Static Video Compression’s Influence on Neural Network Performance
The concept of action recognition in smart security heavily relies on deep learning and artificial intelligence to make predictions about actions of humans. To draw appropriate conclusions from these hypotheses, a large amount of information is required. The data in question are often a video feed,...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/1/8 |
| _version_ | 1797626056058863616 |
|---|---|
| author | Vishnu Sai Sankeerth Gowrisetty Anil Fernando |
| author_facet | Vishnu Sai Sankeerth Gowrisetty Anil Fernando |
| author_sort | Vishnu Sai Sankeerth Gowrisetty |
| collection | DOAJ |
| description | The concept of action recognition in smart security heavily relies on deep learning and artificial intelligence to make predictions about actions of humans. To draw appropriate conclusions from these hypotheses, a large amount of information is required. The data in question are often a video feed, and there is a direct relationship between increased data volume and more-precise decision-making. We seek to determine how far a static video can be compressed before the neural network’s capacity to predict the action in the video is lost. To find this, videos are compressed by lowering the bitrate using FFMPEG. In parallel, a convolutional neural network model is trained to recognise action in the videos and is tested on the compressed videos until the neural network fails to predict the action observed in the videos. The results reveal that bitrate compression has no linear relationship with neural network performance. |
| first_indexed | 2024-03-11T10:05:12Z |
| format | Article |
| id | doaj.art-acaeba10d5884eabb6638814532ba2f5 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T10:05:12Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-acaeba10d5884eabb6638814532ba2f52023-11-16T15:09:51ZengMDPI AGElectronics2079-92922022-12-01121810.3390/electronics12010008Static Video Compression’s Influence on Neural Network PerformanceVishnu Sai Sankeerth Gowrisetty0Anil Fernando1Department of Computer & Information Sciences, University of Strathclyde, Glasgow G1 1XQ, UKDepartment of Computer & Information Sciences, University of Strathclyde, Glasgow G1 1XQ, UKThe concept of action recognition in smart security heavily relies on deep learning and artificial intelligence to make predictions about actions of humans. To draw appropriate conclusions from these hypotheses, a large amount of information is required. The data in question are often a video feed, and there is a direct relationship between increased data volume and more-precise decision-making. We seek to determine how far a static video can be compressed before the neural network’s capacity to predict the action in the video is lost. To find this, videos are compressed by lowering the bitrate using FFMPEG. In parallel, a convolutional neural network model is trained to recognise action in the videos and is tested on the compressed videos until the neural network fails to predict the action observed in the videos. The results reveal that bitrate compression has no linear relationship with neural network performance.https://www.mdpi.com/2079-9292/12/1/8bitrate compressionconvolutional neural networkaction recognition |
| spellingShingle | Vishnu Sai Sankeerth Gowrisetty Anil Fernando Static Video Compression’s Influence on Neural Network Performance Electronics bitrate compression convolutional neural network action recognition |
| title | Static Video Compression’s Influence on Neural Network Performance |
| title_full | Static Video Compression’s Influence on Neural Network Performance |
| title_fullStr | Static Video Compression’s Influence on Neural Network Performance |
| title_full_unstemmed | Static Video Compression’s Influence on Neural Network Performance |
| title_short | Static Video Compression’s Influence on Neural Network Performance |
| title_sort | static video compression s influence on neural network performance |
| topic | bitrate compression convolutional neural network action recognition |
| url | https://www.mdpi.com/2079-9292/12/1/8 |
| work_keys_str_mv | AT vishnusaisankeerthgowrisetty staticvideocompressionsinfluenceonneuralnetworkperformance AT anilfernando staticvideocompressionsinfluenceonneuralnetworkperformance |