• 대한임베디드공학회논문지
• /
• 제3권2호
• /
• pp.74-81
• /
• 2008

This paper describes a low-cost omnidirectional camera system designed for the intruder detection capability of a security robot. Moving targets on sequential images are detected first by an adaptive background subtraction technique, and the targets are identified as intruders if they fail to enter a password within a preset time. A warning message is then sent to the owner's mobile phone. The owner can check scene pictures posted by the system on the web. The system developed worked well in experiments including a situation when the indoor lighting was suddenly changed.

• 한국군사과학기술학회지
• /
• 제20권5호
• /
• pp.708-716
• /
• 2017

We deal with the target selection in seeker-detection image through network, using the detection information from aerial vehicle and the target information from surveillance and reconnaissance system. Especially, we constrain the sea battle environment, where it is difficult to perform scene-matching rather than land. In this paper, we suggest the target selection algorithm based on the confidence estimation with respect to distance and size. In detail, we propose the generation method of reference point for distance evaluation, and we investigate the effect of pixel margin and target course for size evaluation. Finally, the proposed algorithm is simulated and analyzed through several scenarios.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.986-1005
• /
• 2020

In this paper, we propose AnoVid, an automated video annotation tool based on deep neural networks, that automatically generates various meta data for each scene or shot in a long drama video containing rich elements. To this end, a novel meta data schema for drama video is designed. Based on this schema, the AnoVid video annotation tool has a total of six deep neural network models for object detection, place recognition, time zone recognition, person recognition, activity detection, and description generation. Using these models, the AnoVid can generate rich video annotation data. In addition, AnoVid provides not only the ability to automatically generate a JSON-type video annotation data file, but also provides various visualization facilities to check the video content analysis results. Through experiments using a real drama video, "Misaeing", we show the practical effectiveness and performance of the proposed video annotation tool, AnoVid.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.159-161
• /
• 2004

Many motion object detection algorithms rely on the process of background subtraction, an important technique that is used for detecting changes from a model of the background scene. This paper propose a novel method to update the background model image of a visual surveillance system which is not stationary. In order to do this, we use a background model based on statistical qualities of monitored images and another background model that excluded motions. By comparing each changed area computed from the two background model images and current monitored image, the areas that will be updated are decided.

• Advances in robotics research
• /
• 제1권2호
• /
• pp.127-140
• /
• 2014

This work presents an IR-based system for parking assistance and obstacle detection in the automotive field that employs the Microsoft Kinect camera for fast 3D point cloud reconstruction. In contrast to previous research that attempts to explicitly identify obstacles, the proposed system aims to detect "reachable regions" of the environment, i.e., those regions where the vehicle can drive to from its current position. A user-friendly 2D traversability grid of cells is generated and used as a visual aid for parking assistance. Given a raw 3D point cloud, first each point is mapped into individual cells, then, the elevation information is used within a graph-based algorithm to label a given cell as traversable or non-traversable. Following this rationale, positive and negative obstacles, as well as unknown regions can be implicitly detected. Additionally, no flat-world assumption is required. Experimental results, obtained from the system in typical parking scenarios, are presented showing its effectiveness for scene interpretation and detection of several types of obstacle.

• Journal of Multimedia Information System
• /
• 제4권4호
• /
• pp.225-232
• /
• 2017

Understanding actions in videos is an important task. It helps in finding the anomalies present in videos such as fights. Detection of fights becomes more crucial when it comes to sports. This paper focuses on finding fight scenes in Hockey sport videos using blur & radon transform and convolutional neural networks (CNNs). First, the local motion within the video frames has been extracted using blur information. Next, fast fourier and radon transform have been applied on the local motion. The video frames with fight scene have been identified using transfer learning with the help of pre-trained deep learning model VGG-Net. Finally, a comparison of the methodology has been performed using feed forward neural networks. Accuracies of 56.00% and 75.00% have been achieved using feed forward neural network and VGG16-Net, respectively.

• Journal of information and communication convergence engineering
• /
• 제13권3호
• /
• pp.197-204
• /
• 2015

In this paper, we present an algorithm for the detection of illegally parked vehicles based on a combination of some image processing algorithms. A digital camera is fixed in the illegal parking region to capture the video frames. An adaptive Gaussian mixture model (GMM) is used for background subtraction in a complex environment to identify the regions of moving objects in our test video. Stationary objects are detected by using the pixel-level features in time sequences. A stationary vehicle is detected by using the local features of the object, and thus, information about illegally parked vehicles is successfully obtained. An automatic alarm system can be utilized according to the different regulations of different illegal parking regions. The results of this study obtained using a test video sequence of a real-time traffic scene show that the proposed method is effective.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 춘계학술대회
• /
• pp.149-151
• /
• 2011

동적 모자이크 영상 생성을 위해서는 카메라의 움직임을 계산한 후에 객체의 움직임을 인지해야 한다. 본 논문에서는 어파인 파라미터로 카메라의 움직임을 추출 하였고 지역적 탐색으로 객체의 움직임을 탐지한다. 동적 객체가 존재하는 경우엔 동적 객체 판별을 위하여 영역 분할 방법을 통하여 계산한다. 그리고 동적 객체의 궤도를 표현하기 위하여 우선적으로 동적 객체를 추출하는데 추출 방법은 4분할 탐색 기법을 이용하여 추출하게 된다. 마지막으로 구축되어진 배경 모자이크 영상위에 동적 객체의 궤도르 표현한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.931-932
• /
• 2008

An implementation of modified stereo matching using efficient belief propagation(BP) algorithm is presented in this paper. Edges of the image were found using conventional edge detection algorithms. Resulting edge information is used to suppress propagation of wrong probabilistic information. Proposed method can effectively reduce errors that incurred by ambiguous scene properties.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.421-424
• /
• 1999

Automatic human face detection in a complex background is one of the difficult problems In this paper. we propose an effective automatic face detection system that can locate the face region in natural scene images when the system is used as a pre-processor of a face recog- nition system. We use two natural and powerful visual cues, the color and the human head shape. The outline of the human head can be generally described as being roughly elliptic in nature. In the first step of the proposed system, we have tried the approach of fitting the best Possible ellipse to the outline of the head In the next step, the method based on the human skin color space by selecting flesh tone regions in color images and histogramming their r(＝R/(R＋G＋B)) and g(＝G/R＋G＋B)) values. According to our experiment. the proposed system shows robust location results