Motion Representation with Acceleration Images
This work addresses motion analysis in video processing, but it is incremental as it builds on existing two-stream CNN methods.
The paper tackled the problem of motion representation by incorporating second-order differential acceleration images into a two-stream CNN, showing that adding an acceleration stream improves performance.
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.