Method of motion detection and autonomous motion tracking using dynamic sensitivity masks in a pan-tilt camera

1. A method of identifying motion within a field of view, the method comprising the steps of:

capturing at least two sequential images within the field of view, each of the images including a respective array of pixel values;

calculating an array of difference values between corresponding ones of the pixel values in the sequential images;

providing a sensitivity region map corresponding to the field of view, the sensitivity region map including a plurality of regions having different threshold values, the plurality of regions including at least one polygon-shaped region and a background region, at least one of the regions including a variable threshold value, the variable threshold value being dependent upon a corresponding group of the pixel values in a corresponding one of the sequential images; and

determining a presence of motion by comparing the difference values to corresponding ones of the threshold values.

2. The method of claim 1 wherein the determining step includes determining a presence of motion by comparing the difference values corresponding to one of the regions to a selected said threshold value of the region.

3. The method of claim 1 comprising the further steps of:

identifying a portion of the field of view having a higher expected variability of pixel values than another portion of the field of view; and

locating the at least one of the regions in correspondence with the portion of the field of view having a higher expected variability of pixel values.

4. A method of identifying motion within a field of view, the method comprising the steps of:

capturing at least two sequential images within the field of view, each of the images including a respective array of pixel values;

calculating difference values between corresponding ones of the pixel values in the sequential images;

providing a sensitivity region map corresponding to the field of view, the sensitivity region map including a plurality of regions, the plurality of regions including at least one polygon-shaped region and a background region, at least one of the regions having a variable threshold value dependent upon a corresponding group of the pixel values in at least one of the sequential images; and

determining a presence of motion by comparing the difference values corresponding to the at least one region to the threshold value of the at least one region.

5. The method of claim 1 comprising the further steps of:

selecting a first threshold value more suitable for determining a presence of vehicle motion than for determining a presence of pedestrian motion;

identifying a first portion of the field of view having at least one of a higher likelihood of vehicle motion and a lower likelihood of pedestrian motion than a second portion of the field of view; and

assigning the first threshold value to a first region of the sensitivity region map corresponding to the first portion of the field of view, the first threshold value being greater than a second threshold value assigned to a second region of the sensitivity region map corresponding to the second portion of the field of view.

6. A method of identifying motion within a field of view, the method comprising the steps of:

capturing at least two sequential images within the field of view, each of the images including a respective array of pixel values;

calculating difference values between corresponding ones of the pixel values in the sequential images;

providing a sensitivity region map corresponding to the field of view, the sensitivity region map including a plurality of regions, the plurality of region including at least one polygon-shaped region and a background region, at least one of the regions having a variable threshold value dependent upon a corresponding group of the pixel values in at least one of the sequential images; and

determining a presence of motion by comparing the difference values corresponding to the at least one region to the threshold value of the at least one region.

7. A method of identifying motion within a field of view, the method comprising the steps of:

capturing at least two sequential images within the field of view, each of the images including a respective array of pixel values;

calculating difference values between corresponding ones of the pixel values in the sequential images;

providing a sensitivity region map corresponding to the field of view, the sensitivity region map including a plurality of regions, the plurality of regions including at least one polygon-shaped region and a background region;

deciding whether to assign at least one of the regions a fixed threshold value or a variable threshold value, the variable threshold value being dependent upon a corresponding group of the pixel values in a corresponding one of the sequential images, the deciding being dependent upon an expected variability of the pixel values in a portion of the field of view, the portion of the field of view corresponding to the at least one region; and

determining a presence of motion by comparing the difference values corresponding to the at least one region to the threshold value of the at least one region.

8. The method of claim 6 comprising the further step of selecting the corresponding group of pixel values based upon the corresponding group of pixel values having a higher expected variability between subsequent sequential images than another group of pixel values in the at least one of the sequential images.

9. The method of claim 6 wherein another one of the regions has a fixed threshold value.

10. The method of claim 9 wherein the fixed threshold value is selected to be more suitable for determining a presence of a first type of motion than for determining a presence of a second type of motion;

identifying a first portion of the field of view having at least one of a higher likelihood of the first type of motion and a lower likelihood of the second type of motion than a second portion of the field of view; and

assigning the selected fixed threshold value to a first region of the sensitivity region map corresponding to the first portion of the field of view.

11. A method of identifying motion within a field of view, the method comprising the steps of:

capturing at least two sequential images within the field of view, each of the images including a respective array of pixel values;

calculating difference values between corresponding ones of the pixel values in the sequential images;

providing a sensitivity region map corresponding to the field of view, the sensitivity region map including a plurality of regions, the plurality of region including at least one polygon-shaped region and a background region;

deciding whether to assign at least one of the regions a fixed threshold value or a variable threshold value, the variable threshold value being dependent upon a corresponding group of the pixel values in a corresponding one of the sequential images, the deciding being dependent upon an expected variability of the pixel values in a portion of the field of view, the portion of the field of view corresponding to the at least one region; and determining a presence of motion by comparing the difference values corresponding to the at least one region to the threshold value of the at least one region.

12. The method of claim 11 wherein the deciding step includes deciding to assign a variable threshold value to a first of the regions, and deciding to assign a fixed threshold value to a second of the regions, a first expected variability of the pixel values in a first portion of the field of view corresponding to the first region being greater than a second expected variability of the pixel values in a second portion of the field of view corresponding to the second region.

13. The method of claim 12 wherein the second of the regions comprises a background region substantially surrounding the first of the regions.

14. The method of claim 12 , comprising the further step of selecting the fixed threshold value dependent upon a size of a body whose motion is desired to be detected.

15. The method of claim 11 wherein the variable threshold value varies dependent upon brightness values in at least one subsequent one of the sequential images.

16. The method of claim 11 wherein boundaries of the regions are automatically moved during operation based upon empirically measured pixel values of the captured images.