Statistical noise analysis for motion detection
View Patent ↗An approach is provided to detecting motion using statistical noise analysis. In the approach, reference statistics are calculated that relate to one or more noise characteristics that correspond to pixels in a first set of video images of an area being monitored. Current noise characteristics are received that correspond to the same pixels in a second set of video images of the area being monitored, with the first set of video images being captured before the second set of video images. Motion is detected in the area being monitored by comparing the reference statistics to the current noise characteristics.
1. A machine-implemented method comprising:
calculating reference statistics related to one or more noise characteristics that correspond to a plurality of pixels in a first set of a plurality of video images of an area being monitored;
receiving current noise characteristics that correspond to the plurality of pixels in a second set of one or more video images of the area being monitored, wherein the first set of video images were captured before the second set of video images; and
detecting a motion in the area being monitored by comparing the reference statistics to the current noise characteristics.
2. The method of claim 1 wherein the reference statistics include an average and a standard deviation related to each of the plurality of pixels.
3. The method of claim 1 further comprising:
identifying a set of pixels in the second set of video images with current noise characteristics that deviate from the corresponding reference statistics by a statistically significant amount, wherein each of the set of pixels is within a section of the area being monitored;
comparing a size of the section with a size threshold; and
detecting the motion in response to the size of the section exceeding the size threshold.
4. The method of claim 1 wherein the second set of video images is a plurality of images captured over a period of time, the method further comprising:
identifying a set of pixels in the second set of video images with current noise characteristics that deviate from the corresponding reference statistics by a statistically significant amount;
identifying an amount of time that the set of pixels have the current noise characteristics that deviate from the corresponding reference statistics by the statistically significant amount;
comparing the amount of time to a time threshold; and
detecting the motion in response to the amount of time exceeding the time threshold.
5. The method of claim 4 wherein the detecting further comprises:
identifying a section of the area being monitored that encompass the set of pixels;
comparing a size of the section with a size threshold; and
detecting the motion in response to the size of the section exceeding the size threshold in addition to the amount of time exceeding the time threshold.
6. The method of claim 1 further comprising:
calculating current statistics related to the noise characteristics that correspond to the plurality of pixels in a second set of video images, wherein the current noise characteristics are the calculated current statistics; and
comparing the current statistics to the reference statistics.
7. The method of claim 6 wherein the reference statistics are selected from a group consisting of a mode, a mean, a variance, a skewness, and a Kurtosis.
8. An information handling system comprising:
one or more processors;
a memory coupled to at least one of the processors; and
a set of instructions stored in the memory and executed by at least one of the processors to:
calculate reference statistics related to one or more noise characteristics that correspond to a plurality of pixels in a first set of a plurality of video images of an area being monitored;
receive current noise characteristics that correspond to the plurality of pixels in a second set of one or more video images of the area being monitored, wherein the first set of video images were captured before the second set of video images; and
detect a motion in the area being monitored by comparing the reference statistics to the current noise characteristics.
9. The information handling system of claim 8 wherein the reference statistics include an average and a standard deviation related to each of the plurality of pixels.
10. The information handling system of claim 8 wherein the set of instructions further comprises instructions to:
identify a set of pixels in the second set of video images with current noise characteristics that deviate from the corresponding reference statistics by a statistically significant amount, wherein each of the set of pixels is within a section of the area being monitored;
compare a size of the section with a size threshold; and
detect the motion in response to the size of the section exceeding the size threshold.
11. The information handling system of claim 8 wherein the second set of video images is a plurality of images captured over a period of time, and wherein the set of instructions further comprises instructions to:
identify a set of pixels in the second set of video images with current noise characteristics that deviate from the corresponding reference statistics by a statistically significant amount;
identify an amount of time that the set of pixels have the current noise characteristics that deviate from the corresponding reference statistics by the statistically significant amount;
compare the amount of time to a time threshold; and
detect the motion in response to the amount of time exceeding the time threshold.
12. The information handling system of claim 11 wherein the set of instructions to detect further comprises instructions to:
identify a section of the area being monitored that encompass the set of pixels;
compare a size of the section with a size threshold; and
detect the motion in response to the size of the section exceeding the size threshold in addition to the amount of time exceeding the time threshold.
13. The information handling system of claim 8 wherein the set of instructions further comprises instructions to:
calculate current statistics related to the noise characteristics that correspond to the plurality of pixels in a second set of video images, wherein the current noise characteristics are the calculated current statistics; and
compare the current statistics to the reference statistics.
14. The information handling system of claim 8 wherein the reference statistics are selected from a group consisting of a mode, a mean, a variance, a skewness, and a Kurtosis, and wherein the information handling system further comprises:
a digital camera that captures the first and second sets of video images.
15. A computer program product comprising:
a set of computer instructions stored on a computer readable storage medium comprising, the computer instructions effective to:
calculate reference statistics related to one or more noise characteristics that correspond to a plurality of pixels in a first set of a plurality of video images of an area being monitored;
receive current noise characteristics that correspond to the plurality of pixels in a second set of one or more video images of the area being monitored, wherein the first set of video images were captured before the second set of video images; and
detect a motion in the area being monitored by comparing the reference statistics to the current noise characteristics.
16. The computer program product of claim 15 wherein the reference statistics include an average and a standard deviation related to each of the plurality of pixels.
17. The computer program product of claim 15 wherein the set of instructions further comprise instructions effective to:
identify a set of pixels in the second set of video images with current noise characteristics that deviate from the corresponding reference statistics by a statistically significant amount, wherein each of the set of pixels is within a section of the area being monitored;
compare a size of the section with a size threshold; and
detect the motion in response to the size of the section exceeding the size threshold.
18. The computer program product of claim 15 wherein the second set of video images is a plurality of images captured over a period of time, and wherein the set of instructions further comprise instructions effective to:
identify a set of pixels in the second set of video images with current noise characteristics that deviate from the corresponding reference statistics by a statistically significant amount;
identify an amount of time that the set of pixels have the current noise characteristics that deviate from the corresponding reference statistics by the statistically significant amount;
compare the amount of time to a time threshold; and
detect the motion in response to the amount of time exceeding the time threshold.
19. The computer program product of claim 18 wherein the set of instructions to detect further comprise instructions effective to:
identify a section of the area being monitored that encompass the set of pixels;
compare a size of the section with a size threshold; and
detect the motion in response to the size of the section exceeding the size threshold in addition to the amount of time exceeding the time threshold.
20. The computer program product of claim 15 wherein the set of instructions further comprise instructions effective to:
calculate current statistics related to the noise characteristics that correspond to the plurality of pixels in a second set of video images, wherein the current noise characteristics are the calculated current statistics; and
compare the current statistics to the reference statistics.