Learn More
This paper presents an approach to infer what is happening in a (crowded) scene using a statistical method. Rather than trying to segment and track the individuals in each frame, our basic idea is to detect salient points (corners) along with their motion vectors. Finally, we obtain statistical measures on this data which are highly correlated with the kind(More)
In this paper, we describe a unique new paradigm for video database management known as ViBE (Video Indexing and Browsing Environment). ViBE is a browseable/searchable paradigm for organizing video data containing a large number of sequences. The system first segments video sequences into shots by using a new feature vector known as the Generalized Trace(More)
This paper presents a system that labels TV shots either as commercial or program shots. The system uses two observations: logo presence and shot duration. These observations are modeled using HMMs, and a Viterbi decoder is finally used for shot labeling. The system has been tested on several hours of real video, achieving more than 99% correct labeling.
The objective of this work is to provide a simple and yet efficient tool to detect human faces in video sequences. This information can be very useful for many applications such as video indexing and video browsing. In particular the paper will focus on the significant improvements made to our face detection algorithm presented in [l]. Specifically, a novel(More)
This paper presents an unsupervised color segmentation technique to divide skin detected pixels into a set of homogeneous regions which can be used in face detection applications or any other application which may require color segmentation. The algorithm is carried out in a two stage processing, where the chrominance and luminance infor-mations are used(More)