Skip to main content

Research Repository

Advanced Search

Spatial effects of video compression on classification in convolutional neural networks.

Johnston, Pamela; Elyan, Eyad; Jayne, Chrisina

Authors

Pamela Johnston

Chrisina Jayne



Abstract

A collection of Computer Vision application reuse pre-learned features to analyse video frame-by-frame. Those features are classically learned by Convolutional Neural Networks (CNN) trained on high quality images. However, available video content is almost always subject to compression which is nearly never considered during the analysis process. In this paper, we present an empirical study to measure how the visual discrepancy of compressed data limit the learning performance of the CNN model. The learning performance is evaluated using a benchmark of synthetic datasets compressed at various levels using H.264/AVC. We measure the image quality quantitatively using classical evaluation metrics such as Peak Signal to Noise Ratio and Structural SIMilarity. A cross-evaluation is performed to measure the robustness of the CNN model in processing for a wide range of quality-varying visual data. Our experimental results have shown that the performance of the CNN depends on the compression rate. The results show that, in general, higher compression results in lower performance. However performance on lower quality test data can be improved by using lower quality data for CNN training. Finally, our work demonstrates that conditioning the CNN with the compression properties could potentially lead to better learning.

Start Date Jul 8, 2018
Publication Date Dec 31, 2018
Print ISSN 2161-4393
Electronic ISSN 2161-4407
Publisher Institute of Electrical and Electronics Engineers
Article Number 8489370
Series ISSN 2161-4407
Institution Citation JOHNSTON, P., ELYAN, E. and JAYNE, C. 2018. Spatial effects of video compression on classification in convolutional neural networks. In Proceedings of the 2018 International joint conference on neural networks (IJCNN 2018), 8-13 July 2018, Rio de Janeiro, Brazil. Piscataway, NJ: IEEE [online], article number 8489370. Available from: https://doi.org/10.1109/IJCNN.2018.8489370
DOI https://doi.org/10.1109/IJCNN.2018.8489370
Keywords CNN; Learning performance; Image quality; Compression

Files





You might also like



Downloadable Citations

;