People detection and tracking from fish-eye image based on probabilistic appearance model

This paper presents a method for automated people detection and tracking by using fisheye lens camera. In our method, human is modeled as probabilistic features of body silhouette and head-shoulder contour. These features are extracted from the human images taken at various distance and orientation with respect to the camera, and form the training data set. A probabilistic appearance model is built by means of kernel ridge regression (KRR) and human detection is formulated as maximum a posteriori (MAP) estimation using this model. Finally, people tracking is achieved by the combination of Kalman filter and nearest neighbor standard filter (NNSF). 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.