• Journal of Broadcast Engineering
• /
• v.1 no.2
• /
• pp.176-187
• /
• 1996

This paper deals with the accurate estimation of 3- D pose (position and orientation) of a moving object with reference to the world frame (or robot base frame), based on a sequence of stereo images taken by cameras mounted on the end - effector of a robot manipulator. This work is an extension of the previous work[1]. Emphasis is given to the 3-D pose estimation relative to the world (or robot base) frame under the presence of not only the measurement noise in 2 - D images[ 1] but also the camera position errors due to the random noise involved in joint angles of a robot manipulator. To this end, a new set of discrete linear Kalman filter equations is derived, based on the following: 1) the orientation error of the object frame due to measurement noise in 2 - D images is modeled with reference to the camera frame by analyzing the noise propagation through 3- D reconstruction; 2) an extended Jacobian matrix is formulated by combining the result of 1) and the orientation error of the end-effector frame due to joint angle errors through robot differential kinematics; and 3) the rotational motion of an object, which is nonlinear in nature, is linearized based on quaternions. Motion parameters are computed from the estimated quaternions based on the iterated least-squares method. Simulation results show the significant reduction of estimation errors and also demonstrate an accurate convergence of the actual motion parameters to the true values.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.155-166
• /
• 2012

This paper proposes a new method of estimating the hand pose through the Mean-Shift tracking algorithm using the fusion of color and depth information for marker-less augmented reality. On marker-less augmented reality, the most of previous studies detect the hand region using the skin color from simple experimental background. Because finger features should be detected on the hand, the hand pose that can be measured from cameras is restricted considerably. However, the proposed method can easily detect the hand pose from complex background through the new Mean-Shift tracking method using the fusion of the color and depth information from 3D sensor. The proposed method of estimating the hand pose uses the gravity point and two random points on the hand without largely constraints. The proposed Mean-Shift tracking method has about 50 pixels error less than general tracking method just using color value. The augmented reality experiment of the proposed method shows results of its performance being as good as marker based one on the complex background.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.44-55
• /
• 2022

In order to automatically provide information on fruits in agricultural related broadcasting contents, instance image segmentation of target fruits is required. In addition, the information on the 3D pose of the corresponding fruit may be meaningfully used. This paper represents research that provides information about tomatoes in video content. A large amount of data is required to learn the instance segmentation, but it is difficult to obtain sufficient training data. Therefore, the training data is generated through a data augmentation technique based on a small amount of real images. Compared to the result using only the real images, it is shown that the detection performance is improved as a result of learning through the synthesized image created by separating the foreground and background. As a result of learning augmented images using images created using conventional image pre-processing techniques, it was shown that higher performance was obtained than synthetic images in which foreground and background were separated. To estimate the pose from the result of object detection, a point cloud was obtained using an RGB-D camera. Then, cylinder fitting based on least square minimization is performed, and the tomato pose is estimated through the axial direction of the cylinder. We show that the results of detection, instance image segmentation, and cylinder fitting of a target object effectively through various experiments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.1
• /
• pp.30-37
• /
• 2021

Accurate 3D object tracking with camera images is a key enabling technology for augmented reality applications. Motivated by the impressive success of convolutional neural networks (CNNs) in computer vision tasks such as image classification, object detection, image segmentation, recent studies for 3D object tracking have focused on leveraging deep learning. In this paper, we review deep learning approaches for 3D object tracking. We describe key methods in this field and discuss potential future research directions.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.71-74
• /
• 2022

본 논문은 최적화알고리즘을 이용한 관절각 기반 3차원 자세 추정 기법의 정확도를 휴머노이드 로봇을 이용하여 검증하는 방법을 제안한다. 구글의 자세 추정 오픈소스 패키지인 MPP(MediaPipe Pose)로 특정자세를 취한 휴머노이드 로봇의 관절 좌표를 카메라의 픽셀 좌표로 추출한다. 추출한 픽셀 좌표를 전역최적화 방법인 uDEAS(univariate Dynamic Encoding Algorithm for Searches)를 통해 시상면과 관상면에서의 각도를 추정하고 휴머노이드 로봇의 실제 관절 각도와 비교하여 알고리즘의 정확도를 검증하는 방법을 제시한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.187-194
• /
• 2015

In this paper, we present an effective visual odometry estimation system to track the real-time pose of a camera moving in 3D space. In order to meet the real-time requirement as well as to make full use of rich information from color and depth images, our system adopts a feature-based sparse odometry estimation method. After matching features extracted from across image frames, it repeats both the additional inlier set refinement and the motion refinement to get more accurate estimate of camera odometry. Moreover, even when the remaining inlier set is not sufficient, our system computes the final odometry estimate in proportion to the size of the inlier set, which improves the tracking success rate greatly. Through experiments with TUM benchmark datasets and implementation of the 3D scene reconstruction application, we confirmed the high performance of the proposed visual odometry estimation method.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.5
• /
• pp.417-428
• /
• 2017

In this paper, we describe the architectural design, unit component hardware design and core software design(Helmet Pose Tracking Software and Terrain Elevation Data Correction Software) of IHDS(Intelligent Helmet Display System), and describe the results of unit test and integration test. According to the trend of the latest helmet display system, the specifications which includes 3D map display, FLIR(Forward Looking Infra-Red) display, hybrid helmet pose tracking, visor reflection type of binocular optical system, NVC(Night Vision Camera) display, lightweight composite helmet shell were applied to the design. Especially, we proposed unique design concepts such as the automatic correction of altitude error of 3D map data, high precision image registration, multi-color lighting optical system, transmissive image emitting surface using diffraction optical element, tracking camera minimizing latency time of helmet pose estimation and air pockets for helmet fixation on head. After completing the prototype of all system components, unit tests and system integration tests were performed to verify the functions and performance.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.2
• /
• pp.1-11
• /
• 2014

The quality of 2D-to-3D conversion depends on the accuracy of the assigned depth to scene objects. Manual depth painting for given objects is labor intensive as each frame is painted. Specifically, a human is one of the most challenging objects for a high-quality conversion, as a human body is an articulated figure and has many degrees of freedom (DOF). In addition, various styles of clothes, accessories, and hair create a very complex silhouette around the 2D human object. We propose an efficient method to estimate visually pleasing depths of a human at every frame in a monocular video. First, a 3D template model is matched to a person in a monocular video with a small number of specified user correspondences. Our pose estimation with sequential joint angular constraints reproduces a various range of human motions (i.e., spine bending) by allowing the utilization of a fully skinned 3D model with a large number of joints and DOFs. The initial depth of the 2D object in the video is assigned from the matched results, and then propagated toward areas where the depth is missing to produce a complete depth map. For the effective handling of the complex silhouettes and appearances, we introduce a partial depth propagation method based on color segmentation to ensure the detail of the results. We compared the result and depth maps painted by experienced artists. The comparison shows that our method produces viable depth maps of humans in monocular videos efficiently.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.373-380
• /
• 2022

This paper considers a method of fast correspondence matching for iterative closest point (ICP) algorithm. In robotics, the ICP algorithm and its variants have been widely used for pose estimation by finding the translation and rotation that best align two point clouds. In computational perspectives, the main difficulty is to find the correspondence point on the reference point cloud to each observed point. Jump-table-based correspondence matching is one of the methods for reducing computation time. This paper proposes a method that corrects errors in an existing jump-table-based correspondence matching algorithm. The criterion activating the use of jump-table is modified so that the correspondence matching can be applied to the situations, such as point-cloud registration problems with highly curved surfaces, for which the existing correspondence-matching method is non-applicable. For demonstration, both hardware and simulation experiments are performed. In a hardware experiment using Hokuyo-10LX LiDAR sensor, our new algorithm shows 100% correspondence matching accuracy and 88% decrease in computation time. Using the F1TENTH simulator, the proposed algorithm is tested for an autonomous driving scenario with 2D range-bearing point cloud data and also shows 100% correspondence matching accuracy.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.167-177
• /
• 2021

In the field of augmented reality, edge-based methods have been popularly used in tracking textureless 3D objects. However, edge-based methods are inherently vulnerable to cluttered backgrounds. Another way to track textureless or poorly-textured 3D objects is to directly align image intensity of 3D object between consecutive frames. Although the direct methods enable more reliable and stable tracking compared to using local features such as edges, they are more sensitive to occlusion and less accurate than the edge-based methods. Therefore, we propose a method that combines an edge-based method and a direct method to leverage the advantages from each approach. Experimental results show that the proposed method is much robust to both fast camera (or object) movements and occlusion while still working in real time at a frame rate of 18 Hz. The tracking success rate and tracking accuracy were improved by up to 84% and 1.4 pixels, respectively, compared to using the edge-based method or the direct method solely.