News Video Summarization Combining SURF and Color Histogram Features
Because the data volume of news videos is increasing exponentially, a way to quickly browse a sketch of the video is important in various applications, such as news media, archives and publicity. This paper proposes a news video summarization method based on SURF features and an improved clustering...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/23/8/982 |
_version_ | 1797523980846891008 |
---|---|
author | Buyun Liang Na Li Zheng He Zhongyuan Wang Youming Fu Tao Lu |
author_facet | Buyun Liang Na Li Zheng He Zhongyuan Wang Youming Fu Tao Lu |
author_sort | Buyun Liang |
collection | DOAJ |
description | Because the data volume of news videos is increasing exponentially, a way to quickly browse a sketch of the video is important in various applications, such as news media, archives and publicity. This paper proposes a news video summarization method based on SURF features and an improved clustering algorithm, to overcome the defects in existing algorithms that fail to account for changes in shot complexity. Firstly, we extracted SURF features from the video sequences and matched the features between adjacent frames, and then detected the abrupt and gradual boundaries of the shot by calculating similarity scores between adjacent frames with the help of double thresholds. Secondly, we used an improved clustering algorithm to cluster the color histogram of the video frames within the shot, which merged the smaller clusters and then selected the frame closest to the cluster center as the key frame. The experimental results on both the public and self-built datasets show the superiority of our method over the alternatives in terms of accuracy and speed. Additionally, the extracted key frames demonstrate low redundancy and can credibly represent a sketch of news videos. |
first_indexed | 2024-03-10T08:49:54Z |
format | Article |
id | doaj.art-9076ef8da8a34abba6fef7bfc7ce25e5 |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-10T08:49:54Z |
publishDate | 2021-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-9076ef8da8a34abba6fef7bfc7ce25e52023-11-22T07:34:35ZengMDPI AGEntropy1099-43002021-07-0123898210.3390/e23080982News Video Summarization Combining SURF and Color Histogram FeaturesBuyun Liang0Na Li1Zheng He2Zhongyuan Wang3Youming Fu4Tao Lu5School of Computer Science, Wuhan University, Wuhan 430072, ChinaThe Archives of Wuhan University, Wuhan University, Wuhan 430072, ChinaSchool of Computer Science, Wuhan University, Wuhan 430072, ChinaSchool of Computer Science, Wuhan University, Wuhan 430072, ChinaSchool of Computer Science, Wuhan University, Wuhan 430072, ChinaSchool of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430073, ChinaBecause the data volume of news videos is increasing exponentially, a way to quickly browse a sketch of the video is important in various applications, such as news media, archives and publicity. This paper proposes a news video summarization method based on SURF features and an improved clustering algorithm, to overcome the defects in existing algorithms that fail to account for changes in shot complexity. Firstly, we extracted SURF features from the video sequences and matched the features between adjacent frames, and then detected the abrupt and gradual boundaries of the shot by calculating similarity scores between adjacent frames with the help of double thresholds. Secondly, we used an improved clustering algorithm to cluster the color histogram of the video frames within the shot, which merged the smaller clusters and then selected the frame closest to the cluster center as the key frame. The experimental results on both the public and self-built datasets show the superiority of our method over the alternatives in terms of accuracy and speed. Additionally, the extracted key frames demonstrate low redundancy and can credibly represent a sketch of news videos.https://www.mdpi.com/1099-4300/23/8/982video summarizationSURF featuresclusteringshot boundary detectionkey frame extraction |
spellingShingle | Buyun Liang Na Li Zheng He Zhongyuan Wang Youming Fu Tao Lu News Video Summarization Combining SURF and Color Histogram Features Entropy video summarization SURF features clustering shot boundary detection key frame extraction |
title | News Video Summarization Combining SURF and Color Histogram Features |
title_full | News Video Summarization Combining SURF and Color Histogram Features |
title_fullStr | News Video Summarization Combining SURF and Color Histogram Features |
title_full_unstemmed | News Video Summarization Combining SURF and Color Histogram Features |
title_short | News Video Summarization Combining SURF and Color Histogram Features |
title_sort | news video summarization combining surf and color histogram features |
topic | video summarization SURF features clustering shot boundary detection key frame extraction |
url | https://www.mdpi.com/1099-4300/23/8/982 |
work_keys_str_mv | AT buyunliang newsvideosummarizationcombiningsurfandcolorhistogramfeatures AT nali newsvideosummarizationcombiningsurfandcolorhistogramfeatures AT zhenghe newsvideosummarizationcombiningsurfandcolorhistogramfeatures AT zhongyuanwang newsvideosummarizationcombiningsurfandcolorhistogramfeatures AT youmingfu newsvideosummarizationcombiningsurfandcolorhistogramfeatures AT taolu newsvideosummarizationcombiningsurfandcolorhistogramfeatures |