• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.24 no.6
• /
• pp.703-709
• /
• 2015

In this work, a robot aimed at grapping and delivering an object by using a simple finger-pointing command from a hand- or arm-handicapped person is introduced. In this robot system, a Leap Motion sensor is utilized to obtain the finger-motion data of the user. In addition, a Kinect sensor is also used to measure the 3D (Three Dimensional)-position information of the desired object. Once the object is pointed at through the finger pointing of the handicapped user, the exact 3D information of the object is determined using an image processing technique and a coordinate transformation between the Leap Motion and Kinect sensors. It was found that the information obtained is transmitted to the robot controller, and that the robot eventually grabs the target and delivers it to the handicapped person successfully.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.670-678
• /
• 2014

This paper presents a method to extract objects in radiographic images where all the allowable combinations of segmented regions are compared to a target object using Fourier descriptor. In the object extraction for usual images, a main problem is occlusion. In radiographic images, there is an advantage that the shape of an object is not occluded by other objects. It is because radiographic images represent the amount of radiation penetrated through objects. Considering the property of no occlusion in radiographic images, the shape based descriptors can be very effective to find objects. After all, the proposed object extraction method consists of three steps of segmenting regions, finding all the combinations of the segmented regions, and matching the combinations to the shape of the target object. In finding the combinations, we reduce a lot of computations to remove unnecessary combinations before matching. In matching, we employ Fourier descriptor so that the proposed method is rotation and shift invariant. Additionally, shape normalization is adopted to be scale invariant. By experiments, we verify that the proposed method works well in extracting objects.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.1
• /
• pp.96-107
• /
• 2014

Tracking the tactical object is a fundamental affair in network-equipped modern warfare. Geodetic coordinate system based on longitude, latitude, and height is suitable to represent the location of tactical objects considering multi platform data fusion. The motion of tactical object described as a dynamic model requires an appropriate filtering to overcome the system and measurement noise in acquiring information from multiple sensors. This paper introduces the filter suitable for multi-sensor data fusion and tactical object tracking, particularly the unscented transform(UT) and its detail. The UT in Unscented Kalman Filter(UKF) uses a few samples to estimate nonlinear-propagated statistic parameters, and UT has better performance and complexity than the conventional linearization method. We show the effects of UT-based filtering via simulation considering practical tactical object tracking scenario.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.48 no.6
• /
• pp.456-461
• /
• 1999

In this study, the characteristics of Ultrasonic Transducer fabricated with PZT-Polymer 1-3 type piezoelectric ceramic/polymer composite are investigated. 3-D underwater object restoration using the self-made ultrasonic transducer and modified SCL(Simple Competitive Learning) neural network was presented. The ultrasonic transducer was satisfied with the required condition of commerical ultrasonic transducer in underwater. The modified SCL neural network using the acquired object data $16\times16$ low resolution image was used for object restoration of $32\times32$ high resolution image. The experimental results have shown that the ultrasonic transducer fabricated with PZT-Polymer 1-3 type piezoelectric ceramic/polymer composite could be applied for SONAR system.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2007.05a
• /
• pp.231-232
• /
• 2007

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.957-960
• /
• 2007

The construction information used in the design and construction phases are being gradually changed by 3D objects based on virtual reality (VR). This study developed an algorithm and computerized system to visualize layer object simulation that can be used in the pre-design phase. Layer object simulation enables designer to review expecting problems, which can reappear in real construction site, by building construction structures in a VR system. This function can be used as an important tool of virtual construction system.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.4 no.2
• /
• pp.46-60
• /
• 2001

This study proposes the Web-based GIS system based on distributed object management and conceptualise system architecture and its methods specifications through UML(unified modeling language). By using class diagram and creating prototype based on UML and reverse engineering, our conceptual shape file model is proposed to illustrate an integrated architecture. Through system analysis and software configuration management, this study enables to not only improve pliable capabilities for problematic domains and increase abilities for analytical domains when user requirements are dynamic, but also assist effective and consistent maintenances of large software systems.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11c
• /
• pp.2277-2280
• /
• 2002

1995년 이후 NGIS(National Geographic Information System) 사업의 시작과 함께 활성화되기 시작한 GIS는 1990 년대 말 인터넷의 급속한 보급으로 인하여 비약적인 발전을 거듭하였다. 최근에는 무선 인터넷의 확산과 함께 모바일 GIS가 등장하였으며, OGC(Open GIS Consortium)에서는 효율적인 지리정보의 저장과 전달을 위해 GML(Geographic Markup Language)을 제안하였다. 본 논문에서는 GVM(General Virtual Machine)기반의 모바일 디바이스에서 GML 문서를 처리하기 위한 XML 파서와 맵매니저(MapManager)를 설계하고 구현하였다. XML 파서는 서버로부터 GML문서를 다운로드 받아서 파싱과정을 거쳐서 DOM(Document Object Model)형태의 자료구조를 생성한다. 맵매니저는 DOM 구조를 입력으로 받아서 모바일 디바이스의 화면에 지도를 표시하고, 사용자 상호작용을 처리한다.

• Journal of Korean Neurosurgical Society
• /
• v.66 no.1
• /
• pp.53-62
• /
• 2023

Objective : Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability. Methods : A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm's diagnostic performance. Results : In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anterior-posterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor. Conclusion : The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.