In order to track and recognize the movements of multiple people using multiple cameras, each person needs to be segmented and identified in the image of each camera. We propose a...
We propose an adaptive figure-ground classification algorithm to automatically extract a foreground region using a user-provided bounding-box. The image is first over-segmented wi...
Blob trackers have become increasingly powerful in recent years largely due to the adoption of statistical appearance models which allow effective background subtraction and robus...
—We propose a probabilistic formulation of joint silhouette extraction and 3D reconstruction given a series of calibrated 2D images. Instead of segmenting each image separately i...
We present a method to identify and localize people by leveraging existing CCTV camera infrastructure along with inertial sensors (accelerometer and magnetometer) within each pers...