• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.413-416
• /
• 2021

본 논문에서는 서비스용 다관절 로봇팔의 주요기능인 다양한 컵의 검출과 조작, 이동등을 지능적으로 구현하기 위해 로봇 오픈소스 운영체제인 ROS(Robot Operation System)을 기반으로 관련 프로 그램을 개발하고 기능을 구현하였다. 연구의 주요 목표인 다양한 종류의 컵, 병과 같은 물체를 실수없이 집어서 옮기기 위한 처리과정으로 관심물체인식, 3D좌표생성, 결과데이터의 역 기구학 해석등을 수행하였으며, 이를 통해 각 기구부의 축들이 물체에 정확히 도달하고 동작의 오류를 최소화하기 위해 ROS기반의 6축 서비스 로봇팔을 활용한 경로 생성과정과 물체의 검출 성능 과정 및 실험등을 제시하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.1
• /
• pp.197-205
• /
• 2006

This paper presents the moving object tracking method using vision system. In order to track object in real time, the image of moving object have to be located the origin of the image coordinate axes. Accordingly, Fuzzy Control System is investigated for tracking the moving object, which control the camera module with Pan/Tilt mechanism. Hereafter, so the this system is applied to mobile robot, we design and implement image processing board for vision system. Also fuzzy controller is implemented to the StrongArm board. Finally, the proposed fuzzy controller is useful for the real-time moving object tracking system by experiment.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.6
• /
• pp.108-115
• /
• 2013

A developed skill of an intelligent CCTV is also advancing by using its Image Acquisition Device. In this field, area for technique can be divided into Foreground Subtraction which detects individuals and objects in a potential observing area and a tracing technology which figures out moving route of individuals and objects. In this thesis, an improved algorism for a settled engine development, which is stable to change in both noise and illumination for detecting moving objects is suggested. The proposed algorism from this thesis is focused on designing a stable and real time processing method which is perfect model in detecting individuals, animals, and also low-speeding transports and catching a change in an illumination and noise.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.3
• /
• pp.249-262
• /
• 1989

We present a method of boundary extraction of moving objects. We propose four methods for detecting moving edge pixels which can be located on the boundaries of moving objects. We select the best one after we test the above four methods to real image sequences. The portion of the boundaries of moving objects which is marked as moving edge pixels is searched along the moving edge pixels with simple heuristics. And the end points of the resultant line segments are utilized as the start points of the secon stage heuristic search. This second stage search is performed for the boundaries of moving objects which is not marked as moving edge pixels due to various reasons. We test our algorithm for two real sequences and we find that this simple algorithm has good performance.

• Journal of Advanced Navigation Technology
• /
• v.22 no.1
• /
• pp.20-26
• /
• 2018

In this paper, we propose a moving object detection and tracking algorithm based on multi-frame feature point tracking information to reduce false positives. However, there are problems of detection error and tracking speed in existing studies. In order to compensate for this, we first calculate the corner feature points and the optical flow of multiple frames for camera movement compensation and object tracking. Next, the tracking error of the optical flow is reduced by the multi-frame forward-backward tracking, and the traced feature points are divided into the background and the moving object candidate based on homography and RANSAC algorithm for camera movement compensation. Among the transformed corner feature points, the outlier points removed by the RANSAC are clustered and the outlier cluster of a certain size is classified as the moving object candidate. Objects classified as moving object candidates are tracked according to label tracking based data association analysis. In this paper, we prove that the proposed algorithm improves both precision and recall compared with existing algorithms by using quadrotor image - based detection and tracking performance experiments.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.151-156
• /
• 2006

This paper presents an background edge generation based automatic algorithm for detection of moving objects under moving camera. Background image is generated by rotating the fixed the camera on the tripod horizontally, aligning and reorganizing this images. We develop an efficient approach for robust panoramic background edge generation as well as method of edge matching between input image and background image. We applied the proposed algorithm to real image sequences. The proposed method can be successfully realized in various monitoring systems like intrusion detection as well as video surveillance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.1-9
• /
• 2003

The CNN-UM algorithm which performs the analog parallel subtraction of images has been developed and its application study to the moving target detection has been done. The CNN-UM is the state of the art computation architecture with high computational potential of analog parallel processing. It is one of the strong candidates for the next generation of computing system which fulfills requirement of the real-time image processing. One weakness of the CNN-UM is that its analog parallel processing function is not fully utilized for the inter frame processing. If two subsequent image frames are superimposed with opposite signs on identical capacitors for short time period, the analog subtraction between them is achieved. The Principle of such temporal inter-frame processing algorithm has been described and its mathematical analysis has been done. Practical usefulness of the proposed algorithm has also been verified through the application for moving target detection.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.419-420
• /
• 2007

영상에서 경계선 추적은 영상내에 존재하는 특정 물체가 배경과 구분되어지는 외각선을 검출하기 위해 사용되어지는 알고리즘이다. 이렇게 해서 얻어진 외각선의 데이터는 물체를 분석하는데 사용되어 질 수 있다. 본 논문에서는 물체의 외각선 데이터를 획득하기 위해 사용되어지는 경계선 추적 알고리즘중 검색윈도우의 중심점 이동 횟수를 개선한 이동벡터 윈도우 알고리즘과 간단한 경계 추적자(SBF:Simple Boundary Follower)알고리즘을 부분적으로 적용하여 검색윈도우의 중심점 이동횟수 및 검색픽셀의 수를 줄이기 위한 방법을 제안한다. 제안한 경계선 추적 방법은 직선보다는 곡선이 많이 포함되어 있는 물체의 경계선을 추적하는데 보다 효과적임을 실험을 통하여 확인 할 수 있었다.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.425-428
• /
• 2000

본 논문에서는 Pan/Tilt 움직임이 있는 카메라 영상에서 실시간으로 이동하는 물체를 검출하고 추적하기 위한 라인매칭(Line-matching)알고리즘을 제안한다. 또한 물체를 추적하기 위해 색상 성분의 분포와 물체의 움직임을 동시에 이용하여 특징 값을 매칭 하는 모션-칼라 매칭(Motion-Color matching)방법을 제안한다. 본 논문에서 제시한 라인매칭 알고리즘은 움직이는 카메라 영상 안에서 움직이는 물체를 추적하는데 있어 효율적으로 카메라의 움직임을 보정하며, 그에 따른 연산 시간도 현저히 줄일 수 있는 방법이다. 실험에 의하면 카메라로부터 입력되는 영상에서 움직임을 검출 추적하는데에 있어 초당 10∼12 frame의 연산 속도를 보였으며, 추적하는 대상에 대하여 배경의 움직임이나 주위의 환경에 영향을 받지 않는 강인한 추적 결과를 보였다.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.403-412
• /
• 2005

In this paper, we propose an effective method for detecting and classifying shot transitions in video sequences. The proposed method detects and classifies shot transitions including cuts, fades and dissolves by compensating camera operations in video sequences, so that our method prevents false positives resulting from camera operations. Also, our method eliminates local moving objects in the process of compensating camera operations, so that our method prevents errors resulting from moving objects. In the experiments, we show that our shot transition approach can work as a promising solution by comparing the proposed method with previously known methods in terms of performance.