http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
수중 소나 영상의 부분 왜곡에 따른 학습 데이터 Augmentation을 통한 마커 검출 성능에 관한 연구
이언호(Eon-ho Lee),이영준(Yeongjun Lee),최진우(Jinwoo Choi),이세진(Sejin Lee) 대한기계학회 2018 대한기계학회 춘추학술대회 Vol.2018 No.12
The existing SLAM study refines the position of the mobile robot by using the landmarks obtained from the environment based on GPS. However, since it is impossible to use GPS in an underwater environment, detection of landmarks by sensors becomes very important. Unfortunately, the use of artificial landmarks is necessary because few features make it a natural landmark in a typical aquatic environment. The purpose of this study is to detect artificial markers based on the deep learning technique robustly. It always does not guarantee good results to use a complex deep-learning model, so it is needed to find the best model by adjusting the layers to get the best performance. In addition, the recognition rate of the deep-learning model is reduced by several noise such as distortion etc. during data acquisition. To solve this problem, the training data augmentation for the distortion was executed with the rotation. In this paper, we apply the object detection for the sonar image data of three types of artificial markers by using the Faster R-CNN.
최재찬,조해용,권혁흥,이언호,Choe, Jae-Chan,Jo, Hae-Yong,Gwon, Hyeok-Heung,Lee, Eon-Ho 한국정밀공학회 1992 한국정밀공학회지 Vol. No.
A new helical gear extrusion process was proposed and its numerical solution program based on the upper bound method was developed. In the analysis the involute curve was used as a shape of die and the upper bound method was used to calculate energy dissipation rate. By this method the power requirement and optimum conditions necessary for extruding helical gear were successfully calculated. These numerical solutions were in good agreement with experimental data. In the experiment, die life was greatly improved compared with that of Samanta process and 4 .approx. 5 class helical gear of KS standard for automobile transmission was successfully manufactured.
Rats의 유영훈련강도에 따른 혈중 Lactate 농도 변화에 관한 실험연구
이언호 부산 외국어 대학교 2000 外大論叢 Vol.21 No.1
This study has been analyzed by variation in blood lactate density from swimming training intensity of the Rats. The experimental animals have used of Sprague-Dawley 25 and were practiced 12 weeks of swiming training. this experimental animals were assigned to 5 Group: one was control group(untraining group), another group was experimental group(10min, 30min, 60min, 90min training group). The results were as follows: 1) The lactate density of control group was the Mean=5.37mg/dl, SD= ±1.31 and the 10min group of the Mean=8.27mg/dl, SD=±0.65mg/dl and the 30min group Mean=9.97mg/dl, SD=±0.95mg/dl, and the 60min group mean=6.76mg/dl, SD=±1.85mg/dl, and the 90min group mean=3.40mg/dl, SD=±0.28mg/dl. 2) There was significant difference in Lactate all group(p<.01). compare with Total Mean Lactate was decrease in energy using for longer exercise time.