http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : ( Jihun Park ) (검색결과 395 건)
- 무료
- 기관 내 무료
- 유료
-
Object Tracking and Elimination using Level-of-Detail Canny Edge Maps
Park, Jihun Research Institute of Science and Technology HONGI 2005 Hongik Journal of Science and Technology Vol.9 No.-
We propose a simple method for tracking a nonparameterized subject contour in a single video stream with a moving camera. Then we eliminate the tracked contour object by replacing the background scene we get from other frame that is not occluded by the tracked object. Our method consists of two parts: first we track the object using LOD (Level-of-Detail) canny edge maps, then we generate background of each image frame and replace the tracked object in a scene by a background image from other frame. In order to track a contour object, LOD Canny edge maps are generated by changing scale parameters for a given image. A simple (strong) Canny edge map has the smallest number of edge pixels while the most detailed Canny edge map, Wcanny_(N) , has the largest number of edge pixels. To reduce side-effects because of irrelevant edges, we start our basic tracking by using simple (strong) Canny edges generated from large image intensity gradients of an input image, called Scanny edges. Starting from Scanny edges, we get more edge pixels ranging from simple Canny edge maps until the most detailed (weaker) Canny edge maps, called Wcanny maps along LOD hierarchy. LOD Canny edge pixels become nodes in routing, and LOD values of adjacent edge pixels determine routing costs between the nodes. We find the best route to follow Canny edge pixels favoring stronger Canny edge pixels. The first frame background scene is determined by camera motion, and other background scenes are computed from the previous background scenes.
-
Park, Jihun,Kim, Joohee,Kim, Kukjoo,Kim, So-Yun,Cheong, Woon Hyung,Park, Kyeongmin,Song, Joo Hyeb,Namgoong, GyeongHo,Kim, Jae Joon,Heo, Jaeyeong,Bien, Franklin,Park, Jang-Ung The Royal Society of Chemistry 2016 Nanoscale Vol.8 No.20
<P>Herein, we report the fabrication of a highly stretchable, transparent gas sensor based on silver nanowire-graphene hybrid nanostructures. Due to its superb mechanical and optical characteristics, the fabricated sensor demonstrates outstanding and stable performances even under extreme mechanical deformation (stable until 20% of strain). The integration of a Bluetooth system or an inductive antenna enables the wireless operation of the sensor. In addition, the mechanical robustness of the materials allows the device to be transferred onto various nonplanar substrates, including a watch, a bicycle light, and the leaves of live plants, thereby achieving next-generation sensing electronics for the 'Internet of Things' area.</P>
-
Jihun Park,Minkyung Kim,Jae-Eun Hyun 한국예방수의학회 2024 예방수의학회지 Vol.48 No.1
An ameroid constrictor (AC) was placed to occlude the shunt vessel in a dog diagnosed with a single extrahepatic portocaval shunt, and the patient showed favorable outcomes post-surgery. However, the 1-year postoperative assessment revealed that the shunt vessel was completely occluded, but the AC had migrated into the abdominal cavity. The examination of the surgically removed migrated AC revealed an internal space filled with fibrous tissues with no swelling in the casein, and notably, the key remained securely in place. This is the first veterinary medicine case in which migration of the AC without dislodgement of ameroid key was identified.
-
Deep Convolutional Neural Network Architectures for Tonal Frequency Identification in a Lofargram
Jihun Park,Dae-Jin Jung 제어·로봇·시스템학회 2021 International Journal of Control, Automation, and Vol.19 No.2
Advances in convolutional neural networks (CNNs) have driven the development of computer vision. Recent CNN architectures, such as those with skip residual connections (ResNets) or densely connected architectures (DenseNets), have facilitated backpropagation and improved the performance of feature extraction and classification. Detecting objects in underwater environments by analyzing sound navigation and ranging (sonar) signals is considered an important process that should be automated. Several previous approaches have addressed this challenge; however, there has been no in-depth study of CNN architectures that effectively analyze sonar grams. In this paper, we have presented the identification of tonal frequencies in lofargrams using recent CNN architectures. Our study includes 175 CNN models that are derived from five different CNN architectures and 35 different input patch sizes. The study results showed that the accuracy of the best model was as high as 96.2% for precision and 99.5% for recall, with an inference time of 0.184 s.
-
Contour Tracking using Modified Canny Edge Maps with Level-of-Detail
Park, Jihun Research Institute for Science & Technology, Hong- 2004 Hongik Journal of Science and Technology Vol.8 No.-
Generating motion and capturing motion of an articulated body for computer animation is a time-consuming task. We propose a simple but powerful brand-new method for tracking a nonparameterized subject contour in a single video stream with a moving camera and changing background for the purpose of video background removal to capture motion in a scene. Our method is based on level-of-detail (LOD) modified Canny edge maps and graph-based routing operations on the LOD maps. We generated modified Canny edge maps by computing intensity derivatives in a normal direction of a previous frame contour. The previous frame contour is an input to the system, and computing Canny edge maps in the contour normal have effects of removing irrelevant edges. LOD Canny edge maps are generated by changing scale parameters for a given image. A simple (strong) Canny edge map has the smallest number of edge pixels while the most detailed Canny edge map, , has the largest number of edge pixels. To reduce side-effects because of irrelevant edges, we start our basic tracking by using simple (strong) Canny edges generated from large image intensity gradients of an input image, called Scanny edges. Starting from Scanny edges, we get more edge pixels ranging from simple Canny edge maps until the most detailed (weaker) Canny edge maps, called Wcanny maps along LOD hierarchy. LOD Canny edge pixels become nodes in routing, and LOD values of adjacent edge pixels determine routing costs between the nodes. We find the best route to follow Canny edge pixels favoring stronger Canny edge pixels. If Scanny edges are disconnected, routing between disconnected parts are planned using Wcanny edges in LOD hierarchy. Our accurate tracking is based on reducing effects from irrelevant edges by selecting the stronger edge pixels, thereby relying on the current frame edge pixel as much as possible contrary to other approaches of always combining the previous contour. Our experimental results show that this tracking approach is robust enough to handle a complex-textured scene.
-
Log canonical thresholds on Gorenstein canonical del Pezzo surfaces
Park, Jihun,Won, Joonyeong Cambridge University Press 2011 Proceedings of the Edinburgh Mathematical Society Vol.54 No.1
<B>Abstract</B><P>We classify all the effective anticanonical divisors on weak del Pezzo surfaces. Through this classification we obtain the smallest number among the log canonical thresholds of effective anticanonical divisors on a given Gorenstein canonical del Pezzo surface.</P>
-
Jihun Park,Jae-Nam Lee,Lee, One-Ki Daniel,Yunmo Koo IEEE 2017 IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT - Vol.64 No.3
<P>Only a few firms possess all of the information technology (IT) resources required to compete effectively in today's dynamic business environment. Consequently, firms face critical challenges in developing their IT governance by integrating, building, and reconfiguring IT resources available internally and externally to achieve a competitive advantage. However, prior studies have mostly examined IT governance only from an internal (e.g., IT organization design) or external (e.g., IT outsourcing) perspective. Therefore, how the internal and external IT governance of firms simultaneously lead to firmperformance remains unclear. To address this research gap, we conceptualize internal and external IT governance from the extended resource-based view, propose three alignments between both types of governance, and hypothesize their effects on distinctive firm performance. We then empirically test these hypotheses using 213 Korean firms that have implemented IT outsourcing. Results show that a hierarchy-based alignment (i.e., between internal and external hierarchy governance) optimizes the operational efficiency of firms, a market-based alignment (i.e., between internal and external market governance) offers the greatest advantage in terms of market growth, and a network-based alignment (i.e., between internal and external network governance) leads to the best innovation performance. Furthermore, our post hoc test also reveals some unexpected alignments (e.g., between internal market and external hierarchy governance) that positively influence firm performance, which call for new areas of discussion with alternative theoretical perspectives. This study guides practitioners in choosing outsourcing alignments by comprehensively analyzing the effects of various alignments on distinctive outcomes.</P>
-
-
-
Articulated Rigid Body Motion Tracking Using Model Body Parts
Park, Jihun Research Institute for Science & Technology HONG-I 2003 Hongik Journal of Science and Technology Vol.7 No.-
The generation of motion of an articulated body for computer animation is an expensive and time consuming task. Conventionally, animators manually generate intermediate frames between key frames, but this task is very time consuming. Recently there are strong trends to use motion capture devices to generate intermediate frames. This paper presents a new approach to articulated body motion capture using widely-available, static-background monocular video sequences. We combine view-based and model-based techniques by processing color video at both pixel level and object level. At the pixel level, a Gaussian mixture model is used to train and classify individual pixel colors. At the object level, a 3D human body model projected on a 2D image plane is used to fit the image data. Our method does not use inverse kinematics due to the singularity problem. While many others use stochastic sampling for model-based motion tracking, our method is purely dependent on parameter optimization. We convert the human motion capture problem into two types of parameter optimization problem: static optimization and dynamic optimization. First, we determine each model body configuration using static optimizations for every input image. Then, to get better motion, the results from all static optimizations are fed into a dynamic optimization process, where the entire sequence of motion is considered for the user-specified motion. The user-specified motion is defined by each user and the final form of the motion they want. A cost function for static optimization is used to estimate the degree of overlapping between the foreground input image silhouette and a projected 3D model body silhouette. The overlapping is computed using computational geometry by converting a set of pixels from the image domain to a polygon in the real projection plane domain. A cost function for dynamic optimization is the user-specified motion based on the static optimization results as well as image matching. Our method is used to capture various human motions. Motion capture results from color video sequences are very encouraging.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
