Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain

TL;DR

This paper introduces a method to accelerate action recognition in compressed videos by accumulating residuals, reducing processing time while maintaining high accuracy, suitable for real-time applications.

Contribution

It proposes a novel residual accumulation technique in the compressed domain, enabling faster action recognition without full decoding.

Findings

Significant reduction in processed frames for recognition

High classification accuracy comparable to raw video methods

Enhanced real-time applicability of action recognition

Abstract

With the widespread use of installed cameras, video-based monitoring approaches have seized considerable attention for different purposes like assisted living. Temporal redundancy and the sheer size of raw videos are the two most common problematic issues related to video processing algorithms. Most of the existing methods mainly focused on increasing accuracy by exploring consecutive frames, which is laborious and cannot be considered for real-time applications. Since videos are mostly stored and transmitted in compressed format, these kinds of videos are available on many devices. Compressed videos contain a multitude of beneficial information, such as motion vectors and quantized coefficients. Proper use of this available information can greatly improve the video understanding methods' performance. This paper presents an approach for using residual data, available in compressed videos directly, which can be obtained by a light partially decoding procedure. In addition, a method for accumulating similar residuals is proposed, which dramatically reduces the number of processed frames for action recognition. Applying neural networks exclusively for accumulated residuals in the compressed domain accelerates performance, while the classification results are highly competitive with raw video approaches.