• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.573-578
• /
• 2001

This research proposes a generalized local feature structure named "LSG(Local Surface Group) for model-based 3D object recognition". An LSG consists of a surface and its immediately adjacent surface that are simultaneously visible for a given viewpoint. That is, LSG is not a simple feature but a viewpoint-dependent feature structure that contains several attributes such as surface type. color, area, radius, and simultaneously adjacent surface. In addition, we have developed a new method based on Bayesian theory that computes a measure of how distinct an LSG is compared to other LSGs for the purpose of object recognition. We have experimented the proposed methods on an object databaed composed of twenty 3d object. The experimental results show that LSG and the Bayesian computing method can be successfully employed to achieve rapid 3D object recognition.

• Journal of Korean Society for Atmospheric Environment
• /
• v.22 no.6
• /
• pp.821-830
• /
• 2006

To identify the effect of local air pollutants on the $PM_{2.5}$ level at Gosan, $PM_{2.5}$ composition data, continuous $O_3,\;NO_x,\;SO_2,\;CO$ data, VOCs data, surface wind characteristics, and backward trajectory analysis results were analyzed for the measurements in March 2000 during which high concentrations of mass and anthropogenic ionic species were reported. It was found that the combination of surface wind and continuous gaseous species data can help to identify local effect in Jeju Island. Even in a high $PM_{2.5}$ level case mainly affected by long range transport from China, it was Identified that local effects were also significant for both the duration and pollutants' levels.

• Journal of Magnetics
• /
• v.5 no.3
• /
• pp.81-84
• /
• 2000

A magneto-optical microscope magnetometer (MOMM) has been developed to simultaneously measure 2-dimensional array hysteresis loops of each local area of $320\times320-nm^2$ spots on ferromagnetic films, in addition to grabbing time-resolved domain evolution patterns. Using the system, spatial distribution of local coercivity can be quantitatively generated and then, compared directly with domain patterns grabbed at precisely the same position of a sample. It is clearly demonstrated that local coercivity distribution governs domain reversal behavior via a thermally activated relaxation process.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.1481-1486
• /
• 2004

This report presents experimental results on the heat transfer coefficients in the boiling region of spray cooling for actual metallurgical process. In this study, the heat flux distribution of a two dimensional dilute spray impinging on hot plate was experimentally investigated. Based on the experimental results, they classified the heat transfer area into the stagnation region and wall-flow region. In the stagnation region, the local heat transfer coefficient relates mainly to the droplet-flow-rate supplied from spray nozzle directly, so the local heat transfer coefficients is good agreement with the predicted values from correlation for spray cooling proposed by former report However, the local heat transfer coefficient in wall-flow region is larger than predicted values, and it is found that the rebounding droplets-flow-rate must be accurately evaluated to predict the local heat transfer coefficient in this region.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.8
• /
• pp.678-687
• /
• 2005

This paper describes a relative localization algorithm using odometry data and consecutive local maps. The purpose of this paper is the odometry error correction using the area matching of two consecutive local maps. The local map is built up using a sensor module with dual laser beams and USB camera. The range data form the sensor module is measured using the structured lighting technique (active stereo method). The advantage in using the sensor module is to be able to get a local map at once within the camera view angle. With this advantage, we propose the AVS (Aligned View Sector) matching algorithm for. correction of the pose error (translational and rotational error). In order to evaluate the proposed algorithm, experiments are performed in real environment.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.6
• /
• pp.719-725
• /
• 2013

In this paper, we propose a local path planning method based on RANGER algorithm and autonomy manager for autonomous navigation of UGV in urban environment. LPP method is designed to generate the local path in sensing area by using lane and curb of pavement and autonomy manager is designed to make a decision which transit the status of LPP component to a proper status for current navigation environment. A field test is conducted with scenarios in real urban environment in which crossroad, crosswalk and pavement are included and the performance of proposed method is validated.

• Journal of the Semiconductor & Display Technology
• /
• v.8 no.2
• /
• pp.23-29
• /
• 2009

To increase the data capacity of one-dimensional symbology, 2D barcodes have been proposed a decade ago. In this paper, a new 2D barcode detection algorithm based on Local Binary Pattern is presented. To locate 2D barcode symbols, a texture analysis scheme based on the Local Binary Pattern is adopted, and a gray-scale projection with sub-pixel operation is utilized to separate the symbol precisely from the input image. Finally, the segmented symbol is normalized using the inverse perspective transformation for the decoding process. The proposed method ensures high performances under various lighting/printing conditions and strong perspective deformations. Experiments show that our method is very robust and efficient in detecting the symbol area for the various types of 2D barcodes.

• Journal of Magnetics
• /
• v.18 no.1
• /
• pp.74-79
• /
• 2013

This paper proposes a sampling-based optimization method for electromagnetic design problems, where design sensitivities are obtained from the elaborate surrogate models based on the universal Kriging method and a local window concept. After inserting additional sequential samples to satisfy the certain convergence criterion, the elaborate surrogate model for each true performance function is generated within a relatively small area, called a hyper-cubic local window, with the center of a nominal design. From Jacobian matrices of the local models, the accurate design sensitivity values at the design point of interest are extracted, and so they make it possible to use deterministic search algorithms for fast search of an optimum in design space. The proposed method is applied to a mathematical problem and a loudspeaker design with constraint functions and is compared with the sensitivity-based optimization adopting the finite difference method.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.52-60
• /
• 2022

Few-shot learning is a sub-area of machine learning problems, which aims to classify target images that only contain a few labeled samples for training. As a representative few-shot learning method, the Prototypical network has been received much attention due to its simplicity and promising results. However, the Prototypical network uses the sample mean of samples from the same class as the prototypes of that class, which easily results in learning uncharacteristic features in the low-data scenery. In this study, we propose to use local descriptors (i.e., patches along the channel within feature maps) from the same class to explicitly obtain more representative prototypes for Prototypical Network so that significant intra-class feature information can be maintained and thus improving the classification performance on few-shot learning tasks. Experimental results on various benchmark datasets including mini-ImageNet, CUB-200-2011, and tiered-ImageNet show that the proposed method can learn more discriminative intra-class features by the local descriptors and obtain more generic prototype representations under the few-shot setting.

• Convergence Security Journal
• /
• v.8 no.3
• /
• pp.73-81
• /
• 2008

We can find easily about researches or technical development that deal with grasping the location of an object with GPS(Global Positioning System) in order to use them as a useful information. Most researches or technical development on application of tracing have been developed for the purpose of tracing objects in broad area as physical distribution or transportation, but recently, there are many researches on tracing materials in premise area as a fork lift, carts, or the equipment of work. In general, a system that utilizes location information of objects needs data communication network to transmit location data and it ensures data communication network by using common networks(SK, LG, KFT) or wireless LAN. However these two methods need monthly payment for the rental fee or require considerable amount of investment for the early stage so it is difficult to use them merely for tracing premise subjects. This study was conducted to build a tracing system for premise area by local area RF relay algorithm with low cost applying RF relay algorithm to local area wireless communication(ZIGBEE, 424MHz, Bluetooth, 900MHz) system in order to supplement these demerits and included relay algorithm, RF locating information terminal, local area RF gab-fillers, a plan for collection server of locating information, and the way of realization as they are needed in this system. I consider that this study would be applicable with flexibility in the industry area that needs tracing solution within a specific area or needs ensuring data communication network, to transmit data in ubiquitous environment, by easier and more rapid way with lower cost.