Mastering Quantization is Key for Video Compression

Ropert, Michael; Tanou, Julien Le; Blestel, Médéric

doi:10.5594/jmi.2022.3167782

Search citation statements

Order By: Relevance

Paper Sections

Select...

Bitrate-compression1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When video is compressed, the compression technique uses Discrete Cosine Transform (DCT) [? ] to transfer video from the pixel domain to the frequency domain, and Quantization [14] to reject a significant number of frequencies that the human eye cannot distinguish. When compressing a video, information is compromised in order to maintain the video's quality.…”

Section: Bitrate-compressionmentioning

confidence: 99%

Static Video Compression’s Influence on Neural Network Performance

Gowrisetty

Fernando

2022

Electronics

View full text Add to dashboard Cite

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.

show abstract

Section: Bitrate-compressionmentioning

confidence: 99%