Human Detection from Hemispherical Image Based on Probabilistic Appearance Model

Abstract

This paper presents a method for automated human detection using fisheye lens camera. In our method, human is modeled as probabilistic templates of body silhouette and head-shoulder contour. The problem of human detection is formulated as maximum a posteriori (MAP) estimation using the template model. Experiments are conducted on indoor space where a fisheye lens camera is installed on the ceiling of crossing hallway. The feasibility and accuracy of our method is discussed through the experimental results.