• 전자공학회논문지
• /
• 제54권8호
• /
• pp.67-80
• /
• 2017

본 논문에서는 추정된 시공간 배경 정보를 이용하여 자유 시점에서 합성영상을 생성하기 위한 홀채움 방식을 제안한다. 시간적 배경 정보를 추정하기 위해 비겹침 패치 기반의 배경 코드북을 이용한 새로운 시간적 배경 모델을 소개한다. 더불어, 공간적 배경 후보의 하한 및 상한 값의 제약 조건을 설정하는 깊이영상 기반 공간적 국부 배경 예측 방식에 대해 제안한다. 추정된 시간적 배경 정보와 공간적 배경 정보의 유사도를 비교하여 가려짐 배경 영역의 홀채움 과정을 수행한다. 또한 3-D 워핑 후 발생하는 컬러영상과 깊이영상간의 불일치 문제를 해결하기 위해 깊이영상 기반의 고스트 제거 필터를 기술한다. 마지막으로 잔여 홀을 채우기 위해 새로운 깊이 항을 포함한 우선순위 함수를 이용하여 인페인팅 방식이 적용된다. 실험 결과를 통해 기존의 홀채움 방식들과 비교하여 제안하는 방식의 객관적, 주관적 성능의 우수성을 확인할 수 있었다.

• ETRI Journal
• /
• 제45권5호
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• Journal of Electrical Engineering and Technology
• /
• 제10권1호
• /
• pp.372-378
• /
• 2015

Background subtraction is the first processing stage in video surveillance. It is a general term for a process which aims to separate foreground objects from a background. The goal is to construct and maintain a statistical representation of the scene that the camera sees. The output of background subtraction will be an input to a higher-level process. Background subtraction under dynamic environment in the video sequences is one such complex task. It is an important research topic in image analysis and computer vision domains. This work deals background modeling based on modified adaptive Gaussian mixture model (GMM) with three temporal differencing (TTD) method in dynamic environment. The results of background subtraction on several sequences in various testing environments show that the proposed method is efficient and robust for the dynamic environment and achieves good accuracy.

• 정보처리학회논문지B
• /
• 제17B권6호
• /
• pp.405-412
• /
• 2010

기존의 배경 생성방법은 주로 시간에 따른 context만을 이용해 복잡한 환경에서는 적용하기 힘들다. 이러한 단점을 해결하기 위해, 본 논문에서는 움직이는 물체를 포함하지 않는 배경 영상을 생성하기 위해 시간에 따른 context와 공간에 따른 context를 융합한 새로운 배경 생성 방법을 제안한다. 제안한 방법은 먼저 샘플링된 프레임 이미지를 m*n의 블록으로 나누고 각각의 블록을 고정 블록과 비고정 블록으로 나눈다. 비고정 블록에 대해서, 각 블록의 시간적 context와 공간적 context를 모델링하기 위해 MRF 프레임워크를 이용한다. MRF 프레임워크는 영상 픽셀과 연관된 특징과 같은 context에 독립된 entity를 모델링하는데 많이 이용되는 방법으로 본 논문에서는 비고정 블록에 대한 시간적 context와 공간적 context를 모델링하기 위해 이용된다. 실험결과는 제안한 방법이 기존의 시간에 따른 context만을 이용했을 경우보다 더 효율적임을 보여준다.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.558-570
• /
• 2018

Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.

• 한국통신학회논문지
• /
• 제34권5C호
• /
• pp.505-513
• /
• 2009

본 논문은 모노 카메라로 입력받은 영상에서 실시간으로 전경과 배경을 분리하여 배경을 자연스럽게 대체 하는 방법을 제안한다. 기존 연구는 대부분 단일 색상의 배경을 이용하여 전경 색에 대한 제약이 있거나, 깊이 정보를 추출을 위한 스테레오 카메라와 같은 장치에 대한 제약이 있거나, 제한적인 전경의 모양 모델을 이용하여 분리할 수 있는 전경의 모양에 대한 제약이 있었다. 이에 본 논문에서는 일반적으로 사용되는 웹캠과 같은 고정된 모노 카메라를 이용하여 실시간으로 전경 분리가 가능한 전경 분리 방법을 제안한다. 또한, 전경 분리의 성능 향상을 위하여 통영상의 시간적인 특징 정보를 이용한 시간적 전경 확률 모델을 제안한다. 또한 분리된 전경과 새로운 배경의 자연스러운 합성을 위한 알파 매트를 이용한 경계선 영역 처리방법과 간단한 후 처리 방법을 제안한다. 제안된 방법은 실제의 화상통신에서 개인의 사적인 정보가 포함된 배경을 자연스럽게 대체시켜 개인의 사생활을 보호할 수 있다.

• 산업기술연구
• /
• 제38권1호
• /
• pp.41-52
• /
• 2018

Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.

• 대기
• /
• 제27권4호
• /
• pp.423-433
• /
• 2017

The spatial and temporal variations in radiative forcing (RF) and mean temperature changes of greenhouse gases (GHGs), such as $CO_2$, $CH_4$, and $N_2O$, were analyzed at urban center (Yeon-dong) and background sites (Gosan) on Jeju Island during 2010~2015, based on a modeling approach (i.e., radiative transfer model). Overall, the RFs and mean temperature changes of $CO_2$ at Yeon-dong during most years (except for 2014) were estimated to be higher than those at Gosan. This might be possibly because of its higher concentrations at Yeon-dong due to relatively large energy consumption and small photosynthesis and also the difference in radiation flux due to the different input condition (e.g., local time and geographic coordinates of solar zenith angle) in the model. The annual mean RFs and temperature changes of $CO_2$ were highest in 2015 ($2.41Wm^{-2}$ and 1.76 K) at Yeon-dong and in 2013 ($2.22Wm^{-2}$ and 1.62 K) at Gosan (except for 2010 and 2011). The maximum monthly/seasonal mean RFs and temperature changes of $CO_2$ occurred in spring (Mar. and/or Apr.) or winter (Jan. and/or Feb.) at the two sites during the study period, whereas the minimum RFs and temperature changes in summer (Jun.-Aug.). In the case of $CH_4$ and $N_2O$, their impacts on the RF and mean temperature changes were very small (an order of magnitude lower) compared to $CO_2$. The spatio-temporal differences in these RF values of GHGs might primarily depend on the atmospheric profile (e.g., ozone profile), surface albedo, local time (or solar zenith angle), as well as their mass concentrations.

• 환경영향평가
• /
• 제15권3호
• /
• pp.193-206
• /
• 2006

Recently, high ozone episode occurred frequently in Korea. Moreover ozone episode occurred not only in the city but also in background area where local anthropogenic sources are not important. It analyzed frequency exceeding 100ppb ozone at air quality monitoring stations in Seoul and rural area during 1995-2004. This paper reports on the use of the Community Multiscale Air Quality (CMAQ) modelling system to predict hourly ozone levels. Domain resolutions of 30km, 10km, 3.333km (innermost) have been employed for this study. Summer periods in June 2004 have been simulated and the predicted results have been compared to data for metropolitan and rural air quality monitoring stations. The model performance has been evaluated with measured data through a range of statistical measures. Although, the CMAQ model reproduces the ozone temporal spatial trends it was not able to simulate the peak magnitudes consistently.

• International Journal of Contents
• /
• 제14권3호
• /
• pp.7-16
• /
• 2018

The extent and depth of the event plan determines the scope of pedagogical experience in situations and consequently the quality of immersive learning based on our simulated world. In contrast to planning in conventional narrative-based systems mainly pursuing dramatic interests, planning in virtual world-based pedagogical systems strive to provide realistic experiences in immersed situations. Instead of story plot comprising predetermined situations, our inter-event planning method aims at simulating diverse situations that each involve multiple events coupled via their associated agents' conditions and meaningful associations between events occurring in a background world. The specific techniques to realize our planning method include, two-phase planning based on inter-event search and intra-event decomposition (down to the animated action level); autonomous and independent agents to behave proactively with their own belief and planning capability; full-blown background world to be used as the comprehensive stage for all events to occur in; coupling events via realistic association types including deontic associations as well as conventional causality; separation of agents from event roles; temporal scheduling; and parallel and concurrent event progression mechanism. Combining all these techniques, diverse exogenous events can be derived and seamlessly (i.e., semantically meaningfully) integrated with the original event to form a wide scope of situations providing chances of abundant pedagogical experiences. For effective implementation of plan execution, we devise an execution scheme based on multiple priority queues, particularly to realize concurrent progression of many simultaneous events to simulate its corresponding reality. Specific execution mechanisms include modeling an action in terms of its component motions, adjustability of priority for agent across different events, and concurrent and parallel execution method for multiple actions and its expansion for multiple events.