• 로봇학회논문지
• /
• 제19권2호
• /
• pp.188-195
• /
• 2024

This paper proposes a photorealistic real-time dense 3D mapping system that utilizes a neural network-based image enhancement method and mesh-based map representation. Due to the characteristics of the underwater environment, where problems such as hazing and low contrast occur, it is hard to apply conventional simultaneous localization and mapping (SLAM) methods. At the same time, the behavior of Autonomous Underwater Vehicle (AUV) is computationally constrained. In this paper, we utilize a neural network-based image enhancement method to improve pose estimation and mapping quality and apply a sliding window-based mesh expansion method to enable lightweight, fast, and photorealistic mapping. To validate our results, we utilize real-world and indoor synthetic datasets. We performed qualitative validation with the real-world dataset and quantitative validation by modeling images from the indoor synthetic dataset as underwater scenes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.3981-4004
• /
• 2019

This paper proposes a novel method for locating objects in real space from a single remote image and measuring actual distances between them by automatic detection and perspective transformation. The dimensions of the real space are known in advance. First, the corner points of the interested region are detected from an image using deep learning. Then, based on the corner points, the region of interest (ROI) is extracted and made proportional to real space by applying warp-perspective transformation. Finally, the objects are detected and mapped to the real-world location. Removing distortion from the image using camera calibration improves the accuracy in most of the cases. The deep learning framework Darknet is used for detection, and necessary modifications are made to integrate perspective transformation, camera calibration, un-distortion, etc. Experiments are performed with two types of cameras, one with barrel and the other with pincushion distortions. The results show that the difference between calculated distances and measured on real space with measurement tapes are very small; approximately 1 cm on an average. Furthermore, automatic corner detection allows the system to be used with any type of camera that has a fixed pose or in motion; using more points significantly enhances the accuracy of real-world mapping even without camera calibration. Perspective transformation also increases the object detection efficiency by making unified sizes of all objects.

• 방송공학회논문지
• /
• 제21권2호
• /
• pp.192-199
• /
• 2016

혼합증강현실 기술은 순수 현실세계와 순수 가상세계를 제외한 증강현실과 증강 가상을 포함하여 현실세계와 가상세계를 혼합하는 내용을 다룬다. 혼합증강현실에서 현실세계에서 움직이는 라이브행동자와 실체(LAE: live actor and entity)가 3D 가상공간과 혼합하여 자연스럽게 표현될 수 있으면, 원격 3D 몰입 회의, 3D 가상 체험 교육 서비스 등이 가능하다. 따라서 본 논문에서는 LAE를 3D 가상공간에 자연스럽게 혼합하고, 서로서로 상호작용할 수 모델을 표준 제안한다. 제안한 모델을 기반으로 LAE의 혼합과 상호작용이 수행될 수 있다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제9권3호
• /
• pp.1-8
• /
• 2017

Recently, the development of the head mounted display (HMD) device has attracted a great deal of attention to the actual contents. Especially, Augmented Reality (AR), which is a mixture of actual information and virtual world information, is focused on. AR HMD is able to interact by arranging virtual objects in real space through spatial recognition using depth camera. In order to naturally mix virtual space with real space, it is necessary to develop a technology for realizing spatial mapping information with high accuracy. The purpose of this paper is to evaluate the optimal configuration of augmented reality application program by realizing accurate spatial mapping information when mapping a real space and an object placement environment using HoloLens. To do this, we changed the spatial mapping information in real space to three levels, which are the number of meshes used in cubic meters to scan step by step. After that, it was compared with the 3D model obtained by changing the actual space and mesh number. Experimental result shows that the higher the number of meshes used in cubic meters, the higher the accuracy between real space and spatial mapping. This paper is expected to be applied to augmented reality application programs that require scanning of highly mapped spatial mapping information.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.789-792
• /
• 2003

Pipe inspection has a great importance to ensure safety for the nuclear power plant. In this paper, we designed visual inspection module for the tube internal, which diameter is 15${\sim}$20mm. And we made inspection module which consisted of CCD camera and light. And the relation between image and real world coordinate is established. Image processing is performed to calculate mapping parameter and analyze the size of defect. For the calculation of mapping parameter, experiment is performed using grid type test pattern. Acquired image is processed to extract image coordinate. Edge detection, thresholding, median filtering and morphology filtering is applied to extract grid pattern. Extracted image coordinate is used to calculate image to real world mapping. Lens distortion was considered and corrected to get exact data. Coordinate transformation data is provided for the users to recognize easily. Experiment was performed using grid type test pattern, we extracted lens distortion parameter and real coordinate of defect point. Radial distortion of lens was corrected but tangential distortion was not considered. As continuum to this study, the tangential distortion of lens is considered and improvement of analy zing technique for the tube internal be explored continuously.

• 한국콘텐츠학회논문지
• /
• 제13권6호
• /
• pp.55-66
• /
• 2013

현대의 디스플레이는 스마트폰과 같은 소형기기, TV, 프로젝터 등에 다양하게 적용되고 있으며, 빠른 속도로 발전하고 있다. 그중 LDP, VCR, PC, DVD 등의 영상기기들에 연결하여 스크린에 이미지를 비추는 프로젝터는 다른 디스플레이 기기들과 비교하면 상대적으로 큰 화면을 표현할 수 있는 특징 때문에 영화관, 전시장 등에서 폭넓게 활용되고 있다. 프로젝터의 이러한 특징은 예술분야에서 프로젝션 매핑이라는 새로운 형식의 표현 기법을 탄생시켰으며, 프로젝션 매핑은 다양한 형태의 면을 스크린으로 사용하며, 현대에 들어 공연의 무대장치로까지 널리 활용되고 있다. 그러나 이와는 다르게 공연에서의 프로젝션 매핑기법은 공간상의 한계점을 갖고 있다. 본 연구에서는 이러한 제약사항을 보완할 수 있는 프로젝션 매핑공연을 위한 새로운 형태의 공연 시스템을 제안하며, 실제 공연에서의 활용 결과를 논의해 봄으로써, 공연에서의 프로젝션 매핑의 활용 가능성을 높이고자 한다.

• 대한원격탐사학회지
• /
• 제19권1호
• /
• pp.71-80
• /
• 2003

In this Paper, we Propose web-based Media GIS architecture using 3D geographical database and GPS-related data resulted from 45-Van. We introduce a novel interoperable geographical data service concept; so-called, Virtual World Mapping (VWM) that can map 3D graphic world with real-world video. Our proposed method can easily retrieve geographical information and attributes to reconstruct 3D virtual space according to certain frame in video sequences. Our proposed system architecture also has an advantage that can provide geographical information service with video stream without any image processing procedures. In addition to, describing the details of our components, we present a Media GIS web service system by using GeoVideoServer, which performs VWM technique.

• 반도체디스플레이기술학회지
• /
• 제20권4호
• /
• pp.182-186
• /
• 2021

Tone mapping operator is designed to reproduce visibility of real-world scenes such as HDR images on limited dynamic range display devices. This paper presents and implements compare and to estimate some tone mapping algorithms commonly used. The evaluation is performed by applying tone mapping operators on 7 HDR images, and by presenting the results with subjective estimation. Reinhard tone mapping algorithm is the best in the visual experimental results. The goal of this work is to discuss what is visible of high dynamic range on a normal display device and to determine to which better algorithm is. This work motivates us to make more progress through the new proposal of tone mapping operator on future work.

• 한국측량학회지
• /
• 제35권4호
• /
• pp.213-220
• /
• 2017

This study examines the limitations of existing crime mapping that relies mainly on reported crime data, suggests a crime mapping method based on experts' and users' assessments of a neighborhood environment as an alternative approach, and conducts a case study on a real-world site by applying the suggested approach. According to the results of the case analysis, while the areas adjoining arterial roads with heavy pedestrian traffic were shown as high crime risk areas in the crime map based on actual reported crime data, the areas adjoining local roads with low pedestrian traffic were high-risk areas in the crime risk area map based on experts' and residents' evaluations. This study makes a contribution to the field in that it demonstrates the detailed application process of crime risk area mapping according experts' and residents' evaluations, compares the results with those of an existing crime map, and finally shows that the former can function as a complement to the latter.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.92.2-92
• /
• 2002

Building autonomous robots have been a central objective of research in artificial intelligence. The development of techniques for autonomous navigation in real environment consist one of the main tendencies of the current researches about Robotics. An important problem in autonomous navigation is the necessity of dealing with a great amount of uncertainties inherent to the real environments. The paraconsistent logic has characteristics that make it become an adequate tool to solve this problem. In this work, it is proposed a technique of mapping the real world in the navigation of an autonomous robot using the paraconsistent logic.