115 lines
8.6 KiB
HTML
115 lines
8.6 KiB
HTML
<?php include('../inc/pageheader_eng.php');?>
|
||
<link rel="stylesheet" href="../css/rnd.css">
|
||
<script src="../js/picLoad.js"></script>
|
||
<script src="../js/rnd.js?v=190507"></script>
|
||
<?php include('../inc/menubar_eng.php'); ?>
|
||
<section>
|
||
<h1 class="hidden">Start of Content</h1>
|
||
<article class="subBanner">
|
||
<h2 class="hidden">서브배너</h2>
|
||
|
||
<div class="inner">
|
||
<div class="subBannerInfo">
|
||
<ul>
|
||
<li>REFERENCE</li>
|
||
<li>Provides diverse solutions with Innovative technology for customer satisfaction</li>
|
||
</ul>
|
||
</div><!--end of subBannerInfo-->
|
||
</div><!--end of inner-->
|
||
</article><!--end of subBanner-->
|
||
|
||
<div class="siteIndex">
|
||
<div class="inner">
|
||
REFERENCE 》 Automatic detection system of craters on the Lunar surface
|
||
</div>
|
||
</div><!--end of siteIndex-->
|
||
<article class="rndContainer">
|
||
<h2 class="hidden">REFERENCE</h2>
|
||
<ol>
|
||
<li><a href="./RnD_deep.html"><</a></li>
|
||
<li><a href="./RnD_module.html">></a></li>
|
||
</ol>
|
||
<div class="rndWrapper">
|
||
|
||
<div class="lunarSystem">
|
||
<h2 class="hidden">월면 크레이터 자동 인식 시스템</h2>
|
||
<ul class="clearfix">
|
||
<li class="bigPic2"><img src="../images/lunar/Ori_00033_ori.jpg" alt=""></li>
|
||
<li>
|
||
<dl>
|
||
<dt>Automatic detection system of craters on the Lunar surface</dt>
|
||
<dd>
|
||
This system uses Deep-learning image recognition technology to recognize the lunar ground image objects and automatically detect craters. As deep learning-based object recognition technique learns DEM image with shading relief and a large number of unlabeled craters can be detected, so it contributes to securing high-performance terrain object image processing and automatic statistical technology in space construction.
|
||
</dd>
|
||
<dd>
|
||
<ul class="clearfix">
|
||
<li><img src="../images/lunar/Ori_00033_ori.jpg" alt=""></li>
|
||
<li><img src="../images/lunar/img_00033_dem.jpg" alt=""></li>
|
||
<li><img src="../images/lunar/img_00033.jpg" alt=""></li>
|
||
</ul>
|
||
</dd>
|
||
</dl>
|
||
</li>
|
||
</ul>
|
||
|
||
<div class="rndInfo">
|
||
<div class="innerScroll">
|
||
<ul class="techIntroduce">
|
||
<li class="techIntroduceTitle">1) Technology Introduction : Automatic detection system of craters on the Lunar surface</li>
|
||
<li>
|
||
Detection of craters on the lunar surface is one of the most important research areas in aerospace. Traditionally, detecting craters on the lunar surface has been determined by experts’ visual check-up with high-resolution DEM (Digital Elevation Model) images. However, the results of the crater detection varied among experts so that it was difficult to maintain the reliability and consistency of the results. DBNtech conducted a study on automatic crater detection system using Deep Learning-based object detection technology as a consignment project of KICT(KOREA INSTITUTE of CIVIL ENGINEERING and BUILDING TECHNOLOGY). Using various techniques such as "Hill Shade" techniques as a preprocess instead of "DEM images" that are difficult to distinguish by the naked eye, we improved object detection performance of the Deep-learning model. As a result, not only was it possible to detect the large and small craters more precisely, but also a large number of craters that could not be detected with the naked eye could be detected. The result of this study can be also applied in other areas such as construction and transportation infrastructure using Deep-learning based object recognition in addition to space construction, and will contribute to revitalizing extreme environmental construction technologies and creating new markets related to future space exploration.
|
||
</li>
|
||
</ul><!--end of techIntroduce-->
|
||
<ul class="techIntroduce">
|
||
<li class="techIntroduceTitle">２) Test Result</li>
|
||
<li class="techIntroduceImg">
|
||
<span><img src="../images/reference/lunar/1.PNG" alt="레티나넷"></span>
|
||
<span><img src="../images/reference/lunar/2.PNG" alt="SSD and YOLO"></span>
|
||
<span><img src="../images/reference/lunar/3.PNG" alt="SSD and YOLO"></span>
|
||
</li>
|
||
</ul><!--end of techIntroduce-->
|
||
<ul class="techIntroduce">
|
||
<li class="techIntroduceTitle">3) Application of Deep Learning-based object detection</li>
|
||
<li class="techIntroduceHandle clearfix">
|
||
<dl>
|
||
<dt>A. Surface condition analysis of SOC facilities based on image</dt>
|
||
<dd><img src="../images/reference/lunar/4.PNG" alt=""></dd>
|
||
<dd>
|
||
1. Recognition of conditions such as deterioration, cracking, breakage and etc.<br />
|
||
2. Possible to identify the position and size of damage in image<br />
|
||
</dd>
|
||
</dl>
|
||
<dl>
|
||
<dt>B. Character detection in images</dt>
|
||
<dd><img src="../images/reference/lunar/5.PNG" alt=""></dd>
|
||
<dd>
|
||
1. Character detection in images<br />
|
||
2. Fault diagnosis based on Deep-learning(video/sound)<br />
|
||
</dd>
|
||
</dl>
|
||
</li>
|
||
</ul><!--end of techIntroduce-->
|
||
</div><!--end of innerScroll-->
|
||
|
||
</div><!--end of rndInfo-->
|
||
|
||
</div><!--end of deepLearning-->
|
||
|
||
</div><!--end of rndWrapper-->
|
||
|
||
</article><!--end of rndContainer-->
|
||
|
||
<div class="fixMenu">
|
||
<p class="btn_fix"></p>
|
||
<ul>
|
||
<li><a href="#" alt="딥러닝 기반 사고영상 감지 시스템">Deep Learning-based accident image detection system</a></li>
|
||
<li><a href="#" alt="월면 크레이터 자동 인식 시스템">Automatic detection system of craters on the Lunar surface</a></li>
|
||
<li><a href="#" alt="시추정보 기반의 액상화 모델링 및 3차원 분석 모듈">liquefaction modeling and 3D analysis module based on Drilling information </a></li>
|
||
<li><a href="#" alt="도로표지관리/안내시스템">Road sign management/guide system</a></li>
|
||
</ul>
|
||
|
||
</div><!--end of fixMenu-->
|
||
</section><!--end of section, mainPage-->
|
||
<?php include('../inc/footer_eng.php'); ?>
|
||
</body>
|
||
</html> |