检索结果-南通市图书馆

Removing fences from sweep motion videos using global 3D reconstruction and fence-aware light field rendering

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2019年第1期5卷 21-32页

作者： Chanya Lueangwattana Shohei Mori hideo saito Department of Science and Technology Keio University Institute of Computer Graphics and Vision Graz University of Technology

Diminishing the appearance of a fence in an image is a challenging research area due to the characteristics of fences(thinness, lack of texture, etc.) and the need for occluded background restoration. In this paper, we describe a fence removal method for an image sequence captured by a user making a sweep motion, in which occluded background is potentially observed. To make use of geometric and appearance information such as consecutive images, we use two well-known approaches: structure from motion and light field rendering. Results using real image sequences show that our method can stably segment fences and preserve background details for various fence and background combinations. A new video without the fence, with frame coherence, can be successfully provided.

关键词： video fence video repair diminished reality(DR) structure from motion(SfM) light field rendering(LFR)

On-line Free-viewpoint Video:From Single to Multiple View Rendering

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2008年第3期5卷 257-267页

作者： Vincent Nozick hideo saito Graduate School of Science and Technology Keio University

In recent years, many image-based rendering techniques have advanced from static to dynamic scenes and thus become video-based rendering （VBR） methods. But actually, only a few of them can render new views on-line. We present a new VBR system that creates new views of a live dynamic scene. This system provides high quality images and does not require any background subtraction. Our method follows a plane-sweep approach and reaches real-time rendering using consumer graphic hardware, graphics processing unit （GPU）. Only one computer is used for both acquisition and rendering. The video stream acquisition is performed by at least 3 webcams. We propose an additional video stream management that extends the number of webcams to 10 or more. These considerations make our system low-cost and hence accessible for everyone. We also present an adaptation of our plane-sweep method to create simultaneously multiple views of the scene in real-time. Our system is especially designed for stereovision using autostereoscopic displays. The new views are computed from 4 webcams connected to a computer and are compressed in order to be transfered to a mobile phone. Using GPU programming, our method provides up to 16 images of the scene in real-time. The use of both GPU and CPU makes this method work on only one consumer grade computer.

关键词： Video-based rendering (VBR) free-viewpoint video view interpolation graphics processing unit (GPU) webcam stereovision autostereoscopic.

Synthesis of a stroboscopic image from a hand-held camera sequence for a sports analysis

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2016年第3期2卷 277-289页

作者： Kunihiro Hasegawa hideo saito Keio University

This paper presents a method for synthesizing a stroboscopic image of a moving sports player from a hand-held camera sequence. This method has three steps: synthesis of background image,synthesis of stroboscopic image, and removal of player's shadow. In synthesis of background image step, all input frames masked a bounding box of the player are stitched together to generate a background image. The player is extracted by an HOG-based people *** synthesis of stroboscopic image step, the background image, the input frame, and a mask of the player synthesize a stroboscopic image. In removal of shadow step, we remove the player's shadow which negatively affects an analysis by using mean-shift. In our previous work, synthesis of background image has been timeconsuming. In this paper, by using the bounding box of the player detected by HOG and by subtracting the images for synthesizing a mask, computational speed and accuracy can be improved. These have contributed greatly to the improvement from the previous *** are main improvements and novelty points from our previous method. In experiments, we confirmed the effectiveness of the proposed method, measured the player's speed and stride length, and made a footprint image. The image sequence was captured under a simple condition that no other people were in the background and the person controlling the video camera was standing still, such like a motion parallax was not occurred. In addition, we applied the synthesis method to various scenes to confirm its versatility.

关键词： sports vision stroboscopic image stitching mask synthesis

FusionMLS:Highly dynamic 3D reconstruction with consumergrade RGB-D cameras

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2018年第4期4卷 287-303页

作者： Siim Meerits Diego Thomas Vincent Nozick hideo saito Department of Information and Computer Science Keio University Department of Advanced Information Technology Kyushu University LIGM UMR 8049Universit'e Paris-Est Marne-la-Vall'ee Japanese–French Laboratory for Informatics CNRS

Multi-view dynamic three-dimensional reconstruction has typically required the use of custom shutter-synchronized camera rigs in order to capture scenes containing rapid movements or complex topology changes. In this paper, we demonstrate that multiple unsynchronized low-cost RGB-D cameras can be used for the same purpose. To alleviate issues caused by unsynchronized shutters, we propose a novel depth frame interpolation technique that allows synchronized data capture from highly dynamic 3 D scenes. To manage the resulting huge number of input depth images, we also introduce an efficient moving least squares-based volumetric reconstruction method that generates triangle meshes of the scene. Our approach does not store the reconstruction volume in memory,making it memory-efficient and scalable to large *** implementation is completely GPU based and works in real time. The results shown herein, obtained with real data, demonstrate the effectiveness of our proposed method and its advantages compared to stateof-the-art approaches.

关键词： 3D reconstruction RGB-D cameras motion capture GPU

PCA-based 3D Shape Reconstruction of Human Foot Using Multiple Viewpoint Cameras

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2008年第3期5卷 217-225页

作者： Edmée Amstutz Tomoaki Teshima Makoto Kimura Masaaki Mochimaru hideo saito Graduate School of Science and Technology Keio University Digital Human Research Center National Institute of Advanced Industrial Science and Technology(AIST)

This paper describes a multiple camera-based method to reconstruct the 3D shape of a human foot. From a foot database, an initial 3D model of the foot represented by a cloud of points is built. The shape parameters, which can characterize more than 92% of a foot, are defined by using the principal component analysis method. Then, using ＂active shape models＂, the initial 3D model is adapted to the real foot captured in multiple images by applying some constraints （edge points＇ distance and color variance）. We insist here on the experiment part where we demonstrate the efficiency of the proposed method on a plastic foot model, and also on real human feet with various shapes. We propose and compare different ways of texturing the foot which is needed for reconstruction. We present an experiment performed on the plastic foot model and on human feet and propose two different ways to improve the final 3D shapers accuracy according to the previous experiments＇ results. The first improvement proposed is the densification of the cloud of points used to represent the initial model and the foot database. The second improvement concerns the projected patterns used to texture the foot. We conclude by showing the obtained results for a human foot with the average computed shape error being only 1.06 mm.

关键词： Shape measurement 3D reconstruction from multiview cameras principal component analysis

Effects of Particle Size on Microstructure of the Matrix Alloy in Aluminum Matrix Composites

在线全文

学校读者我要写书评

暂无评论

Effects of Particle Size on Microstructure of the Matrix All...

亚微米颗粒对铝基复合材料基体显微结构的影响

International Conference on Aerospace Materials(ICAM 2006)

作者： Norio kouno hideo saito Department of Metallurgical Engineering Chiba Institute of Technology Japan Analysis Center of Materials Chiba Institute of Technology Japan

Aluminum matrix composites, reinforced by 0.15μm and 5μm Al2O3 particles with 40% volume fractions were fabricated by squeeze casting technique. The microstructure characterization near the interfaces of Al2O3p/1070Al composites was investigated by SADP and HREM techniques. Results showed that high-density dislocations were generated in the 5μm-Al2O3p/Al composite due to the thermal mismatch stress. In contrast, the matrix of the 0.15μm-Al2O3p/Al composite appeared to be nearly free dislocations and some "micro distortion areas" of 1-5nm were observed, which was attributed to the dispersion of fine sub-micron particles and uniform distribution of the stress near the interfaces.

关键词： Metal matrix composites Al2O3p/Al sub-micron Al2O3 particles Microstructure

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

稀有金属材料与工程 2007年第6期36卷 1002-1004页

作者：姜龙涛武高辉河野纪雄齐藤秀雄哈尔滨工业大学黑龙江哈尔滨150001 日本千叶工业大学金属工学科

选用0.15μm和5μm的Al2O3颗粒,采用挤压铸造法制备了体积分数为40%的铝基复合材料。利用选区电子衍射和高分辨电子显微技术研究了Al2O3P/1070Al界面附近基体的显微组织。结果表明,复合材料增强体颗粒为5μm时,基体存在大量的由热错配... 详细信息

选用0.15μm和5μm的Al2O3颗粒,采用挤压铸造法制备了体积分数为40%的铝基复合材料。利用选区电子衍射和高分辨电子显微技术研究了Al2O3P/1070Al界面附近基体的显微组织。结果表明,复合材料增强体颗粒为5μm时,基体存在大量的由热错配应力引发的位错,颗粒粒径为0.15μm时,基体表现为近无位错的组织特征,其缺陷形式为1～5nm的“微畸变区”,这主要是由于粒径小、分布弥散,微区应力均匀所致。

关键词：金属基复合材料 Al2O3P/Al 亚微米级Al2O3 显微组织

Natural Convection Melting in a Rectangular Heat Storage Tank of Carbon Nanotube Dispersed Latent Heat Storage Material

在线全文

学校读者我要写书评

暂无评论

Journal of Thermal Science 2024年第3期33卷 847-855页

作者： Shin-ichi MORITA Tomoya saito Kazunori TAKAI Yasutaka HAYAMIZU Naoto HARUKI Division of Mechanical and Electrical Engineering Kitami Institute of Technology165 Koen-choKitami-shiHokkaido090-8507Japan National Institute of Technology Yonago College4448 Hikona-cyoYonago-shiTottori683-8502Japan Okayama Prefectural University 111 KubokiSoja-shiOkayama719-1197Japan

A dispersion system fluid can convect even if the dispersoid is a solid ***,heat exchange performance can be improved while maintaining fluidity using a material with high thermal conductivity as the *** study presents the melting performance evaluation results of a latent heat storage material with a carbon nanotube(CNT)dispersion system with high thermal conductivity,which enhances the thermal conductivity of the latent heat storage material and does not limit free *** the thermal conductivity and enhancing the melting convection of the heat storage material result in increased latent heat storage *** this study,the thermal conductivity of the latent heat storage material was successfully increased by dispersing CNTs in the *** 0.1%(in mass)of multi-wall CNT(MWCNT)was dispersed in a paraffin-based latent heat storage material,the shear stress increased by 1.5 times at a shear rate of 500 s^(-1),while taking into account the potential effects of convective ***,a latent heat storage experiment was conducted in a rectangular heat storage tank using the CNT dispersion composition ratio as a parameter.A rectangular vessel with a heated vertical surface was used for the latent heat storage *** melting speed was determined by comparing the amount of latent heat stored in a CNT-dispersed latent heat storage material and a single-phase latent heat storage material *** experimental results show that the time required for the latent heat storage material to completely melt in the heat storage tank was the shortest for the single-phase latent heat storage material ***,the fastest melting progress was observed for the sample with 0.02%(in mass)MWCNT content in the melting rate range of up to approximately 40%in the *** results indicate that this phenomenon is caused by the difference in the melting rates in the upper part of the *** generated data are useful for det

关键词： latent heat storage phase change carbon nano tube free convection heat transfer

DiffMat:Latent diffusion models for image-guided material generation

在线全文

学校读者我要写书评

暂无评论

Visual Informatics 2024年第1期8卷 6-14页

作者： Liang Yuan Dingkun Yan Suguru saito Issei Fujishiro Graduate School of Science and Technology Keio UniversityKanagawaJapan School of Computing Tokyo Institute of TechnologyTokyoJapan Department of Information and Computer Science Keio UniversityKanagawaJapan

Creating realistic materials is essential in the construction of immersive virtual *** existing techniques for material capture and conditional generation rely on flash-lit photos,they often produce artifacts when the illumination mismatches the training *** this study,we introduce DiffMat,a novel diffusion model that integrates the CLIP image encoder and a multi-layer,crossattention denoising backbone to generate latent materials from images under various *** a pre-trained StyleGAN-based material generator,our method converts these latent materials into high-resolution SVBRDF textures,a process that enables a seamless fit into the standard physically based rendering pipeline,reducing the requirements for vast computational resources and expansive *** surpasses existing generative methods in terms of material quality and variety,and shows adaptability to a broader spectrum of lighting conditions in reference images.

关键词： SVBRDF Diffusion model Generative model Appearance modeling