http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
어안 렌즈를 이용한 디지털 영상기반의 사람 수 측정에 관한 연구
김영학,권헌진,고재필,조수현,남인길 한국특허학회 2009 특허학연구 : 한국특허학회지 Vol.11 No.1
본 연구에서는 어안 렌즈를 사용한 디지털 영상에 기반 하여 사람의 수를 계산하는 새로운 방법을 제안한다. 먼저, 촬영화각이 180도에 가까운 어안 렌즈가 장착된 디지털 카메라를 임의의 장소나 공간 설치하여 입력영상을 생성하고 그 입력영상을 분석한 데이터를 만든다. 다음에 새로운 영상을 전 단계에서 분석된 입력 영상과 비교하여 확률적인 방법을 사용하여 사람의 수를 측정한다. 실험결과에 의하면 제안된 방법은 기존의 바둑판식 방법보다 성능이 좋음을 보였다. This paper proposes a new method that counts the number of people based on digital image using fish-eye lens. First, a digital camera with built-in fish-eye lens near 108˚ angle of view is installed in an arbitrary place and space, and then the input image is created and the analysis data of the input image is made. Second, the new input image is compared to the analyzed input image in the previous step, and the number of people is counted using the probability method. According to the experiment result, the performance of the proposed method is much improved than the one of baduk board.
A Study on 360° Image Production Method for VR Image Contents
곽대위,정진헌 한국디지털정책학회 2017 디지털융복합연구 Vol.15 No.12
360°panoramic image can give people an unprecedented visual experience, and there are many different ways to make a 360°panoramic image. In this paper, we will introduce two easy and effective methods from those many ways. The first one is through 48 photos to make a 360°panoramic image, the second way is through 6 photos to make a 360°panoramic image. We will compare those methods and tell the audience which one suits themselves. Through those easy design methods introduced above, we can see VR works design became easy and popular, normal people can also make 360°panoramic image, and it promotes the industry of VR image contents.
한갑수,윤영활,조현길,Han Gab-Soo,Yoon Young-Hwal,Jo Hyun-Kil 한국조경학회 2005 韓國造景學會誌 Vol.33 No.4
The purpose of this study was to analyze and evaluate landscape characteristics by classification of landscapes in Chuncheon. A system was developed to convert images taken with a fish-eye lens to panoramic pictures. Landscape characteristics were analyzed by appearance rate and area distribution rate of landscape elements on panorama picture. Landscape characteristics were analyzed according to the number of times landscape elements appeared and the amount of area that each element occupied in the panoramic picture. Each panoramic picture was classified into five types based on these landscape element factors. Landscape evaluation was carried out using dynamic images converted from picture by fish-eye lens. The results of this study can be summarized as follows. The urban landscape can be characterized by four essential factors: interconnectedness, nature, urban centrality and landscape scale. Five types of landscapes were determined: detached residential building landscape (type 1), street landscape with various elements (type 2), street landscape in the center of a city (type 3), landscape of housing complex (type 4), and landscape of green space (type 5). Type 5 had the highest degree of landscape satisfaction and the landscape satisfaction increased with the number of appearances of natural elements. The amount of peen space had a high relation with a landscape satisfaction.
어안 이미지의 배경 제거 기법을 이용한 실시간 전방향 장애물 감지
최윤원,권기구,김종효,나경진,이석규,Choi, Yun-Won,Kwon, Kee-Koo,Kim, Jong-Hyo,Na, Kyung-Jin,Lee, Suk-Gyu 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.8
This paper proposes an object detection method based on motion estimation using background subtraction in the fisheye images obtained through omni-directional camera mounted on the vehicle. Recently, most of the vehicles installed with rear camera as a standard option, as well as various camera systems for safety. However, differently from the conventional object detection using the image obtained from the camera, the embedded system installed in the vehicle is difficult to apply a complicated algorithm because of its inherent low processing performance. In general, the embedded system needs system-dependent algorithm because it has lower processing performance than the computer. In this paper, the location of object is estimated from the information of object's motion obtained by applying a background subtraction method which compares the previous frames with the current ones. The real-time detection performance of the proposed method for object detection is verified experimentally on embedded board by comparing the proposed algorithm with the object detection based on LKOF (Lucas-Kanade optical flow).
어안 이미지의 배경 제거 기법을 이용한 실시간 전방향 장애물 감지
최윤원(Yun-Won Choi),권기구(Kee-Koo Kwon),김종효(Jong-Hyo Kim),나경진(Kyung-Jin Na),이석규(Suk-Gyu Lee) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.18 No.1
This paper proposes an object detection method based on motion estimation using background subtraction in the fisheye images obtained through omni-directional camera mounted on the vehicle. Recently, most of the vehicles installed with rear camera as a standard option, as well as various camera systems for safety. However, differently from the conventional object detection using the image obtained from the camera, the embedded system installed in the vehicle is difficult to apply a complicated algorithm because of its inherent low processing performance. In general, the embedded system needs system-dependent algorithm because it has lower processing performance than the computer. In this paper, the location of object is estimated from the information of object’s motion obtained by applying a background subtraction method which compares the previous frames with the current ones. The real-time detection performance of the proposed method for object detection is verified experimentally on embedded board by comparing the proposed algorithm with the object detection based on LKOF (Lucas-Kanade optical flow).