| 摘要 |
Disclosed is a method for accurately determining dwell time of a face in front of a camera and for linking together face tracks obtained at different times or from different cameras. The method comprises the steps of detecting a colour property of the image sub-area in a current image; generating a filtered colour property in respect of the current image by combining a colour property for the current image with a filtered colour property derived in respect of a corresponding sub-area of a previous image and deriving the representative colour value in dependence on a difference between the colour property of the sub-area of the current image and the filtered colour property. |
