• 제목/요약/키워드: Photo Classification

검색결과 79건 처리시간 0.029초

위성사진과 지리정보체계(GIS)에 의한 브라질 서부농장지역의 토지이용구분과 인공조림계획에 관한 연구 - Mato Grosso do Sul 주의 장가다 및 쟈마이카 농장 - (A Study of the Farm Land Use Classification and the Tree Plantation Planning of the Western Farm District in Brazil using Remote Sensing and Geographic Information Systems -Jangada and Jamaica Farm of the State Mato Grosso do Sul-)

  • 우종춘;죠세이마나-엔시나스
    • 대한원격탐사학회지
    • /
    • 제16권3호
    • /
    • pp.281-291
    • /
    • 2000
  • 본 연구에서는 브라질 서부의 Mato Grosso do Sul 주의 위치하는 장가다. 쟈마이카 두 개의 농장에 유칼리나무 인공조림블록단지를 위한 식재계획을 세워 보았다. 우선 위성사진을 분석하고 GIS에 의해서 현상태대로의 토지이용구분 및 산림식생구분을 하였고 이것을 기초로 하여 조림가능 지역을 계산하였다. 그리고 농장주인의 요구에 따라 조림가능지역에 대한 식재계획을 3차년도까지 수립하였다. 두 개의 농장 총면적은 5,301ha이며 조림가능면적은 3,913ha로서 전체면적의 74%에 해당하는 것으로 추정되었다. 그리고 나머지 26%에 해당하는 1,388ha의 면적은 산림법상 영구보존시켜야 할 산림식생 면적으로 추정되었다. 토양손실을 최소화하기 위해서 등고선에 따라 구획한 조림블록은 1년차에 27개 블록으로 총 1,308.8ha에 이르고, 2년차에도 27개 블록에 1,327.4ha, 그리고 3년차에는 30개 블록에 1,276.5ha의 면적으로 구획되었다.

지적정보 서비스 모바일 애플리케이션 개발 (Development of Mobile Application for Cadastre Information Service)

  • 이근상;김형준
    • 한국지리정보학회지
    • /
    • 제15권4호
    • /
    • pp.55-64
    • /
    • 2012
  • 본 연구에서는 지적재조사사업을 비롯하여 다양한 지적업무를 효과적으로 추진하기 위해 필요한 지적정보를 서비스하기 위한 모바일 애플리케이션 시스템을 개발하였다. 먼저 스마트폰이나 태블릿 PC 등의 모바일 기반 지적정보시스템을 구현하기 위해 BlackPoint-Xr을 공간 클라이언트 엔진으로 선정하였다. 모바일 지적정보 시스템은 항공사진, 지적도, 행정구역도, DEM 등의 공간정보를 기반으로 GPS를 통한 위치 찾기, 주소와 지번을 통한 필지 검색 그리고 필지에 대한 주소, 지목, 공시지가 등의 토지대장 정보를 확인할 수 있는 기능이 포함되어 있다. 특히 본 연구에서는 건설공사나 토지정비사업 등에 활용하기 위해 필지에 대한 거리, 면적, 경사 그리고 횡단면도 등을 분석할 수 있는 기능도 개발하였다. 본 시스템은 현장에서 다양한 지적정보를 사용자들에게 서비스해 줌으로서 지적업무와 건설공사 등을 효과적으로 지원할 수 있고 디지털 지적정보 분야에도 응용될 수 있을 것으로 판단된다.

마케팅 믹스를 활용(活用)한 의류(衣類)브랜드 웹사이트 분석(分析) -유니섹스 브랜드를 중심(中心)으로- (A Study on Website Analysis of apparel Brand through Marketing Mix -Focusing on Unisex Brand-)

  • 이미경;나수임
    • 패션비즈니스
    • /
    • 제11권4호
    • /
    • pp.69-81
    • /
    • 2007
  • This study, for the purpose of comparing and analyzing 23ea of national unisex apparel brands website consists of product, price, promotion and place divided by marketin gmix. Based of theoretical study and pre-research about the marketing mix, we made the classification standard for the marketing mix and analyzed the unisex apparel brand website according to 4P's individual item and the result was appeared like this. First of all, in the product section, this study provide information about product introduction/guidance, a product figure for item, introduction for new items, propose for coordination and brand introduction/information. Secondly, in the price part, almost apparel brands are provide their product's image, or present their goods photo with price, or displayed through the banner advertisement of discount or special price. Thirdly, For the marketing promotion part, compare to the other component in the most of apparel brand's website, marketing promotion has more section than the other marketing mix. And, especially, various events and customer service space has more weight than the others. Forth, in the place section, it's focused on the information of shopping mall location, contact number, address, and on-line shopping mall. In Conclusion, when the most of apparel brands are doing internet marketing, they're concern to product and promotion, but price and place needs more supplement in the unisex apparel brand's marketing mix.

효과적인 이미지 검색을 위한 태그 기반의 폭소노미 이미지 카테고리화 기법 (A Categorization Scheme of Tag-based Folksonomy Images for Efficient Image Retrieval)

  • 하은지;김용성;황인준
    • 정보과학회 컴퓨팅의 실제 논문지
    • /
    • 제22권6호
    • /
    • pp.290-295
    • /
    • 2016
  • 최근 사용자들이 협동적으로 이미지 주석인 태그를 만들고 활용하는 폭소노미 기반의 이미지 공유 사이트들이 많은 인기를 얻고 있다. 이러한 사이트는 사용자 질의에 대해 단순한 텍스트 매칭 기반의 검색을 수행하고 매칭되는 결과 이미지들을 포토 스트림 형태로 나열하여 보여 준다. 하지만 이러한 태그들은 매우 개인적이고 주관적이며, 이미지 역시 카테고리로 분류되어 있지 않기 때문에 검색의 정확도나 사용자 만족도가 떨어진다는 문제점이 있다. 본 연구에서는 태그를 기반으로 하는 이미지 검색에서 검색의 정확도를 높일 수 있는 폭소노미 이미지의 카테고리화 기법을 제안하고, 폭소노미 환경에서 생성된 태그와 이미지 정보를 모두 이용하며 의미적으로 유사한 이미지들끼리 분류된 검색 결과를 생성한다. 제안하는 기법의 성능 평가를 위해 폭소노미 이미지를 수집하고 텍스트, 이미지 특성에 따른 카테고리 분류를 수행하여 기존 검색 기법과 이미지 검색의 정확도를 비교한다.

Fold 건축 특성 분석에 따른 Issey Miyake 패션의 Fold 특성 (Issey Miyake fashion's fold characteristics through fold architecture)

  • 서미희;윤정아;이연희
    • 복식문화연구
    • /
    • 제23권5호
    • /
    • pp.861-875
    • /
    • 2015
  • This study examines the formative characteristics of Fold architecture and how its properties are shown in the fashion of the modern work of Issey Miyake through analysis. In this research, the Fold classification criteria for analysis features that appeared in Issey Miyake fashion features were established through research literature on Fold architecture and leading research. Empirical data collection was conducted for Issey Miyake's work and collection by collecting photo materials, and design concepts and the results are analyzed in terms of features. Study ranges of Issey Miyake's creative design development are Pleats Please, A-POC, 132.5 project, and collections from 2000 to 2014. The conclusion is as follows. First, design concepts presented in the Issey Miyake fashion features of Fold are Hybrid, topology, and uncertainty. Hybrid look for the meaning of fashion, which is the interaction between the wearer and garments. The concept of topology designs clothing, focusing on interrelationship of the body and clothing, and pays no attention to absolute size or the form of the clothing. The concept of uncertainty is an uncertain form that is infinitely expandable because all the elements have openness and uncertainty due to the determined incomplete state by the creator. Second, in the results presented in the Issey Miyake fashion features is the destruction of the boundary and diagram form. The destruction of the boundary is free from traditional clothing. The diagram form is a geometric form which does not create a Dart or Princess line.

서양복식에 나타난 양적과장의 미의식에 관한 연구 (II) - 현대패션을 중심으로 - (The Aesthtics Consciousness of Voluminous Enlargement in the Western Costume - In the 20th Century -)

  • 성광숙;이순홍
    • 복식
    • /
    • 제54권7호
    • /
    • pp.151-164
    • /
    • 2004
  • This Studies on 20th century fashion was carried out according to the classification of the times as made up Belle Epoque, New Look, Big Look, and Body-Consciousness. Aside from research in literatures, research into 20th fashion also include the analysis of photo had been taken from various collection. The enlargement beauty of costume had been place under the aesthetic category and, by interpreting the analogies of presented in aesthetic consciousness. the true nature of the voluminous enlargement in costume had been traced. To conclude, this study finds there are between the aesthetic characteristic differences in the aesthetic consciousness of the costumes in history and the present-day fashion. The aesthetic consciousness of the voluminous enlargement of the present-day was found to have the following characteristic ; (1) History-oriented tradition (2) Metaphorica autonomous (3) Freedom of breaking with restriction (4) Dismantling the irregularity (5) Hedonistic play instinct (6) Psychological compensation (7) Sexual sensuality (8) Ideal of the times (9) Aesthetic ornament (10) Feeling of satisfaction through self-enlargement. From list above. metaphorical sensuality, aesthetic ornament and the feeling of satisfaction driven by Self-Enlargement are the same characteristics found in the aesthetics consciousness of the voluminous enlargement of the costume In history in that they are the aesthetic consciousness above time and space. It is metaphorical sensuality which transform woman's body in to distorted images as influenced by both capitalism and materialism in the last 20 years. These are represented by the sadomasochistic and fetish images as the woman's metaphorical voluminous enlargement is apparently becoming more positive, radical and obscene especially in terms of expression.

12인승 밴 전복사고의 상해 분석 (Injury Analysis of a 12-passenger Van Rollover Accident)

  • 김상철;최형연;김병우;박관진;안성민;이강현
    • 자동차안전학회지
    • /
    • 제10권1호
    • /
    • pp.20-26
    • /
    • 2018
  • The fatality of rollover accidents in motor vehicle crashes is high despite their low incidence. Through the investigation of a 12-passenger van rollover accident in which 10 passengers were involved, we intend to analyze the correlation between the severity of the injury and the position of the occupants. We collected accident information from medical records, interviews, photo-images of the damaged van, field surveys, and the results of the Korean New Car Assessment Program (KNCAP). Based on the occupants' position, we classified injury sites and estimated injury severity. Passenger injury severity was evaluated by trauma score calculation. The initiation type of the rollover accident was passenger side 'fall-over' and the Collision Deformation Classification (CDC) code for the damaged van was 00TDZO3. The crash of the van involved 10 passengers, with an average age of $16.3{\pm}4.2years$. Few of the occupants had fastened seat belts at the time of the incident, and there was no airbag installed. One patient sustained severe liver injury and another was diagnosed with a fracture of the right humerus. The most common injuries were at the upper extremities and the neck. The average of Injury Severity Score (ISS) was $4.8{\pm}5.9$, and the average ISS of right-seated, mid-seated and left-seated occupants was $7.5{\pm}9.3$, $1.5{\pm}0.7$, and $3.3{\pm}2.1$ respectively (p>0.05). In the rollover (to-passenger side) accident of occupant unfastened, the average ISS of right-seated occupants (near side) was higher, but there was no statistically significant difference.

TMDL에서의 토지피복지도 활용 제고를 위한 GIS기반 현행화 방법 연구 (A Study on a GIS based Updating Methodology of Landcover Maps for the Enhancement of Utilization in the Total Maximum Daily Loads)

  • 곽근호;김계현;이철용;오성광
    • 한국물환경학회지
    • /
    • 제30권3호
    • /
    • pp.340-350
    • /
    • 2014
  • Recently, TMDL has been implemented to estimate the amount of pollutant loads and to establish proper mitigation strategy to decrease the pollutant loads by the Ministry of Environment. To estimate the amount of pollutant loads with reasonable accuracy, securing landcover map with periodically updating is essential. However, in reality, due to the technical and financial difficulties, the landcover map has not been updated annually. Hence, this study mainly aims to suggest an effective GIS-based updating method in order to promote utilization of landcover map in the estimation of pollutant loads. Bupyeong-gu at the City of Incheon with the total area of $31.98km^2$ was chosen for this study and spatial data including digital topographic maps, ortho aerial photo, and satellite images were collected and utilized. A total of 7,235 feature entities were newly produced through the updating process of five steps and it was revealed that the classification of landcover with the total area of $3.34km^2$ was to be changed. The validity and feasibility of the suggested method were proved with the accuracy of 97.9% from the field verification. Further study needs to be made for devising more automated method to update landcover map to facilitate TMDL for individual local governments.

3차원 안면 자동 인식기(3D-FARA)의 안면 위치변화에 따른 정확도 검사 (Precision Test of 3D Face Automatic Recognition Apparatus(3D-FARA) by Rotation)

  • 석재화;조경래;조용범;유정희;곽창규;이수경;고병희;김종원;김규곤;이의주
    • 사상체질의학회지
    • /
    • 제18권3호
    • /
    • pp.57-63
    • /
    • 2006
  • 1. Objectives The Face is an important standard for the classification of Sasang Contitutions. Now We are developing 3D Face Automatic Recognition Apparatus to analyse the facial characteristics. This apparatus show us 3D image of man's face and measure facial figure. We should examine accuracy of position recognition in 3D Face Automatic Recognition Apparatus. 2. Methods We took a photograph of Face status with Land Mark 8 times using Face Automatic Recognition Apparatus. Each taking-photo, We span Face statusby 10 degree. At last time, We took a photograph of Face status's lateral face. And We analysed Error Averige of Distance between seven Land Marks. So We examined the accuracy of position recognition in 3D Face Automatic Recognition Apparatus at indirectly in degree changing of Face status. 3. Results and Conclusions According to degree change of Face status, Error Averige of Distance between Seven Land Marks is 0.1848mm. In conclusion, We assessed that accuracy of position recognition in 3D Face Automatic Recognition Apparatus is considerably good in spite of degree changing of Face status

  • PDF

불법 산양삼 검출을 위한 인공지능 기술에서의 산양삼과 인삼 이미지의 분류 기저화 연구 (A Study on Basalization of the Classification in Mountain Ginseng and Plain Ginseng Images in Artificial Intelligence Technology for the Detection of Illegal Mountain Ginseng)

  • 박수경;나호준;김지혜
    • 한국빅데이터학회지
    • /
    • 제5권1호
    • /
    • pp.209-225
    • /
    • 2020
  • 본 연구는 인삼과 산양삼에 대해 아무런 정보가 없는 초보 소비자가 인삼을 산양삼이라 여기는 사기 상황을 방지하는 차원에서 산양삼 형태에 대한 기저수준을 확립하려했다. 이를 위해 연구자들은 소비자가 스마트폰의 전용 APP으로 인삼을 촬영하면 그 사진이 원격으로 전송되어, 기계학습데이터를 기반으로 판별한 결과가 소비자에게 전송되는 서비스디자인을 고안했다. 연구과정에서의 데이터 셋과 소비자들이 스마트폰을 통해 촬영했을 때의 배경색, 산양삼의 위치, 크기, 조도, 색온도 등과의 차이를 최소화 하기 위해 소비자 용 전용 촬영 박스를 디자인 했다. 이에 따라 산양삼 샘플 수집은 디자인된 박스와 동일한 통제된 환경과 세팅 하에서 이루어졌다. 이를 통해 기계학습에서 통상 필요한 것 보다 약 1/10이 적은 샘플을 사용해 CNN(VGG16)모델에서 예측 확율 100%를 얻었다.