Systems and methods for identifying user-customized relevant individuals in an ambient image at a doorbell device
Systems and methods for identifying user-customized relevant individuals in an ambient image at a doorbell device are provided. Such systems and methods can include receiving user input that includes image information, using the image information to compile a custom image database containing a plurality of images that depict such relevant individuals, and storing the custom image database in local memory of the doorbell device. Then, such systems and methods can include capturing an ambient image with a camera of the doorbell device, determining whether any person depicted in the ambient image matches any of the relevant individuals by comparing the ambient image to the plurality of images at the doorbell device, and generating an alert when any person depicted in the ambient image matches any of the relevant individuals.
1 . A method comprising:
capturing, via a camera associated with a device, an image, the image corresponding to a region outside a location, the image comprising content corresponding to a representation of a person;
analyzing, by the device, the image, and determining characteristics of the person;
extracting, by the device, from the image, the determined characteristics;
accessing, by the device, from memory of the device, a collection of stored images, the collection of stored images being images previously captured by the camera and stored in the memory of the device, each stored image comprising information related to a known threat previously determined via analysis of the previously captured images within the collection, the known threat based on a location range of a residence of a depicted individual in a respectively stored image to the location, wherein the collection of stored images has a maximum number that corresponds to processing power of the device;
comparing, by the device, the determined characteristics extracted from the captured image with characteristics associated with images in the collection of stored images to identify a match with the known threat;
determining, by the device, based on analysis of the captured image and the comparison based on the collection of stored images, an event to the location; and
generating, by the device, an alert at the location based on a type of the alert, the alert indicating detection of the known threat.
2 . The method of claim 1 , further comprising:
communicating, from a cloud server to the device, image information, the image information corresponding to a type of activity for the device to detect via the camera, wherein the communication causes the device to compile and store a plurality of images based on the image information.
3 . The method of claim 2 , further comprising:
storing, in storage associated with the device, the plurality of images, wherein the collection of stored images further comprises the plurality of images stored in storage.
4 . The method of claim 1 , wherein the compilation of the plurality of images is based on analysis of a threat criteria.
5 . The method of claim 1 , wherein the type of event corresponds to a determination that the person is a safe person.
6 . The method of claim 1 , wherein the type of event corresponds to a determination that the person is an un-safe person.
7 . The method of claim 1 , wherein the analysis of the image is based on a facial recognition analysis of the image.
8 . The method of claim 1 , wherein the analysis of the image is based on an artificial intelligence (AI) vector mapping of the image.
9 . The method of claim 1 , wherein the captured image is an ambient image.
10 . A device comprising:
a processor configured to:
capturing, via an associated camera, an image, the image corresponding to a region outside a location, the image comprising content corresponding to a representation of a person;
analyze, the image, and determine characteristics of the person;
extract, from the image, the determined characteristics;
access, from memory of the device, a collection of stored images, the collection of stored images being images previously captured by the camera and stored in the memory of the device, each stored image comprising information related to a known threat previously determined via analysis of the previously captured images within the collection, the known threat based on a location range of a residence of a depicted individual in a respectively stored image to the location, wherein the collection of stored images has a maximum number that corresponds to processing power of the device;
compare the determined characteristics extracted from the captured image with characteristics associated with images in the collection of stored images to identify a match with the known threat;
determine, based on analysis of the captured image and the comparison based on the collection of stored images, an event to the location; and
generate, by the device, an alert at the location based on a type of the alert, the alert indicating detection of the known threat.
11 . The device of claim 10 , wherein the processor is further configured to:
communicate, from a cloud server to the device, image information, the image information corresponding to a type of activity for the device to detect via the camera, wherein the communication causes the device to compile and store a plurality of images based on the image information.
12 . The device of claim 11 , wherein the processor is further configured to:
store, in storage associated with the device, the plurality of images, wherein the collection of stored images further comprises the plurality of images stored in storage.
13 . The device of claim 10 , wherein the compilation of the plurality of images is based on analysis of a threat criteria.
14 . The device of claim 10 , wherein the type of event corresponds to a determination that the person is one of a safe person or un-safe person.
15 . The device of claim 10 , wherein the analysis of the image is based on a facial recognition analysis of the image.
16 . The device of claim 10 , wherein the analysis of the image is based on an artificial intelligence (AI) vector mapping of the image.
17 . The device of claim 10 , wherein the captured image is an ambient image.
18 . A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a device, perform a method comprising:
capturing, via a camera associated with the device, an image, the image corresponding to a region outside a location, the image comprising content corresponding to a representation of a person;
analyzing, by the device, the image, and determining characteristics of the person;
extracting, by the device, from the image, the determined characteristics;
accessing, by the device, from memory of the device, a collection of stored images, the collection of stored images being images previously captured by the camera and stored in the memory of the device, each stored image comprising information related to a known threat previously determined via analysis of the previously captured images within the collection, the known threat based on a location range of a residence of a depicted individual in a respectively stored image to the location, wherein the collection of stored images has a maximum number that corresponds to processing power of the device;
comparing, by the device, the determined characteristics extracted from the captured image with characteristics associated with images in the collection of stored images to identify a match with the known threat;
determining, by the device, based on analysis of the captured image and the comparison based on the collection of stored images, an event to the location; and
generating, by the device, an alert at the location based on a type of the alert, the alert indicating detection of the known threat.