• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.240-243
• /
• 2018

최근 VR(Virtual Reality)와 AR(Augmented Reality)의 발전에 따라 영상 또는 이미지에서 카메라와 물체 사이의 거리를 추정하는 기술에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 카메라와 물체 사이의 거리 추정 방법 중에서 단일 카메라를 이용하여 촬영한 이미지의 흐림 정도를 분석하여 3D 거리를 추정하는 알고리즘을 연구한다. 특히 고가의 렌즈가 장착된 DSLR 카메라가 아닌 스마트폰 카메라 이미지에서 DFD를 이용한 거리 추정 방법 중 1개의 이미지를 이용한 3D 거리 추정 방법과 초점이 서로 다른 2개의 이미지를 결합하여 3D 거리를 추정하는 방법을 연구하고 최적회된 피사체 범위에 대해 연구하였다. 한 개의 이미지를 이용한 거리 추정에서는 카메라의 초점 거리를 200 mm로 설정할 때, 두 개의 이미지를 이용한 거리 추정에서는 두 이미지의 초점 거리를 각각 150 mm, 250 mm로 설정했을 때 가장 넓은 거리 추정 범위를 갖는다. 또한, 두 거리 추정 방법 모두 초점 거리가 가까울수록 가까운 물체의 거리 추정에 효율적인 것으로 나타났다.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1689-1692
• /
• 2003

본 논문에서는 홍채인식 시스템에서 효율적인 영상을 획득을 위한 이미지 기반 자동초점 계산방법을 제안한다. 제안된 방법은 동공 영역을 중심으로 Block단위로 이미지 기반 초점 계수를 조합하여 Out-of-Focusing 현상이나 노이즈의 간섭을 줄여줄 수 있다. 22800장의 홍채 영상을 이용한 실험 결과를 통해 제안하는 방법이 약 95%의 효율성을 가짐을 증명하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.189-196
• /
• 2024

Currently, it is almost impossible to move the focus of a previously taken photo to a different location. This paper challenges a technology that can move the focus of a captured photo to another location after shooting. To achieve this goal, this paper proposed and implemented a method for taking photos with various focuses at the moment the camera took pictures and storing them in a single JPEG file to extract photos focused on the user's preferred location. In this paper, two methods are implemented: taking various photos by quickly moving the focal length of the lens from close to far away, and taking various photos focused on each object by recognizing objects in the camera viewfinder. Various photos taken are stored in a single JPEG to maintain compatibility with traditional photo viewers. At this time, this JPEG file used the All-in-JPEG format proposed in previous research to store a variety of images. This paper verified its practicality by implementing these technologies in an Android app named OnePIC.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2697-2704
• /
• 2011

In tissue engineering area, researchers observe symbiotic relationship such as proliferation, interaction, division apoptosis with time between cells in process of the 3D cell culture in hydrogels. The 3D cell culture process can be taken photographs into sliced images using confocal microscope. Symbiotic mechanism and changes of cell behaviors can be observed and analyzed from the images acquired by confocal microscope. In this paper, we proposed and developed graded noise elimination method and cluster boundary extraction method to extract boundaries information from sliced confocal images acquired in process of the 3D cell culture in hydrogels. The experiment based algorithm showed excellent performance for eliminating noises that have very small millet-shaped size. It is also showed to extract exact boundaries information for even complex clusters.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.31-41
• /
• 2023

Directly converting the focal depth and image size of computer-generated-hologram (CGH), which is obtained by calculating the interference pattern of light from the 3D image, is known to be quite difficult because of the less similarity between the CGH and the original image. This paper proposes a method for separately converting the each of focal length of the given CGH, which is composed of multi-depth images. Firstly, the proposed technique converts the 3D image reproduced from the CGH into a Light-Field (LF) image composed of a set of 2D images observed from various angles, and the positions of the moving objects for each observed views are checked using an object detection algorithm YOLOv5 (You-Only-Look-Once-version-5). After that, by adjusting the positions of objects, the depth-transformed LF image and CGH are generated. Numerical simulations and experimental results show that the proposed technique can change the focal length within a range of about 3 cm without significant loss of the image quality when applied to the image which have original depth of 10 cm, with a spatial light modulator which has a pixel size of 3.6 ㎛ and a resolution of 3840⨯2160.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1311-1316
• /
• 2021

In this paper, we present a bifocal stereo camera system combining two cameras with different focal length cameras to generate stereoscopic image and their corresponding depth map. In order to obtain the depth data using the bifocal stereo camera system, we perform camera calibration to extract internal and external camera parameters for each camera. We calculate a common image plane and perform a image rectification for generating the depth map using camera parameters of bifocal stereo camera. Finally we use a SGM(Semi-global matching) algorithm to generate the depth map in this paper. The proposed bifocal stereo camera system can performs not only their own functions but also generates distance information about vehicles, pedestrians, and obstacles in the current driving environment. This made it possible to design safer autonomous vehicles.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.124-127
• /
• 2019

본 논문에서는 단일 이미지의 관심 영역에 기반한 저심도 후처리 방법을 제안한다. 저심도 이미지란 사진에서 초점이 선명하게 포착되는 깊이의 범위가 좁은 이미지를 말한다. 기존의 광학적 특성을 이용한 저심도 이미지를 만드는 과정은 물리적인 구조 설계비용 문제가 존재한다. 또한, 이미지의 후처리 보정을 통한 방법은 이미지상의 사물 깊이 정보를 알기 어렵기 때문에 이미지의 심도를 후처리하기 어려웠다. 이에 따라 본 논문에서는 슈퍼 픽셀 군집화 방법을 통해 관심 영역을 찾고, 이에 기반하여 관심 영역이 부각될 수 있는 저심도 후처리 방법을 제안한다. 제안하는 후처리 방법은 슈퍼픽셀 군집화 방법을 통해 관심영역을 설정하여 배경 영역을 분리하고 블러 과정을 수행한다. 관심 영역을 제외한 부분을 확장 한 뒤 배경 블러를 거치기 때문에 후광효과가 현저히 줄어든 저심도 효과가 적용된 이미지를 얻을 수 있었고 MSRA-1000 데이터 셋 이미지에서 우수한 주관적 화질 결과를 보였다.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.3 s.357
• /
• pp.12-19
• /
• 2007

This paper proposes the enhanced auto-focus algorithm detecting several objects and selecting the target object. Proposed algorithm first detects some objects distributed in the image using focus measure operator and multi-window and then selects the target object through fuzzy reasoning with three fuzzy membership functions. Implementation can be simple because it only needs image sensor instead of infrared or ultrasonic equipment. Experimental result shows that the proposed algorithm can improve the quality of image by focusing to the target object.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.389-390
• /
• 2023

본 논문에서는 패션 매칭의 어려움을 해결해주기 위하여 '무신사' 쇼핑몰을 이용하여 크롤링하고 이를 정제한 dataset을 이용하여 패션 스타일의 핵심 요소 중 하나인 신발에 초점을 맞추어, 이미지 기반의 패션 매칭 시스템인 빅데이터 기반 패션 도우미, Shoes Navigator 를 제안한다. 이를 위해 컴퓨터 비전 및 딥 러닝 기술을 활용하여 이미지에서 의류 항목을 자동으로 감지하고, 스타일, 색상과 같은 패션 특성을 추출한다. 또한, 사용자의 개인적인 스타일을 고려하여 최적의 매칭을 제안하기 때문에 패션 코디 문제를 용이하게 해결할 수 있다.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.31 no.2 s.257
• /
• pp.159-166
• /
• 2007

Mixing between two or more reagents is one of important processes in biochemical microfluidics. In efficient micromixer design, it is essential to analyze flow pattern and evaluate mixing efficiency with good precision. In this work, mixing efficiency for Y-channel micromixer is measured by fluorescence intensity using LIF(Laser Induced Fluorescence) Confocal Microscope. The Y-channel micromixers are fabricated with polydimethylsiloxane(PDMS) and those are bonded to glass plate through Plasma bonding. Nile Blue A is injected into the micromixer as a fluorescence dye for measuring of fluorescence intensity by He/Ne laser. For visualization of the flow pattern, dynamic image capturing is carried out using CAM scope. For the comparison with computer simulation, modified SIMPLE algorithm for incompressible flow equation is solved for the same geometry as in the experiment. Throughout the experiments and computer simulation, accurate mixing efficiency evaluation process for a PDMS Y-channel micromixer is established.