5
• /
• pp.327-330
• /
• 2016

Currently, the world's elderly population continues to grow at a dramatic rate. As the number of senior citizens increases, detection of someone falling has attracted increasing attention for visual surveillance systems. This paper presents a novel fall-detection algorithm using motion estimation and an integrated spatiotemporal energy map of the object region. The proposed method first extracts a human region using a background subtraction method. Next, we applied an optical flow algorithm to estimate motion vectors, and an energy map is generated by accumulating the detected human region for a certain period of time. We can then detect a fall using k-nearest neighbor (kNN) classification with the previously estimated motion information and energy map. The experimental results show that the proposed algorithm can effectively detect someone falling in any direction, including at an angle parallel to the camera's optical axis.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.339-348
• /
• 1997

In this paper, we propose a coding method to improve compression efficiency for MR image. This can be achieved by combining coding scheme and segmentation scheme which removes noisy background region, which is meaningless for diagnosis in the MR image. In segmentation algoritm, we use full-resolution wavelet transform to extract features of regions in image and Kohonen self-organizing map to classify the features. The subsequent wavelet coder encodes only diagnostically significant foreground regions refering to segmentation map. Our proposed algorithm provides about 15% of bit rate reduction when compared with the same coder which is not combined with segmentation scheme. And the proposed scheme shows better reconstructed image quality than JPEG at the same compression ratio.

• Journal of the Korean Geographical Society
• /
• v.41 no.4 s.115
• /
• pp.375-390
• /
• 2006

The Carte do Cassini is the first accurate topographic map of an entire country and it influenced enormously in the development of cartography in other countries. The purpose of this paper is to examine the production process and characteristics of the Carte do Cassini, and to and the place of 'Carte de Cassini' in the development of cartography. For this, firstly, the background of French national topographic mapping is examined and scientific work of the Cassini family is resumed. Second, the map production process is considered; location and attribute data collection, copperplate printing, social and economic difficulties. Third, map characteristics such as map projection, sheet numbering system, positional accuracy, legend, typographies, and depiction of cartographic signs are explored. Finally, the influence of the Carte de Cassini on cartographic development and its historical meaning is discussed.

• Journal of the Korean association of regional geographers
• /
• v.9 no.2
• /
• pp.217-231
• /
• 2003

The purpose of this study is to examine the characteristics of advertizing maps which were presented in one of the major daily newspapers(JoongAng Ilbo) from 1966 to 2000. The use of advertizing maps has been gradually increased year by year. Advertizing maps have appeared much frequently in spring and fall seasons, in October, and on Saturday and Wednesday. The predominance of such seasons, month, days is related to the real estate advertizement. The important categories which have been presented frequently are real estate for sale(62%), clothing sale(7%) and the image advertizement of big corporations(3%). Locator maps are preferred in the first two categories and background maps are usually used in the corporation advertizement. The symbols in the maps are different according to the custom, interest and the preference of map-producers and clients. The basic symbols for the good map, which are required in the general cartography, are scarcely shown in the advertizing maps. That is because the goal of advertizement is to appeal visually to consumers, therefore, the creativity of map-producer and the attraction of maps to draw the reader's interest are much required in the advertizing maps. It is concluded that the advertizing maps have their own values in themselves and we have to treat the journalistic cartography as a special field in cartography.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.1
• /
• pp.34.1-34.1
• /
• 2013

The first generation stars in the universe are not observed as discrete objects by using current observational facilities, but their contributions are redshifted to the near infrared wavelength bands at present universe. Therefore, investigation of background radiation at near infrared is important for the study of the first stars. In this study, we present new observations of spatial fluctuations in sky brightness toward the north ecliptic pole using data from AKARI. Among pointed observation program of AKARI, we used two pointing surveys named Monitor field and NEP wide field at three wavelength bands 2.4, 3.2, and 4.1 ${\mu}m$. To obtain spatial fluctuations from observed images, first of all, we exclude pixels affected by resolved foreground objects and then obtain diffuse map which consists of diffused radiation only. Because the diffuse map contains not only cosmological components but also various foreground components, in order to detect cosmological components, we estimate the contributions of foreground components separately. The results of this study show that there remains excess spatial fluctuation that cannot be explained by known foreground sources. This work is based on observations with AKARI, a JAXA project with the participation of ESA.