US 6,661,918 B1 · Background estimation and segmentation based on range and color

Abstract

Segmentation of background and foreground objects in an image is based upon the joint use of both range and color data. Range-based data is largely independent of color image data, and hence not adversely affected by the limitations associated with color-based segmentation, such as shadows and similarly colored objects. Furthermore, color segmentation is complementary to range measurement in those cases where reliable range data cannot be obtained. These complementary sets of data are used to provide a multidimensional background estimation. The segmentation of a foreground object in a given frame of an image sequence is carried out by comparing the image frames with background statistics relating to range and normalized color, using the sets of statistics in a complementary manner.

Claims29

Dependent claims

A method for distinguishing between background and foreground objects in an image, comprising the steps of:

i) determining respective range values for pixels in each of a plurality of related images;
ii) determining respective intensity values for pixels in each of said plurality of related images;
iii) establishing a multi-dimensional background model for at least some of said pixels on the basis of said range values and said intensity values;
iv) comparing the range value for a particular pixel in a given image with the background model for that pixel, and labeling the pixel as a foreground pixel if the range value differs from the background model by a range threshold;
v) comparing the intensity value for said particular pixel in a given image with the background model for that pixel, and labeling the pixel as a foreground pixel if the intensity value differs from the background model by an intensity threshold;
and
vi) adjusting said intensity threshold in accordance with a determination made during said comparing step (iv).

4 more elements

Dependencies are inferred from the claim text.

Background estimation and segmentation based on range and color

Life of this patent

Background estimation and segmentation based on range and color

Life of this patent

Abstract

Claims29