Motion Representation with Acceleration Images

TL;DR

This paper introduces an acceleration stream to the two-stream CNN for motion representation, demonstrating that incorporating acceleration images improves motion feature extraction despite noise challenges.

Contribution

The paper proposes adding an acceleration stream to the two-stream CNN, showing its effectiveness in enhancing motion representation.

Findings

Acceleration stream improves motion recognition accuracy.

Adding acceleration features enhances robustness against noise.

Acceleration stream complements existing spatial and temporal streams.

Abstract

Information of time differentiation is extremely important cue for a motion representation. We have applied first-order differential velocity from a positional information, moreover we believe that second-order differential acceleration is also a significant feature in a motion representation. However, an acceleration image based on a typical optical flow includes motion noises. We have not employed the acceleration image because the noises are too strong to catch an effective motion feature in an image sequence. On one hand, the recent convolutional neural networks (CNN) are robust against input noises. In this paper, we employ acceleration-stream in addition to the spatial- and temporal-stream based on the two-stream CNN. We clearly show the effectiveness of adding the acceleration stream to the two-stream CNN.