• Journal of Broadcast Engineering
• /
• v.17 no.3
• /
• pp.437-446
• /
• 2012

A face detection algorithms using two-dimensional (2-D) intensity or color images have been studied for decades. Recently, with the development of low-cost range sensor, three-dimensional (3-D) information (i.e., depth image that represents the distance between a camera and objects) can be easily used to reliably extract facial features. Most people have a similar pattern of 3-D facial structure. This paper proposes a face detection method using intensity and depth images. At first, adaboost algorithm using intensity image classifies face and nonface candidate regions. Each candidate region is divided into $5{\times}5$ blocks and depth values are averaged in each block. Then, $5{\times}5$ block rank pattern is constructed by sorting block averages of depth values. Finally, candidate regions are classified as face and nonface regions by matching the constructed depth map based block rank patterns and a template pattern that is generated from training data set. For template matching, the $5{\times}5$ template block rank pattern is prior constructed by averaging block ranks using training data set. The proposed algorithm is tested on real images obtained by Kinect range sensor. Experimental results show that the proposed algorithm effectively eliminates most false positives with true positives well preserved.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.764-781
• /
• 2013

In this paper, we propose a highly precise vehicle detection method with low false alarm using billboard sweep stereo matching and multi-stage hypothesis generation. First, we capture stereo images from cameras established in front of the vehicle and obtain the disparity map in which the regions of ground plane or background are removed using billboard sweep stereo matching algorithm. And then, we perform the vehicle detection and tracking on the labeled disparity map. The vehicle detection and tracking consists of three steps. In the learning step, the SVM(support vector machine) classifier is obtained using the features extracted from the gabor filter. The second step is the vehicle detection which performs the sobel edge detection in the image of the left camera and extracts candidates of the vehicle using edge image and billboard sweep stereo disparity map. The final step is the vehicle tracking using template matching in the next frame. Removal process of the tracking regions improves the system performance in the candidate region of the vehicle on the succeeding frames.

• Journal of Korea Multimedia Society
• /
• v.8 no.10
• /
• pp.1369-1382
• /
• 2005

Vehicle segmentation, which extracts vehicle areas from road scenes, is one of the fundamental opera tions in lots of application areas including Intelligent Transportation Systems, and so on. We present a vehicle segmentation approach for still images captured from outdoor CCD cameras mounted on the supporting poles. We first divided the input image into a set of two-dimensional grids and then calculate the feature values of the edges for each grid. Through analyzing the feature values statistically, we can find the optimal rectangular grid area of the vehicle. Our preprocessing process calculates the statistics values for the feature values from background images captured under various circumstances. For a car image, we compare its feature values to the statistics values of the background images to finally decide whether the grid belongs to the vehicle area or not. We use dynamic programming technique to find the optimal rectangular gird area from these candidate grids. Based on the statistics analysis and global search techniques, our method is more systematic compared to the previous methods which usually rely on a kind of heuristics. Additionally, the statistics analysis achieves high reliability against noises and errors due to brightness changes, camera tremors, etc. Our prototype implementation performs the vehicle segmentation in average 0.150 second for each of $1280\times960$ car images. It shows $97.03\%$ of strictly successful cases from 270 images with various kinds of noises.

• Journal of Cadastre & Land InformatiX
• /
• v.47 no.1
• /
• pp.15-26
• /
• 2017

The decrease of green space according to the urbanization has caused many environmental problems as the destruction of habitat, air pollution, heat island effect. With interest growing in natural view recently, proper management of evergreen tree which is lived even the winter season has been on the rise importantly. This study analyzed the distribution area of evergreen tree using vegetation index based on unmanned aerial vehicle (UAV). Firstly, RGB and NIR+RG camera were loaded in fixed-wing UAV and image mosaic was achieved using GCPs based on Pix4d SW. And normalized differences vegetation index (NDVI) and soil adjusted vegetation index (SAVI) was calculated by band math function from acquired ortho mosaic image. validation points were applied to evaluate accuracy of the distribution of evergreen tree for each range value and analysis showed that kappa coefficient marked the highest as 0.822 and 0.816 respectively in "NDVI > 0.5" and "SAVI > 0.7". The area of evergreen tree in "NDVI > 0.5" and "SAVI > 0.7" was $11,824m^2$ and $15,648m^2$ respectively, that was ratio of 4.8% and 6.3% compared to total area. It was judged that UAV could supply the latest and high resolution information to vegetation works as urban environment, air pollution, climate change, and heat island effect.

• Journal of Cadastre & Land InformatiX
• /
• v.48 no.1
• /
• pp.111-121
• /
• 2018

RIn this research, digital elevation models, true-ortho image and 3-dimensional digital complied data was generated and evaluated using unmanned aircraft vehicle stereoscopic images by applying photogrammetric principles. In order to implement stereoscopic vision, digital Photogrammetric Workstation should be used necessarily. For conducting this, in this study GEOMAPPER 1.0 is used. That was developed by the Ministry of Trade, Industry and Energy. To realize stereoscopic vision using two overlapping images of the unmanned aerial vehicle, the interior and exterior orientation parameters should be calculated. Especially lens distortion of non-metric camera must be accurately compensated for stereoscope. In this work. photogrammetric orientation process was conducted using commercial Software, PhotoScan 1.4. Fixed wing KRobotics KD-2 was used for the acquisition of UAV images. True-ortho photo was generated and digital topographic map was partially produced. Finally, we presented error analysis on the generated digital complied map. As the results, it is confirmed that the production of digital terrain map with a scale 1:2,500~1:3,000 is available using stereoscope method.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.26 no.4
• /
• pp.363-368
• /
• 2000

The purposes of the study was to examine changes in thickness and strength of the rat femur after administration of sodium fluoride in the drinking water. 48 female Sprague-Dawley rats were randomly divided into 4 groups, and they were supplied with 0(control), 1, 5 and 50 ppm of fluoride in the drinking water ad libitum for 6 weeks. Rats were killed and both sides of femur were dissected. Bone strength was measured as the stress of failure of femur at the middle point and femoral neck with Instron. Histologic slides were prepared from the femur shaft with routine processing of fixing, demineralizing, embedding and HE staining. Thickness and area of cortical bone and medullary cavity were measured by using Camera Lucida and Image Analyzer. All the collected data were analyzed with one-way ANOVA, Duncan's multiple range test for post-hoc tests and ANCOVA using the SAS 6.12 package at the level of 0.05. Bone strength increased significantly in the animals given 1 and 5 ppm of fluoride in the water, as compared to the control group. There were significant decreases of stress at fracture in 50 ppmF group compared to the 1 and 5 ppmF groups. The similar trends of bone strength at the femoral neck fracture test, but there were no statistical significances. Cortical bone thickness and area of the femur increased in the 1 and 5 ppmF groups compared to the control. However, the thickness of 50 ppmF group also decreased significantly as compared to 1 and 5 ppmF groups. On the other hand, medullary thickness and area increased in all fluoride groups than control group. All of the findings presented support the conclusion that, low fluoride dosage used in water fluoridation could increase the bone strength and might have preventive effect on femur fracture.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.7 no.3
• /
• pp.13-21
• /
• 2004

The dissemination of commercial satellite images. which have the high spatial resolution such as aerial photos, are the active trend in remote sensing community because of the recent development in satellite and sensor technology. Such high resolution satellite images provide a unique tool for the monitoring of ongoing urban land use change. Especially KOMPSAT-1, which was launched at December 1999 and successfully operated up to now, provides repeatedly panchromatic images over Korean peninsula, which has the spatial resolution of 6.6m. Based upon this KOMPSAT-1 EOC image data we can try to analyze and assess the temporal urban land use change, which could not be done because lack of such data. The aim of this paper is to analyze and assess the spatial land use characteristics of Daejeon Metropolitan City based on KOMPSAT-1 EOC data. The land use map of year 2001 is generated through the modification of the year 2000 land use map, which is published by National Geographic Information Institute, using visual interpretation of KOMPSAT-1 EOC image which is acquired in year 2001. This study can be the start point of the time series analysis of the long term land use change monitoring mit KOMPSAT-1 EOC data.

• The Journal of Korean Academy of Prosthodontics
• /
• v.46 no.3
• /
• pp.307-319
• /
• 2008

STATEMENT OF PROBLEM: It is known that an anodic oxidation technique, one of the methods for the implant surface treatment, remarkably increased surface area, enhanced wettability and accelerated the initial bone healing. Purpose: This study was performed to evaluate the wettability of anodized titanium surface which has a nanotubular structure, to assess osseointegration after the placement of implant with nano-size tubes on tibia of rats and to analyze quantitatively transferable rhBMP-2 on each surface. MATERIAL AND METHOD: Four different kinds of surface-treated titanium discs (polished (machined surface) group, micro (blasting surface) group, nano (anodizedmachined surface) group, and nano-micro (anodized-blasting surface) group) were fabricated (n=10). Three different media were chosen to measure the surface contact angles; distilled water, plasma and rhBMP-2 solution. After a single drop (0.025 $m{\ell}$) of solution, the picture was taken with the image camera, and contact angle was measured by using image analysis system. For the test of osseointegration, 2 kinds of anodized surface (anodized-machined surface, anodized-blasting surface) implants having 2.0 mm in diameter and 5.0 mm in length inserted into the tibia of Wistar rats. After 3 weeks, tibia were harvested and the specimens were stained with hematoxylin and eosin for histological analysis. To test the possibility of drug delivery, after soaking sample groups in the concentration of 250 ng/$m{\ell}$l of rhBMP-2 for 48 hours, the excess solution of rhBMP-2 were removed. After that, they were lyophilized for 24 hours, and then the rhBMP-2 on the surface of titanium was resolved for 72 hours in PBS. All the extracted solution was analyzed by ELISA. One-way analysis of variance (ANOVA) was performed on the data. RESULTS: The wettability is improved by anodic oxidation. The best wettability was shown on the nano-micro group, and it was followed by nano group, micro group, and polished group. In the histological findings, all implants showed good healing and the new bone formation were observed along the implant surface. After 3 days, nano-micro group delivered the most amount of rhBMP-2, followed by nano group, micro group, and polished group. CONCLUSION: It indicated that anodic oxidation on blasting surface produce functionally graded nano-micro porous structure and enhance hydrophilicity of the surface and osseointegration. The findings suggest that the nano-micro porous structure could be a useful carrier of osteogenic molecules like rhBMP-2.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.31-38
• /
• 2017

In this paper, we propose a system which estimates Manhattan coordinate systems for urban scene images using a convolutional neural network (CNN). Estimating the Manhattan coordinate system from an image under the Manhattan world assumption is the basis for solving computer graphics and vision problems such as image adjustment and 3D scene reconstruction. We construct a CNN that estimates Manhattan coordinate systems based on GoogLeNet [1]. To train the CNN, we collect about 155,000 images under the Manhattan world assumption by using the Google Street View APIs and calculate Manhattan coordinate systems using existing calibration methods to generate dataset. In contrast to PoseNet [2] that trains per-scene CNNs, our method learns from images under the Manhattan world assumption and thus estimates Manhattan coordinate systems for new images that have not been learned. Experimental results show that our method estimates Manhattan coordinate systems with the median error of $3.157^{\circ}$ for the Google Street View images of non-trained scenes, as test set. In addition, compared to an existing calibration method [3], the proposed method shows lower intermediate errors for the test set.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.23 no.10
• /
• pp.1265-1273
• /
• 1999

PIV(Particle Image Velocimetry) velocity field measurements inside the snout of a1/10 scale model of the Zn plating process were carried out at the strip speed $V_s=1.5m/s$. Aluminum powder particles ($1{\mu}m$) and atomized olive oil ($3{\mu}m$) were used as seeding particles to simulate the molten Zinc flow and deoxidization gas flow, respectively. A pulsed Nd:Yag laser and a $2K{\times}2K$ high-resolution CCD camera were synchronized for the PIV velocity field measurement. From flow visualization study, it is found that the liquid flow in the Zn pot is dominantly governed by the uprising flow caused by the rotating sink roll, with its effect on the steel strip inside the snout largely diminished by installing of the snout. The deoxidization gas flow in front of the strip inside the snout can be characterized by a large-scale vortex rotating clockwise direction formed by the moving strip. In the rear side of the strip, a counter-clockwise vortex is formed and some of the flow entrained by the moving strip impinges on the free surface of molten zinc. The liquid flow in front of the strip is governed by the flow entering the snout, caused by the spinning sink roll. Just below the free surface a counter-clockwise vortex is formed near the snout wall. The moving strip affects dominantly the flow behind the strip inside the snout, and large amount of the liquid flow follows the moving strip toward the sink roll. The thickness of the flow following the strip is very thin in the front side due to the uprising flow, however thick boundary layer is formed in the rear side of the strip. Its thickness is increased as moving downstream toward the sink roll. Inside the snout, the deoxidization gas flow above the free surface is much faster than the liquid flow in the zinc pot. Due to the larger influx of the flow following the moving strip in the rear side of the strip, higher percentage of imperfection can be anticipated on the rear surface of the strip.