• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.295-304
• /
• 2022

The purpose of this study is to detect the sorghum panicle using YOLOv5 based on RGB images acquired by a unmanned aerial vehicle (UAV) system. The high-resolution images acquired using the RGB camera mounted in the UAV on September 2, 2022 were split into 512×512 size for YOLOv5 analysis. Sorghum panicles were labeled as bounding boxes in the split image. 2,000images of 512×512 size were divided at a ratio of 6:2:2 and used to train, validate, and test the YOLOv5 model, respectively. When learning with YOLOv5s, which has the fewest parameters among YOLOv5 models, sorghum panicles were detected with mAP@50=0.845. In YOLOv5m with more parameters, sorghum panicles could be detected with mAP@50=0.844. Although the performance of the two models is similar, YOLOv5s ( 4 hours 35 minutes) has a faster training time than YOLOv5m (5 hours 15 minutes). Therefore, in terms of time cost, developing the YOLOv5s model was considered more efficient for detecting sorghum panicles. As an important step in predicting sorghum yield, a technique for detecting sorghum panicles using high-resolution RGB images and the YOLOv5 model was presented.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.541-548
• /
• 2021

Recently, multispectral cameras are being actively utilized in various application fields such as agriculture, forest management, coastal environment monitoring, and so on, particularly onboard UAV's. Resultant multispectral images are typically georeferenced primarily based on the onboard GPS (Global Positioning System) and IMU (Inertial Measurement Unit)or accurate positional information of the pixels, or could be integrated with ground control points that are directly measured on the ground. However, due to the high cost of establishing GCP's prior to the georeferencing or for inaccessible areas, it is often required to derive the positions without such reference information. This study aims to provide a means to improve the georeferencing performance of a multispectral camera images without involving such ground reference points, but instead with the simultaneously onboard high resolution RGB camera. The exterior orientation parameters of the drone camera are first estimated through the bundle adjustment, and compared with the reference values derived with the GCP's. The results showed that the incorporation of the images from a high resolution RGB camera greatly improved both the exterior orientation estimation and the georeferencing of the multispectral camera. Additionally, an evaluation performed on the direction estimation from a ground point to the sensor showed that inclusion of RGB images can reduce the angle errors more by one order.

• Proceedings of the Materials Research Society of Korea Conference
• /
• 2003.11a
• /
• pp.198-198
• /
• 2003

LED(Light Emitting Diode)는 전기 신호를 빛으로 신호를 보내고 받는데 사용되는 반도체의 일종으로 가정용 가전제품, 리모컨, 전광판, 각종 자동화 기기등에 사용된다. 3색광 백색 LED는 soft-UV 또는 blue 빛을 내는 device 와 RGB 형광체로 이루어져 있다. 현재 연구중인 3색광 백색 LED는 InGaN 또는 GaN 이 RGB 형광체를 여기 시키는것이 대부분이다. 이러한 경우에 유기물과 무기물 형과체가 백색광을 구현하기 위해 사용된다. 유기물의 경우에는 lift-time 이 짧고, 무기물의 경우에는 유해원소인 S, Cd등이 포함되기 때문에 환경오염이 야기된다. 이러한 단점을 보완하기 위해 진화 최적방법을 이용하여 alkali earth borosilicate ((Eu,Mg,Ca,Sr,Ba)$_{x}$ $B_{y}$ S $i_{z}$ $O_{d}$ ) 계열에 $^{Eu3+}$을 도핑하여 고효율 형광체를 합성하였다.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.13 no.1
• /
• pp.73-91
• /
• 1995

Spectroscopic and Photoelectric Characteristics in the Cyanine and Merocyanine Dye according to systematically change of their structures were experimentally discussed. As result, in solution, Hetero atoms(X) of Cyanine and Merocyanine dye were participated in resonance X of d obital rather than X of pobital,effected in resonance and contributed in extension of conjugated system. in solid film,new spectra,called eximer-fluorenscence,were appeared in 3-dimensional fluorenscence of high density of Cyanine dye but not of Merocyanine. The activational energy of conductivity in Merocyanine dye was lower than in cyanine, an the contrary,the drift mobility was higher and the former in photoelectric characteristics was more effec-tive than the latter. In this paper,authors invertigated the changes of dye structure by molecular obital method to confirm the results of spectroscopic and photoelectric characteristics in the Cyanine and Merocyanine Dye acco-rding to systematically cally change of their structure, and counted total energy on dihedral angle and dipol miments if dyes in S0 and S1.

• Proceedings of the Korea Contents Association Conference
• /
• 2013.05a
• /
• pp.161-162
• /
• 2013

본 논문에서는 Mental ray 렌더러를 통해 렌더링 된 이미지의 색감과 사실적인 빛의 감쇠효과를 위해 사용되는 Color Management를 활용한 Linear Work Flow 작업과정을 제시하고 그 이론적인 배경을 설명하고자 한다. 디지털로 사용되는 대부분의 이미지 포맷은 모든 모니터에서 동일한 색감을 표현하기 위해 sRGB라는 표준화된 형식을 사용하고 있다. 하지만 Mental ray는 기본적으로 감마 커브가 1.0으로 이루어진 이미지를 렌더링한다. sRGB가 가지고 있는 2.2의 감마커브와 차이가 발생함에 따라 사용자가 원하는 색감을 얻어내기 어렵다. 반면에 Color Management를 활용해 렌더링 된 이미지의 감마 커브를 수정해주면 3D 소프트웨어로 사용 된 텍스쳐의 원본 색감을 렌더링 후에도 유지할 수 있다. 또한 라이팅의 감쇠(Decay)와 산란에도 영향을 주어 보다 풍부한 색감의 이미지를 얻게 된다. 본 연구에서는 Autodesk Maya의 Mental Ray를 이용해 실험을 하고 Color Management를 활용한 이미지와 그렇지 않은 이미지를 비교 분석한다. 연구의 범위는 제품 렌더링을 위한 스튜디오 라이팅 기법으로 한정하였다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2009.10a
• /
• pp.1088-1091
• /
• 2009

A boost converter with charge-recycling technique fabricated by $0.25{\mu}m$ CMOS BCD process can provide different supply voltages to drive series RGB LEDs in sequence for reducing the power consumption on the constant current generator. The proposed technique stores and restores extra energy to improve the efficiency, as well as enhances the reference tracking response. Experimental results show that the period of reference-tracking response can be improved. When the load current is 100mA, the periods of reference down-tracking and uptracking are smaller than $10{\mu}s$ and $20{\mu}s$, respectively. Experimental results demonstrate fast and efficient reference tracking performance is achieved.

• Journal of KIISE:Software and Applications
• /
• v.31 no.10
• /
• pp.1332-1344
• /
• 2004

Upon development of information super-highway and multimedia-related technoiogies in recent years, more efficient technologies to transmit, store and retrieve the multimedia data are required. Among such technologies, firstly, it is common that the semantic-based image retrieval is annotated separately in order to give certain meanings to the image data and the low-level property information that include information about color, texture, and shape Despite the fact that the semantic-based information retrieval has been made by utilizing such vocabulary dictionary as the key words that given, however it brings about a problem that has not yet freed from the limit of the existing keyword-based text information retrieval. The second problem is that it reveals a decreased retrieval performance in the content-based image retrieval system, and is difficult to separate the object from the image that has complex background, and also is difficult to extract an area due to excessive division of those regions. Further, it is difficult to separate the objects from the image that possesses multiple objects in complex scene. To solve the problems, in this paper, I established a content-based retrieval system that can be processed in 5 different steps. The most critical process of those 5 steps is that among RGB images, the one that has the largest and the smallest background are to be extracted. Particularly. I propose the method that extracts the subject as well as the background by using an Image, which has the largest background. Also, to solve the second problem, I propose the method in which multiple objects are separated using RGB channel selection techniques having optimized the excessive division of area by utilizing Watermerge's threshold value with the object separation using the method of RGB channels separation. The tests proved that the methods proposed by me were superior to the existing methods in terms of retrieval performances insomuch as to replace those methods that developed for the purpose of retrieving those complex objects that used to be difficult to retrieve up until now.

• Journal of Satellite, Information and Communications
• /
• v.11 no.2
• /
• pp.48-54
• /
• 2016

As the nonlinear viewing patterns are getting generalized, the needs for VOD service of consumers are increasing in TV, webTV. But today's VOD system is all automated, except the part for posting contents. This study proposes the method for automation of the content posting. For this we analyzed the broadcast program structures by genre in order to detect the transition point between the advertisement and the contents. It was found that regular black frames were set in the transition during fade in and out. We propose an efficient approach to automatically detect the black frames using RGB values of each frame that enable VOD content posting and replace an advertisement in VOD service.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.2
• /
• pp.1-8
• /
• 2007

This study is to generate optimal values of brightness and achieve more realistic images by varying such values according to individual materials in order to create better quality simulation images using Lightscape. Because there are discolorations of materials by adding the radiation of luminaires to that of daylight during the daytime, when low brightness values are inputted in case of daytime, the results are founded that images of materials can be seen much similar with real images. And in most of the materials, when low values in the daytime and high values in the nighttime are inputted this study verifies that the realest simulation images can be obtained using Lightscape, because the RGB data of simulation images are almost similar with that of real materials.

• Journal of Fashion Business
• /
• v.17 no.1
• /
• pp.30-41
• /
• 2013

Augmented reality techniques have been increasingly employed in the textile and fashion industry as well as computer graphics sectors. Three-dimensional virtual clothing CAD systems have also been widely used in the textile industries and academic institutes. Motion tracking techniques are grafted together in the 3D and augmented reality techniques in order to develop the virtual three-dimensional clothing and fitting systems in the fashion and textile industry sectors. In this study, three-dimensional virtual clothing sample has been prepared using a 3D virtual clothing CAD along with a 3D scanning and reconstruction system. Motion of the user has been captured through an RGB-D sensor system, and the virtual clothing fitted on the user's body is allowed to move along with the captured motion flow of the user. Acutal fabric specimens are selected for the material characterization. This study is a primary step toward building a comprehensive system for the user to experience interactively virtual clothing under real environment.