Inter-Feature-Map Differential Coding of Surveillance Video

TL;DR

This paper introduces a differential coding method for compressing intermediate feature maps in surveillance videos within collaborative AI systems, achieving high compression ratios with minimal accuracy loss.

Contribution

It proposes inter-feature-map differential coding (IFMDC) for efficient video feature map compression, outperforming traditional methods like HEVC in certain scenarios.

Findings

IFMDC achieves comparable or better compression ratios than HEVC.

The method is particularly effective for quality-sensitive surveillance videos.

Minimal accuracy reduction is maintained with significant compression gains.

Abstract

In Collaborative Intelligence, a deep neural network (DNN) is partitioned and deployed at the edge and the cloud for bandwidth saving and system optimization. When a model input is an image, it has been confirmed that the intermediate feature map, the output from the edge, can be smaller than the input data size. However, its effectiveness has not been reported when the input is a video. In this study, we propose a method to compress the feature map of surveillance videos by applying inter-feature-map differential coding (IFMDC). IFMDC shows a compression ratio comparable to, or better than, HEVC to the input video in the case of small accuracy reduction. Our method is especially effective for videos that are sensitive to image quality degradation when HEVC is applied