We propose a method of shot boundary detection based on the co-occurrence of global motion in video stream. In addition to the conventional features based on appearance and local ...
In this paper, we propose a novel and robust method for extracting motion layers in video sequences. Taking advantage of temporal continuity, our framework considers both the visi...
In this paper, we present a new model-based approach for building 3-D models of vehicles from color video provided by a traffic surveillance camera. We incrementally build 3D mode...
A system is described that tracks moving objects in a video dataset so as to extract a representation of the objects' 3D trajectories. The system then finds hierarchical clus...
We address the synchronization of a pair of video sequences captured from moving vehicles and the spatial registration of all the temporally corresponding frames. This is necessar...
Felipe Lumbreras, Ferran Diego, Joan Serrat, Jos&e...