This paper presents a fast, accurate, and novel method for the problem of estimating the number of humans and their positions from background differenced images obtained from a si...
Lan Dong, Vasu Parameswaran, Visvanathan Ramesh, I...
— This paper presents a novel approach for visual scene modeling and classification, investigating the combined use of text modeling methods and local invariant features. Our wo...
Pedro Quelhas, Florent Monay, Jean-Marc Odobez, Da...
Aerial video provides strong cues for automatic road extraction that are not available in static aerial images. Using stabilized (or geo-referenced) video data, capturing the dist...
This paper presents reliable techniques for detecting, tracking, and storing keyframes of people in surveillance video. The first component of our system is a novel face detector ...
Abstract. We introduce a view–point invariant representation of moving object trajectories that can be used in video database applications. It is assumed that trajectories lie on...