Outdoor camera and neighborhood watch techniques

An apparatus for security or automation systems, comprising:

• a processor;
• memory in electronic communication with the processor;
• and
• instructions stored in the memory, the instructions being executable by the processor to:
• receive, from a camera located outside a structure, data associated with an occurrence of a security event associated with the structure;
• determine that the received data is associated with the security event based at least in part on one or more computer learning techniques;
• assign a threat level to the security event based at least in part on data from the camera and a type of the security event, the type of the security event determined based at least in part on the one or more computer learning techniques;
• determine, using the one or more computer learning techniques, whether the security event is authorized based at least in part on detecting a plurality of security events having the type of the security event within a period of time, the plurality of security events comprising the security event;
• determine, using the one or more computer learning techniques, that the plurality of security events occurs in a threshold field of view;
• send a notification to adjust a field of view of the camera based at least in part on determining that the plurality of security events occurs in the threshold field of view;
• update the threat level of the security event using the one or more computer learning techniques based at least in part on processing a user input received in response to the security event and determining whether the security event is authorized;
• activate a light of the camera based at least in part on determining the received data is associated with the security event and the updated threat level, wherein a characteristic of the light is associated with the updated threat level;
• and
• initiate an action at a first location based at least in part on the one or more computer learning techniques, determining that the received data is associated with the security event, and the updated threat level.

A non-transitory computer-readable medium storing computer-executable code, the code executable by a processor to:

• receive, from a camera located outside a structure, data associated with an occurrence of a security event associated with the structure;
• determine that the received data is associated with the security event based at least in part on one or more computer learning techniques;
• assign a threat level to the security event based at least in part on data from the camera and a type of the security event, the type of the security event determined based at least in part on the one or more computer learning techniques;
• determine, using the one or more computer learning techniques, whether the security event is authorized based at least in part on detecting a plurality of security events having the type of the security event within a period of time, the plurality of security events comprising the security event;
• determine, using the one or more computer learning techniques, that the plurality of security events occurs in a threshold field of view;
• send a notification to adjust a field of view of the camera based at least in part on determining that the plurality of security events occurs in the threshold field of view;
• update the threat level of the security event using the one or more computer learning techniques based at least in part on processing a user input received in response to the security event and determining whether the security event is authorized;
• activate a light of the camera based at least in part on determining the received data is associated with the security event and the updated threat level, wherein a characteristic of the light is associated with the updated threat level;
• and
• initiate an action at a first location based at least in part on the one or more computer learning techniques, determining that the received data is associated with the security event, and the updated threat level.