| 摘要 |
A system and method for locating and tracking people and non-stationary objects of interest in a scene using a series of range images of the scene taken over time. The system and process generally entails first generating the series of range images which are preferably a continuous temporal sequence of depth maps of the scene. A background model is computed from a block of the range images. Once the background model has been computed, a range image generated subsequent to the block of range images is selected for processing. The background is then subtracted from this currently selected range image based on the background model to produce a foreground image. The foreground image is next segmented into regions, each of which represents a different person or object of interest in the scene captured by the currently selected range image. The locating process continues by projecting the segmented regions of the foreground image onto a ground plane of the scene. The ground plane coordinates determined in the projection procedure can be used to designate the location of each separate person or object of interest in the scene captured by the currently selected range image. However, if desired an optional ground plane segmentation refinement technique can be employed first to ensure each projected region represents only a single person or object. Once the location of each person or object of interest has been established, they can be tracked by analyzing subsequently generated range images.
|
