Repetitive Activity Counting by Sight and Sound
This work addresses the problem of accurate activity counting for video analysis applications, particularly in scenarios with poor visual quality, representing an incremental advance by integrating sound into an existing visual-only framework.
The paper tackles repetitive activity counting in videos by incorporating sound alongside visual data for the first time, improving accuracy under challenging vision conditions such as occlusion and low resolution, with the sight-only model outperforming state-of-the-art and further gains when sound is added.
This paper strives for repetitive activity counting in videos. Different from existing works, which all analyze the visual video content only, we incorporate for the first time the corresponding sound into the repetition counting process. This benefits accuracy in challenging vision conditions such as occlusion, dramatic camera view changes, low resolution, etc. We propose a model that starts with analyzing the sight and sound streams separately. Then an audiovisual temporal stride decision module and a reliability estimation module are introduced to exploit cross-modal temporal interaction. For learning and evaluation, an existing dataset is repurposed and reorganized to allow for repetition counting with sight and sound. We also introduce a variant of this dataset for repetition counting under challenging vision conditions. Experiments demonstrate the benefit of sound, as well as the other introduced modules, for repetition counting. Our sight-only model already outperforms the state-of-the-art by itself, when we add sound, results improve notably, especially under harsh vision conditions.