• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.74.2-74
• /
• 2001

The availability of endoscope has been increased not only for observing inner parts of body but also for operating. Nowdays, the market of the endoscope has been widely extended and we presume that the value of marketablity will reach to wide. Most of the endoscope equipment is very expensive and as well, it costs a lot to repair or change the specific parts of equipment when it´s out of order on account of carelessness. About 90 percent of the endoscope equipment in the world is made in Japan. Therefore, to buy or repair the equipment, we can´t help outflowing foreign currency. In domestic, the efforts for localization and manufacturing the endoscope equipment are short. This paper shows that captured image from a CCD miniature carema is managed ...

• Journal of Internet Computing and Services
• /
• v.18 no.6
• /
• pp.85-92
• /
• 2017

Recently, in the field of video surveillance, a Deep Learning based learning method has been applied to a method of detecting a moving person in a video and analyzing the behavior of a detected person. The human activity recognition, which is one of the fields this intelligent image analysis technology, detects the object and goes through the process of detecting the body keypoint to recognize the behavior of the detected object. In this paper, we propose a method for Body Keypoint Localization based on Object Detection using RGB-D information. First, the moving object is segmented and detected from the background using color information and depth information generated by the two cameras. The input image generated by rescaling the detected object region using RGB-D information is applied to Convolutional Pose Machines for one person's pose estimation. CPM are used to generate Belief Maps for 14 body parts per person and to detect body keypoints based on Belief Maps. This method provides an accurate region for objects to detect keypoints an can be extended from single Body Keypoint Localization to multiple Body Keypoint Localization through the integration of individual Body Keypoint Localization. In the future, it is possible to generate a model for human pose estimation using the detected keypoints and contribute to the field of human activity recognition.

• Transactions of the Korean hydrogen and new energy society
• /
• v.31 no.6
• /
• pp.509-521
• /
• 2020

This study aims to propose a mid- to long-term fostering plan for the hydrogen industry customized to Changwon City by reviewing the government's policy and the status of the domestic and foreign hydrogen industry. The adopted methodologies were policy analysis, literature review, field investigation, and committee operation that could consider institutions, knowledge (technology), and networking between activity subjects. The short-term projects and long-term projects for the fostering plan are established using these methodologies. The short-term projects were structured so that the ongoing hydrogen industry fostering plan leads to a successful result, and the hydrogen mobility field is expanded to not only land vehicles but also marine and air vehicles. The long-term projects consist of a high proportion of the hydrogen utilization field to take advantage of the industrial strength of Changwon City, and a support system for new and turning companies for localization of parts was added to provide industrial competitiveness.

• Korean Journal of Veterinary Research
• /
• v.33 no.3
• /
• pp.361-368
• /
• 1993

The midbrain periaqueductal gray is a midline structure that encircles the mesencephalic aqueduct of midbrain and plays an important role in anaglgesia and modulation of nociceptive input to the central nervous system. It has been demonstrated that the periaqueductal gray contains several neuropeptides including neurotensin, which has been postulated antinociceptive effect to the periaqueductal gray. The present study was performed to provide immunohistochemical localization of neurotensin of midbrain periaqueductal gray in the Korean native goat by using immunohistochemical method. Neurotensin-like immunireactive neurons were localized throughout the midbrain periaqueductal gray, although more immunoreactive neurons were present in the middle and caudal parts of periaquductal gray than the rostral part. Dense neurotensin-like immunoreactive neurons were much more numerous in the ventral lateral division of the mid- and caudal periaqueductal grays. Neurotensin-like immunoreactive neurons were much larger and more prominent near the external margin of the gray than in the juxta-aqueductal region. Neurotensin-like immunoreactive fibers were observed as short processes extending from immunoreactive cells and some small immunoreactive puncta and varicose-like fibers were also seen.

• Journal of Aerospace System Engineering
• /
• v.13 no.1
• /
• pp.54-61
• /
• 2019

The 3D printing technology took the second place within the top ten rising technologies at the World Economic Forum in 2012. It arose as a core technology that would enable transformation in the manufacturing industry and develop new markets through the change of existing industry paradigms. Leading countries, like the United States of America, are actively expanding the use of 3D printing technologies within their defense areas. In order to utilize the technology within her defense areas, the Republic of Korea is planning to acquire defense spare parts manufacturing technologies and nurture professional defense personnel specializing in the 3D printing technology. Hence, this study offers various methods to efficiently apply reliable 3D printing spare parts to operation fields in the future by utilizing spare parts localization development management methods within existing weapon systems' development, manufacturing and sustainment phases.

• Journal of Korea Multimedia Society
• /
• v.11 no.12
• /
• pp.1658-1667
• /
• 2008

Reconstruction of 3D objects from a single view image is generally an ill-posed problem because of the projection distortion. A monocular vision based 3D object localization method is proposed in this paper, which approximates an object on the ground to a simple bounding solid and works automatically without any prior information about the object. A spherical or cylindrical object determined based on a circularity measure is approximated to a bounding cylinder, while the other general free-shaped objects to a bounding box or a bounding cylinder appropriately. For a general object, its silhouette on the ground is first computed by back-projecting its projected image in image plane onto the ground plane and then a base rectangle on the ground is determined by using the intuition that touched parts of the object on the ground should appear at lower part of the silhouette. The base rectangle is adjusted and extended until a derived bounding box from it can enclose the general object sufficiently. Height of the bounding box is also determined enough to enclose the general object. When the general object looks like a round-shaped object, a bounding cylinder that encloses the bounding box minimally is selected instead of the bounding box. A bounding solid can be utilized to localize a 3D object on the ground and to roughly estimate its volume. Usefulness of our approach is presented with experimental results on real image objects and limitations of our approach are discussed.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.5
• /
• pp.597-608
• /
• 2021

The control head components used in small military vessels are designed to be domestically produced, prototypes, structural analysis, and casting methods are designed and cast. The control head assembly consists of a lever, an aluminum outside cover, Middle, front gear cover, back gear cover, and a zinc worm gear. In order to reverse the design of each component, 3D scanning device was used, 3D modeling was performed by CATIA, and prototype productions were carried out by 3D printer. In order to reduce the cost of components, gating system is used by gravity casting method. The SRG ratio of 1:0.9:0.6 was set by applying non-pressurized gating system to aluminum parts, 1:2.2:2.0 and pressurized gating system to zinc parts, and the shapes of sprue, runner and gate were designed. The results of porosity were also confirmed by casting analysis in order to determine whether the appropriate gating system can be designed. The results showed that all parts started solidification after filling completely. ANSYS was used for structural analysis, and the results confirmed that all five components had a safety factor of 15 more. All castings are free of defects in appearance, and CT results show only very small porosity. ZnDC1 zinc alloy worm gear has a tensile strength of 285 MPa and an elongation of 8%. The tensile strength of the four components of A356 aluminum alloy is about 137-162 MPa and the elongation is 4.8-6.5%.

• Journal of Aerospace System Engineering
• /
• v.17 no.4
• /
• pp.95-103
• /
• 2023

Aircraft engine parts repair is a field belonging to the lowest level in the hierarchy of the aircraft industry, and it is marginalized in terms of research, compared to aircraft manufacturing or maintenance that belong to the upper level. On the other hand, in 2019, Korean Air's Powerplant Maintenance Center paid USD $130 million to foreign countries for engine parts repair, making it an industry with great need for localization. To achieve the goal of localizing engine parts repair, a certification system is needed that can perform independent repairs based on the development of repair technology, aligning contractual relationships with engine manufacturers, and free from dependence on engine manufacturers or foreign repair companies. The purpose of this study is to provide a basis for subsequent research to secure an actual certification system by suggesting the need for securing such a certification system.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2006.06a
• /
• pp.251-257
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization)and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architecture II, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortion

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.113-121
• /
• 2020

Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.