• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.383-392
• /
• 2017

This paper introduces a real-time 3D model generation system that can process in real time from multi-view image acquisition to image-based 3D model generation. This system describes how to collect, transmit, and manage the HD images input from 18 cameras and explain the background separation and smooth 3D volume model generation process. This paper proposes a new distributed data transmission and reception method for real-time processing of HD images input from 18 cameras. In addition, we describe a codebook-based background separating algorithm and a modified marching cube algorithm using perspective difference interpolation to generate smooth 3D models from multi-view images. The system is currently being built with a throughput rate of 30 frames per second.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.33-35
• /
• 2017

최근 영상 내에서 보행자를 검출하는 기술이 발전하면서 보행자 검출 기술이 다양한 분야에서 응용되고 있다. 영상 내에서 보행자들을 검출함으로써 보행자의 통행량이나 이동경로를 분석할 수 있고, 위험 지역이나 보안 지역에 진입하려는 보행자에게 경고를 줄 수도 있다. CCTV와 같이 고정된 카메라를 이용하여 촬영된 영상의 경우 배경 분리 기술을 적용할 수 있는데, 배경 분리 기술을 통해 영상 내에서 움직이는 물체의 영역을 검출해 낼 수 있다. 본 논문에서는 영상의 배경 분리 결과를 이용하여 보행자 검출의 정확도를 높이고자 한다. 영상 내에서 보행자를 검출 했을 때, 보행자 외에 다른 영역이 보행자로 검출되는 상황이 발생할 수 있다. 이로 인해 보행자 검출의 정확도가 낮아진다. 하지만 배경 분리 결과를 이용하여 전경 부분에서만 보행자가 검출되도록 하고 배경 부분에서는 보행자가 검출되지 않도록 한다면, 보행자가 아닌 영역이 보행자로 검출되는 현상을 막을 수 있다. 실제 HDA Person Dataset에서 실험을 해본 결과, 정량적인 성능 향상을 확인 할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.273-274
• /
• 2016

본 논문에서는 다중 랜덤 워커(multiple random walkers)에 기반한 객체 추적 기법을 제안한다. 우선 서포트 벡터 머신(support vector machine)을 이용한 분류기 기반 객체 추적 기법을 소개한다. 다음으로 영상의 영역에 대한 특징 벡터 중 배경으로부터 추출된 특징 벡터를 억제하는 기법을 제안한다. 영역에서 배경 요소를 찾기 위해 다중 랜덤 워커를 이용한 전경 및 배경 추출 방법을 제시한다. 배경 요소를 억제하여 학습된 서포트 벡터 머신은 객체와 배경이 유사한 영상, 객체가 다른 물체에 의해 가려지는 영상 등에서 객체와 배경을 확실하게 구분하여 객체를 잃지 않고 추적할 수 있다. 마지막으로 실험을 통해 제안하는 기법이 기존 기법에 비해 우수한 추적 성능을 보임을 확인한다.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1001-1002
• /
• 2008

본 논문에서는 조명 또는 장면의 갑작스러운 변화에 효과적으로 배경모델링을 하기 위해 국부이진패턴을 이용한 다중 배경모델링 방법을 제안한다. 제안하는 방법은 각 장면에서 독립적인 배경모델을 이용하여 모델 업데이트를 실시한다. 이후 검출된 전경 영역의 비율이 일정 임계치를 넘게 되면 기존의 모델 중 적합한 모델을 찾거나 새로운 모델을 생성하여 현재 배경모델을 대체한다. 이는 배경모델의 성능을 유지하면서 효율적으로 장면의 변화에 바로 대응할 수 있는 장점이 있다. 실험결과에서는 실내조명이 갑작스럽게 변하는 영상과 Pan Tilt Zoom 카메라를 이용한 다중 영상에서 제안한 방법이 효과적으로 동작함을 확인할 수 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.9
• /
• pp.1120-1131
• /
• 2016

In this paper, we propose a smoker recognition algorithm, detecting smokers in a video sequence in order to prevent fire accidents. We use description-based method in hierarchical approaches to recognize smoker's activity, the algorithm consists of background subtraction, object detection, event search, event judgement. Background subtraction generates slow-motion and fast-motion foreground image from input image using Gaussian mixture model with two different learning-rate. Then, it extracts object locations in the slow-motion image using chain-rule based contour detection. For each object, face is detected by using Haar-like feature and smoke is detected by reflecting frequency and direction of smoke in fast-motion foreground. Hand movements are detected by motion estimation. The algorithm examines the features in a certain interval and infers that whether the object is a smoker. It robustly can detect a smoker among different objects while achieving real-time performance.

• Korean Journal of Cognitive Science
• /
• v.27 no.3
• /
• pp.355-376
• /
• 2016

We used holes defined by color similarity (Experiment 1) and binocular disparity (Experiment 2) to study how the inner contour of an object (i.e., boundary of a hole in it) is encoded in visual working memory. Many studies in VWM have shown that an object's boundary properties can be integrated with its surface properties via their shared spatial location, yielding an object-based encoding benefit. However, encoding of the hole contours has rarely been tested. We presented objects (squares or circles) containing a bar under a change detection paradigm, and relevant features to be remembered were the color of objects and the orientation of bars (or holes). If the contour of a hole belongs to the surrounding object rather than to the hole itself, the object-based feature binding hypothesis predicts that the shape of it can be integrated with color of an outer object, via their shared spatial location. Thus, in the hole display, change detection performance was expected to better than in the conjunction display where orientation and color features to be remembered were assigned to different parts of a conjunction object, and comparable to that in a single bar display where both orientation and color were assigned into a single bar. However, the results revealed that performance in the hole display did not differ from that in the conjunction display. This suggests that the shape of holes is not automatically encoded together with the surface properties of the outer object via object-based feature binding, but encoded independently from the surrounding object.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.38-47
• /
• 2013

An image coding based on MRC model, a kind of multi-layer image model, first segments a screen image into foreground, mask, and background layers, and then compresses each layer using a codec that is suitable to the layer. The mask layer defines the position of foreground regions such as textual and graphical contents. The colour signal of the foreground (background) region is saved in the foreground (background) layer. The mask layer which contains the segmentation result of foreground and background regions is of importance since its accuracy directly affects the overall coding performance of the codec. This paper proposes a new layer segmentation algorithm for the MRC based image coding. The proposed method extracts text pixels from the background using morphological top hat filtering. The application of white or black top hat transformation to local blocks is controlled by the information of relative brightness of text compared to the background. In the proposed method, the boundary information of text that is extracted from the edge map of the block is used for the robust decision on the relative brightness of text. Simulation results show that the proposed method is superior to the conventional methods.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.417-429
• /
• 2010

Though background subtraction has been widely studied for last decades, it is still a poorly solved problem especially when it meets real environments. In this paper, we first address some common problems for background subtraction that occur in real environments and then those problems are resolved by improving an existing GMM-based background modeling method. First, to achieve low computations, fixed point operations are used. Because background model usually does not require high precision of variables, we can reduce the computation time while maintaining its accuracy by adopting fixed point operations rather than floating point operations. Secondly, to avoid erroneous backgrounds that are induced by high pedestrian traffic, static levels of pixels are examined using shot-time statistics of pixel history. By using a lower learning rate for non-static pixels, we can preserve valid backgrounds even for busy scenes where foregrounds dominate. Finally, to adapt rapid illumination changes, we estimated the intensity change between two consecutive frames as a linear transform and compensated learned background models according to the estimated transform. By applying the fixed point operation to existing GMM-based method, it was able to reduce the computation time to about 30% of the original processing time. Also, experiments on a real video with high pedestrian traffic showed that our proposed method improves the previous background modeling methods by 20% in detection rate and 5~10% in false alarm rate.

• Journal of the Korea Convergence Society
• /
• v.12 no.2
• /
• pp.1-6
• /
• 2021

In the modern society, traffic problems are occurring as vehicle ownership increases. In particular, the incidence of highway traffic accidents is low, but the fatality rate is high. Therefore, a technology for detecting an abnormality in a vehicle is being studied. Among them, there is a vehicle anomaly detection technology using deep learning. This detects vehicle abnormalities such as a stopped vehicle due to an accident or engine failure. However, if an abnormality occurs on the road, it is possible to quickly respond to the driver's location. In this study, we propose a deep learning-based vehicle anomaly detection using road CCTV data. The proposed method preprocesses the road CCTV data. The pre-processing uses the background extraction algorithm MOG2 to separate the background and the foreground. The foreground refers to a vehicle with displacement, and a vehicle with an abnormality on the road is judged as a background because there is no displacement. The image that the background is extracted detects an object using YOLOv4. It is determined that the vehicle is abnormal.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.520-522
• /
• 2003

디지털데스크는 일반 책상 표면에 프로젝션 화면을 만들어 가상물체를 사람이 직접 조작할 수 있는 인터페이스를 제공한다. 이러한 인터페이스를 구축하기 위해서는 전경물체 검출이 필수 과정인데, 지금까지는 조명과 배경의 변화로 인한 색상의 변화로 인하여 색상 정보를 사용하지 못하였다. 본 논문에서는 디지털데스크 상에서 색상 정보를 이용하여 전경물체를 검출하는 방법을 제안한다. 디지털데스크의 화면은 프로젝터를 통해 책상 표면에 투사되고, 투사된 화면은 카메라를 통해 영상으로 획득되는데, 이때 많은 왜곡이 존재하게 된다. 우리는 이런 왜곡을 기하 왜곡과 색 휘도의 왜곡 두가지로 정의하여 모델링하였고. 실험 결과에서 제안된 방법의 실효성을 입증하였다.