• Proceedings of the KAIS Fall Conference
• /
• 2005.05a
• /
• pp.147-150
• /
• 2005

본 논문에서는 실시간 영상에서 적응적 배경영상을 이용하여 객체를 추출하고 추적하는 방법을 제안it다. 입력되는 영상에서 배경영역의 잡음을 제거하고 조명에 강인한 객체 추출을 위하여 객체영역이 아닌 배경영역 부분을 실시간으로 갱신함으로써 적응적 배경영상을 생성한다. 그리고 배경영상과 카메라로부터 입력되는 입력영상과의 차를 이용하여 객체를 추출한다. 추출된 객체의 내부점을 이용하여 최소사각영역을 설정하고, 이를 통해 객체를 추적한다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.111-121
• /
• 2011

Intelligent video analysis systems require techniques which can predict accidents and provide alarms to the monitoring personnel. In this paper, we present an abnormal behavior analysis technique based on adaptive background generation. More specifically, abnormal behaviors include fence climbing, abandoned objects, fainting persons, and loitering persons. The proposed video analysis system consists of (i) background generation and (ii) abnormal behavior analysis modules. For robust background generation, the proposed system updates static regions by detecting motion changes at each frame. In addition, noise and shadow removal steps are also were added to improve the accuracy of the object detection. The abnormal behavior analysis module extracts object information, such as centroid, silhouette, size, and trajectory. As the result of the behavior analysis function objects' behavior is configured and analyzed based on the a priori specified scenarios, such as fence climbing, abandoning objects, fainting, and loitering. In the experimental results, the proposed system was able to detect the moving object and analyze the abnormal behavior in complex environments.

• Journal of Korea Multimedia Society
• /
• v.11 no.5
• /
• pp.597-609
• /
• 2008

Due to the recursive updating nature of background model, previous background modeling methods are often perturbed by crowd scenes where foreground pixels occurs more frequently than background pixels. To resolve this problem, an adaptive background modeling method, which is based on the well-known Gaussian mixture background model, is proposed. In the proposed method, the learning rate of background model is adaptively adjusted with respect to the crowdedness of the scene. Consequently, the learning process is suppressed in crowded scene to maintain proper background model. Experiments on real dataset revealed that the proposed method could perform background subtraction effectively even in crowd situation while the performance is almost the same to the previous method in normal scenes. Also, the F-measure was increased by 5-10% compared to the previous background modeling methods in the video of crowded situations.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.99-106
• /
• 2007

In this paper, we present an AAW(Adaptive Attention Window) based cell image segmentation method. For semantic AAW detection we create an initial Attention Window by using a luminance map. Then the initial AW is reduced to the optimal size of the real ROI(Region of Interest) by using a quad tree segmentation. The purpose of AAW is to remove the background and to reduce the amount of processing time for segmenting ROIs. Experimental results show that the proposed method segments one or more ROIs efficiently and gives the similar segmentation result as compared with the human perception.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.59-68
• /
• 2005

Object tracking in a real time image is one of interesting subjects in computer vision and many practical application fields Past couple of years. But sometimes existing systems cannot find object by recognize background noise as object. This paper proposes a method of object detection and tracking using adaptive background image in real time. To detect object which does not influenced by illumination and remove noise in background image, this system generates adaptive background image by real time background image updating. This system detects object using the difference between background image and input image from camera. After setting up MBR(minimum bounding rectangle) using the internal point of detected otject, the system tracks otiect through this MBR. In addition, this paper evaluates the test result about performance of proposed method as compared with existing tracking algorithm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.11a
• /
• pp.199-202
• /
• 2006

본 논문에서는 적응적 관심윈도우에 기반한 세포영상 세그먼테이션 기법을 제안한다. 명암지도를 이용하여 초기 관심윈도우를 생성하고, 초기 관심윈도우를 쿼드-트리 분할을 통해 실제 관심영역과 유사한 크기가 될 때까지 축소한다. 이렇게 생성된 적응적 관심윈도우는 세포영상에서 배경을 제거하고 관심영역 추출의 처리시간을 줄일 수 있다. 그리고 세그먼테이션과 관심영역의 분리를 위한 영역 병합 및 제거를 수행하여 최종적으로 정밀한 관심영역을 얻어낸다. 실험에서 제안된 기법은 세포영상의 관심영역을 효과적으로 분리하여 인간 시각과 유사한 향상된 세그먼테이션 결과를 보여준다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.647-650
• /
• 2003

실시간 영상에서 객체 추적은 수년간 컴퓨터 비전 및 여러 실용적 응용 분야에서 관심을 가지는 주제 중 하나이다. 실제로 실시간 영상내의 객체 추적은 빠른 처리와 많은 연산은 요구하고 고가의 장비가 필요하기 때문에 많은 어려움이 따른다. 본 논문에서는 보안시스템에 적용될 수 있게 실시간으로 배경영상을 갱신하면서 객체를 추출 및 추적하고 추출된 객체에서 얼굴을 추출하는 방법을 제안한다. 배경영상과 입력영상의 차이를 이용하여 실시간으로 배경영상을 입력영상으로 대체하여 시간의 흐름에 의한 배경잡음을 최소화하도록 적응적 배경영상을 생성한다 그리고 배경영상과 카메라로부터 입력되는 입력영상과의 차를 이용하여 객체의 크기와 위치를 탐지하여 객체를 추출한다. 추출된 객체의 내부점을 이용하여 최소사각영역을 설정하고 이를 통해 실시간 객체추적을 하였다. 또한 설정된 최소사각영역은 피부색의 RGB 영역에서 얼굴 영역을 추출하는데도 적용한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.6
• /
• pp.1243-1248
• /
• 2006

Object tracking in a real time image is one of interesting subjects in computer vision and many practical application fields past couple of years. But sometimes existing systems cannot find object by recognize background noise as object. This paper proposes a method of object detection and tracking using adaptive background image in real time. To detect object which does not influenced by illumination and remove noise in background image, this system generates adaptive background image by real time background image updating. This system detects object using the difference between background image and input image from camera. After setting up MBR(minimum bounding rectangle) using the internal point of detected object, the system tracks object through this MBR. In addition, this paper evaluates the test result about performance of proposed method as compared with existing tracking algorithm.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.4
• /
• pp.85-94
• /
• 2004

Object tracking in a real time image is one of interesting subjects in computer vision and many Practical application fields during the past couple of years. But sometimes existing systems cannot find all objects by recognizing background noise as object. This paper proposes a method of object detection and tracking using adaptive background image in real time. To detect object which is not influenced by illumination and to remove noise in background image, this system generates adaptive background image by real time background image updating. This system detects object using the difference between background image and input image from camera. After setting up Minimum Bounding Rectangle(MBR) using the internal point of detected object, the system tracks object through this MBR In addition, this paper evaluates the test result about performance of proposed method as compared with existing tracking algorithm.

• Journal of Korea Multimedia Society
• /
• v.6 no.3
• /
• pp.409-418
• /
• 2003

Object tracking in video is one of subject that computer vision and several practical application field have interest in several years. This paper proposes real time object tracking and face region extraction method that can be applied to security and supervisory system field. For this, in limited environment that camera is fixed and there is seldom change of background image, proposed method detects position of object and traces motion using difference between input image and background image. The system creates adaptive background image and extracts pixels in object using line scan method for more stable object extraction. The real time object tracking is possible through establishment of MBR(Minimum Bounding Rectangle) using extracted pixels. Also, effectiveness for security and supervisory system is improved due to extract face region in established MBR. And through an experiment, the system shows fast real time object tracking under limited environment.