• 로봇학회논문지
• /
• 제13권4호
• /
• 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.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.336-337
• /
• 2021

본 논문에서는 웹상에서 실시간 사용자 인터페이스를 통해 비디오 컨텐츠 검색과 비디오 브라우징을 모두 제공하는 비디오 브라우징 서비스를 제안한다. 영상 시퀀스의 장면 분할 및 키 프레임 추출을 위해 RGB 컬러 히스토그램과 𝛘² 히스토그램을 결합한 효율적인 장면 변경 감지 방법을 제안한다.

• Journal of Computing Science and Engineering
• /
• 제5권3호
• /
• pp.161-166
• /
• 2011

We present a fast algorithm for Korean text extraction and segmentation from subway signboards using smart phone sensors in order to minimize computational time and memory usage. The algorithm can be used as preprocessing steps for optical character recognition (OCR): binarization, text location, and segmentation. An image of a signboard captured by smart phone camera while holding smart phone by an arbitrary angle is rotated by the detected angle, as if the image was taken by holding a smart phone horizontally. Binarization is only performed once on the subset of connected components instead of the whole image area, resulting in a large reduction in computational time. Text location is guided by user's marker-line placed over the region of interest in binarized image via smart phone touch screen. Then, text segmentation utilizes the data of connected components received in the binarization step, and cuts the string into individual images for designated characters. The resulting data could be used as OCR input, hence solving the most difficult part of OCR on text area included in natural scene images. The experimental results showed that the binarization algorithm of our method is 3.5 and 3.7 times faster than Niblack and Sauvola adaptive-thresholding algorithms, respectively. In addition, our method achieved better quality than other methods.

• 스마트미디어저널
• /
• 제2권2호
• /
• pp.14-19
• /
• 2013

Recently, due to the increase of the use of scanned images, the text segmentation techniques, which play critical role to optimize the quality of the scanned images, are required to be updated and advanced. In this study, an algorithm has been developed based on the modification of Gaussian mixture model (GMM) by integrating the calculation of Gaussian detection gradient and the estimation of the number clusters. The experimental results show an efficient method for text segmentation in natural scenes such as storefronts, street signs, scanned journals and newspapers at different size, shape or color of texts in condition of lighting changes and complex background. These indicate that our model algorithm and research approach can address various issues, which are still limitations of other senior algorithms and methods.

• 로봇학회논문지
• /
• 제12권3호
• /
• pp.249-257
• /
• 2017

This paper proposes a method to segment urban scenes semantically based on location prior information. Since major scene elements in urban environments such as roads, buildings, and vehicles are often located at specific locations, using the location prior information of these elements can improve the segmentation performance. The location priors are defined in special 2D coordinates, referred to as road-normal coordinates, which are perpendicular to the orientation of the road. With the help of depth information to each element, all the possible pixels in the image are projected into these coordinates and the learned prior information is applied to those pixels. The proposed location prior can be modeled by defining a unary potential of a conditional random field (CRF) as a sum of two sub-potentials: an appearance feature-based potential and a location potential. The proposed method was validated using publicly available KITTI dataset, which has urban images and corresponding 3D depth measurements.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.171-176
• /
• 1999

Intelligent schemes for an automatic generation of DEM (digital elevation model) are implemented. The need for these post-processing schemes is that interpolation alone produces severe blunders, however sophisticated it is. These blunders occur most seriously along the boundaries of a scene, over rivers, and along the coast. Even a state-of-the-art commercial software retains such blunders. The intelligent schemes implemented are (1) center-of-gravity and empty-center-index which quantify how evenly distributed interpolants are within in interpolation radius. (2) a segmentation scheme to discern whether or not an empty segment in stereo-match results should be interpolated, and (3) a segmentation scheme for removing noise-like features, with these methods, in the final DEM, identical coastline and river region to those in the original SPOT scenes are achieved. The DEM exhibits substantial improvements over the products of an existing commercial software.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.781-784
• /
• 1998

An image segmentation approach based on the fuzzy worm searching and MIN-MAx clusterng algorithm is proposed in this paper. This algorithm deals with fuzzy worm value and min-max node at a gross scene level, which investigates the edge information including fuzzy worm action. But current segmentation methods based edge extraction methods generally need the mask information for the algebraic model, and take long run times at mask operation, wheras the proposed algorithm has single operation ccording to active searching of fuzzy worms. In addition, we also genetic min-max clustering using genetic algorithm to complete clustering and fuzyz searching on grey-histogram of image for the optimum solution, which can automatically determine the size of rnages and has both strong robust and speedy calculation. The simulation results showed that the proposed algorithm adaptively divided the quantized images in histogram region and performed single searching methods, significantly alleviating the increase of the computational load and the memory requirements.

• 한국멀티미디어학회논문지
• /
• 제17권4호
• /
• pp.420-432
• /
• 2014

In detection of moving objects from video sequences, an essential process for intelligent visual surveillance, the cast shadows accompanying moving objects are different from background so that they may be easily extracted as foreground object blobs, which causes errors in localization, segmentation, tracking and classification of objects. Most of the previous research results about moving cast shadow detection and removal usually utilize color information about objects and scenes. In this paper, we proposes a novel cast shadow removal method of moving objects in gray level video data for visual surveillance application. The proposed method utilizes observations about edge patterns in the shadow region in the current frame and the corresponding region in the background scene, and applies Laplacian edge detector to the blob regions in the current frame and the corresponding regions in the background scene. Then, the product of the outcomes of application determines moving object blob pixels from the blob pixels in the foreground mask. The minimal rectangle regions containing all blob pixles classified as moving object pixels are extracted. The proposed method is simple but turns out practically very effective for Adative Gaussian Mixture Model-based object detection of intelligent visual surveillance applications, which is verified through experiments.

• 한국통신학회논문지
• /
• 제27권4A호
• /
• pp.356-363
• /
• 2002

컷 검출은 내용기반 검색에 필요한 인덱싱을 위해 수행되어야 하는 기초 작업으로 이를 위한 매우 다양한 기법들이 제안된바 있다. 그러나 기존의 연구에서는 대부분 고정된 하나의 임계값을 사용하기 때문에 통영상의 종류나 내용에 따라 최적의 임계값을 정해야만 하는 문제점을 갖는다. 본 논문에서는 컷 검출 간격의 확률적인 분포에 따라 임계값을 조절하며 컷이 발생하면 이전 컷과의 간격과 특징값 차이를 다음 컷 검출을 위한 임계값 설정에 반영하는 가변형 동적 임계값 방법을 제안한다. 이를 위해 임계값 조절에 필요한 인자 값들을 실행시간에 구하는 방법과 이를 사용한 컷 검출 알고리즘을 제시한다. 또한 실험을 통해 제안하는 방법이 기존의 방법에 비해 오 검출율을 줄일 수 있어 효율적임을 보인다.

• 방송공학회논문지
• /
• 제11권1호
• /
• pp.28-41
• /
• 2006

양방향 맞춤형 방송의 실현으로 인해 비디오의 내용을 자동으로 분석하여 그 구조를 기술하거나 요약을 생성하는 등의 내용 기반 비디오 분석 기술의 필요성이 요구되고 있다. 본 논문에서는 온라인에서 수요가 높고 특히 맞춤형 방송에 적합한 방송 콘텐츠인 교육용 비디오의 ToC를 자동으로 생성하기 위한 방법을 제안한다. 제안한 ToC 생성 방법은 씬 분할과 씬 서술의 두 단계로 이루어져 있다. 씬 분할 단계에서는 삿 분할을 수행한 후 샷 간의 연결관계 분석을 통해 입력 영상을 씬 단위로 분할하게 된다. 씬 서술 단계에서는 분할된 각 씬이 장면 분류, 자막 검출, 화자 인식 등에 의해 그 내용이 자동으로 서술된다. 제안된 방법을 통해 생성된 ToC는 씬과 샷의 계층 구조를 통해 비디오의 구성을 표현하고, 검출된 여러 특정을 이용해 각 씬과 샷의 내용을 서술함으로써 사용자가 비디오의 내용을 한눈에 알아볼 수 있고 원하는 내용에 손쉽게 접근할 수 있도록 도와줄 수 있다. 또 보다 상세한 ToC가 요구되는 경우에는 유용한 정보들이 포함되어 있는 초기 형태의 ToC로써 이용되어 수작업에 의한 ToC 생성에 필요한 시간을 효과적으로 줄이는 것이 가능하다. 실험을 통해 제안한 방법으로 여러 개의 교육용 비디오에서 ToC를 효과적으로 생성될 수 있음을 확인하였다.