| 摘要 |
A method and system for detecting the movement of 3D objects, in particular people, in a defined zone uses a time-of flight (TQF) camera with range-finding ability to acquire 3d positional information for each pixel in a scene. The method comprises the steps of calibrating the camera to define a zone with respect to a ground plane, such that the zone is set at a desired height relative to the ground plane; capturing a multi-array of 3D pixel data from the camera in a single frame in the defined zone; and segmenting the 3D pixel data as volume features for the subsequent purpose of object identification and tracking through multiple captured frames. The invention overcomes disadvantages of traditional multi-camera systems as image-point matching is not required, which further negates the effects of occlusion and the requirement for texture in the image. Planar surfaces with no texture can now be measured with accuracy, which is particularly important due the variety of potential surfaces encountered. Also disclosed is a method for counting people in which the above method may identify the 3D objects as people, who are counted when identified as such. |
