• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.586-588
• /
• 2000

KUeyes는 3차원 실세계의 영상처리를 위해 고려대학교 인공시각연구센터에서 개발된 컬러 스테레오 헤드아이 시스템이다. KUeyes는 인간의 시각 시스템을 모델로 하여 다해상도 변환 영상, 칼라 정보와 거리 정보, 움직임 정보를 이용하여 지능적이고 빠르게 객체를 탐지하여 추적한다. 또한 병렬적으로 수행되는 인식기를 통해 탐지된 사람의 얼굴을 인식한다. 다양한 실험 및 분석을 통해 KUeyes가 복잡한 실영상을 대상으로 움직이는 개체를 신시간으로 안정되게 추적하고 인식하는 것을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.599-601
• /
• 2019

본 논문에서는 움직이는 객체 탐지 및 배경 분리 기술을 응용하여 영상 흔들림 보정 기술과 접목하고, 모바일 디바이스에 사용될 수 있는 방법을 설명한다. 또한 이미지에서 사람을 인식하는 기술을 이용하여 모바일에 추가적으로 활용할 수 있는 방법을 소개한다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.317-320
• /
• 2000

동영상 분할은 컴퓨터 비전 분야에서 중요한 단계로 많이 연구되고 있다 그러나 동영상 분할은 계산 복잡도에 의해 제약을 받는다. 이를 해결하기 위해, 본 논문은 분산 유전자 알고리즘에 기반한 계산 효율을 높일 수 있는 새로운 동영상 분할 방법을 제안한다. 일반적으로 동영상에서 연속한 두 프레임은 높은 상관관계를 가진다. 따라서, 한 프레임의 분할 결과는 이전 프레임의 분할 결과를 사용해서 연속적으로 얻어진다. 그리고 중복된 계산을 제거하기 위해 움직이는 객체에 대응되는 염색체만을 진화시킨다. 실험 결과는 제안한 방법의 효율성을 보여준다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.28-30
• /
• 2022

본 연구에서는 컴퓨터 비전 기반의 딥러닝 객체 인식 기술을 이용하여 속초해수욕장에서 수집한 레이더 이미지에서 선박, 섬 및 부유체에 대해 탐지(Detection), 인식(Recognition)하는 연구를 수행하였다. 2021년 8월에 수집한 레이더 영상을 이용하여 본 연구를 수행하였으며, 움직이는 물표와 섬 등을 구분하였다. 일부 환경적인 제약에 따라 에러 발생이 있었지만, 향후 현재까지 수집한 레이더 영상을 추가하여 정확도를 높일 예정이다.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.473-482
• /
• 2019

There have already been studies analyzing the trajectories of objects from data streams of moving objects. Among those studies, there are also studies to discover groups of objects that move together, called companion groups. Most studies to discover companion groups use existing clustering techniques to find groups of objects close to each other. However, these clustering-based methods are often difficult to find the right companion groups because the number of clusters is unpredictable in advance or the shape or size of clusters is hard to control. In this study, we propose a new method that discovers companion groups based on the distance specified by the user. The proposed method does not apply the existing clustering techniques but periodically determines the groups of objects close to each other, by using a technique that efficiently finds the groups of objects that exist within the user-specified distance. Furthermore, unlike the existing methods that return only companion groups and their trajectories, the proposed method also returns their appearance and disappearance time. Through various experiments, we show that the proposed method can detect companion groups correctly and very efficiently.

• Journal of the Korea Convergence Society
• /
• v.8 no.11
• /
• pp.271-277
• /
• 2017

In the image processing, foreground image extraction is mainly applied to recognize a moving object or an object. In the game, the objects included in the foreground image can be mainly characters, non player characters, items, and the like. These objects can be the player's primary concern with objects that are the target of players' movement, attack, defense, and collection. In this background, this research is a study to extract players' interest areas. To this end, first, the foreground image is extracted. Second, the extracted foreground image is accumulated for a certain period of time, and the image is displayed as a result image. The accumulated foreground image according to the play time helps to know the location and frequency of screen appearance of game objects. This study can help players design their interest areas and design an efficient UX/UI.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.1
• /
• pp.94-98
• /
• 2015

Recently, with the rapid advancement in information and computer vision technology, a CCTV system using object recognition and tracking has been studied in a variety of fields. However, it is difficult to recognize a precise object outdoors due to varying pixel values by moving background elements such as shadows, lighting change, and moving elements of the scene. In order to adapt the background outdoors, this paper presents to analyze a variety of background models and proposed background update algorithms based on the weight factor. The experimental results show that the accuracy of object detection is maintained, and the number of misrecognized objects are reduced compared to previous study by using the proposed algorithm.

• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.59-69
• /
• 2007

In the video with a various environment, background modeling is important for extraction and recognition the moving object. For this object recognition, many methods of the background modeling are proposed in a process of preprocess. Among these there is a Kumar method which represents the Queue-based background modeling. Because this has a fixed period of updating examination of the frame, there is a limit for various system. This paper use a background modeling based on the queue. We propose the method that major parameters are decided as adaptive by background model. They are the queue size of the sliding window, the sire of grouping by the brightness of the visual and the period of updating examination of the frame. In order to determine the factors, in every process, RCO (Ratio of Correct Object), REO (Ratio of Error Object) and UR (Update Ratio) are considered to be the standard of evaluation. The proposed method can improve the existing techniques of the background modeling which is unfit for the real-time processing and recognize the object more efficient.

• Journal of Digital Convergence
• /
• v.12 no.11
• /
• pp.357-364
• /
• 2014

AR contents, if markers to be tracked move fast, show flickering while updating images captured from cameras. Conventional methods employing image based markers and SLAM algorithms for tracking objects have the problem that they do not allow more than 2 objects to be tracked simultaneously and interacted with each other in the same camera scene. In this paper, an improved SLAM type algorithm for tracking dynamic objects is proposed and investigated to solve the problem described above. To this end, method using 2 virtual cameras for one physical camera is adopted, which makes the tracked 2 objects interacted with each other. This becomes possible because 2 objects are perceived separately by single physical camera. Mobile robots used as dynamic objects are synchronized with virtual robots in the well-designed contents, proving usefulness of applying the result of individual tracking for multiple moving objects to augmented visualization of objects.

• Journal of Korea Multimedia Society
• /
• v.15 no.8
• /
• pp.986-995
• /
• 2012

In this paper we propose a real-time moving object tracking method on a smart phone camera. By considering the limit of non-learning approach on low-performance platforms, we use the sliding-window detection technique based on histogram features. We solve the problem of the time-consuming histogram computation on each sub-window by adapting the integral histogram. For additional speed and tracking performance, we propose a new adaptive bin method. From the experiments on our dataset, we achieved high speed performance demonstrating 34~63 frames per second.