• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.302-305
• /
• 1996

This paper presents a visual servoing combined by Neural Network with optimal structure and predictive control for robotic manipulators to tracking or grasping of the moving object. Using the four feature image information from CCD camera attached to end-effector of RV-M2 robot manipulator having 5 dof, we want to predict the updated position of the object. The Kalman filter is used to estimate the motion parameters, namely the state vector of the moving object in successive image frames, and using the multi layer feedforward neural network that permits the connection of other layers, evolutionary programming(EP) that search the structure and weight of the neural network, and evolution strategies(ES) which training the weight of neuron, we optimized the net structure of control scheme. The validity and effectiveness of the proposed control scheme and predictive control of moving object will be verified by computer simulation.

• Journal of Advanced Marine Engineering and Technology
• /
• v.30 no.3
• /
• pp.428-437
• /
• 2006

This paper attempts to derive and analyze the dynamic system of grasping a rigid object by means of two multi-degrees-of-freedom robot flngers with soft and deformable tips. It is shown firstly that a set of differential equation describing dynamics system of the manipulators and object together with geometric constraint of tight area-contacts is formulated by Lagrange's equation. It is shown secondly that the problems of controlling both the forces of pressing object and the rotation angle of the object under the geometric constraints are discussed. In this paper. the control method for dynamic stable grasping and enhancing dexterity in manipulating things is proposed. It is illustrated by computer simulation that the control system gives the performance improvement in the dynamic stable grasping of the dual fingers robot with soft tips.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.1
• /
• pp.25-33
• /
• 1998

This paepr presents an algorithm for searching an object in a fast way which contains a continuous moving object in multi-dimensional spatical databases. This algorithm improves the search method of R-tree for the case that a target object is continuously moving in a spatial database. It starts the searching from the current node instead of the root of R-tree. Thus, the algorithm will find the target object from the entries of current node or sibling nodes in the most cases. The performance analysis shows that it is more efficient than the existing algorithm for R-tree when search windows or target objects are continuously moving.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10c
• /
• pp.239-242
• /
• 2007

본 논문에서는 다수의 저가형 웹캠(Web Cam)으로 촬영된 다각도의 다중 영상을 입력으로 받아 이들을 자연스럽게 연결하여 임의의 각도에서 물체의 모습을 관찰할 수 있도록 하는 ${\ulcorner}$다중 카메라 촬영 영상을 이용한 Object Movie 생성 기반 기술${\lrcorner}$을 제안한다. 기존 Object Movie 생성도구들이 다중의 이미지들을 스티칭(stiching)하기 위해 정확한 카메라의 위치와 방향을 요구하는 데 비해, 제안된 방법은 고가의 트랙장비를 사용하기 어려운 경우에 다수의 저가형 웹캠으로 촬영된 카메라의 위치와 방향을 보정하는 단계를 추가하여 트랙장비를 사용한 것과 같은 매끄러운 영상을 생성할 수 있도록 하였다.

• Journal of the Korean Society of Industry Convergence
• /
• v.18 no.4
• /
• pp.231-240
• /
• 2015

In this paper, it was presented to design and analyze the kinematics of grasping a rigid object by means of multi-degrees-of-freedom hand fingers. It is shown firstly that a set of kinematic equation describing dynamics system of the arm and object together with geometric constraint of tight area-contacts is formulated by Lagrange's equation. It has been presented secondly that the problems of controlling both the forces of pressing object and the rotation angle of the object under the geometric constraints are discussed. In this research, the control method for static stable grasping and enhancing dexterity in manipulating things is proposed. It is illustrated by computer simulation that the control system gives the performance improvement in the kinematic grasping of the hand fingers of robot.

• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.2
• /
• pp.54-62
• /
• 2001

In this paper, we proposed multimedia based ExamBank system in web environments. In the proposed system the database was designed based on the object-relation model and the application program was implemented with Java such that independent execution would be possible to guarantee no fault for multi-client in Web environments. We defined the Exam entities as objects, and implemented those inter-relationships as user definition and type. In addition, by mapping the schema object of DBMS and JAVA class, it becomes to possible transferring the object systematically between DHMS and JAVA application server.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1268-1271
• /
• 2003

In the edge detection of RS image, the useful detail losing and the spurious edge often appear. To solve the problem, we use the dyadic wavelet to detect the edge of surface features by combining the edge detecting with the multi-resolution analyzing of the wavelet transform. Via the dyadic wavelet decomposing, we obtain the RS image of a certain appropriate scale, and figure out the edge data of the plane and the upright directions respectively, then work out the grads vector module of the surface features, at last by tracing them we get the edge data of the object therefore build the RS image which obtains the checked edge. This method can depress the effect of noise and examine exactly the edge data of the object by rule and line. With an experiment of a RS image which obtains an airport, we certificate the feasibility of the application of dyadic wavelet in the object edge detection.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.3
• /
• pp.113-116
• /
• 2018

This paper proposes a mobile image search system which uses a sensor information of smart phone, and enables running in a variety of environments, which is implemented on Android platform. The implemented system deals with a new image descriptor using combination of the visual feature (CEDD) with EXIF attributes in the target of JPEG image, and image matching scheme, which is optimized to the mobile platform. Experimental result shows that the proposed method exhibited a significant improved searching results of around 80% in precision in the large image database. Considering the performance such as processing time and precision, we think that the proposed method can be used in other application field.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.46.2-46.2
• /
• 2021

We present solar event auto detection using deep-learning-based object detection algorithms and DeepSDO event dataset. DeepSDO event dataset is a new detection dataset with bounding boxed as ground-truth for three solar event (coronal holes, sunspots and prominences) features using Solar Dynamics Observatory data. To access the reliability of DeepSDO event dataset, we compared to HEK data. We train two representative object detection models, the Single Shot MultiBox Detector (SSD) and the Faster Region-based Convolutional Neural Network (R-CNN) with DeepSDO event dataset. We compared the performance of the two models for three solar events and this study demonstrates that deep learning-based object detection can successfully detect multiple types of solar events. In addition, we provide DeepSDO event dataset for further achievements event detection in solar physics.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.307-322
• /
• 2024

Most object detection methods use a horizontal bounding box that causes problems between adjacent objects with arbitrary directions, resulting in misaligned detection. Hence, the horizontal anchor should be replaced by a rotating anchor to determine oriented bounding boxes. A two-stage process of delineating a horizontal bounding box and then converting it into an oriented bounding box is inefficient. To improve detection, a box-boundary-aware vector can be estimated based on a convolutional neural network. Specifically, we propose a ResNeXt101 encoder to overcome the weaknesses of the conventional ResNet, which is less effective as the network depth and complexity increase. Owing to the cardinality of using a homogeneous design and multi-branch architecture with few hyperparameters, ResNeXt captures better information than ResNet. Experimental results demonstrate more accurate and faster oriented object detection of our proposal compared with a baseline, achieving a mean average precision of 89.41% and inference rate of 23.67 fps.