A Fast 3D Scene Reconstructing Method Using Continuous Video
碩士 === 國立臺灣科技大學 === 電子工程系 === 104 === Accurate 3D measuring system thrives in the past few years. Most of them are based on laser scanners because these laser scanners are able to acquire 3D information directly and precisely in real time. However, comparing to the conventional cameras, this kinds o...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2016
|
Online Access: | http://ndltd.ncl.edu.tw/handle/11389581580504099128 |
id |
ndltd-TW-104NTUS5428124 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-104NTUS54281242017-09-24T04:40:50Z http://ndltd.ncl.edu.tw/handle/11389581580504099128 A Fast 3D Scene Reconstructing Method Using Continuous Video 使用連續影像之快速3D場景重建方法 Bo-Yi Sung 宋柏毅 碩士 國立臺灣科技大學 電子工程系 104 Accurate 3D measuring system thrives in the past few years. Most of them are based on laser scanners because these laser scanners are able to acquire 3D information directly and precisely in real time. However, comparing to the conventional cameras, this kinds of equipment are usually expensive and they are not commonly available to customers. Moreover, laser scanners interfere easily with each other sensors of the same type. On the other hand, computer vision based 3D measuring techniques use stereo matching to acquire the cameras’ relative position and then estimate the 3D location of points on the image. Because this kind of systems needs additional estimation of the 3D information, systems with real time capability often relies on heavy parallelism that prevents implementation on mobile devices. Inspired by the structure from motion systems, we propose a system that reconstructs sparse feature points to a 3D point cloud using a mono video sequence so as to achieve higher computation efficiency. The system keeps tracking all detected feature points and calculates both the amount of these feature points and their moving distances. We only use the key frames to estimate the current position of the camera in order to reduce the computation load and the noise interference on the system. Furthermore, for the sake of avoiding duplicate 3D points, the system reconstructs the 2D point only when the point shifts out of the boundary of a camera. In our experiments, we show that our system is able to achieve state-of-the-art accuracy and a denser point cloud with a high speed. Chang-Hong Lin 林昌鴻 2016 學位論文 ; thesis 73 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣科技大學 === 電子工程系 === 104 === Accurate 3D measuring system thrives in the past few years. Most of them are based on laser scanners because these laser scanners are able to acquire 3D information directly and precisely in real time. However, comparing to the conventional cameras, this kinds of equipment are usually expensive and they are not commonly available to customers. Moreover, laser scanners interfere easily with each other sensors of the same type. On the other hand, computer vision based 3D measuring techniques use stereo matching to acquire the cameras’ relative position and then estimate the 3D location of points on the image. Because this kind of systems needs additional estimation of the 3D information, systems with real time capability often relies on heavy parallelism that prevents implementation on mobile devices.
Inspired by the structure from motion systems, we propose a system that reconstructs sparse feature points to a 3D point cloud using a mono video sequence so as to achieve higher computation efficiency. The system keeps tracking all detected feature points and calculates both the amount of these feature points and their moving distances. We only use the key frames to estimate the current position of the camera in order to reduce the computation load and the noise interference on the system. Furthermore, for the sake of avoiding duplicate 3D points, the system reconstructs the 2D point only when the point shifts out of the boundary of a camera. In our experiments, we show that our system is able to achieve state-of-the-art accuracy and a denser point cloud with a high speed.
|
author2 |
Chang-Hong Lin |
author_facet |
Chang-Hong Lin Bo-Yi Sung 宋柏毅 |
author |
Bo-Yi Sung 宋柏毅 |
spellingShingle |
Bo-Yi Sung 宋柏毅 A Fast 3D Scene Reconstructing Method Using Continuous Video |
author_sort |
Bo-Yi Sung |
title |
A Fast 3D Scene Reconstructing Method Using Continuous Video |
title_short |
A Fast 3D Scene Reconstructing Method Using Continuous Video |
title_full |
A Fast 3D Scene Reconstructing Method Using Continuous Video |
title_fullStr |
A Fast 3D Scene Reconstructing Method Using Continuous Video |
title_full_unstemmed |
A Fast 3D Scene Reconstructing Method Using Continuous Video |
title_sort |
fast 3d scene reconstructing method using continuous video |
publishDate |
2016 |
url |
http://ndltd.ncl.edu.tw/handle/11389581580504099128 |
work_keys_str_mv |
AT boyisung afast3dscenereconstructingmethodusingcontinuousvideo AT sòngbǎiyì afast3dscenereconstructingmethodusingcontinuousvideo AT boyisung shǐyòngliánxùyǐngxiàngzhīkuàisù3dchǎngjǐngzhòngjiànfāngfǎ AT sòngbǎiyì shǐyòngliánxùyǐngxiàngzhīkuàisù3dchǎngjǐngzhòngjiànfāngfǎ AT boyisung fast3dscenereconstructingmethodusingcontinuousvideo AT sòngbǎiyì fast3dscenereconstructingmethodusingcontinuousvideo |
_version_ |
1718540284648751104 |