Background Subtraction in Dynamic Environment based on Modified Adaptive GMM with TTD for Moving Object Detection

Niranjil Kumar A,Sureshkumar C 대한전기학회 2015 Journal of Electrical Engineering & Technology Vol.10 No.1

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.

3차원 객체 복원을 위한 정규 상관도 기반 다중 시점 배경 차분 기법

팽경현(Kyunghyun Paeng),황성수(Sung Soo Hwang),김희동(Hee-Dong Kim),김수정(Sujung Kim),유지성(Jisung Yoo),김성대(Seong Dae Kim) 대한전자공학회 2013 전자공학회논문지 Vol.50 No.6

본 논문에서는 배경과 객체의 색상이 유사한 상황에서 강인한 정규 상관도(Normalized Cross Correlation) 기반 다중 시점 배경 차분 기법을 제안한다. 인위적으로 배경을 구성한 경우가 아닐 경우, 다중 시점 영상의 배경 영상에서 객체로 인해 가려지게 되는 영역들은 서로 다른 색상을 가지고 있을 확률이 높다. 그러나 객체의 등장으로 인해 이러한 영역들은 서로 유사한 색상을 가지게 된다. 이에 기반하여 본 논문은 GoNCC(Graph of Normalized Cross Correlation)을 제안한다. GoNCC는 임의 시점 영상의 한 화소와 에피폴라 제약조건 관계에 있는 인접 영상 내 화소와 해당 화소와의 정규 상관도 값의 분포를 의미한다. 제안하는 다중 시점 배경 차분 기법은 현재 영상의 GoNCC와 배경 영상의 GoNCC를 비교함으로써 이루어진다. 계산량을 줄이기 위해 다중 시점 배경 차분 기법을 모든 화소에 적용하지 않고 간단한 단일 시점 배경 차분 기법으로 판단하기 어려운 영역에 대해서만 제안 방법을 수행한다. 실험 결과 단순한 단일 시점 배경 차분 기법에 비하여 매우 우수한 성능을 보였고, 기존의 다중 시점 배경 차분 기법에 비해서도 보다 정확하게 객체 영역을 검출하는 것을 확인하였다. In this paper, we propose a normalized cross correlation(NCC)-based multiview background subtraction method which is robust when an object and background have similar color. When the background of the capturing environment is not artificially composed, the regions in the background images which would be occluded by an object tends to have difference colors. The colors of those regions, however, becomes similar when an object enters the capturing environment. Based on this assumption, this paper proposes a concept of GoNCC(Graph of Normalized Cross Correlation). GoNCC is the distribution of NCC between a pixel in an image and pixels related by epipolar constraints with the pixel. The proposed multiview background subtraction method is performed by comparing GoNCC of the current images with the background images. To reduce computational complexity, we perform multiview background subtraction only to the pixels undetermined by single view background subtraction. Experimental results show that the proposed method is more robust to color similarity between an object and background than a single-view background subtraction method and a previous multiview background subtraction method.

Probabilistic Background Subtraction in a Video-based Recognition System

( Heesung Lee ),( Sungjun Hong ),( Euntai Kim ) 한국인터넷정보학회 2011 KSII Transactions on Internet and Information Syst Vol.5 No.4

In video-based recognition systems, stationary cameras are used to monitor an area of interest. These systems focus on a segmentation of the foreground in the video stream and the recognition of the events occurring in that area. The usual approach to discriminating the foreground from the video sequence is background subtraction. This paper presents a novel background subtraction method based on a probabilistic approach. We represent the posterior probability of the foreground based on the current image and all past images and derive an updated method. Furthermore, we present an efficient fusion method for the color and edge information in order to overcome the difficulties of existing background subtraction methods that use only color information. The suggested method is applied to synthetic data and real video streams, and its robust performance is demonstrated through experimentation.

정지 물체를 고려한 적응적 배경생성 알고리즘

정종면(Jongmyeon Jeong) 한국컴퓨터정보학회 2014 韓國컴퓨터情報學會論文誌 Vol.19 No.10

배경과 현재 프레임 영상간의 차영상을 이용하여 이동 물체를 탐지하는 방법은 비디오 감시 시스템에서 가장 보편적인 방법 중 하나이지만 신뢰할 수 있는 배경의 생성은 여전히 쉽지 않은 문제이다. 본 논문에서는 정지 물체를 고려한 적응적 배경 생성 기법을 제안한다. 연속적으로 입력되는 영상들의 산술 평균을 이용하여 초기 배경을 생성한다. 배경과 현재 영상간의 차영상을 구하여 물체를 탐지한 다음, 탐지된 물체가 일정시간이상 계속 정지해 있는 경우에는 그 물체를 정지 물체로 간주하고 정지 물체 영역을 배경으로 갱신한다. 한편, 이동 물체인 경우에는 배경갱신에서 현재 프레임을 배제함으로써 지속적으로 물체를 탐지할 수 있도록 한다. 제안된 방법은 점진적인 조명의 변화, 느리게 이동하는 물체, 정지 물체 등이 존재하는 동영상에서도 적응적으로 배경을 생성할 수 있으며 이는 실험을 통해 확인되었다. In the intelligent video surveillance system, moving objects generally are detected by calculating difference between background and input image. However formation of reliable background is known to be still challenging task because it is hard to cope with the complicated background. In this paper we propose an adaptive background formation algorithm considering stationary object. At first, the initial background is formed by averaging the initial N frames. Object detection is performed by comparing the current input image and background. If the object is at a stop for a long time, we consider the object as stationary object and background is replaced with the stationary object. On the other hand, if the object is a moving object, the pixels in the object are not reflected for background modification. Because the proposed algorithm considers gradual illuminance change, slow moving object and stationary object, we can form background adaptively and robustly which has been shown by experimental results.

Improved MOG Algorithm based on Adaptive Threshold for Effective Background Classification

Jeong-Su Oh,Sangkeun Lee 중앙대학교 영상콘텐츠융합연구소 2014 TechArt :Journal of Arts and Imaging Science Vol.1 No.4

In a conventional mixture of Gaussians (MOG) approach for background classification, a small threshold for background decisions causes a recognition delay in a periodic background (PBG) and a large threshold causes passing objects to be considered part of the background in a stationary background. This paper discusses an improved MOG algorithm using an adaptive threshold. Specifically, the proposed scheme evaluates the number of model changes and dominant models for both short and long-term periods; classifies backgrounds as static, non-periodic dynamic, or periodic dynamic; and assigns the appropriate threshold for each case. The simulation results confirm that the proposed approach can significantly reduce a background recognition delay, from 137 to 4 frames for a PBG, and prevent a moving object from being recognized as part of the stationary background. Therefore, we believe that this improved algorithm can be a useful tool for object tracking or background-segmentation-related fields in outdoor applications.

Fast-Optimized Object Detection in Dynamic Scenes Using Efficient Background Weighting

RahebehNiaraki Asli,MarjanMozafari Zavaraki 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.3

Moving object detection is an important fundamental process in intelligent vision systems and an essential preprocessing step in high-level machine vision applications such as object tracking and moving analysis. This technique helps to detect suspicious events in video monitoring and is a key process for concentration estimation in traffic management. It is also one of the methods used in advanced vehicle control systems to keep vehicle in path and prevent accidents.In this paper, an effective weighted background moving object detection is presented,which is optimized for scenes with dynamic background. The proposed detection is based on real time background subtracting with high accuracy, low computational complexity and a short processing time, which makes it a good candidate for hardware implementation. The proposed algorithm is simulated in MATLAB software. The simulation results in MATLAB on various image sequences and comparison with mixture Gaussian method and median filter algorithm shows the effective weighted background method has better performance in different evaluation criteria that approves its efficiency in dynamic scenes.

우리 춤 동작의 정량적 분석을 위한 가상환경 시스템

엄태영,박한훈,이문현,박종일,김운미 한양대학교 우리춤연구소 2009 우리춤과 과학기술 Vol.5 No.2

우리 춤은 우리 고유의 정서를 담고 있는 종합예술이므로 우리 춤을 분석하고 이해하는 것은 큰 의미가 있다. 우리 춤 동작의 표현성을 위해 프로젝션 이미지들을 이용 하여 사용자와 컴퓨터의 인터랙션을 증가시키는 가상환경시스템을 사용하고자한다. 이 시스템에서 우리 춤동작의 정량적 분석을 위해서는 입력영상에서 사용자 영역 추출이 필수적인 요소이다. 본 논문에서는 우리 춤의 표현력 증대를 위해 프로젝션 기반 가상환경시스템을 구축하고 이러한 가상환경시스템의 배경 스크린에 투영되는 영상에 서 사용자의 영역을 추출하기 위해 기하학적 보정과 컬러 보정을 적용한 배경제거 방법을 제안한다. 이는 동적인 프로젝션 배경영상을 각 프레임별로 만들어 추출하는 기법으로서, 가상환경시스템내의 프로젝션 배경에서도 사용자 영역을 정의할 수 있다. 따라서 한 대의 카메라만을 사용하여 실시간으로 사용자 추출이 가능하기 때문에 영 상 분석 및 혼합현실 등에 폭넓은 활용을 기대할 수 있다. There has been considerable interest in virtual environment system and how to improve human and computer interaction has been a main challenge. For vision-based human-computer interaction methods, the extraction of user region from camera images is an essential part. In this paper, we propose a background subtraction method for segmenting dynamic projected background in virtual environment system. In projectorcamera system, the projected background is inherently known by the projector input images although its appearance is changed by the geometric and radiometric transformation between projector and camera. Therefore, we can compute the expected background location and appearance based on geometric and radiometric calibration of projector-camera system and thus extract user region from dynamic projected background by simple subtraction between camera images and the computed background. Experimental results are given for verifying the usefulness of the proposed method.

Laser Spot Detection Using Robust Dictionary Construction and Update

Wang, Zhihua,Piao, Yongri,Jin, Minglu The Korea Institute of Information and Commucation 2015 Journal of information and communication convergen Vol.13 No.1

In laser pointer interaction systems, laser spot detection is one of the most important technologies, and most of the challenges in this area are related to the varying backgrounds, and the real-time performance of the interaction system. In this paper, we present a robust dictionary construction and update algorithm based on a sparse model of background subtraction. In order to control dynamic backgrounds, first, we determine whether there is a change in the backgrounds; if this is true, the new background can be directly added to the dictionary configurations; otherwise, we run an online cumulative average on the backgrounds to update the dictionary. The proposed dictionary construction and update algorithm for laser spot detection, is robust to the varying backgrounds and noises, and can be implemented in real time. A large number of experimental results have confirmed the superior performance of the proposed method in terms of the detection error and real-time implementation.

Multi-Person Tracking Using SURF and Background Subtraction for Surveillance

Yu, Juhee,Lee, Kyoung-Mi Korea Information Processing Society 2019 Journal of information processing systems Vol.15 No.2

Surveillance cameras have installed in many places because security and safety is becoming important in modern society. Through surveillance cameras installed, we can deal with troubles and prevent accidents. However, watching surveillance videos and judging the accidental situations is very labor-intensive. So now, the need for research to analyze surveillance videos is growing. This study proposes an algorithm to track multiple persons using SURF and background subtraction. While the SURF algorithm, as a person-tracking algorithm, is robust to scaling, rotating and different viewpoints, SURF makes tracking errors with sudden changes in videos. To resolve such tracking errors, we combined SURF with a background subtraction algorithm and showed that the proposed approach increased the tracking accuracy. In addition, the background subtraction algorithm can detect persons in videos, and SURF can initialize tracking targets with these detected persons, and thus the proposed algorithm can automatically detect the enter/exit of persons.

Unmanned Aerial Vehicles Tracking using Mixture of Gaussian and Optical Flow

Gicheol Kim,Sohee Son,Haechul Choi 한국정보통신학회 2018 2016 INTERNATIONAL CONFERENCE Vol.10 No.1

Background subtraction is very useful for object detection from image sequences. The Mixture of Gaussian (MOG) algorithm that is a representative example for the background subtraction makes 3-5 Gaussian models per pixel as background to robust to a variety of background changes. as background, which is robust to background change. Optical Flow is a typical method to object tracking. It is an apparent motion pattern in image sequences represented by the relative movement between objects and background. This paper introduces a combination method of the MOG and the Optical Flow for robust object tracking. The proposed method achieves foreground regions using the MOG, and it applies the Optical Flow only to the foreground regions. The experimental results show that the proposed method can track an unmanned aerial vehicle well under being robust to noise and other moving objects.