A survey of techniques for human detection from video
Neeti A. Ogale · 2006
Recent research in computer vision has increasingly focused on building systems for observing humans and understanding their appearance, movements, and activities, providing advanced interfaces for interacting with humans, and creating realistic models of humans for various purposes. In order for any of these systems to function, they require methods for detecting people from a given input image or a video. In this paper, we discuss a representative sample of techniques for finding people using visual input. These techniques are classified with respect to the need for pre-processing (background subtraction or direct detection), features used to describe human appearance (shape, color, motion), use of explicit body models, learning techniques, . . .