Abstract

We propose a fully automatic framework to detect and ex- tract arbitrary human motion volumes from real-world videos collected from YouTube. Our system is composed of two stages. A person detector is first applied to provide crude information about the possible locations of humans. Then a constrained clustering algorithm groups the detections and rejects false positives based on the appearance similarity and spatio- temporal coherence. In the second stage, we apply a top-down pictorial structure model to complete the extraction of the humans in arbitrary motion. During this procedure, a density propagation technique based on a mixture of Gaussians is employed to propagate temporal informa- tion in a principled way. This method reduces greatly the search space for the measurement in the inference stage. We demonstrate the initial success of this framework both quantitatively and qualitatively by using a number of YouTube videos.