• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1330-1339
• /
• 2022

3D object detection generally aims to detect relatively large data such as automobiles, buses, persons, furniture, etc, so it is vulnerable to small object detection. In addition, in an environment with limited resources such as embedded devices, it is difficult to apply the model because of the huge amount of computation. In this paper, the accuracy of small object detection was improved by focusing on local features using only one layer, and the inference speed was improved through the proposed knowledge distillation method from large pre-trained network to small network and adaptive quantization method according to the parameter size. The proposed model was evaluated using SUN RGB-D Val and self-made apple tree data set. Finally, it achieved the accuracy performance of 62.04% at mAP@0.25 and 47.1% at mAP@0.5, and the inference speed was 120.5 scenes per sec, showing a fast real-time processing speed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.613-613
• /
• 2012

ADCP는 매우 상세한 유속 및 하상자료를 측정할 수 있어 하천의 수리학적 계측에 많은 가능성을 열어주고 있다. 하지만 현재까지 대부분 하천 단면에서의 유량 측정에 국한되어 운영되고 있는 실정이다. 본 연구에서는 ADCP가 제공하는 원자료인 3차원 유속과 하상자료를 유량 외의 평균유속장 및 하상 계측에 활용될 수 있도록 하는 후처리 소프트웨어 개발을 통해 ADCP가 하천의 흐름해석 및 2차원 및 3차원 수치모델의 검보정 등에 활용될 수 있는 가능성을 보이고자 한다. 따라서 계측 방식도 하천의 단면뿐만 아니라 하도에 따른 지그재그 방식의 자료를 포괄한다. ADCP 자료의 후처리는 제작사에서 제공하는 소프트웨어가 유량 제공에 초점을 맞춰 다른 분야에의 활용을 위해 별도의 후처리 소프트웨어의 제작이 필요하나 자료구조가 까다롭고 수십에서 수백 개의 파일을 동시에 처리할 수 있는 툴의 개발은 용이하지 않아 ADCP를 흐름분석 등에 활용하고자하는 연구자나 관계 기관종사자들에 한계로 작용하였다. 또한 제작사 (RDI, SonTek)에 따라 원자료의 구조가 완전히 달라 한꺼번에 처리하는 데 많은 문제가 있어왔다. 본 연구를 통해 개발된 툴은 두 제작사의 ADCP 원자료 포맷으로 구성된 다수의 관측 파일도 동시에 처리할 수 있다. 또한 GIS 기반에서 ADCP 자료의 위치를 표출할 수 있어 지형정보와 결부된 흐름장 해석이 가능하게 한다. ADCP 3차원 속도자료는 매우 정밀한 공간에서 측정되는 부분이 장점인 반면에 지나치게 정밀하고 또한 난류 등이 포함되어 원자료 만으로 흐름장을 분석하는 데 한계가 있다. 따라서 본 연구에서는 다양한 공간평균방법을 제공하여 2차원 및 3차원 공간에서의 공간보간된 평균유속장을 볼 수 있게 하였다. 이러한 방식은 2,3차원 수치모델의 격자에 ADCP 유속자료를 보간할 수 있어 모델 검보정에도 활용될 수 있다. ADCP 원자료 및 후처리된 결과는 GIS, Excel, Google Earth 파일 형태 등으로 제공될 수 있어 추후 활용가능성을 높였다.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.31 no.1
• /
• pp.107-119
• /
• 1995

Turbulent flow characteristics and heat transfer in a three-dimensional room with a desk-type heat generating obstacle have been investigated numerically by the k-$\varepsilon$ two equation turbulence model. The room mole has one supply opening on the ceiling and two exhaust openings on the side walls. Th results of the flow structure and heat transfer have been represented for air for the inlet velocities in the range 0.1-10.0m/s. As the results of the three dimensional simulations, the relationships between mean Nusselt number and Reynolds number are clarified.

• Spatial Information Research
• /
• v.18 no.1
• /
• pp.57-67
• /
• 2010

Recently, 2D GIS technology is applied for urban facility management. However, urban facilities are located in 3D space and the information loss is occurring during data abstraction from 3D urban facility to 2D object. Also, the number of urban facilities is increasing steadily and most of urban facilities are located in underground space in the city. Therefore 2D urban facility management system has a limitation on visualization and management for a large number of urban facilities. In this paper, a multi-dimensions urban facility management system based on multi-texture technology is proposed. The proposed system reduces the information loss and improves the readability of information by visualizing urban facilities on 3D virtual space. A multi-texturing technology is applied for integrating of 2D vector data and 3D raster data, and a multi-thread technology is used for improving speed and performance of the system. The proposed technology can be used as a guideline for urban facility monitoring as providing visual information of a facility status with 3D image and facility data.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.33 no.1
• /
• pp.73-79
• /
• 2013

In this study, NIMAX material has been processed using the three-dimensional measuring instrument and white light interferometer. they were tested to roundness and surface roughness and results are as follows: As for a cutting characteristic, it indicated that F4 showed a lower result than 2F showed due to the high hardness of the material and showed a good result when spindle rotation speed and tool feed were low. As for the measurement of roundness through 3-Dimensional measuring machine, it indicated that 4F showed a good result like the condition of cutting component and that roundness showed a good result when spindle rotation speed of 1,700 rpm and tool feed speed of 85 mm/min were applied. As for the surface roughness of processing surface, Surface roughness showed better 4F than 2F and conditions of spindle rotation speed 1,700 rpm, tool feed rate 55 mm/min showed good results in the Ra $0.4025{\mu}m$.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.7
• /
• pp.737-747
• /
• 2013

A 3-D surveillance radar is a pulsed-doppler radar to provide various target information, such as range, doppler and angle by performing TWS. This paper introduces HW/SW architecture of radar signal processing board to process in real-time using high-speed multiple DSP(Digital Signal Processor) based on COTS. Moreover, we introduced a implemented algorithm consisted of clutter map creation/renewal, FIR(Finite Impulse Response) filter for rejection of zero velocity components, doppler filter, hybrid CFAR and finally presented computational burden of each algorithm by performing operational test using a beacon.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.2
• /
• pp.29-39
• /
• 2017

This paper presents a unified framework to efficiently and realistically simulate surface and wave foams. The framework is designed to first project 3D water particles from an underlying water solver onto 2D screen space in order to reduce the computational complexity of determining where foam particles should be generated. Because foam effects are often created primarily in fast and complicated water flows, we analyze the acceleration and curvature values to identify the areas exhibiting such flow patterns. Foam particles are emitted from the identified areas in 3D space, and each foam particle is advected according to its type, which is classified on the basis of velocity, thereby capturing the essential characteristics of foam wave motions. We improve the realism of the resulting foam by classifying it into two types: surface foam and wave foam. Wave foam is characterized by the sharp wave patterns of torrential flow s, and surface foam is characterized by a cloudy foam shape even in water with reduced motion. Based on these features, we propose a technique to correct the velocity and position of a foam particle. In addition, we propose a kernel technique using the screen space density to efficiently reduce redundant foam particles, resulting in improved overall memory efficiency without loss of visual detail in terms of foam effects. Experiments convincingly demonstrate that the proposed approach is efficient and easy to use while delivering high-quality results.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.3
• /
• pp.249-255
• /
• 2017

The finger vein recognition technology is a method to acquire a finger vein image by illuminating infrared light to the finger and to authenticate a person through processes such as feature extraction and matching. In order to recognize a finger vein, a 2D mask-based two-dimensional convolution method can be used to detect a finger edge but it takes too much computation time when it is applied to a low cost micro-processor or micro-controller. To solve this problem and improve the recognition rate, this study proposed an extraction method for the region of interest based on virtual core points and moving average filtering based on the threshold and absolute value of difference between pixels without using 2D convolution and 2D masks. To evaluate the performance of the proposed method, 600 finger vein images were used to compare the edge extraction speed and accuracy of ROI extraction between the proposed method and existing methods. The comparison result showed that a processing speed of the proposed method was at least twice faster than those of the existing methods and the accuracy of ROI extraction was 6% higher than those of the existing methods. From the results, the proposed method is expected to have high processing speed and high recognition rate when it is applied to inexpensive microprocessors.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.7
• /
• pp.132-139
• /
• 1989

Optical flow is important not only for determining velocity and trajectory of the object but also for image segmentation and 3D information. The gradient-based method is mostly used to compute optical flow form image sequences, but it accomanies smoothing effect of velocity vectors. In this paper, an enhanced algorithm for computing optical flow using scalar edge to restrict is also applied to reduce errors both around motion boundary and in the occlusion region.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.246-250
• /
• 2023

Magnetic Contactor (MC) research traditionally focuses on arc erosion influenced by contact material. In recent times, with an increasing demand for efficient utilization of DC devices and swift processing, the operational speed of MCs has become paramount. While AgSnO2 generally displays superior response characteristics to AgCdO, this understanding remains material-specific. In this paper, complete MCs were constructed, and the operational speeds were validated based on the two materials.