Use of three-dimensional top-down views for business analytics
A method of analyzing a depth image in a digital system is provided that includes detecting a foreground object in a depth image, wherein the depth image is a top-down perspective of a scene, and performing data extraction and classification on the foreground object using depth information in the depth image.
1. A business intelligence system comprising:
means for capturing a depth image of a scene from a top-down perspective;
means for detecting a foreground object in the depth image; and
means for performing data extraction and classification on the foreground object using depth information in the depth image, wherein the means for performing data extraction and classification classifies the foreground object based on the computed height and a 2D shape of the foreground object, and wherein the means for performing data extraction and classification computes a height of the foreground object based on a height of a depth camera used to capture the depth image.
2. The business intelligence system of claim 1 , wherein the means for performing data extraction and classification uses both XY spatial shape of the foreground object in the depth image and depth information in the depth image.
3. The business intelligence system of claim 1 , wherein the means for performing data extraction and classification computes the height of the foreground object by:
determining a smallest depth value of pixels in the depth image corresponding to the foreground object; and
computing the height as a difference between the height of the depth camera and the smallest depth value.
4. The business intelligence system of claim 1 , wherein the means for performing data extraction and classification classifies the foreground object as an adult or a child based on expected heights for an adult and a child.
5. The business intelligence system of claim 1 , wherein the means for performing data extraction and classification classifies the foreground object as an animal when the computed height is within an expected height range for an animal and the 2D shape of the foreground object corresponds to an expected 2D shape for an animal.
6. The business intelligence system of claim 1 , wherein the means for performing data extraction and classification classifies the foreground object as a shopping cart when the computed height is an expected height for a shopping cart and the 2D shape of the foreground object corresponds to an expected 2D shape for a shopping cart and determines fullness of the shopping cart based on depth values inside the foreground object.