Systems and methods of person recognition in video streams

1 . A method comprising:

obtaining data relating to an environment, the data comprising one or more images of a scene within a field of view of the environment;

detecting a first entity in the one or more images;

responsive to the detection of the first entity in the one or more images, determining, from analysis of the one or more images, first information that identifies an attribute of the first entity;

determining, based on at least some of the first information, that the first entity is not identifiable to a computing system having a stored set of classified entities, the determination sufficient to classify the first entity as an unknown entity;

storing in a database at least some of the data; and

in response to: (i) a determination that the first entity is a stranger, (ii) not receiving a user classification of the first entity within a predetermined amount of time, or (iii) a determination that the first entity was involved in a trivial event based on an event categorization, deleting one or more portions of the stored data, wherein the one or more portions of the stored data comprise at least one of: one or more images of the first entity; or the first information that identifies the attribute of the first entity.

2 . The method of claim 1 , further comprising:

receiving, prior to deleting one or more portions of the stored data, the user classification of the first entity, and wherein the determination that the first entity is a stranger is based on the user classification.

3 . The method of claim 1 , wherein determining the first information comprises:

selecting at least one image of the first entity from the one or more images; and

characterizing a plurality of features of the first entity based on the at least one image.

4 . The method of claim 3 , wherein the first entity is a person, the method further comprising:

identifying one or more poses of the person in at least one respective image of the at least one image; and

for each identified pose of the one or more poses, in accordance with a determination that an image of the person in the identified pose has not previously been stored, storing (i) the image of the person in the identified pose, and (ii) corresponding pose information.

5 . The method of claim 1 , wherein the first entity comprises at least one of a person, an animal, or a vehicle.

6 . The method of claim 5 , further comprising:

receiving, from the user, a designation that the first entity is the person, the animal, or the vehicle; and

responsive to the designation, storing the designation in association with the first information of the first entity.

7 . The method of claim 1 , further comprising:

receiving, from the user and responsive to storing in the database at least some of the data, a designation that the first entity is a known entity, and wherein deleting one or more portions of the stored data is in response to a determination that the known entity was involved in a trivial event based on an event categorization.

8 . The method of claim 1 , further comprising:

in accordance with the determination that the first entity is not identifiable, generating a notification of detection of an unidentified object.

9 . The method of claim 1 , wherein the stored data comprises a first plurality of characterized features, the method further comprising:

detecting a second entity in the one or more images;

characterizing a second plurality of features of the second entity based on at least one image of the second entity; and

determining whether the second entity is the first entity by comparing the second plurality of characterized features of the second entity with the first plurality of characterized features.

10 . The method of claim 9 , wherein the first plurality of characterized features and the second plurality of characterized features comprise at least one of physical feature information, location information, or behavioral information.

11 . The method of claim 1 , further comprising:

in accordance with the determination that the first entity is a stranger, causing a device in the environment to emit at least one of an audible notification or a visual light alert.

12 . A computer system comprising:

one or more processors; and

memory coupled to the one or more processors, the memory storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions for:

obtaining data relating to an environment, the data comprising one or more images of a scene within a field of view of the environment;

detecting a first entity in the one or more images;

responsive to the detection of the first entity in the one or more images, determining, from analysis of the one or more images, first information that identifies an attribute of the first entity;

determining, based on at least some of the first information, that the first entity is not identifiable to a computing system having a stored set of classified entities, the determination sufficient to classify the first entity as an unknown entity;

storing in a database at least some of the data; and

in response to: (i) a determination that the first entity is a stranger, (ii) not receiving a user classification of the first entity within a predetermined amount of time, or (iii) a determination that the first entity was involved in a trivial event based on an event categorization, deleting one or more portions of the stored data, wherein the one or more portions of the stored data comprise at least one of: one or more images of the first entity; or the first information that identifies the attribute of the first entity.

13 . The computer system of claim 12 , wherein the one or more programs further comprise instructions for:

receiving, prior to deleting one or more portions of the stored data, the user classification of the first entity, and wherein the determination that the first entity is a stranger is based on the user classification.

14 . The computer system of claim 12 , wherein determining the first information comprises:

selecting at least one image of the first entity from the one or more images; and

characterizing a plurality of features of the first entity based on the at least one image.

15 . The computer system of claim 14 , wherein the first entity is a person, and the one or more programs further comprise instructions for:

identifying one or more poses of the person in at least one respective image of the at least one image; and

for each identified pose of the one or more poses, in accordance with a determination that an image of the person in the identified pose has not previously been stored, storing (i) the image of the person in the identified pose, and (ii) corresponding pose information.

16 . The computer system of claim 12 , wherein the first entity comprises at least one of a person, an animal, or a vehicle.

17 . The computer system of claim 16 , wherein the one or more programs further comprise instructions for:

receiving, from the user, a designation that the first entity is the person, the animal, or the vehicle; and

responsive to the designation, storing the designation in association with the first information of the first entity.

18 . The computer system of claim 12 , wherein the one or more programs further comprise instructions for:

receiving, from the user and responsive to storing in the database at least some of the data, a designation that the first entity is a known entity, and wherein deleting one or more portions of the stored data is in response to a determination that the known entity was involved in a trivial event based on an event categorization.

19 . The computer system of claim 12 , wherein the one or more programs further comprise instructions for:

in accordance with the determination that the first entity is not identifiable, generating a notification of detection of an unidentified object.

20 . The computer system of claim 12 , wherein the stored data comprises a first plurality of characterized features, the method further comprising:

detecting a second entity in the one or more images;

characterizing a second plurality of features of the second entity based on at least one image of the second entity; and

determining whether the second entity is the first entity by comparing the second plurality of characterized features of the second entity with the first plurality of characterized features.

21 . The computer system of claim 20 , wherein the first plurality of characterized features and the second plurality of characterized features comprise at least one of physical feature information, location information, or behavioral information.

22 . The computer system of claim 12 , wherein the one or more programs further comprise instructions for:

in accordance with the determination that the first entity is a stranger, causing a device in the environment to emit at least one of an audible notification or a visual light alert.