Real-World Repetition Estimation by Div, Grad and Curl

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(2018)

引用 46|浏览81
暂无评分
摘要
We consider the problem of estimating repetition in video, such as performing push-ups, cutting a melon or playing violin. Existing work shows good results under the assumption of static and stationary periodicity. As realistic video is rarely perfectly static and stationary, the often preferred Fourier-based measurements is inapt. Instead, we adopt the wavelet transform to better handle non-static and non-stationary video dynamics. From the flow field and its differentials, we derive three fundamental motion types and three motion continuities of intrinsic periodicity in 3D. On top of this, the 2D perception of 3D periodicity considers two extreme viewpoints. What follows are 18 fundamental cases of recurrent perception in 2D. In practice, to deal with the variety of repetitive appearance, our theory implies measuring time-varying flow and its differentials (gradient, divergence and curl) over segmented foreground motion. For experiments, we introduce the new QUVA Repetition dataset, reflecting reality by including non-static and non-stationary videos. On the task of counting repetitions in video, we obtain favorable results compared to a deep learning alternative.
更多
查看译文
关键词
grad,curl,push-ups,melon,static periodicity,stationary periodicity,realistic video,preferred Fourier-based measurements,nonstationary video dynamics,flow field,differentials,fundamental motion types,motion continuities,intrinsic periodicity,extreme viewpoints,recurrent perception,repetitive appearance,time-varying flow F,segmented foreground motion,QUVA Repetition dataset,nonstationary videos,repetition estimation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要