US 7,956,889 B2 · Video surveillance system

Abstract

Viewing a three dimensional area from numerous camera angles at different exposures using intensity and chromaticity data at the different exposures to create a pixel model for each pixel. A current image is compared with the background model to find pixels that have changed from their pixel model. These novel pixels are processed using contiguous region detection and grouped into foreground figures. For each camera, software extracts features from each foreground figure. A central processor maintains an object model for each foreground figure. A graphical user interface displays the relative locations of foreground figures in a world model. The location and identification of the foreground figures is checked against a table of permissions so as to selectively generate an alert. If a figure leaves or is about to leave a cell, the invention accounts for its approximate position and notifies adjacent cells of the expected arrival of the foreground figure.

Claims73

Dependent claims

A method for video surveillance, the method comprising the following steps:

storing video data, in a physical computer readable medium, for at least two images at more than one exposure time;
analyzing, in a computer, the video data for the at least two images at more than one exposure time to create a pixel model for each pixel in the at least two images;
storing video data, in a physical computer readable medium, for a current image at a current exposure time;
and
comparing, in a computer, each pixel of said current image with a corresponding pixel model so as to detect novel pixels.

2 more elements

A method for video surveillance, the method comprising the following steps:

storing video data, in a physical computer readable medium, for at least two images at more than one exposure time;
analyzing, in a computer, the video data for the at least two images at more than one exposure time to create a pixel model for each pixel in the at least two images;
storing video data, in a physical computer readable medium, for a current image at a current exposure time;
and
comparing, in a computer, each pixel of said current image with a corresponding pixel model so as to detect novel pixels, wherein the step of storing video data for at least two images comprises the following steps:
storing video data for a plurality of images at a minimum exposure time;
storing video data for a plurality of images at a plurality of intermediate exposure times;
and
storing video data for a plurality of images at a maximum exposure time,
wherein the number of images stored at the minimum exposure time is greater than the number of exposures stored at any of the intermediate exposure times
wherein the step of analyzing the video data comprises the step of saving video data in the pixel model,
wherein the step of analyzing the video data further comprises the step of calculating an average for the video data in the pixel mode,
wherein the step of analyzing the video data further comprises the step of calculating a standard deviation for the video data in the pixel model, and
wherein the step of analyzing the video data further comprises the step of adjusting the average if the sum of the average and the product of a constant and the standard deviation is less than the sum of an underexposed threshold and the product of the constant and a predetermined standard deviation.

11 more elements

Dependencies are inferred from the claim text.

Video surveillance system

Life of this patent

Video surveillance system

Life of this patent

Abstract

Claims73