• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권8호
• /
• pp.1423-1443
• /
• 2011

Background compensation plays an important role in detecting and isolating object motion in visual tracking. Here, we propose a Genetic Hough Transform, which combines the Hough Transform and Genetic Algorithm, as a method for eliminating background motion. Our method can handle cases in which the background may contain only a few, if any, feature points. These points can be used to estimate the motion between two successive frames. In addition to dealing with featureless backgrounds, our method can successfully handle motion blur. Experimental comparisons of the results obtained using the proposed method with other methods show that the proposed approach yields a satisfactory estimate of background motion.

• 한국초전도저온공학회:학술대회논문집
• /
• 한국초전도저온공학회 2000년도 KIASC Conference 2000 / 2000년도 학술대회 논문집
• /
• pp.185-188
• /
• 2000

The voltage induced in the superconducting background magnet system is analyzed according to the calculation of self inductance and mutual inductance. The voltage induced by blip and compensation coils of the background magnet system is about 6.4V. In order to charge the main background magnet, the power supply must provide the minimum voltage of 1.1 kV. the compensation coils have an influence on the field distribution. The compensation coils result in the decreasing center field about 2.67%. It can remarkably decrease the ac losses and the voltage on the current leads of the background magnet.

• 한국통신학회논문지
• /
• 제40권1호
• /
• pp.52-54
• /
• 2015

본 논문은 이동하는 단안 카메라 환경에서 차영상 기반 이동물체 검출 시스템을 위한 새로운 배경 움직임 보상방법을 제안한다. 제안하는 방법은 특징점 대응쌍의 움직임 정보와 카메라 움직임 추정결과를 통해 입력영상에 배치한 격자점들의 배경 움직임을 추정하며 각각의 개별적인 대응 패치간의 영상워핑을 수행한다. 기존 방법과의 비교실험 결과는 약 50% 빠른 처리속도와 약 8dB 더 높은 PSNR을 보였다.

• 한국정보통신학회논문지
• /
• 제17권12호
• /
• pp.2793-2799
• /
• 2013

본 논문에서는 시간에 따라 변하는 잡음 환경에 강인한 음성 인식을 위해 효과적인 특징 보상 기법을 제안한다. 제안하는 기법에서는 기존의 Variational 모델 생성 기법의 모델 정확도를 향상시키고자 PCA를 도입한다. 제안된 기법은 다중 모델을 사용하는 PCGMM 기반의 특징 보상에 적용된다. 실험 결과는 제안한 PCA 기반의 Variational 모델 생성 기법이 배경 음악 환경의 다양한 SNR 조건에서 기존의 전처리 기법에 비하여 음성 인식 성능을 향상 시키는데 우수함을 입증한다. 제안한 모델 생성 기법이 기존의 Variational 모델 생성 방법에 비해 배경 음악 환경에서 평균 12.14%의 상대적 인식 성능 향상률을 나타낸다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.15-17
• /
• 2006

This paper presents a new global intensity compensation method for extracting moving object in a visual surveillance system by compensating time variant intensity changes of background region. The method that compensates a little changes of intensity due to time variant illumination change and automatic gain control of camera is called global intensity compensation. The proposed method expresses global intensity change with a mapping table to describe complex form of intensity change while the previous method models this global intensity change with a simple function as a straight line. The proposed method builds the mapping table by calculating the cross histogram between two images and then by selecting an initial point for generating the mapping table by using Hough transform applied to the cross histogram image. Then starting from the initial point, the mapping table is generated according to the proposed algorithm based on the assumption that reflects the characteristic of global intensity change. Experimental results show that the proposed method makes the compensation error much smaller than the previous GIC method

• Safety and Health at Work
• /
• 제14권4호
• /
• pp.398-405
• /
• 2023

Background: Starting from March 2020 until December 2021, different phases of Covid-19 pandemic have been identified in Italy, with several containing/lifting measures progressively enforced by the National government. In the present study, we investigate the change in occupational risk during the subsequent pandemic phases and we propose an estimate of the incidence of the cases by economic sector, based on the analysis of insurance claims for compensation for Covid-19. Methods: Covid-19 epidemiological data available for the general population and injury claims of workers covered by the Italian public insurance system in 2020-2021 were analyzed. Monthly Incidence Rate of Covid-19 compensation claims per 100,000 workers (MIRw) was calculated by the economic sector and compared with the same indicator for general population in different pandemic periods. Results: The distribution of Covid-19 MIRw by sector significantly changed during the pandemic related to both the strength of different waves and the mitigation/lifting strategies enforced. The level of occupational fraction was very high at the beginning phase of the pandemic, decreasing to 5% at the end of 2021. Healthcare and related services were continuously hit but the incidence was significantly decreasing in 2021 in all sectors, except for postal and courier activities in transportation and storage enterprises. Conclusion: The analysis of compensation claim data allowed to identify time trends for infection risk in different working sectors. The claim rates were highest for human health and social work activities but the distribution of risk among sectors was clearly influenced by the different stages of the pandemic.

• 대한음성학회지:말소리
• /
• 제53호
• /
• pp.119-127
• /
• 2005

Speech recognition is one of the user interface technologies in commanding and controlling any terminal such as a TV, PC, cellular phone etc. in a ubiquitous environment. In controlling a terminal, the mismatch between training and testing causes rapid performance degradation. That is, the mismatch decreases not only the performance of the recognition system but also the reliability of that. Therefore, the performance degradation due to the mismatch caused by the change of the environment should be necessarily compensated. Whenever the environment changes, environment adaptation is performed using the user's speech and the background noise of the changed environment and the performance is increased by employing the models appropriately transformed to the changed environment. So far, the research on the environment compensation has been done actively. However, the compensation method for the effect of distant-talking speech has not been developed yet. Thus, in this paper we apply MLLR-based environment adaptation to compensate for the effect of distant-talking speech and the performance is improved.

• 수산경영론집
• /
• 제34권1호
• /
• pp.9-30
• /
• 2003

This paper tries to suggest a rational proposal for the distribution of compensation of common property fisheries damages caused by a large scale coastal reclamation. For the purpose the paper introduces the approach of alternative cost of the use of fishing ground. The background of the paper is the legal conflict between tenants and non-tenants, both of whom are common owners of seaweed cultivation ground, in the distribution of compensation for damages. In principal, so far as the seaweed cultivation right is a common property of the fishing association, the compensation is also a common property of it. Therefore the distribution method of the compensation entirely depends on the decision of the association. But in case that the numbers of non-tenants is larger than those of tenants, the distribution of the compensation is usually unfavorable to the tenants even though the latter is the key contributor to the realization of present value of the common property. The paper aims to show an appropriate distribution method based on the economic principle of optimal distribution. In others words, the value added to the economic value of alternative use of the fishing ground should be distributed to the tenants. the value amount of alternative use of the fishing ground should be equally distributed to the members of the association.

• 전자공학회논문지S
• /
• 제34S권9호
• /
• pp.67-76
• /
• 1997

This ppaer describes the development of the stereo camera system(KASS-1) and the control of the vergence of the stereo camera to fix a gaze on a moving object in real-time using a stereo disparity. The motion energy and the stereo disparity of a moving object from the stereo image are used to control the vergence of stereo camera to keep stereo disparity constant. The disparity from the rotating stereo camera is introduced not only from the moving object but also from the background. In this paper, the background disparity error due to the vergence control of the stereo camera is eliminated by compensation algoithm, and the vergence of steereo camera system can be controlled continuously using the disparity of a moving object only.

• 전자공학회논문지CI
• /
• 제46권4호
• /
• pp.102-110
• /
• 2009

본 논문은 적외선영상(infrared image)에서 배경모델링 기반의 실시간 객체 탐지 기법과 고속 PPC(PowerPC) & FPGA(Field Programmable Gate Array) 기반 개방형 구조의 하드웨어 설계 방법을 제안한다. 개방형 구조는 하드웨어 및 소프트웨어의 이식이 용이하고, 확장, 호환성, 관리 및 유지보수 등이 편리한 장점이 있다. 제안된 배경모델링 방법을 개방형 구조에 탑재하기 위하여 입력영상에서 검색영역 템플릿을 성긴 블록으로 구성하여 탐색영역의 크기를 줄인다. 또한, 이전 프레임과 현재 프레임에서 영상의 흔들림이 발생했을 때 보정하기 위해 전역움직임 보상방법을 적용한다. 배경과 객체를 분리는 픽셀 밝기의 시간 분석을 통해 적응적 값을 적용한다. 분리된 객체주변에 발생하는 클러터 제거 방법은 중앙값 필터를 적용한다. 설계된 임베디드 시스템에서 배경모델링, 객체탐지, 중앙값 필터, 라벨링, 합병 등의 방법은 PPC에서 구현하였다. 실험결과 제안된 임베디드 시스템에서 전역 움직임 보정과 배경예측을 통해 실시간으로 객체가 탐지될 수 있음을 보였다.