• The Journal of Korea Robotics Society
• /
• v.13 no.4
• /
• pp.237-247
• /
• 2018

In this paper, we describe a sensor module that monitors fire environment by analyzing fire characteristics. We analyzed the smoke characteristics of indoor fire. Six different environments were defined according to the type of smoke and the flame, and the sensors available for each environment were combined. Based on this analysis, the sensors were selected from the perspective of firefighter. The sensor module consists of an RGB camera, an infrared camera and a radar. It is designed with minimum weight to fit on the robot. the enclosure of sensor is designed to protect against the radiant heat of the fire scene. We propose a single camera mode, thermal stereo mode, data fusion mode, and radar mode that can be used depending on the fire scene. Thermal stereo was effectively refined using an image segmentation algorithm, SLIC (Simple Linear Iterative Clustering). In order to reproduce the fire scene, three fire test environments were built and each sensor was verified.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.1294-1297
• /
• 2011

최근, Flickr, YouTube 와 같은 사용자 참여형 미디어 공유 및 검색 사이트가 폭발적으로 증가하면서, 이를 멀티미디어 정보 검색 서비스에 효과적으로 활용하기 위한 다양한 연구들이 시도되고 있다. 특히, 이미지에 할당되어 있는 태그를 이용하여 이미지를 효과적으로 검색하기 위한 연구가 활발히 진행 중이다. 그러나 사용자들에 의해 제공되는 소셜 이미지들은 매우 다양한 범위와 주제를 가지고 있기 때문에, 소셜 이미지들의 분류 및 태그 할당을 위한 트레이닝 집합의 획득이 쉽지 않다는 한계점을 가지고 있다. 본 논문에서는 데이터 군집화를 위한 클러스터링 알고리즘들 중 K-Means, K-Medoids, Affinity Propagation 을 활용하여 소셜 이미지 집합으로부터 트레이닝 집합을 획득하기 위한 방법들을 살펴 본다. 또한, 각 알고리즘으로부터 획득한 트레이닝 집합을 이용하여 소셜 이미지를 분류한 결과를 비교 분석한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.97-100
• /
• 2021

Light field (LF) superpixel segmentation aims to group the similar pixels not only in the single image but also in the other views to improve the computational efficiency of further applications like object detection and pattern recognition. Among the state-of-the-art methods, there is an approach to segment the LF images while enforcing the view consistency. However, it leaves too much noise and inaccuracy in the shape of superpixels. In this paper, we modify the process of the clustering step. Experimental results demonstrate that our proposed method outperforms the existing method in terms of view-consistency.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.55-57
• /
• 2020

실감미디어의 수요가 높아짐에 따라, 실감 미디어 컨텐츠 제작에 반드시 필요한 깊이영상에 대한 중요성이 커지고 있다. 다시점 영상으로부터 계산된 깊이 영상은 물체 주위와 배경 영역에 홀을 가지고 있다. 이러한 깊이영상에서의 홀을 채울 때, 이에 대응하는 컬러영상의 색상 특성을 고려하는 방법을 제안한다. 본 논문에서는 컬러 영상의 화소들을 색상 유사성을 이용하여 클래스로 분류하고, 홀의 깊이정보를 예측할 때 같은 클래스의 유효한 깊이값 만을 사용하는 방법을 소개한다. 제안하는 방법을 사용하면 깊이영상의 홀을 효율적으로 채워 넣을 수 있다. 실감미디어 제작에 있어 제안하는 방법을 사용한다면, 사실감 있는 깊이 정보를 얻을 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.135-138
• /
• 2008

본 논문은 의료 영상에 대한 효과적인 분류와 검색을 위한 알고리즘을 제안한다. 영상 분류와 검색을 위해서 MPEG-7 표준 기술자인 색 구조 기술자와 경계선 히스토그램 기술자를 사용해 영상들에 대한 특징 값을 추출한다. 이렇게 구해진 특징 값들을 의료 영상의 분류와 검색에 적용해 본 결과 비교적 낮은 성능을 보여줌을 확인하고 앞서 구해진 특징 값들을 교사 학습 방법인 SVM(Support Vector Machine)과 비교사 학습 방법인 FCM(Fuzzy C-means Clustering)에 적용시켰다. 기존 연구에서는 SVM과 FCM의 통합으로 의료 영상에 대한 분류와 검색을 시행하였지만 본 논문에서 실험한 결과 SVM과 MPEG-7 시각 기술자 중에 하나인 EHD(Edge Histogram Descriptor)를 가중치 선형 결합하여 실험한 결과가 더 정확한 분류와 높은 검색 성능을 나타냄을 확인하였다.

• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.713-723
• /
• 2017

Since the panoramic image can overcome the limitation of the viewing angle of the camera and have a wide field of view, it has been studied effectively in the fields of computer vision and stereo camera. In order to generate a panoramic image, stitching images taken by a plurality of general cameras instead of using a wide-angle camera, which is distorted, is widely used because it can reduce image distortion. The image stitching technique creates descriptors of feature points extracted from multiple images, compares the similarities of feature points, and links them together into one image. Each feature point has several hundreds of dimensions of information, and data processing time increases as more images are stitched. In particular, when a panorama is generated on the basis of an image photographed by a plurality of unspecified cameras with respect to an object, the extraction processing time of the overlapping feature points for similar images becomes longer. In this paper, we propose a preprocessing process to efficiently process stitching based on an image obtained from a number of unspecified cameras for one object or environment. In this way, the data processing time can be reduced by pre-grouping images based on camera sensor information and reducing the number of images to be stitched at one time. Later, stitching is done hierarchically to create one large panorama. Through the grouping preprocessing proposed in this paper, we confirmed that the stitching time for a large number of images is greatly reduced by experimental results.

• Journal of Korean Clinical Nursing Research
• /
• v.22 no.2
• /
• pp.173-182
• /
• 2016

Purpose: This study investigated the linking words of nurse which were presented together with nurse on phrase, clauses or sentence of documents or conversations in the Internet portals and social media. Methods: The linking words with nurse were calculated by the number of presentation on conversations or documents, in Google, Daum, Naver, Twitter and Facebook. The changes of characteristics and the trend of yearly changes of major linking words of nurse were investigated by the type of media. In order to identify the meaning of the words, clustering of the collected linking words by categories was analysed and the characteristics of each cluster were classified. Results: A total number of reviewed linking words was 17,399,711 and the most frequently presenting words were hospital, work and person. The words related to people were the most highly presented and the next were those of emotion, professional and place respectively. Conclusion: With analysing the trends of changes and characteristics of words by yearly base and clusters, we attempted to investigate the image of nurse that the public think and feel about nurse.

• Journal of Broadcast Engineering
• /
• v.22 no.5
• /
• pp.643-651
• /
• 2017

Steganography is one of information hiding technologies and discriminated from cryptography in that it focuses on avoiding the existence the hidden information from being detected by third parties, rather than protecting it from being decoded. In this paper, as an image steganography method which uses images as media, we propose a new block matching method that embeds information into the discrete wavelet transform (DWT) domain. The proposed method, based on a statistical analysis, reduces loss of embedding capacity due to inequable use of candidate blocks. It works in such a way that computes the variance of each candidate block, preserves candidate blocks with high frequency components while reducing candidate blocks with low frequency components by compressing them exploiting the k-means clustering algorithm. Compared with the previous block matching method, the proposed method can reconstruct secret images with similar PSNRs while embedding higher-capacity information.

• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.15-27
• /
• 2006

In this paper, a novel approach is addressed to facilitate the browsing of large collection of digital photos associated with specified person(s) in the photos. The goal of the proposed method is to exploit additional person-identity features as incorporating facial regions and peripheral clothes region associated with them. For more effective incorporation of the clothes and facial features, situation-based photo clustering is also proposed. To evaluate the efficacy of the proposed method experiment was performed with 1120 generic home photos. The experiment results showed that the proposed method outperformed the conventional method us El.g only face feature as showing the average performance of about 92% contrary to the average performance of about 70% in the conventional method.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.21-26
• /
• 2004

Color image quantization is a process of selecting a set of colors to display an image with some representative colors without noticeable perceived difference. It is very important in many applications to display a true color image in a low cost color monitor or printer. The basic problem is how to display 256 colors or less colors, called color palette, In this paper, we propose improved binary tree vector quantization based on spatial sensitivity which is one of the human visual properties. We combine the weights based on the responsibility of human visual system according to changes of three Primary colors in blocks of images with the process of splitting nodes using eigenvector in binary tree vector quantization. The test results show that the proposed method generates the quantized images with fine color and performs better than the conventional method in terms of clustering the similar regions. Also the proposed method can get the better result in subjective quality test and WSNR.