• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.596-601
• /
• 2001

본 논문에서는 두 대의 카메라로부터 입력받은 인간의 신체와 같은 관절체의 움직임을 Color Marker의 색상 특성을 이용하여 3차원 공간 정보를 인식하는 방법에 관해 기술한다. 이 방법은 인체에 물리적인 장치를 하지 않고 단순히 영상정보만을 이용하여 3차원 정보를 구하였다. 보다 정확한 인체의 특징점을 구하기 위해 환 논문에서는 신체의 관절각에 칼라 마커를 부착하고 칼라 마커틀을 세그먼트하여 관절각의 2차원 정보를 구한 다음 스테레오 기하(Stereo Geometry)를 이용하여 3차원 정보를 계산하고 가상 공간상에서 인간의 움직임을 추적하는 방법을 제안한다. 제안하는 방법은 제스쳐 인식과 3차원 Virtual Reality 인터페이스 시스템 구성 등에 사용될 수 있다.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.641-644
• /
• 1999

스테레오 물체 추적기는 좌. 우측 카메라의 스테레오 입력 영상에서 이동 물체의 주시각을 제어하면서 자동으로 추적 물체가 항상 영상의 중앙에 위치하도록 제어해야 한다. 본 논문에서는 복잡한 배경이 존재하고 카메라가 움직이는 경우 스테레오 물체 추적을 위한 방법으로 블록 정합 알고리즘(BMA)으로 추적 물체와 배경을 분리하고, JTC를 이용해 주시각 및 팬/틸트 제어 값을 구하여 좌, 우측 카메라를 제어하는 스테레오 자동 물체 추적 시스템을 제시하였다. 추적결과 배경잡음에 상관없이 적응적으로 작용하여 정확히 이동 물체의 위치를 스테레오로 추적할 수 있었다.

• Proceedings of the Optical Society of Korea Conference
• /
• 2001.02a
• /
• pp.68-69
• /
• 2001

스테레오 물체 추적을 위해서는 추적 물체의 현재 위치를 추출하는 것이 선행 되어야한다. 입력된 좌측 영상과 이전 프레임에서 얻은 윈도우 마스크(window mask)의 기준 영상간에 식 (1)의 MSE 알고리즘을 적용하였다. 여기에서 윈도우 마스크의 기준 영상은 초기에만 추적을 원하는 물체를 마스크로 잡아(locking) 초기화 시켜 주면, 이후에는 스스로 계속 갱신(update)하게 된다. (중략)

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.979-980
• /
• 2011

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.6C
• /
• pp.593-603
• /
• 2009

In this paper, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with an active stereo camera. The proposed system consists of three modules: detection, tracking and silhouette extraction. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap is estimated in advance and then this was effectively incorporated into the graph cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data and it was shown to detect and track multiple people very well and also produce high quality silhouettes. The proposed system can assist in gesture and gait recognition in field of Human-Robot Interaction (HRI).

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.239-244
• /
• 2006

In this paper, we present a snake-based scheme for contour tracking of objects in stereo image sequences. We address the problem by managing the insertion of new points and deletion of unnecessary points to better describe and track the object's boundary. In particular, our method uses more points in highly curved parts of the contour, and fewer points in less curved parts. The proposed algorithm can successfully define the contour of the object, and can track the contour in complex images. Furthermore, we tested our algorithm in the presence of partial object occlusion. Performance of the proposed algorithm has been verified by simulation.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2262-2270
• /
• 1999

In this paper, we describe gesture recognition algorithm using computer vision sensor and HMM. The automatic hand region extraction has been proposed for initializing the tracking of the tele-operation gestures. For this, distance informations(disparity map) as results of stereo matching of initial left and right images are employed to isolate the hand region from a scene. PDOE(positive difference of edges) feature images adapted here have been found to be robust against noise and background brightness. The KNU/KAERI(K/K) gesture instruction set is defined for tele-operation in atomic electric power stations. The composite recognition model constructed by concatenating three gesture instruction models including pre-orders, basic orders, and post-orders has been proposed and identified by discrete HMM. Our experimental results showed that consecutive orders composed of more than two ones are correctly recognized at the rate of above 97%.

• Journal of Biosystems Engineering
• /
• v.37 no.1
• /
• pp.65-74
• /
• 2012

Purpose: An autonomous robot was developed for harvesting strawberries cultivated in bench-type systems. Methods: The harvest robot consisted of four main components: an autonomous vehicle, a manipulator with four degrees of freedom (DOF), an end effector with two DOFs, and a color computer vision system. Strawberry detection was performed based on 3D image and distance information obtained from a stereo CCD color camera and a laser device, respectively. Results: In this work, a Cartesian type manipulator system was designed, including an intermediate revolute axis and a double driven arm-based joint axis, so that it could generate collision-free motions during harvesting. A DC servomotor-driven end-effector, consisting of a gripper and a cutter, was designed for gripping and cutting the strawberry stem without damaging the strawberry itself. Real-time position tracking algorithms were developed to detect, recognize, trace, and approach strawberries under natural light conditions. Conclusion: The developed robot system could harvest a strawberry within 7 seconds without damage.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.1
• /
• pp.8-16
• /
• 2016

In the field of computer vision and robotics, bin picking is an important application area in which object pose estimation is necessary. Different approaches, such as 2D feature tracking and 3D surface reconstruction, have been introduced to estimate the object pose accurately. We propose a new approach where we can use both 2D image features and 3D surface information to identify the target object and estimate its pose accurately. First, we introduce a label detection technique using Maximally Stable Extremal Regions (MSERs) where the label detection results are used to identify the target objects separately. Then, the 2D image features on the detected label areas are utilized to generate 3D surface information. Finally, we calculate the 3D position and the orientation of the target objects using the information of the 3D surface.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.3
• /
• pp.51-59
• /
• 2012

This paper suggests an efficient method which tracks articulated human body modeled with markov network using disparity map derived from stereo images. The conventional methods which only use color information to calculate likelihood for energy function tend to fail when background has same colors with objects or appearances of object are changed during the movement. In this paper, we present a method evaluating likelihood with both disparity information and color information to find human body parts. Since the human body part are cylinder projected to rectangles in 2D image plane, we use the properties of distribution of disparity of those rectangles that do not have discontinuous distribution. In addition to that we suggest a conditional-messages-update that is able to reduce unnecessary message update of belief propagation. Since the message update has comprised over 80% of the whole computation in belief propagation, the conditional-message-update yields 9~45% of improvements of computational time. Furthermore, we also propose an another speed up method called three dimensional dynamic models assumed the body motion is continuous. The experiment results show that the proposed method reduces the computational time as well as it increases tracking accuracy.