• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1564-1573
• /
• 2016

With the spread of social media and mobile devices, people spend more time on online than ever before. As more people participate in various online activities, much research has been conducted on how to make use of the time effectively and productively. In this paper, we propose two methods which can be used to extract highlights and make searchable media indexes using online social data. For highlight extraction, we collected the comments from the online baseball broadcasting website. We adopted peak-finding algorithm to analyze the frequency of comments uploaded on the comments section of the website. For each indexes, we collected postings from soap opera forums provided by a popular web service called DCInside. We extracted all the instances when a character's name is mentioned in postings users upload after watching TV, which can be used to create indexes when the character appears on screen for the given episode of the soap opera The evaluation results shows the possibility of the crowdsourcing-based media interaction for both highlight extraction and index building.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5130-5143
• /
• 2019

Football (soccer) is one of the most popular sports in the world. A huge number of people watch live football matches by TV or Internet. A football match takes 90 minutes, but viewers may only want to watch a few highlights to save their time. As far as we know, there is no such a product that can be put into use to achieve intelligent highlight extraction from live football matches. In this paper, we propose an intelligent editing system for live football matches. Our system can automatically extract a series of highlights, such as goal, shoot, corner kick, red yellow card and the appearance of star players, from the live stream of a football match. Our system has been integrated into live streaming platforms during the 2018 FIFA World Cup and performed fairly well.

• 정보처리학회논문지B
• /
• 제14B권1호
• /
• pp.1-4
• /
• 2007

본 논문에서는 축구 동영상으로부터 자동적으로 하이라이트 장면들을 검출하는 방법을 제안한다. 축구 동영상에서 하이라이트 장면들은 슈팅 장면들이나 골 장면들로 정의 될 수 있다. 우리는 축구 동영상에 대한 구조적 분석을 통해서 일반적으로 골 포스트(goal posts) 영역 주위에서 하이라이트 장면들이 나타나는 것과 하이라이트 장면 이후에는 TV 카메라가 축구 선수들이나 관중석을 확대해서 보여주는 것을 확인할 수 있었다. 본 논문에서 축구 동영상으로부터 하이라이트 장면들을 검출하기 위한 과정은 세 단계로 구성된다. 첫 번째 단계는 통계적인 문턱치(statistical threshold)를 이용한 그라운드(playing field) 영역을 추출한다. 두 번째 단계는 골 포스트를 찾기 위해서 그라운드 영역과 그라운드가 아닌 영역들의 경계선 부분을 검출한다. 그리고 마지막 단계에서는 축구 선수나 관객들의 확대 장면을 검출하기 위해서 그라운드가 아닌 영역들에 대해서 connected component labeling 기법을 적용하여 한 장면 내에서 그라운드가 아닌 영역들의 비율을 계산한다. 본 논문에서는 하이라이트 장면 검출에 대한 성능을 평가하기 위하여 정확률(precision)과 재현율(recall)을 사용하고, 실험을 통하여 제안된 방법이 정확률 95.2%, 재현율 854%로 축구 동영상에서 하이라이트 장면을 효과적으로 검출할 수 있음을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제19권10호
• /
• pp.1775-1781
• /
• 2016

Generally, in the underwater target recognition, feature vectors are extracted from the target signal utilizing spatial information according to target shape/material characteristics. In addition, various signal processing techniques have been studied to extract feature vectors which are less sensitive to the location of the receiver. In this paper, we synthesized active echo signals using 3-dimensional highlight distribution. Then, Fractional Fourier transform was applied to echo signals to extract signal features. For the performance verification, classification experiments were performed using backpropagation and probabilistic neural network classifiers based on single aspect and multi-aspect method. As a result, we obtained a better recognition result using proposed feature extraction and multi-aspect based method.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (2)
• /
• pp.607-609
• /
• 2003

동영상 자동 분석은 비디오 데이터의 내용 기반 색인과 검색을 위한 첫 단계이다. 본 논문에서는 정형적인 구조를 가진 뉴스와는 달리 비정형적인 특성을 가진 축구 동영상에서 사용자의 관심이 되는 하이라이트 장면의 영상 특징을 이용하여 그 구조를 분석하여 하이라이트 장면을 검출하는 방법을 제안한다. 이전 연구를 토대로 그라운드영역과 골대 유무에 따라 하이라이트 후보 장면을 찾는 과정에서 경기마다 달라지는 임계값에 영향을 받지 않는 알고리즘을 제안하였다. 실험결과 제안된 방법이 여러 종류의 축구 경기 하이라이트 분석에 있어서 그 성능이 우수함을 확인할 수 있었다.

• 동력기계공학회지
• /
• 제14권2호
• /
• pp.40-47
• /
• 2010

This paper proposes a fault detection system to detect the strip rupture in six-high stand Cold Rolling Mills based on transient current signal of an electrical motor. For this work, signal smoothing technique is used to highlight precise feature between normal and fault condition. Subtracting the smoothed signal from the original signal gives the residuals that contains the information related to the normal or faulty condition. Using residual signal, discrete wavelet transform is performed and acquire the signal presenting fault feature well. Also, feature extraction and classification are executed by using PCA, KPCA and SVM. The actual data is acquired from POSCO for validating the proposed method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 추계학술대회 논문집 전기물성,응용부문
• /
• pp.112-116
• /
• 2004

On-line monitoring of fault discharge is an important approach for indicating the condition of electrical insulation of stator winding in high voltage motor. In this paper, several key aspects of on-line monitoring system are discussed, involving the characteristics of fault discharge of stator winding in high voltage motor, spectrum analysis of four simulation fault signals, feature extraction of internal fault discharge from apply voltage to breakdown. The study of the partial discharge activities allows to highlight the ageing stage in the winding fault under test. During the life of the winding insulation fault, the shape of PD signal change relating to the ageing stage. The ageing of stator winding insulation fault of high voltage motor is investigated based on the characteristics of partial discharge pulse distribution and statistical parameters, such as maximum, skewness and kurtosis using discrete wavelet transform coefficients.

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.265-275
• /
• 2015

This paper describes extraction methods of five different types of geometrical features (line, arc, corner, polynomial curve, NURBS curve) from the obtained raw data by using a two-dimensional laser range finder (LRF). Natural features with their covariance matrices play a key role in the realization of feature-based simultaneous localization and mapping (SLAM), which can be used to represent the environment and correct the pose of mobile robot. The covariance matrices of these geometrical features are derived in detail based on the raw sensor data and the uncertainty of LRF. Several comparison are made and discussed to highlight the advantages and drawbacks of each type of geometrical feature. Finally, the extracted features from raw sensor data obtained by using a LRF in an indoor environment are used to validate the proposed extraction methods.

• 산업경영시스템학회지
• /
• 제44권3호
• /
• pp.86-97
• /
• 2021

As mechatronic systems have various, complex functions and require high performance, automatic fault detection is necessary for secure operation in manufacturing processes. For conducting automatic and real-time fault detection in modern mechatronic systems, multiple sensor signals are collected by internet of things technologies. Since traditional statistical control charts or machine learning approaches show significant results with unified and solid density models under normal operating states but they have limitations with scattered signal models under normal states, many pattern extraction and matching approaches have been paid attention. Signal discretization-based pattern extraction methods are one of popular signal analyses, which reduce the size of the given datasets as much as possible as well as highlight significant and inherent signal behaviors. Since general pattern extraction methods are usually conducted with a fixed size of time segmentation, they can easily cut off significant behaviors, and consequently the performance of the extracted fault patterns will be reduced. In this regard, adjustable time segmentation is proposed to extract much meaningful fault patterns in multiple sensor signals. By considering inflection points of signals, we determine the optimal cut-points of time segments in each sensor signal. In addition, to clarify the inflection points, we apply Savitzky-golay filter to the original datasets. To validate and verify the performance of the proposed segmentation, the dataset collected from an aircraft engine (provided by NASA prognostics center) is used to fault pattern extraction. As a result, the proposed adjustable time segmentation shows better performance in fault pattern extraction.

• 한국음향학회지
• /
• 제28권2호
• /
• pp.135-140
• /
• 2009

본 논문에서는 하이라이트 모델에 기반하여 능동소나의 표적신호를 합성하고, 합성된 신호를 이용하여 표적인식 실험을 수행하였다. 동일 표적이라도 표적의 자세각에 따라 다양한 형태의 파형을 갖는 신호가 합성되는데, 이에 대한 표적인식 결과를 알아보기 위해서 두 가지 방법으로 실험을 수행하였다. 하나는 고정된 여러 가지 자세각에 대한 표적신호에 대한 인식실험이고, 다른 하나는 임의의 자세각을 가지는 교신에 대만 인식 실험을 수행하였다. 인식실험을 위한 특징 인자로는 합성된 표적신호에 대해 시간영역에서 정합필터 및 포락선 검출을 통해 얻어지는 하이라이트 패턴을 사용하였으며, 패턴인식 기법으로는 다중클래스 SVM과 인공신경망을 사용하였다.