http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
박상욱,오선호,박수완,임경수,최범석,박소희,김상원,한승완,한종욱,김건우,Park, Sangwook,Oh, Seon Ho,Park, Su Wan,Lim, Kyung Soo,Choi, Bum Suk,Park, So Hee,Ghyme, Sang Won,Han, Seung Wan,Han, Jong-Wook,Kim, Geonwoo 한국전자통신연구원 2020 전자통신동향분석 Vol.35 No.2
Predicting where and when a crime may occur in an area of interest is one of many strategies of predictive policing. Multidimensional analysis, including CCTV, can overcome the limitations of hotspot prediction, especially of violent crimes. In order to identify the precursors of a crime, it is necessary to analyze dynamic data such as attributes and activities of people, social information, environmental information, traffic flows, and weather. These parameters can be recognized by CCTV. In addition, it provides accurate analysis of the circumstances of a crime in a dynamic situation, calculates the risk, and predicts the probability of a crime occurring in the near future. Additionally, it provides ways to gather historical criminal datasets, including sensitive personal information.
박상욱,최우현,고한석,Park, Sangwook,Choi, Woohyun,Ko, Hanseok 한국음향학회 2016 韓國音響學會誌 Vol.35 No.1
동일한 장소에서도 매우 다양한 음향이 발생하고, 서로 다른 장소에서도 유사한 음향이 발생하기 때문에 훈련 데이터가 적거나, 훈련 단계에서 일부 음향만 고려된 경우 음향 상황 인지 성능을 보장할 수 없다. 이러한 문제점을 해결하기 위한 방법으로 Bag of Words (BOW) 기반 히스토그램 특징이 소개되었다. 하지만 BOW 기반 히스토그램 특징은 일정 시간동안 발생한 음향의 분포를 이용하기 때문에 음향이 발생한 순차적인 정보는 고려할 수 없다. 음향 상황 인지에서 일정 시간 동안 발생한 음향의 주기성과 지속성은 상황을 인지하는데 중요한 정보가 될 수 있다. 따라서 본 논문에서는 재발량 분석을 이용하여 주기성과 지속성에 대한 특징을 추출하였다. 인식 실험에서 재발량 분석을 통해 추출된 특징을 함께 사용한 경우 기존 방법들 보다 향상된 성능을 확인했다. Since a variety of sound occur in same place and similar sound occurs in other places, the performance of acoustic scene classification is not guaranteed in case of insufficient training data. A Bag of Words (BOW) based histogram feature is foreseen as a method to overcome the problem. However, since the histogram features is made by using a feature distribution, the ordering of sequence of features is ignored. A temporal information such as periodicity and stationarity are also important for acoustic scene classification. In this paper, temporal features about a periodicity and a stationarity are extracted by using a recurrent quantification analysis. In the experiment, performance of the proposed method is shown better than other baseline methods.
양서류 울음 소리 식별을 위한 특징 벡터 및 인식 알고리즘 성능 분석
박상욱,고경득,고한석,Park, Sangwook,Ko, Kyungdeuk,Ko, Hanseok 한국음향학회 2017 韓國音響學會誌 Vol.36 No.6
본 논문에서는 양서류 울음소리를 통한 종 인식 시스템 개발을 위해, 음향 신호 분석에서 활용되는 주요 알고리즘의 인식 성능을 평가했다. 먼저, 멸종위기 종을 포함하여 총 9 종의 양서류를 선정하여, 각 종별 울음소리를 야생에서 녹음하여 실험 데이터를 구축했다. 성능평가를 위해, MFCC(Mel Frequency Cepstral Coefficient), RCGCC(Robust Compressive Gammachirp filterbank Cepstral Coefficient), SPCC(Subspace Projection Cepstral Coefficient)의 세 특징벡터와 GMM(Gaussian Mixture Model), SVM(Support Vector Machine), DBN-DNN(Deep Belief Network - Deep Neural Network)의 세 인식기가 고려됐다. 추가적으로, 화자 인식에 널리 사용되는 i-vector를 이용한 인식 실험도 수행했다. 인식 실험 결과, SPCC-SVM의 경우 98.81 %로 가장 높은 인식률을 확인 할 수 있었으며, 다른 알고리즘에서도 90 %에 가까운 인식률을 확인했다. This paper presents the performance assessment of several key algorithms conducted for amphibian species sound classification. Firstly, 9 target species including endangered species are defined and a database of their sounds is built. For performance assessment, three feature vectors such as MFCC (Mel Frequency Cepstral Coefficient), RCGCC (Robust Compressive Gammachirp filterbank Cepstral Coefficient), and SPCC (Subspace Projection Cepstral Coefficient), and three classifiers such as GMM(Gaussian Mixture Model), SVM(Support Vector Machine), DBN-DNN(Deep Belief Network - Deep Neural Network) are considered. In addition, i-vector based classification system which is widely used for speaker recognition, is used to assess for this task. Experimental results indicate that, SPCC-SVM achieved the best performance with 98.81 % while other methods also attained good performance with above 90 %.
FPGA 검증을 위해 SDK의 Memory Map을 이용한 데이터 자동화 시스템 구현
박상욱(Sangwook Park),강봉순(Bongsoon Kang) 한국정보기술학회 2020 한국정보기술학회논문지 Vol.18 No.10
Since image processing can obtain a lot of information visually, various studies such as autonomous driving and face recognition are being conducted. Therefore, image processing uses a lot of FPGA (Field Programmable Gate Array), which is a non-memory semiconductor that allows easy circuit modification and quick verification. In this paper, we use Xilinxs Zynq-7000 ZC706 board and SDK for communication with PC. When the algorithm to be used on the board is changed, the SDK environment must be modified for the parameters of the new algorithm. Therefore, for quick verification, even if the algorithm is changed, the parameter to be used is automatically recognized and an automated system of SDK is proposed for smooth communication. In addition, we propose regularization for automation so that up to 8 algorithms can be used.
색 보정을 위한 HSV 알고리즘의 최적화된 하드웨어 구현
박상욱(Sangwook Park),강봉순(Bongsoon Kang) 한국전기전자학회 2020 전기전자학회논문지 Vol.24 No.1
자율주행 시장이 급성장함에 따라 자율주행에 대한 연구가 진행되고 있다. 자율주행 기능은 운전자의 안전을 위해 날씨에 상관없이 수행되어야 한다. 하지만 안개 낀 날씨에는 가시성이 떨어져 자율주행에 어려움을 겪기 때문에 안개 제거 알고리즘을 사용해야한다. 안개 제거 알고리즘을 통해 얻은 이미지는 영상의 품질저하를 발생 시킨다. 이러한 문제점을 개선하기 위해서 HSV 색 보정을 이용하여 선명도를 증가시킨다. 본 논문에서는 4K 영상에서도 대응할 수 있는 HSV를 이용한 색 보정하드웨어를 제안한다. 이 하드웨어는 Verilog로 설계했으며 Modelsim을 통해 검증했다. 또한, Xilinx사의 xc7z045-2ffg900을 목표로 FPGA를 구현하였다. As the autonomous driving market is rapidly growing, research on autonomous driving is being conducted. Self-driving functions should be performed regardless of the weather for the driver’s safety. However, misty weather is difficult to autonomous driving because of the lack of visibility, so a defog algorithm should be used. The image obtained through the fog removal algorithm causes the image quality to deteriorate. To improve this problem, HSV color correction is used to increase the sharpness. In this paper, we propose a color correction hardware using HSV that can cope with 4K images. The hardware was designed with Verilog and verified by Modelsim. In addition, the FPGA was implemented with the goal of Xilinx’s xc7z045-2ffg900.
박쥐의 먹이 탐지 전략을 모방한 초음파 센서의 물체 위치 추정
박상욱(Sangwook Park),김대은(DaeEun Kim) 제어로봇시스템학회 2012 제어·로봇·시스템학회 논문지 Vol.18 No.3
It is known that big brown bats can distinguish echo of a prey at various angles. In this paper, we suggest a new object localization strategy using ultrasonic echolocation. We calculate the relative energy ratio between a high frequency component of ultrasound signal and a low frequency component of ultrasound signal for a target object. We found the measure depends on bearing angle of the object in space. We also tested energy ratio of echoed FM ultrasound signals depending on frequency, based on cross-correlation. It can determine the relative angular position of objects even though the reflected signals are congested form each object.
유아의 스포츠스태킹 활동이 눈-손 협응성에 미치는 영향
박상욱 ( Park Sangwook ),김규완 ( Kim Kewwan ) 인천대학교 스포츠과학연구소 2015 스포츠科學硏究誌 Vol.28 No.0
The purpose of this study was to investigate the effectiveness of the Sport Stacking on the Eye-Hand coordination ability of Young Children. The subjects of this study were twenty six Young Children participated and they are all of six years olds in Seoul. They were organized two group. One is experimental group(n=13) and the other is control group(n=13). The experimental group performed a ninety minutes of Sport Stacking activities twice weekly for twelve weeks and the control group was not did it. K-DTVP-2(Korean Developmental Test of Visual Perception) was used to measure the Eye-Hand Coordination, correctness of Coordination and visual-motor speed. After a twelve weeks of training program, experimental group were significant differences in the Eye-Hand Coordination, correctness of Coordination and visual-motor speed.