Multi-scale contrast and relative motion-based key frame extraction
Abstract The huge amount of video data available these days requires effective management techniques for storage, indexing, and retrieval. Video summarization, a method to manage video data, provides concise versions of the videos for efficient browsing and retrieval. Key frame extraction is a form...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2018-06-01
|
| Series: | EURASIP Journal on Image and Video Processing |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13640-018-0280-z |
| _version_ | 1818517364535197696 |
|---|---|
| author | Naveed Ejaz Sung Wook Baik Hammad Majeed Hangbae Chang Irfan Mehmood |
| author_facet | Naveed Ejaz Sung Wook Baik Hammad Majeed Hangbae Chang Irfan Mehmood |
| author_sort | Naveed Ejaz |
| collection | DOAJ |
| description | Abstract The huge amount of video data available these days requires effective management techniques for storage, indexing, and retrieval. Video summarization, a method to manage video data, provides concise versions of the videos for efficient browsing and retrieval. Key frame extraction is a form of video summarization which selects only the most salient frames from a given video. Since the automatic semantic understanding of the video contents is not possible so far, most of the existing works employ low level index features for extracting key frames. However, the usage of low level features results in loss of semantic details, thus leading to a semantic gap. In this context, the saliency-based user attention modeling technique can be used to bridge this semantic gap. In this paper, a key frame extraction scheme based on a visual attention mechanism is proposed. The proposed scheme builds static visual attention method based on multi-scale contrast instead of usual color contrast. The dynamic visual attention model is developed based on novel relative motion intensity and relative motion orientation. An efficient fusion scheme for combining three visual attention values is then proposed. A flexible technique is then used for key frame extraction. The experimental results demonstrate that the proposed mechanism provides excellent results as compared to the some of the other prominent techniques in the literature. |
| first_indexed | 2024-12-11T00:55:15Z |
| format | Article |
| id | doaj.art-67f9c0bf10f140afbf9f696d0686c5a7 |
| institution | Directory Open Access Journal |
| issn | 1687-5281 |
| language | English |
| last_indexed | 2024-12-11T00:55:15Z |
| publishDate | 2018-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Image and Video Processing |
| spelling | doaj.art-67f9c0bf10f140afbf9f696d0686c5a72022-12-22T01:26:30ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-52812018-06-012018111110.1186/s13640-018-0280-zMulti-scale contrast and relative motion-based key frame extractionNaveed Ejaz0Sung Wook Baik1Hammad Majeed2Hangbae Chang3Irfan Mehmood4Department of Computer Science, Iqra UniversityDepartment of Software, Sejong UniversityDepartment of Computer Science, National University of Computer and Emerging SciencesDepartment of Industrial Security, College of Business and Economics, Chung-Ang UniversityDepartment of Software, Sejong UniversityAbstract The huge amount of video data available these days requires effective management techniques for storage, indexing, and retrieval. Video summarization, a method to manage video data, provides concise versions of the videos for efficient browsing and retrieval. Key frame extraction is a form of video summarization which selects only the most salient frames from a given video. Since the automatic semantic understanding of the video contents is not possible so far, most of the existing works employ low level index features for extracting key frames. However, the usage of low level features results in loss of semantic details, thus leading to a semantic gap. In this context, the saliency-based user attention modeling technique can be used to bridge this semantic gap. In this paper, a key frame extraction scheme based on a visual attention mechanism is proposed. The proposed scheme builds static visual attention method based on multi-scale contrast instead of usual color contrast. The dynamic visual attention model is developed based on novel relative motion intensity and relative motion orientation. An efficient fusion scheme for combining three visual attention values is then proposed. A flexible technique is then used for key frame extraction. The experimental results demonstrate that the proposed mechanism provides excellent results as compared to the some of the other prominent techniques in the literature.http://link.springer.com/article/10.1186/s13640-018-0280-zKey frame extractionVideo summarizationVisual saliencyVisual attention modelFusion mechanismVideo summary evaluation |
| spellingShingle | Naveed Ejaz Sung Wook Baik Hammad Majeed Hangbae Chang Irfan Mehmood Multi-scale contrast and relative motion-based key frame extraction EURASIP Journal on Image and Video Processing Key frame extraction Video summarization Visual saliency Visual attention model Fusion mechanism Video summary evaluation |
| title | Multi-scale contrast and relative motion-based key frame extraction |
| title_full | Multi-scale contrast and relative motion-based key frame extraction |
| title_fullStr | Multi-scale contrast and relative motion-based key frame extraction |
| title_full_unstemmed | Multi-scale contrast and relative motion-based key frame extraction |
| title_short | Multi-scale contrast and relative motion-based key frame extraction |
| title_sort | multi scale contrast and relative motion based key frame extraction |
| topic | Key frame extraction Video summarization Visual saliency Visual attention model Fusion mechanism Video summary evaluation |
| url | http://link.springer.com/article/10.1186/s13640-018-0280-z |
| work_keys_str_mv | AT naveedejaz multiscalecontrastandrelativemotionbasedkeyframeextraction AT sungwookbaik multiscalecontrastandrelativemotionbasedkeyframeextraction AT hammadmajeed multiscalecontrastandrelativemotionbasedkeyframeextraction AT hangbaechang multiscalecontrastandrelativemotionbasedkeyframeextraction AT irfanmehmood multiscalecontrastandrelativemotionbasedkeyframeextraction |