• 로봇학회논문지
• /
• 제10권1호
• /
• pp.33-41
• /
• 2015

Recent developments in robotics and intelligent vehicle area, bring interests of people in an autonomous driving ability and advanced driving assistance system. Especially fully automatic parking ability is one of the key issues of intelligent vehicles, and accurate parked vehicles detection is essential for this issue. In previous researches, many types of sensors are used for detecting vehicles, 2D LiDAR is popular since it offers accurate range information without preprocessing. The L shape feature is most popular 2D feature for vehicle detection, however it has an ambiguity on different objects such as building, bushes and this occurs misdetection problem. Therefore we propose the accurate vehicle detection method by using a 3D complete vehicle model in 3D point clouds acquired from front inclined 2D LiDAR. The proposed method is decomposed into two steps: vehicle candidate extraction, vehicle detection. By combination of L shape feature and point clouds segmentation, we extract the objects which are highly related to vehicles and apply 3D model to detect vehicles accurately. The method guarantees high detection performance and gives plentiful information for autonomous parking. To evaluate the method, we use various parking situation in complex urban scene data. Experimental results shows the qualitative and quantitative performance efficiently.

• 대한원격탐사학회지
• /
• 제27권5호
• /
• pp.565-572
• /
• 2011

본 연구에서는 초분광영상의 분광혼합분석을 위한 endmember를 효율적으로 추출할 수 있는 알고리즘을 개발하였다. 본 기법은 N-FINDR기법의 장점과 IEA기법의 장점을 혼합한 형태로서, 추출하고자하는 endmemebr의 개수 등 사전 입력변수를 전혀 요구하지 않는다. 또한 반복계산 과정에서 단계별로spectral unmixing을 수행하므로 endmember별 abundance fraction을 최종 결과물로 생성한다. USGS의 분광라이브러리를 이용하여 생성한 모의 초분광 영상자료에의 시험적용 결과, endmember의 개수와 반사특성, abundance fraction이 매우 정확하게 추출되고 있음을 확인할 수 있었다. 향후, 영상 영역 내에 단일 물질로 순수하게 100% 피복된 pure pixel이 존재하지 않는 경우가 흔히 발생하는 실제 초분광 영상자료에의 적용성 시험을 위한 연구가 진행될 예정이다.

• 한국항해항만학회지
• /
• 제32권6호
• /
• pp.447-452
• /
• 2008

본 연구에서는 만타형 수중운동체의 수평 및 수직 방향에 대한 자동제어 및 충돌회피 시스템을 확립하였다. PID 제어이론, 퍼지 추론 등이 적용되었으며, 시뮬레이션에 사용된 6자유도 운동 방정식은 이론계산과 구속모형 시험에 의하여 확립하였다. PID제어에 의한 심도제어 결과가 제시되었으며, UUV의 충돌 위험도는 가상 소나 시스템을 이용한 퍼지 추론으로 추정하였다. 이를 이용하여 만타형 수중운동체의 심도제어 시스템 및 충돌회피 시뮬레이션 시스템이 개발되었다.

• 한국통신학회논문지
• /
• 제39C권6호
• /
• pp.490-496
• /
• 2014

무릎 관절 연골은 두께가 얇아 대부분 무릎 질환의 원인이 되고 있다. 그러므로 무릎 자기공명영상에서 관절 연골 분할은 무릎 질환의 정확한 진단을 위한 필수조건이다. 특히 수동이 아닌 전자동 방식으로 무릎 관절 연골을 분할하여야만 효과적인 무릎 질환 진단을 할 수 있다. 본 논문에서는 뇌 자기공명영상에서 대표적으로 사용되는 레벨 셋 기반의 영상 분할 기법을 분석하여 무릎 자기공명영상에 적용 시 문제점을 파악하고 이를 해결함으로써, 무릎 자기공명영상에 레벨 셋 기반 영상분할 방식을 적용하였다. 이는 본 논문에서 제안하는 분할기법을 사용할 경우 무릎 관절 연골 분할에 대한 모든 과정이 전자동화 되어 기존 반자동화 방식보다 빠른 처리가 가능하며, 3차원 형상화를 통해 보다 정확한 진단에 도움을 줄 수 있다. 또한 우리는 제안하고 있는 분할기법이 기존 대표적인 무릎 관절 분할보다 더 높은 정확도를 갖는 것을 실험을 통해 확인할 수 있었다.

• 정보처리학회논문지A
• /
• 제10A권6호
• /
• pp.685-690
• /
• 2003

새로운 무선인터넷 디바이스로써 주목받고 있는 PDA는 기능 개선을 위해서 다양한 애플리케이션 개발이 이루어지고 있으며 수시로 응용프로그램이 설치되어지고 있다. 또한 PDA는 전원이 방전 될 경우에 RAM(Random Access Memory)에 저장되어 있는 데이터가 모두 삭제되는 단점이 있어서 그때마다 프로그램을 다시 복원해야 한다. 본 논문에서는 PDA의 응용 프로그램을 설치할 경우에 사용자가 직접 애플리케이션을 설치해야 하는 기존의 문제점을 해결하기 위하여 자동으로 PDA 응용프로그램이 설치되는 시스템(PAIS : PDA Automatic Installation System)을 제안하였다. 이 시스템을 적용한 경우 사용자에게는 설치에 소요되는 시간과 노력을 감소시켜 편의를 제공하고, 기업에게는 프로그램 설치관련 홍보물 제작에 소요되던 비용을 절감 할 수 있는 효과가 있다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.544-547
• /
• 2002

According to the rising of national economic level. domestic consumption of vegetables having high additive values is increased continuously due to increased consumption of meat in last decade. These vegetables are produced almost in this country and are limited to import from neighbor countries in due of high transportation expenses for storing in refrigerated container. It is very important to mechanize the harvest work, forming more than 30% for their production cost, in order to cultivate variable vegetables at the same time according to their harvesting seasons. In this state its former harvest methods, with using of human power or semi-automatic harvest, caused to increase their production cost due to high labor cost and low working efficiency. The former onion harvest being operated almost by semi-automatic plant distributer mechanism have many limit and troublesome for cultivation spaces, vinyle mulched ridge, gravel mixture in soil. Therefore, it is necessary to develope a fully automatic and self-running situation and overcome above handicaps, even in the farm covered with vinyle house or mulch sheets. This newly developed onion harvest can be applied to plant various young trees and will be able to export together with onion haying their competition in the worldwide market in which the culinary vegetable method or farm conditions is similar to our country.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권9호
• /
• pp.4248-4270
• /
• 2018

This research aims at a new practical Intent fuzzing tool for detecting Intent vulnerabilities of Android apps causing the robustness problem. We proposed two new ideas. First, we designed an Intent specification language to describe the structure of Intent, which makes our Intent fuzz testing tool flexible. Second, we proposed an automatic tally method classifying unique failures. With the two ideas, we implemented an Intent fuzz testing tool called Hwacha, and evaluated it with 50 commercial Android apps. Our tool offers an arbitrary combination of automatic and manual Intent generators with executors such as ADB and JUnit due to the use of the Intent specification language. The automatic tally method excluded almost 80% of duplicate failures in our experiment, reducing efforts of testers very much in review of failures. The tool uncovered more than 400 unique failures including what is unknown so far. We also measured execution time for Intent fuzz testing, which has been rarely reported before. Our tool is practical because the whole procedure of fuzz testing is fully automatic and the tool is applicable to the large number of Android apps with no human intervention.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 추계학술발표대회
• /
• pp.346-349
• /
• 2018

In North-East asian countries, laver cultivation has been an important marine industry in coastal areas as well as fishery because laver (Porphyra) is nutrient-rich food and has been used in many Asian cuisines. Laver is characterized by high concentrations of fiber and minerals, a low fat content, and, in some cases, relatively high protein levels. In this paper we inplimented design of fully automatic laver harvesting, nowdays most peoples are used to collect a laver harvesting by human, it is very defficult working, due to wind, waves, and the weather conditions which is hard to stand on the ship and holding the seaweed nets it can be injurced human, this is the reason to we are developed automatic harvesting method, in this project we proposed automatic harvesting collect method which is operated without human. Mainly we design and developed automated ship, This ship is devided in to three parts frist part is supporting roller, second part is drum screener, thried part is lifting mechanism. Thise are operated with hydro pnumatic equimpment, this divice are control with micro controller. The system prototype has implemented and satisfied by the performance to realize the further level.

• PNF and Movement
• /
• 제22권1호
• /
• pp.1-11
• /
• 2024

Purpose: The prevalent use of mobile devices may contribute to musculoskeletal disorders, such as forward head posture (FHP), among users. The measurement of the craniovertebral angle (CVA) using photographic images is frequently employed in assessing FHP. Although manual CVA measurement using photographic images is reliable in clinical settings, computer programs or mobile applications to support tele-physical therapy are not yet fully developed. Therefore, in the current study, we propose an automatic method for extracting CVA from photographic images of FHP subjects to facilitate tele-physical therapy. Methods: To develop the automatic CVA measuring computer program, photographic images were obtained from 10 FHP participants. The location information obtained from the markers attached to the tragus and the spinous process of the seventh cervical vertebra were used as coordinates. Using these coordinates, straight line 1 was generated by connecting the seventh spinous process of the cervical vertebra and the tragus, while straight line 2 was drawn parallel to the coordinate obtained from the seventh spinous process of the cervical vertebra. The arc tangent function was used to calculate the angle between the two straight lines. The automatic CVA measurement computer program utilizing photographic images was developed using MATLAB (ver. 2016b). Results: The results showed that the automatic CVA measurement computer program demonstrated stable repeatability and high accuracy. Conclusion: The proposed approach was able to automatically estimate the CVA using photographic images. The developed computer program can potentially be used for easier and more reliable clinical assessment of FHP.

• International Journal of Contents
• /
• 제14권1호
• /
• pp.1-6
• /
• 2018

Text, as one of the most influential inventions of humanity, has played an important role in human life since ancient times. The rich and precise information embodied in text is very useful in a wide range of vision-based applications such as the text data extracted from images that can provide information for automatic annotation, indexing, language translation, and the assistance systems for impaired persons. Therefore, natural-scene text detection with active research topics regarding computer vision and document analysis is very important. Previous methods have poor performances due to numerous false-positive and true-negative regions. In this paper, a fully-convolutional-network (FCN)-based method that uses supervised architecture is used to localize textual regions. The model was trained directly using images wherein pixel values were used as inputs and binary ground truth was used as label. The method was evaluated using ICDAR-2013 dataset and proved to be comparable to other feature-based methods. It could expedite research on text detection using deep-learning based approach in the future.