Low-complexity motion detection based on image edges

1. A method for detecting a motion event comprising:

acquiring a first image;

obtaining a comparison image;

identifying edge pixels in the first image;

generating a first edge image by assigning a first pixel value to the edge pixels of the first image and a second pixel value to non-edge pixels of the first image, the first pixel value being different from the second pixel value;

identifying edge pixels in the comparison image by:

obtaining, for each pixel in the comparison image, pixel values of two neighboring pixels;

computing a difference in pixel value between the two neighboring pixels;

determining whether the difference in pixel value meets or exceeds a first threshold; and

identifying the pixel as an edge pixel if the difference in pixel value meets or exceeds the first threshold;

generating a comparison edge image by assigning the first pixel value to the edge pixels of the comparison image and the second pixel value to non-edge pixels of the comparison image;

generating a difference image based on the first edge image and the comparison edge image;

reducing noise in the difference image by an erosion operation;

determining difference between the first edge image and the comparison edge image by obtaining pixels having the first pixel value in the difference image after noise reduction, wherein the difference comprises distances in the horizontal and vertical directions between the obtained pixels having the maximum coordinate value and the minimum coordinate value and a number count of the obtained pixels in the difference image;

determining whether the difference between the first edge image and the comparison edge image meets or exceeds a second threshold, the second threshold being adjustable by a user, wherein the determining whether the difference between the first edge image and the comparison edge image meets or exceeds a second threshold comprises:

determining whether distances in the horizontal or vertical directions between the obtained pixels having the maximum coordinate value and the minimum coordinate value meets or exceeds a third threshold,

determining whether a number count of the obtained pixels in the difference image meets or exceeds a fourth threshold; and

in response to that the difference is determined to meet or exceed the second threshold, generating an alert indicating that a motion event occurs, and transmitting the alert to a user device, the alert including image data associated with the motion event.

2. The method of claim 1 , the first pixel value being a maximum pixel value among pixels in the first image or the comparison image, and the second pixel value being a minimum pixel value among pixels in the first image or the comparison image.

3. The method of claim 1 , the obtaining the comparison image includes:

determining whether a time that has elapsed since acquiring the first image meets or exceeds a threshold period of time; and

obtaining the comparison image if the time meets or exceeds the threshold period of time.

4. The method of claim 1 , wherein the generating the difference image based on the first edge image and the comparison edge image comprises:

identifying a first group of pixels in the first edge image that have a different pixel value from corresponding pixels in the comparison edge image;

identifying a second group of pixels in the first edge image that have a same pixel value as corresponding pixels in the comparison edge image; and

generating the difference image by assigning a first pixel value to the first group of pixels and a second pixel value to the second group, the first pixel value being different from the second pixel value.

5. A system for detecting a motion event comprising:

a memory storing instructions;

a processor configured to execute the instructions to:

acquire a first image;

obtain a comparison image;

identify edge pixels in the first image;

generate a first edge image by assigning a first pixel value to the edge pixels of the first image and a second pixel value to non-edge pixels of the first image, the first pixel value being different from the second pixel value;

identify edge pixels in the comparison image by:

obtaining, for each pixel in the comparison image, pixel values of two neighboring pixels;

computing a difference in pixel value between the two neighboring pixels;

determining whether the difference in pixel value meets or exceeds a first threshold; and

identifying the pixel as an edge pixel if the difference in pixel value meets or exceeds the first threshold;

generate a comparison edge image by assigning the first pixel value to the edge pixels of the comparison image and the second pixel value to non-edge pixels of the comparison image;

generate a difference image based on the first edge image and the comparison edge image;

reduce noise in the difference image by an erosion operation;

determine difference between the first edge image and the comparison edge image by obtaining pixels having the first pixel value in the difference image after noise reduction, wherein the difference comprises distances in the horizontal and vertical directions between the obtained pixels having the maximum coordinate value and the minimum coordinate value and a number count of the obtained pixels in the difference image;

determine whether the difference between the first edge image and the comparison image meets or exceeds a second threshold, the second threshold being adjustable by a user, wherein the determine whether the difference between the first edge image and the comparison edge image meets or exceeds a second threshold comprises:

determining whether distances in the horizontal or vertical directions between the obtained pixels having the maximum coordinate value and the minimum coordinate value meets or exceeds a third threshold,

determining whether a number count of the obtained pixels in the difference image meets or exceeds a fourth threshold; and

if the difference meets or exceeds the second threshold, generate an alert indicating that a motion event occurs, and transmit the alert to a user device, the alert including image data associated with the motion event.

6. The system of claim 5 , the first pixel value being a maximum pixel value among pixels in the first image or the comparison image, and the second pixel value being a minimum pixel value among pixels in the first image or the comparison image.

7. The system of claim 5 , the obtaining the comparison image includes:

determining whether a time that has elapsed since acquiring the first image meets or exceeds a threshold period of time; and

obtaining the comparison image if the time meets or exceeds the threshold period of time.

8. The system of claim 5 , wherein the generating a difference image based on the first edge image and the comparison edge image comprises:

identifying a first group of pixels in the first edge image that have a different pixel value from corresponding pixels in the comparison edge image;

identifying a second group of pixels in the first edge image that have a same pixel value as corresponding pixels in the comparison edge image; and

generating the difference image by assigning a first pixel value to the first group of pixels and a second pixel value to the second group, the first pixel value being different from the second pixel value.

9. A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a method for video monitoring, the method comprising:

acquiring a first image and a comparison image;

identifying edge pixels in the first image by:

obtaining, for each pixel in the first image, pixel values of two neighboring pixels;

computing a difference in pixel value between the two neighboring pixels;

determining whether the difference in pixel value meets or exceeds a first threshold; and

identifying the pixel as an edge pixel if the difference in pixel value meets or exceeds the first threshold;

generating a first edge image by assigning a first pixel value to the edge pixels of the first image and a second pixel value to non-edge pixels of the first image, the first pixel value being different from the second pixel value;

identifying edge pixels in the comparison image;

generating a comparison edge image by assigning the first pixel value to the edge pixels of the comparison image and the second pixel value to non-edge pixels of the comparison image;

generating a difference image based on the first edge image and the comparison edge image;

reducing noise in the difference image by an erosion operation;

determining difference between the first edge image and the comparison edge image by obtaining pixels having the first pixel value in the generated difference image after noise reduction, wherein the difference comprises distances in the horizontal and vertical directions between the obtained pixels having the maximum coordinate value and the minimum coordinate value and a number count of the obtained pixels in the difference image;

determining whether the difference between the first edge image and the comparison edge image meets or exceeds a second threshold, the second threshold being adjustable by a user, wherein the determine whether the difference between the first edge image and the comparison edge image meets or exceeds a second threshold comprises:

determining whether distances in the horizontal or vertical directions between the obtained pixels having the maximum coordinate value and the minimum coordinate value meets or exceeds a third threshold,

determining whether a number count of the obtained pixels in the difference image meets or exceeds a fourth threshold; and

if the difference meets or exceeds the second threshold, generate an alert indicating that a motion event occurs, and transmit the alert to a user device, the alert including image data associated with the motion event.

10. The non-transitory computer-readable storage medium of claim 9 , wherein the generating a difference image based on the first edge image and the comparison edge image comprises:

identifying a first group of pixels in the first edge image that have a different pixel value from corresponding pixels in the comparison edge image;

identifying a second group of pixels in the first edge image that have a same pixel value as corresponding pixels in the comparison edge image; and

generating the difference image by assigning a first pixel value to the first group of pixels and a second pixel value to the second group, the first pixel value being different from the second pixel value.