Methods and apparatus for detecting unrecognized moving objects
Security methods and apparatus. In one example, a method includes detecting a motion event in a scene using a motion detector, based on detecting the motion event, acquiring a plurality of images of the scene using an image capture device, applying a motion detection process to the plurality of images to detect motion in the scene, applying an object detection process to at least one of the images to detect an object in the scene, pairing the motion with the object to locate a moving object, identifying the moving object as an unrecognized object, and based at least in part on identifying the moving object as an unrecognized object, triggering a video recording of the scene using the image capture device.
1. A method comprising:
acquiring an image of a scene;
pairing motion with an object by determining that a first bounding box and a second bounding box at least partially overlap within the image, the first bounding box indicative of the motion in the scene, the second bounding box indicative of the object in the image, and the pairing indicating that the object is a moving object; and
initiating, based at least in part on the pairing, recording of a video sequence with an image capture device.
2. The method of claim 1 , further comprising:
applying an object detection process to the image to produce the second bounding box.
3. The method of claim 2 , wherein applying the object detection process includes using a trained artificial neural network to locate the object in the image.
4. The method of claim 1 , wherein acquiring the image includes acquiring a first image and a second image.
5. The method of claim 4 , further comprising:
comparing the first and second images to detect the motion in the scene; and
producing the first bounding box based on the comparing.
6. The method of claim 5 , wherein comparing the first and second images includes:
converting the first and second images from color to greyscale to produce first and second greyscale images;
comparing pixel intensities in the first and second greyscale images; and
detecting the motion based on differences in at least some of the pixel intensities in the first and second greyscale images exceeding a value.
7. The method of claim 6 , further comprising downsizing a frame size of the first and second greyscale images to produce a first reduced greyscale image and second reduced greyscale image;
wherein comparing pixel intensities in the first and second greyscale images includes comparing pixel intensities in the first and second reduced greyscale images.
8. The method of claim 1 , further comprising:
controlling the image capture device to record the video sequence for a period of time; and
after the period has ended, deactivating the image capture device.
9. The method of claim 1 , further comprising:
identifying the moving object as an unrecognized object; and
based at least in part on identifying the moving object as an unrecognized object, initiating recording of the video sequence with the image capture device.
10. The method of claim 9 , further comprising:
based on identifying the moving object as an unrecognized object, acquiring at least one additional image of the scene; and
processing the at least one additional image to confirm identification of the moving object as an unrecognized object.
11. A device comprising:
a camera;
at least one processor; and
a data storage device storing instructions that when executed by the at least one processor cause the device to
acquire a first image of a scene,
pair motion with an object to generate a pairing by determining that a first bounding box and a second bounding box at least partially overlap within the first image, the first bounding box indicative of the motion in the scene, the second bounding box indicative of the object in the first image, and the pairing indicating that the object is a moving object, and
based at least in part on the pairing, cause the camera to record begin recording video.
12. The device of claim 11 , wherein the data storage device further stores instructions that when executed by the at least one processor cause the device to:
apply an object detection process to the first image to produce the second bounding box.
13. The device of claim 12 , wherein to apply the object detection process, the at least one processor is configured to operate an artificial neural network detect the object.
14. The device of claim 11 , wherein the data storage device further stores instructions that when executed by the at least one processor cause the device to acquire a second image.
15. The device of claim 14 , wherein the data storage device further stores instructions that when executed by the at least one processor cause the device to apply a motion detection process to the first and second images to produce the first bounding box.
16. The device of claim 15 , wherein to apply the motion detection process, the data storage device further stores instructions that when executed by the at least one processor cause the device to:
convert the first and second images from color to greyscale to produce first and second greyscale images;
compare pixel intensities in the first and second greyscale images; and
detect the motion based on differences in at least some of the pixel intensities in the first and second greyscale images exceeding a value.
17. The device of claim 16 , wherein to apply the motion detection process, the data storage device further stores instructions that when executed by the at least one processor cause the device to:
downsize a frame size of the first and second greyscale images to produce a first reduced greyscale image and second reduced greyscale image; and
compare pixel intensities in the first and second reduced greyscale images.
18. The device of claim 11 , wherein the camera is configured to record the video for a period of time, and wherein the data storage device further stores instructions that when executed by the at least one processor cause the device to:
after the period has ended, deactivate the camera.
19. The device of claim 11 , wherein the data storage device further stores instructions that when executed by the at least one processor cause the device to:
identify the moving object as an unrecognized object; and
based at least in part on identifying the moving object as an unrecognized object, cause the camera to begin recording the video.
20. The device of claim 19 , wherein the data storage device further stores instructions that when executed by the at least one processor cause the device to:
based on identifying the moving object as an unrecognized object, acquire at least one additional image of the scene; and
process the at least one additional image to confirm identification of the moving object as an unrecognized object.
21. A computer program product comprising one or more non-transitory computer-readable media storing sequences of instructions executable to control a security camera disposed at a location, the sequences of instructions comprising instructions to:
acquire an image of a scene;
pair motion with an object to generate a pairing by determining that a first bounding box and a second bounding box at least partially overlap within the image, the first bounding box indicative of the motion in the scene, the second bounding box indicative of the object in the image, and the pairing indicating that the object is a moving object; and
based at least in part on the pairing, cause an image capture device to begin recording video.