Soccer Video Structure Analysis by Parallel Feature Fusion Network and Hidden-to-Observable Transferring Markov Model
Automated analysis of broadcast soccer game video is a challenging computer vision problem. Prior to performing high-level analysis (such as event detection), accurate classification of shot views and play-break segmentation are required to analyze the structure of soccer video. A novel deep network...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2017-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8094116/ |
| _version_ | 1819163240860483584 |
|---|---|
| author | Mehrnaz Fani Mehran Yazdi David A. Clausi Alexander Wong |
| author_facet | Mehrnaz Fani Mehran Yazdi David A. Clausi Alexander Wong |
| author_sort | Mehrnaz Fani |
| collection | DOAJ |
| description | Automated analysis of broadcast soccer game video is a challenging computer vision problem. Prior to performing high-level analysis (such as event detection), accurate classification of shot views and play-break segmentation are required to analyze the structure of soccer video. A novel deep network called parallel feature fusion network (PFF-Net) combines local and full-scene features to produce accurate shot view classification based on camera zoom and out-of-field status. Then, a novel hidden-to-observable Markov model (H<sub>2</sub>O-MM) is introduced to determine play/break status of the shots. Testing is performed using a variety of professional broadcast soccer videos. Variations of the PFF-Net are considered and compared with four existing methods where the PFF-Net demonstrates superior performance (92.6%). The H<sub>2</sub>O-MM has the accuracy of 98.7% for play-break segmentation, which is an improvement over two existing hidden Markov models. The new methods provide improved temporal labeling of broadcast soccer videos, which can be used to further improve overall automated event detection. |
| first_indexed | 2024-12-22T17:41:00Z |
| format | Article |
| id | doaj.art-06a18e42227941c2ac21098809c529db |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T17:41:00Z |
| publishDate | 2017-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-06a18e42227941c2ac21098809c529db2022-12-21T18:18:25ZengIEEEIEEE Access2169-35362017-01-015273222733610.1109/ACCESS.2017.27691408094116Soccer Video Structure Analysis by Parallel Feature Fusion Network and Hidden-to-Observable Transferring Markov ModelMehrnaz Fani0https://orcid.org/0000-0003-2859-435XMehran Yazdi1David A. Clausi2Alexander Wong3Department of Electrical and Computer Engineering, Shiraz University, Shiraz, IranDepartment of Electrical and Computer Engineering, Shiraz University, Shiraz, IranDepartment of System Design, University of Waterloo, Waterloo, ON, CanadaDepartment of System Design, University of Waterloo, Waterloo, ON, CanadaAutomated analysis of broadcast soccer game video is a challenging computer vision problem. Prior to performing high-level analysis (such as event detection), accurate classification of shot views and play-break segmentation are required to analyze the structure of soccer video. A novel deep network called parallel feature fusion network (PFF-Net) combines local and full-scene features to produce accurate shot view classification based on camera zoom and out-of-field status. Then, a novel hidden-to-observable Markov model (H<sub>2</sub>O-MM) is introduced to determine play/break status of the shots. Testing is performed using a variety of professional broadcast soccer videos. Variations of the PFF-Net are considered and compared with four existing methods where the PFF-Net demonstrates superior performance (92.6%). The H<sub>2</sub>O-MM has the accuracy of 98.7% for play-break segmentation, which is an improvement over two existing hidden Markov models. The new methods provide improved temporal labeling of broadcast soccer videos, which can be used to further improve overall automated event detection.https://ieeexplore.ieee.org/document/8094116/Parallel feature fusion networkhidden to observable Markov modelshot view classificationplay-break segmentationsoccer video analysisstacked autoencoders |
| spellingShingle | Mehrnaz Fani Mehran Yazdi David A. Clausi Alexander Wong Soccer Video Structure Analysis by Parallel Feature Fusion Network and Hidden-to-Observable Transferring Markov Model IEEE Access Parallel feature fusion network hidden to observable Markov model shot view classification play-break segmentation soccer video analysis stacked autoencoders |
| title | Soccer Video Structure Analysis by Parallel Feature Fusion Network and Hidden-to-Observable Transferring Markov Model |
| title_full | Soccer Video Structure Analysis by Parallel Feature Fusion Network and Hidden-to-Observable Transferring Markov Model |
| title_fullStr | Soccer Video Structure Analysis by Parallel Feature Fusion Network and Hidden-to-Observable Transferring Markov Model |
| title_full_unstemmed | Soccer Video Structure Analysis by Parallel Feature Fusion Network and Hidden-to-Observable Transferring Markov Model |
| title_short | Soccer Video Structure Analysis by Parallel Feature Fusion Network and Hidden-to-Observable Transferring Markov Model |
| title_sort | soccer video structure analysis by parallel feature fusion network and hidden to observable transferring markov model |
| topic | Parallel feature fusion network hidden to observable Markov model shot view classification play-break segmentation soccer video analysis stacked autoencoders |
| url | https://ieeexplore.ieee.org/document/8094116/ |
| work_keys_str_mv | AT mehrnazfani soccervideostructureanalysisbyparallelfeaturefusionnetworkandhiddentoobservabletransferringmarkovmodel AT mehranyazdi soccervideostructureanalysisbyparallelfeaturefusionnetworkandhiddentoobservabletransferringmarkovmodel AT davidaclausi soccervideostructureanalysisbyparallelfeaturefusionnetworkandhiddentoobservabletransferringmarkovmodel AT alexanderwong soccervideostructureanalysisbyparallelfeaturefusionnetworkandhiddentoobservabletransferringmarkovmodel |