• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.687-696
• /
• 2014

This paper presents a semantic object extraction method using user's stroke input, color, and depth information. It is supposed that a semantically meaningful object is surrounded with a few strokes from a user, and has similar depths all over the object. In the proposed method, deciding the region of interest (ROI) is based on the stroke input, and the semantically meaningful object is extracted by using color and depth information. Specifically, the proposed method consists of two steps. The first step is over-segmentation inside the ROI using color and depth information. The second step is semantically meaningful object extraction where over-segmented regions are classified into the object region and the background region according to the depth of each region. In the over-segmentation step, we propose a new marker extraction method where there are two propositions, i.e. an adaptive thresholding scheme to maximize the number of the segmented regions and an adaptive weighting scheme for color and depth components in computation of the morphological gradients that is required in the marker extraction. In the semantically meaningful object extraction, we classify over-segmented regions into the object region and the background region in order of the boundary regions to the inner regions, the average depth of each region being compared to the average depth of all regions classified into the object region. In experimental results, we demonstrate that the proposed method yields reasonable object extraction results.

• The Journal of the Korea Contents Association
• /
• v.7 no.2
• /
• pp.40-50
• /
• 2007

In this paper, we propose an efficient method for detecting and tracking multiple moving objects based on morphological region merging from real-time video sequences. The proposed approach consists of adaptive threshold extraction, morphological region merging and detecting and tracking of objects. Firstly, input frame is separated into moving regions and static regions using the difference of images between two consecutive frames. Secondly, objects are segmented with a reference background image and adaptive threshold values, then, the segmentation result is refined by morphological region merge algorithm. Lastly, each object segmented in a previous step is assigned a consistent identification over time, based on its spatio-temporal information. The experimental results show that a proposed method is efficient and useful in terms of real-time multiple objects detecting and tracking.

• IMMUNE NETWORK
• /
• v.5 no.3
• /
• pp.137-143
• /
• 2005

Background: Millions of people in the world are suffering from atopic dermatitis (AD), which is a chronic inflammatory skin disease triggered by Th2 immune responses. The NC/Nga mouse is the most extensively studied animal model of AD. Like human AD, NC/Nga mice demonstrate increased levels of IgE, a hallmark of Th2 immune responses. Adaptive immunity cannot be generated without help of innate immunity. Especially natural killer T (NKT) cells and marginal zone B (MZB) cells have been known to play important roles in linking innate immunity to adaptive immunity. Methods: Through flow cytometric analysis and ELISA assay, we investigated whether these lymphocytes might be altered in number in NC/Nga mice. Results: Our data demonstrated that the number of NKT cells was reduced in NC/Nga mice and IFN${\gamma}$ production by NKT cells upon ${\alpha}-GalCer$ stimulation decreased to the levels of CD1d KO mice lacking in NKT cells. However, reduction of NKT cells in NC/Nga mice was not due to CD1d expression, which was normal in the thymus. Interestingly, there was a significant increase of $CD1d^{high}B220^+$ cells in the spleen of NC/Nga mice. Further, we confirmed that $CD1d^{high}B220^+$ cells are B cells, not dendritic cells. These $CD1d^{high}B220^+$ B cells show $IgM^{high}CD21^{high}CD23^{low}$, a characteristic phenotype of MZB cells. Conclusion: We provide the evidence that there are decreased activities of NKT cells and increased number of MZB cells in the NC/Nga mice. Our findings may thus explain why NC/Nga mice are susceptible to AD.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.61-71
• /
• 2004

Recently, various techniques for face detection are studied, but most of them still have problems on processing in real-time. Therefore, in this paper, we propose novel techniques for real-time detection of human faces in sequential images using motion and chroma information. First, background model is used to find a moving area. In this procmoving area. edure, intensity values for reference images are averaged, then skin-color are detected in We use HCr color-space model and adaptive threshold method for detection. Second, binary image labeling is applied to acquire candidate regions for faces. Candidates for mouth and eyes on a face are obtained using differences between green(G) and blue(B), intensity(I) and chroma-red(Cr) value. We also considered distances between eye points and mouth on a face. Experimental results show effectiveness of real-time detection for human faces in sequential images.

• Journal of Environmental Health Sciences
• /
• v.43 no.3
• /
• pp.240-246
• /
• 2017

Objectives: This study was conducted to evaluate the vulnerability of the human health sector to $PM_{10}$ due to climate change in Incheon over the period of 2005-2014. Methods: Vulnerability to $PM_{10}$ consists of the three categories of climate exposure, sensitivity, and adaptive capacity. The indexes for climate exposure and sensitivity indicate positive effects, while adaptive capacity shows a negative effect on vulnerability to $PM_{10}$. The variables in each category were standardized by the rescaling method, and respective relative regional vulnerability was analyzed through the vulnerability index calculation formula of the Intergovernmental Panel on Climate Change. Results: Regions with a high exposure index were the western and northern urban areas with industrial complexes adjacent to a highway, including Bupyong-gu and Seo-gu. Major factors determining the climate exposure index were the $PM_{10}$ concentration, days of $PM_{10}$ >= $100{\mu}g/m^3$, and $PM_{10}$ emissions. The regions showing a high sensitivity index were urban regions with high populations; these commonly had a high mortality rate for related diseases and vulnerable populations. Conclusions: This study is able to support regionally adjusted adaptation policies and the quantitative background of policy priority since it provides information on the regional health vulnerability to $PM_{10}$ due to climate change in Incheon.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.838-846
• /
• 2004

In the case where both a camera and a target are moving at the same time, the image background is successively changed, and the overlap with other moving objects is apt to be generated. The snake algorithms have been variously used in tracking the object, but it is difficult to be applied in the excessive overlap with other objects and the large bias between the snake and the target. To solve this problem, this paper presents an extended snake model. It includes an additional energy function which considers the temporal variation rate of the snake's area and a SSD algorithm which generates the template adaptive to the snake detected in the previous frame. The new energy function prevents the snake from over-shrinking or stretching and the SSD algorithm with adaptively changing template allows the prediction of the target's position in the next frame. The experimental results have shown that the proposed algorithm successfully tracks the target even when the target is temporarily occluded by other objects.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.4
• /
• pp.9-21
• /
• 2004

The current paper proposes a genetic algorithm (GA)-based segmentation method that can automatically extract and track moving objects. The proposed method mainly consists of spatial and temporal segmentation; the spatial segmentation divides each frame into regions with accurate boundaries, and the temporal segmentation divides each frame into background and foreground areas. The spatial segmentation is performed using chromosomes that evolve distributed genetic algorithms (DGAs). However, unlike standard DGAs, the chromosomes are initiated from the segmentation result of the previous frame, then only unstable chromosomes corresponding to actual moving object parts are evolved by mating operators. For the temporal segmentation, adaptive thresholding is performed based on the intensity difference between two consecutive frames. The spatial and temporal segmentation results are then combined for object extraction, and tracking is performed using the natural correspondence established by the proposed spatial segmentation method. The main advantages of the proposed method are twofold: First, proposed video segmentation method does not require any a priori information second, the proposed GA-based segmentation method enhances the search efficiency and incorporates a tracking algorithm within its own architecture. These advantages were confirmed by experiments where the proposed method was success fully applied to well-known and natural video sequences.

• Journal of Korea Multimedia Society
• /
• v.9 no.11
• /
• pp.1445-1454
• /
• 2006

To compress a specific part of an image with high quality or to transfer it, JPEG2000 standard offers an ROI(Region-of-Interest) image coding method. What is important in ROI coding is to process relative importance between ROI and background and to process ROI mask. We propose an adaptive ROI coding method supplemented the existing Implicit ROI coding and Modified implicit ROI coding to improve image quality and reduce ROI mask information. The proposed method is an EBCOT-based ROI coding that extracts ROI from the compressed bitstream, and gets the ROI mask information by classifying the codeblocks into 6 patterns. The information includes the pattern type(3bit) and the width(5bit) expressing the boundary between two regions for each codeblock. As a result, the method shows an excellent compression performance in ROI region as well as in the whole region of an image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.9C
• /
• pp.712-719
• /
• 2008

Temporal error concealment indicates the algorithm that restores the lost video data using temporal correlation between previous frame and current frame with lost data. It can be categorized into the methods of block-based and pixel-based concealment. The proposed method in this paper is for pixel-based temporal error concealment using affine transform. It outperforms especially when the object or background in lost block has geometric transform which can be modeled using affine transform, that is, rotation, magnification, reduction, etc. Furthermore, in order to maintain good performance even though one or more motion vector represents the motion of different objects, we defines a cost function. According to cost from the cost function, the proposed method adopts affine error concealment adaptively. Simulation results show that the proposed method yields better performance up to 1.9 dB than the method embedded in reference software of H.264/AVC.

• The Journal of the Korea Contents Association
• /
• v.11 no.3
• /
• pp.18-25
• /
• 2011

In a manufacturing process of metal coins, surface defects of coins are manually detected. This paper describes an new method for detecting surface defects of metal coins on a moving conveyor belt using image processing. This method consists of multiple procedures: segmentation of a coin from the background, alignment of the coin to the model, projection of the aligned coin to the best eigen image space, and detection of defects by comparison of the projection error with an adaptive threshold. In these procedures, the alignement and the projection are newly developed in this paper for the detection of coin surface defects. For alignment, we use the histogram of the segmented coin, which converts two-dimensional image alignment to one-dimensional alignment. The projection reduces the intensity variation of the coin image caused by illumination and coin rotation change. For projection, we build multiple eigen image spaces and choose the best eigen space using estimated coin direction. Since each eigen space consists of a small number of eigen image vectors, we can implement the projection in real- time.