A Model-Based Approach of Foreground Region of Interest Detection for Video Codecs
Detecting the Region of Interest (ROI) for video clips is a significant and useful technique both in video codecs and surveillance/monitor systems. In this paper, a new model-based detection method is designed which suits video compression codecs by proposing two models: an “inter̶...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/13/2670 |
| _version_ | 1818969975970332672 |
|---|---|
| author | Zhewei Zhang Tao Jing Bowen Ding Meilin Gao Xuejing Li |
| author_facet | Zhewei Zhang Tao Jing Bowen Ding Meilin Gao Xuejing Li |
| author_sort | Zhewei Zhang |
| collection | DOAJ |
| description | Detecting the Region of Interest (ROI) for video clips is a significant and useful technique both in video codecs and surveillance/monitor systems. In this paper, a new model-based detection method is designed which suits video compression codecs by proposing two models: an “inter” and “intra” model. The “inter” model exploits the motion information represented as blocks by global motion compensation approaches while the “intra” model extracts the objects details through objects filtering and image segmentation procedures. Finally, the detection results are formed through a new clustering with fine-tune approach from the “intra” model assisted with the “inter” model. Experimental results show that the proposed method fits well for real-time video codecs and it achieves a good performance both on detection precision and on computing time. In addition, the proposed method is versatile for a wide range of surveillance videos with different characteristics. |
| first_indexed | 2024-12-20T14:29:08Z |
| format | Article |
| id | doaj.art-da558c3aff774d61a98958e1b246035c |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-20T14:29:08Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-da558c3aff774d61a98958e1b246035c2022-12-21T19:37:42ZengMDPI AGApplied Sciences2076-34172019-06-01913267010.3390/app9132670app9132670A Model-Based Approach of Foreground Region of Interest Detection for Video CodecsZhewei Zhang0Tao Jing1Bowen Ding2Meilin Gao3Xuejing Li4Institution of Electronic Information Engineering, Beijing Jiaotong University, Shang Yuan Road No. 3, Haidian District, Beijing 100044, ChinaInstitution of Electronic Information Engineering, Beijing Jiaotong University, Shang Yuan Road No. 3, Haidian District, Beijing 100044, ChinaArtificial Intelligence Research Institute of China Unicom, Beijing 100048, ChinaInstitution of Electronic Information Engineering, Beijing Jiaotong University, Shang Yuan Road No. 3, Haidian District, Beijing 100044, ChinaInstitution of Electronic Information Engineering, Beijing Jiaotong University, Shang Yuan Road No. 3, Haidian District, Beijing 100044, ChinaDetecting the Region of Interest (ROI) for video clips is a significant and useful technique both in video codecs and surveillance/monitor systems. In this paper, a new model-based detection method is designed which suits video compression codecs by proposing two models: an “inter” and “intra” model. The “inter” model exploits the motion information represented as blocks by global motion compensation approaches while the “intra” model extracts the objects details through objects filtering and image segmentation procedures. Finally, the detection results are formed through a new clustering with fine-tune approach from the “intra” model assisted with the “inter” model. Experimental results show that the proposed method fits well for real-time video codecs and it achieves a good performance both on detection precision and on computing time. In addition, the proposed method is versatile for a wide range of surveillance videos with different characteristics.https://www.mdpi.com/2076-3417/9/13/2670ROI detectionglobal motion detection &compensationimage segmentationdecision treecamera status classification |
| spellingShingle | Zhewei Zhang Tao Jing Bowen Ding Meilin Gao Xuejing Li A Model-Based Approach of Foreground Region of Interest Detection for Video Codecs Applied Sciences ROI detection global motion detection & compensation image segmentation decision tree camera status classification |
| title | A Model-Based Approach of Foreground Region of Interest Detection for Video Codecs |
| title_full | A Model-Based Approach of Foreground Region of Interest Detection for Video Codecs |
| title_fullStr | A Model-Based Approach of Foreground Region of Interest Detection for Video Codecs |
| title_full_unstemmed | A Model-Based Approach of Foreground Region of Interest Detection for Video Codecs |
| title_short | A Model-Based Approach of Foreground Region of Interest Detection for Video Codecs |
| title_sort | model based approach of foreground region of interest detection for video codecs |
| topic | ROI detection global motion detection & compensation image segmentation decision tree camera status classification |
| url | https://www.mdpi.com/2076-3417/9/13/2670 |
| work_keys_str_mv | AT zheweizhang amodelbasedapproachofforegroundregionofinterestdetectionforvideocodecs AT taojing amodelbasedapproachofforegroundregionofinterestdetectionforvideocodecs AT bowending amodelbasedapproachofforegroundregionofinterestdetectionforvideocodecs AT meilingao amodelbasedapproachofforegroundregionofinterestdetectionforvideocodecs AT xuejingli amodelbasedapproachofforegroundregionofinterestdetectionforvideocodecs AT zheweizhang modelbasedapproachofforegroundregionofinterestdetectionforvideocodecs AT taojing modelbasedapproachofforegroundregionofinterestdetectionforvideocodecs AT bowending modelbasedapproachofforegroundregionofinterestdetectionforvideocodecs AT meilingao modelbasedapproachofforegroundregionofinterestdetectionforvideocodecs AT xuejingli modelbasedapproachofforegroundregionofinterestdetectionforvideocodecs |