Dynamic contextual video capture

Abstract

Embodiments of the present invention provide a method, computer program product and system for dynamic video capture through a contact lens based on dynamic contextual identification. Initially, a set of identifying information and a video stream from a contact lens is received. A determination is made as to whether to capture the video stream, based on the received information. The determining to capture the video stream is based on, at least one of, the user interest level exceeding a threshold and detecting a contextual identifier within the received the video stream from a contact lens. Responsive to determining to capture the video stream, the video stream is classified into a category and saving based on the classification category of the video stream.

What is claimed is: 
     
         1 . A method comprising:
 receiving, by one or more processors, a set of identifying information and a video stream from a contact lens;   detecting a contextual identifier within the received video stream from the contact lens, wherein detecting the contextual identifier comprises:
 analyzing, by one or more processors, the received video stream from the contact lens; 
 applying, by one or more processors, at least one audio/video recognition system, wherein the at least one audio/video recognition system searches the received video stream for a predefined person, a predefined object, a predefined place, a predefined activity, and a predefined audible clip, and 
 wherein the contextual identifier is one or more predefined person, object, place and activity; 
   determining, by one or more processors, whether to capture the video stream based on, at least one of, the user interest level exceeding a threshold, biometric data of the user, and the detected a contextual identifier within the received video stream from the contact lens, wherein:
 determining the user interest level comprises detecting, by one or more processors, at least one of: a change in the user's pupil dilation; a change in the user's heart rate, and a change in the user's facial expression, and 
 wherein the biometric data of the user is received from the set of identifying information; 
   classifying, by one or more processor, the video stream into a category wherein classifying the video stream into a category comprises:
 establishing, by one or more processors, at least two categories, wherein a first category is public and the second category is private; 
 determining, by one or more processors, a pattern wherein the pattern is of the user placing the video stream into one of the at least two categories, and 
 based on deriving, by one or more processors, at least one common person, object, place and activity within each category; 
   responsive to determining to capture the video stream, saving, by one or more processors, the video stream based on the classification category of the video stream; and   creating, by one or more processor a new contextual identifier by:
 identifying, by one or more processors, at least two incidences of the user deleting the saved video stream, subsequent to the saving the video stream, within a predetermined time, 
 deriving, by one or more processors, at least one common person, object, place and activity within each of the identified incidences, and 
 responsive to deriving at least one common person, object, place and activity within each of the identified incidences, determining, by one or more processors, a pattern of the user deleting the saved video stream, subsequent to the saving the video stream.