Abstract

The task of counting the number of repetitions of ap-proximately the same action in an input video sequence is addressed. The proposed method runs online and not on the complete pre-captured video. It analyzes sequen-tially blocks of 20 non-consecutive frames. The cycle length within each block is evaluated using a convolutional neural network and the information is then integrated over time. The entropy of the network’s predictions is used in order to automatically start and stop the repetition counter and to select the appropriate time scale. Coupled with a region of interest detection mechanism, the method is robust enough to handle real world videos, even when the camera is mov-ing. A unique property of our method is that it is shown to successfully train on entirely unrealistic data created by synthesizing moving random patches. 1.