• Journal of Korea Game Society
• /
• v.17 no.5
• /
• pp.113-122
• /
• 2017

The location of the objects that make up a game can be an element of immersion for players. repeatedly appearing at the same position, the fun may be reduced, and as the play time elapses, the players will feel the game's fun as they appear in a larger area than at the beginning of the game play. This paper is a study to find out the location of objects according to the passage of time and to see how players controlled these objects. First, foreground images are extracted and accumulated using OpenCV programming language. The accumulated result is displayed as a heat map image. Second, the mouse movement area is detected using the mouse tracking program and compared with the heat map image, so that the screen area in which the player is interested can be known.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.3
• /
• pp.1-8
• /
• 2014

We propose a method to compose a foreground object into a background image, where the foreground object is a part (or a region) of an image taken by a front-facing camera and the background image is a whole image taken by a back-facing camera in a smart phone at the same time. Recent high-end cell-phones have two cameras and provide users with preview video before taking photos. We extract the foreground object that is moving along with the front-facing camera using the optical flow during the preview. We compose the extracted foreground object into a background image using a simple image composition technique. For better-looking result in the composed image, we apply a border smoothing technique using a weighted-border mask to blend transparency from background to foreground. Since constructing and grouping pixel-level dense optical flow are quite slow even in high-end cell-phones, we compute a mask to extract the foreground object in low-resolution image, which reduces the computational cost greatly. Experimental result shows the effectiveness of our extraction and composition techniques, with much less computational time in extracting the foreground object and better composition quality compared with Poisson image editing technique which is widely used in image composition. The proposed method can improve limitedly the color bleeding artifacts observed in Poisson image editing using weighted-border blending.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.623-628
• /
• 2008

We present a new method of extracting foreground object from background image for vision-based game interface. Background Subtraction is an important preprocessing step for extracting the features of tracking objects. The image is divided into the cells where the Local Histogram with Gaussian kernel is computed and compared with the corresponding one using Bhattacharyya distance measure. The histogram-based method is partially robust against illumination change, noise and small moving objects in background. We propose a Multi-Scaled Integral Histogram approach for noise suppression and fast computation.

• Journal of the HCI Society of Korea
• /
• v.6 no.1
• /
• pp.9-16
• /
• 2011

The previous researches of 3D object modeling have been performed in a limited environment where a target object only exists. However, in order to model an object in the real environment, we need to consider a dynamic environment, which has various objects and a frequently changing background. Therefore, this paper presents a segmentation and tracking method for a foreground which includes a target object in the dynamic environment. By using depth information than color information, the foreground region can be segmented and tracked more robustly. In addition, the foreground region can be tracked on the sequential images by referring depth distributions of the foreground region because both the position and the status in the consecutive images of the foreground region are almost unchanged. Experimental results show that our proposed method can robustly segment and track the foreground region in various conditions of the real environment. Moreover, as an application of the proposed method, it is presented a method for modeling an object extracting the object regions from the foreground region that is segmented and tracked.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2007.02a
• /
• pp.83-86
• /
• 2007

비디오에서의 물체 추적은 컴퓨터비젼(computer vision)의 주요 연구 분야로 지능형 로봇, 무인 감시 체제 등의 영역의 핵심 기술로 여겨지고 있다. 본 논문에서는 다중물체추적을 통해 카메라로 부터 입력된 동영상에서 특정 장소를 지나가는 사람들을 추적함으로서, 그 지역에서의 인구의 이동 패턴을 추출하고 자 한다. 물체 추적은 블롭 추적(blob tracking) 방식을 이용하며, 이를 위해 정확한 전경물체 추출, 추출된 이미지 블롭(blob)과 기존 트랙과의 연결, 새로운 물체(사람)의 등장과 퇴장등의 작업을 수행한다. 추적된 물체들이 궤적을 통해, 시간의 변화에 따른 그 지역에서의 인구의 밀도, 주 이동 경로, 방향 등의 변화를 추출한다. 이러한 통계치는 해당 지역의 개발 정책 수립 및 시장성 조사를 위한 2차 데이타로 활용할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.330-333
• /
• 2011

TIP 기술은 2D 그림 또는 한 장의 사진으로부터 기하정보를 추출하여 3 차원 입체 효과를 만들어 영상 내부를 네비게이션할 수 있는 기술로써, 게임, 엔터테인먼트, 교육, 홍보 등 다양한 분야에서 요구되는 주요기술이다. 본 논문에서는 최근 대두되고 있는 스마트 device 의 platform 가운데 하나인 android platform 상에서의 OpenGL ES Library 를 이용한 TIP 기술 적용 및 구현 기술을 제안한다. 제안 방법은 전경객체의 추출이 어려운 상황을 감안하여 보다 사실적 장면 구성이 용이하도록 사용자의 선택에 의한 소실점을 이용하고, OpenGL ES Library 를 이용하여 3D 배경 모델을 획득하고, 이미지를 텍스쳐 매핑하여 3D 가상공간을 완성한 후 카메라의 시점 변환을 통해 이미지 내부를 네베게이션할 수 있도록 한다. 실험영상은 android platform 상의 device 에서 촬영한 이미지를 사용하고, android 2.1 및 OpenGL ES 1.0 기반으로 구축함으로써, 제안 기술을 다양한 android platform smart device 에서 적은 비용과 시간으로 응용 개발에 효과적으로 적용 가능하도록 구현하였다.

• Journal of the Korea Convergence Society
• /
• v.8 no.7
• /
• pp.7-13
• /
• 2017

Robot performances in public places are conducted for the purpose of promoting robot technology and inducing interest in events, exhibitions, and streets instead of dedicated stages. This paper extracts robot images in real time from a robot operation in front of a green chroma key cloth, and synthesizes them on various stage images. A simple and robust method for extracting a foreground robot from a chroma key background without a user's preset is proposed. After increasing the color difference between the background and the foreground, this method automatically removes the background based on the histogram of the difference information, thereby eliminating the need for a user's preset. The simulation shows 98.8% of foreground extraction rate and experimental results demonstrate that the robots can effectively be extracted from the background.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.2
• /
• pp.282-287
• /
• 2002

This paper action tracing by techniques to do image sequence component to watch invader based on Mobile internet use. First, detect frame in animation that film fixed area, and make use of image subtraction between two frame that adjoin, segment fixed backing and target who move. Segmentalized foreground object detected and did so that can presume middle value of gouge that is abstracted to position that is specified and watch invader by analyzing action gouge. Those watch information is stored, and made Mobile client send out SMS Message about situation of watch place to server being stored to sensed serial numbers, date, Image file with recording of time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1477-1479
• /
• 2015

기존의 연구와 같이 정확한 피부색 영역을 추출하기 위해 색상공간을 조절하는 방식은 조명이나 주변환경의 영향에 따라 잘못된 결과를 낼 수 있다. Camshift 알고리즘을 이용한 추적을 할 때에도 대상에게 맞춰진 피부색 히스토그램을 이용해서 추적하지 않으므로 범용성이 떨어진다. 이러한 문제점을 해결하기 위해 Camshift 알고리즘의 최초추적 윈도우를 결정하고 히스토그램을 결정하여손 피부색 추적성능을 향상시켰다. 보편적인 피부색 필터를 이용하여 인체 전경을 추출하고, haar like feature detection (특징검출)을 이용하여 손 영역을 검색한다. 이후 피부색 필터를 통해 이진화 된 이미지를 이용해 원 영상을 마스킹 한 후 사용자 고유의 피부색의 히스토그램을 결정한다. 이 방법으로 얻은 히스토그램을 Camshift알고리즘에 적용하면 기존방식 으로 생성한 히스토그램을 사용할 때보다 좋은 추적 성능을 보인다.

• 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.