• The Journal of Korea Robotics Society
• /
• v.4 no.3
• /
• pp.185-191
• /
• 2009

This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship betweenfeatures, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.6
• /
• pp.3735-3742
• /
• 2013

Background: Cardamom (Elettaria cardamom), also known as "Queen of Spices", has been traditionally used as a culinary ingredient due to its pleasant aroma and taste. In addition to this role, studies on cardamom have demonstrated cancer chemopreventive potential in in vitro and in vivo systems. Nevertheless, the precise poly-pharmacological nature of naturally occurring chemo-preventive compounds in cardamom has still not been fully demystified. Methods:In this study, an effort has been made to identify the proapoptopic, anti-inflammatory, anti-proliferative, anti-invasive and anti-angiogenic targets of Cardamom's bioactive principles (eucalyptol, alpha-pinene, beta-pinene, d-limonene and geraniol) by employing a dual reverse virtual screening protocol. Experimentally proven target information of the bioactive principles was annotated from bioassay databases and compared with the virtually screened set of targets to evaluate the reliability of the computational identification. To study the molecular interaction pattern of the anti-tumor action, molecular docking simulation was performed with Auto Dock Pyrx. Interaction studies of binding pose of eucalyptol with Caspase 3 were conducted to obtain an insight into the interacting amino acids and their inter-molecular bondings. Results:A prioritized list of target proteins associated with multiple forms of cancer and ranked by their Fit Score (Pharm Mapper) and descending 3D score (Reverse Screen 3D) were obtained from the two independent inverse screening platforms. Molecular docking studies exploring the bioactive principle targeted action revealed that H- bonds and electrostatic interactions forms the chief contributing factor in inter-molecular interactions associated with anti-tumor activity. Eucalyptol binds to the Caspase 3 with a specific framework that is well-suited for nucleophilic attacks by polar residues inside the Caspase 3 catalytic site. Conclusion:This study revealed vital information about the poly-pharmacological anti-tumor mode-of-action of essential oils in cardamom. In addition, a probabilistic set of anti-tumor targets for cardamom was generated, which can be further confirmed by in vivo and in vitro experiments.

• Journal of Animal Environmental Science
• /
• v.8 no.3
• /
• pp.171-176
• /
• 2002

Physical parameters of milk cow were measured to design and build RMS(Robotic Milking System) with a tape-measurer and body parameter measurer. The parameters are very important variables to design an RMS. For the working zone space of an RMS manipulator and the movement blunting of milk cow, an interval frame was installed on the stall bottom, and then cow's behavioral reactions were tested. The results from this study is summarized as follow. 1. On the general physical condition measurement, the maximum, minimum and average body length of cow which is related to the space that the manipulator could work into the RMS were 175cm, 144cm, and 163cm respectively. It appeared that the average distance between bottom and chest was 60cm. 2. The average length between fore teats, fore and hind teats and hind teats were 178mm, 150mm and 95mm respectively. It appeared that the average length between bottom and teat attachments was 544mm, and the average length between fore teats and tail-end was 331mm. 3. Although a cow kept a some extent length between hind legs for milking, it looked a stable pose. However, the cow kept a some extent distance between front legs for milking, it looked a unstable pose. Based on results of this test, an interval frame of stall bottom should be installed around the position which was located at its hind legs.

• Advances in robotics research
• /
• v.2 no.1
• /
• pp.45-57
• /
• 2018

Even though the popularity of projection mapping continues to increase and it is being implemented in more and more settings, most current projection mapping systems are limited to special purposes, such as outdoor events, live theater and musical performances. This lack of versatility arises from the large number of projectors needed and their proper calibration. Furthermore, we cannot change the positions and poses of projectors, or their projection targets, after the projectors have been calibrated. To overcome these problems, we propose a projection mapping method using a projector robot that can perform projection mapping in more general or ubiquitous situations, such as shopping malls. We can estimate a projector's position and pose with the robot's self-localization sensors, but the accuracy of this approach remains inadequate for projection mapping. Consequently, the proposed method solves this problem by combining self-localization by robot sensors with position and pose estimation of projection targets based on a 3D model. We first obtain the projection target's 3D model and then use it to accurately estimate the target's position and pose and thus achieve accurate projection mapping with a projector robot. In addition, our proposed method performs accurate projection mapping even after a projection target has been moved, which often occur in shopping malls. In this paper, we employ Ubiquitous Display (UD), which we are researching as a projector robot, to experimentally evaluate the effectiveness of the proposed method.

• 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.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.486-492
• /
• 2006

본 논문에서는 비디오에서의 특징점 추적을 통해 얻은 2D 좌표를 이용한 3D 구조를 추정하는 방법과 네 점 이상의 공통점을 이용한 융합 방법을 제안한다. 영상의 각 프레임에서 공통되는 특징점을 이용하여 형상을 추정한다. 영상의 각 프레임에 대한 특징점의 추적은 Lucas-Kanade 방법을 사용하였다. 3D 좌표 추정 방법으로 개선된 직교분해기법을 사용하였다. 개선된 직교분해기법에서는 3D 좌표를 복원함과 동시에 카메라의 위치와 방향을 계산할 수 있다. 복원된 부분 데이터들은 전체를 이루는 일부분이므로, 융합을 통해 완성된 모습을 만들 수 있다. 복원된 부분 데이터들의 서로 다른 좌표계를 기준 좌표계로 변환함으로써 융합할 수 있다. 융합은 카메라의 모션에 해당하는 카메라의 위치와 방향에 의존된다. 융합 과정은 모두 선형으로 평균 0.5초 이하의 수행 속도를 보이며 융합의 오차는 평균 0.1cm 이하의 오차를 보였다.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.504-511
• /
• 2016

3D simulation programs or games on a smart phone and a personal computer have often employed 3D graphic processing techniques and 3D graphical views. However, the user interfaces in those 3D programs have sticked to take a typical 2D style user interface and thus the combination of a 2D user interface view and a 3D simulation view give us a mismatched sense. Since a 2D user interface has been based on the windows controls, it causes sometime DC conflicts between a simulation view and an interface view. Therefore, we will implement the UI developing tool which can be inserted into the pipeline structure for the development of a 3D simulation software and also follows the view-handler design pattern in Microsoft windows system. It will provide various graphical effects such as the deformation of UI depending on the view direction of simulation view and the sitting pose of user. This developing tool gives the natural user interface which heightens the sense of unity with a given 3D simulation view.

• Journal of Broadcast Engineering
• /
• v.25 no.7
• /
• pp.1095-1106
• /
• 2020

In this paper, we propose an algorithm that extracts a high-precision 3D skeleton using a model generated using a distributed RGB-D camera. When information about a 3D model is extracted through a distributed RGB-D camera, if the information of the 3D model is used, a skeleton with higher precision can be obtained. In this paper, in order to improve the precision of the 2D skeleton, we find the conditions to obtain the 2D skeleton well using the PCA. Through this, high-quality 2D skeletons are obtained, and high-precision 3D skeletons are extracted by combining the information of the 2D skeletons. Even though this process goes through, the generated skeleton may have errors, so we propose an algorithm that removes these errors by using the information of the 3D model. We were able to extract very high accuracy skeletons using the proposed method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.4
• /
• pp.674-679
• /
• 2006

In this paper a gesture recognition system using 3D feature data is described. The system relies on a novel 3D sensor that generates a dense range mage of the scene. The main novelty of the proposed system, with respect to other 3D gesture recognition techniques, is the capability for robust recognition of complex hand postures such as those encountered in sign language alphabets. This is achieved by explicitly employing 3D hand features. Moreover, the proposed approach does not rely on colour information, and guarantees robust segmentation of the hand under various illumination conditions, and content of the scene. Several novel 3D image analysis algorithms are presented covering the complete processing chain: 3D image acquisition, arm segmentation, hand -forearm segmentation, hand pose estimation, 3D feature extraction, and gesture classification. The proposed system is tested in an application scenario involving the recognition of sign-language postures.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.9
• /
• pp.745-752
• /
• 2016

We suggest an efficient Simultaneous Localization and 3D Polygon Map Building (SLAM) method with Kinect depth sensor for mobile robots in indoor environments. In this method, Kinect depth data is separated into row planes so that scan line segments are on each row plane. After grouping all scan line segments from all row planes into line groups, a set of 3D Scan polygons are fitted from each line group. A map matching algorithm then figures out pairs of scan polygons and existing map polygons in 3D, and localization is performed to record correct pose of the mobile robot. For 3D map-building, each 3D map polygon is created or updated by merging each matched 3D scan polygon, which considers scan and map edges efficiently. The validity of the proposed 3D SLAM algorithm is revealed via experiments.