Automatic Methods for Segmenting and Summarizing Videos Taken with Google Glasses
碩士 === 國立交通大學 === 多媒體工程研究所 === 105 === This thesis discusses the topic of automatic segmentation and summarization of videos taken with Google Glasses. Using the information from both the video images and additional sensor data that are recorded concurrently, we devise methods that automatically div...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2016
|
Online Access: | http://ndltd.ncl.edu.tw/handle/sr3b2p |
id |
ndltd-TW-105NCTU5641002 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-105NCTU56410022019-05-15T23:09:04Z http://ndltd.ncl.edu.tw/handle/sr3b2p Automatic Methods for Segmenting and Summarizing Videos Taken with Google Glasses 基於Google Glass之影片自動分段與精簡方法 Chiu, Yen-Chia 邱彥嘉 碩士 國立交通大學 多媒體工程研究所 105 This thesis discusses the topic of automatic segmentation and summarization of videos taken with Google Glasses. Using the information from both the video images and additional sensor data that are recorded concurrently, we devise methods that automatically divide the video into coherent segments and estimate the importance of the extracted segments. Such information then enables automatic generation of video summary. The features used include colors, image details, motions, and speeches. We then train multi-layer perceptrons for the two tasks (segmentation and importance estimation) according to expert annotations. We also present a systematic evaluation procedure that compares the automatic segmentation and importance estimation results with those given by multiple users and demonstrate the effectiveness of our approach. Wang, Tsai-Pei 王才沛 2016 學位論文 ; thesis 89 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立交通大學 === 多媒體工程研究所 === 105 === This thesis discusses the topic of automatic segmentation and summarization of videos taken with Google Glasses. Using the information from both the video images and additional sensor data that are recorded concurrently, we devise methods that automatically divide the video into coherent segments and estimate the importance of the extracted segments. Such information then enables automatic generation of video summary. The features used include colors, image details, motions, and speeches. We then train multi-layer perceptrons for the two tasks (segmentation and importance estimation) according to expert annotations. We also present a systematic evaluation procedure that compares the automatic segmentation and importance estimation results with those given by multiple users and demonstrate the effectiveness of our approach.
|
author2 |
Wang, Tsai-Pei |
author_facet |
Wang, Tsai-Pei Chiu, Yen-Chia 邱彥嘉 |
author |
Chiu, Yen-Chia 邱彥嘉 |
spellingShingle |
Chiu, Yen-Chia 邱彥嘉 Automatic Methods for Segmenting and Summarizing Videos Taken with Google Glasses |
author_sort |
Chiu, Yen-Chia |
title |
Automatic Methods for Segmenting and Summarizing Videos Taken with Google Glasses |
title_short |
Automatic Methods for Segmenting and Summarizing Videos Taken with Google Glasses |
title_full |
Automatic Methods for Segmenting and Summarizing Videos Taken with Google Glasses |
title_fullStr |
Automatic Methods for Segmenting and Summarizing Videos Taken with Google Glasses |
title_full_unstemmed |
Automatic Methods for Segmenting and Summarizing Videos Taken with Google Glasses |
title_sort |
automatic methods for segmenting and summarizing videos taken with google glasses |
publishDate |
2016 |
url |
http://ndltd.ncl.edu.tw/handle/sr3b2p |
work_keys_str_mv |
AT chiuyenchia automaticmethodsforsegmentingandsummarizingvideostakenwithgoogleglasses AT qiūyànjiā automaticmethodsforsegmentingandsummarizingvideostakenwithgoogleglasses AT chiuyenchia jīyúgoogleglasszhīyǐngpiànzìdòngfēnduànyǔjīngjiǎnfāngfǎ AT qiūyànjiā jīyúgoogleglasszhīyǐngpiànzìdòngfēnduànyǔjīngjiǎnfāngfǎ |
_version_ |
1719141065798189056 |