Real-Time View Transition between Cameras with Different Perspectives for Visual Monitoring

碩士 === 國立臺灣大學 === 資訊工程學研究所 === 95 === This paper introduces a novel method for real-time view transition between two cameras. One important feature of our method is correspondence free for the single-target case. When there are multiple targets, our approach also works with a reliable multi-camera t...

Full description

Bibliographic Details
Main Authors: Li-Wei Chang, 張禮薇
Other Authors: Yi-Ping Hung
Format: Others
Language:en_US
Published: 2007
Online Access:http://ndltd.ncl.edu.tw/handle/96392732646466481109
id ndltd-TW-095NTU05392124
record_format oai_dc
spelling ndltd-TW-095NTU053921242015-12-07T04:04:29Z http://ndltd.ncl.edu.tw/handle/96392732646466481109 Real-Time View Transition between Cameras with Different Perspectives for Visual Monitoring 視覺監控系統之即時平順轉場技術 Li-Wei Chang 張禮薇 碩士 國立臺灣大學 資訊工程學研究所 95 This paper introduces a novel method for real-time view transition between two cameras. One important feature of our method is correspondence free for the single-target case. When there are multiple targets, our approach also works with a reliable multi-camera tracker. With camera calibration data and pre-constructed background 3D models, we synthesize virtual views by first estimating the 3D position of the foreground object and then using a billboard to model the foreground. With our approach, even when the viewpoints of two cameras are quite different, it still works well as long as the monitoring areas of two cameras have intersections in the real world. The experimental results have shown natural and smooth visual effects of synthesized images, and achieved 22 frames per second on a PC with 3.4GHz Intel Pentium IV CPU and 2G RAM. Yi-Ping Hung 洪一平 2007 學位論文 ; thesis 39 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立臺灣大學 === 資訊工程學研究所 === 95 === This paper introduces a novel method for real-time view transition between two cameras. One important feature of our method is correspondence free for the single-target case. When there are multiple targets, our approach also works with a reliable multi-camera tracker. With camera calibration data and pre-constructed background 3D models, we synthesize virtual views by first estimating the 3D position of the foreground object and then using a billboard to model the foreground. With our approach, even when the viewpoints of two cameras are quite different, it still works well as long as the monitoring areas of two cameras have intersections in the real world. The experimental results have shown natural and smooth visual effects of synthesized images, and achieved 22 frames per second on a PC with 3.4GHz Intel Pentium IV CPU and 2G RAM.
author2 Yi-Ping Hung
author_facet Yi-Ping Hung
Li-Wei Chang
張禮薇
author Li-Wei Chang
張禮薇
spellingShingle Li-Wei Chang
張禮薇
Real-Time View Transition between Cameras with Different Perspectives for Visual Monitoring
author_sort Li-Wei Chang
title Real-Time View Transition between Cameras with Different Perspectives for Visual Monitoring
title_short Real-Time View Transition between Cameras with Different Perspectives for Visual Monitoring
title_full Real-Time View Transition between Cameras with Different Perspectives for Visual Monitoring
title_fullStr Real-Time View Transition between Cameras with Different Perspectives for Visual Monitoring
title_full_unstemmed Real-Time View Transition between Cameras with Different Perspectives for Visual Monitoring
title_sort real-time view transition between cameras with different perspectives for visual monitoring
publishDate 2007
url http://ndltd.ncl.edu.tw/handle/96392732646466481109
work_keys_str_mv AT liweichang realtimeviewtransitionbetweencameraswithdifferentperspectivesforvisualmonitoring
AT zhānglǐwēi realtimeviewtransitionbetweencameraswithdifferentperspectivesforvisualmonitoring
AT liweichang shìjuéjiānkòngxìtǒngzhījíshípíngshùnzhuǎnchǎngjìshù
AT zhānglǐwēi shìjuéjiānkòngxìtǒngzhījíshípíngshùnzhuǎnchǎngjìshù
_version_ 1718146433582891008