Cloud-based segregated video storage and retrieval for improved network scalability and throughput

Abstract

The invention is based, in part, on a system and method designed to be able to easily and automatically scale up to millions of cameras and users. To do this, this discourse teaches use of modern cloud computing technology, including automated service provisioning, automated virtual machine migration services, RESTful API, and various firewall traversing methods to facilitate the scaling process. Moreover, the system and method described herein teaches scalable cloud solutions providing for higher though-put camera provisioning and event recognition. The network may segregate the retrieval server from the storage server, and by doing so, minimizing the load on any one server and improving network efficiency and scalability

1 .- 20 . (canceled) 
     
     
         21 . A server comprising:
 a processor; and   a memory storing instructions that, when executed by the processor, configure the server to perform operations comprising:   accessing an event-detected image frame from a camera;   determining a zone-pixel value from a zone of the event-detected image frame;   detecting a threshold-grade event by referencing the zone-pixel value against a pre-defined reference table of event-recognized pixel values; and   categorizing the threshold-grade event into a recognized event based on the referencing.   
     
     
         22 . The server of  claim 21 , wherein the operations comprise:
 storing a single stream of the recognized event in a storage of the server;   feeding the single stream from the server to a retrieval cloud-based server; and   overlaying contextual data comprising information of the recognized event on the single stream of the recognized event.   
     
     
         23 . The server of  claim 21 , wherein the operations comprise:
 transmitting a status message indicating that the camera is operating improperly, in response to determining that the camera is improperly.   
     
     
         24 . The server of  claim 21 , wherein detecting the threshold-grade event comprises:
 detecting the threshold-grade event from audio-video data of a real-world environment captured from the camera by an event management system applying event detection parameters based on the referencing.   
     
     
         25 . The server of  claim 24 , wherein the event management system comprises at least one of device management services, user management services, or alert management services. 
     
     
         26 . The server of  claim 21 , wherein the event management system detects the threshold-grade event based on a combination of a pre-defined, a user-defined, and a learned threshold of any one of computed pixel values derived from a parameter. 
     
     
         27 . The server of  claim 26 , wherein the parameter is at least one of object detection, scene change, object left or removed, line crossing, movement, count, shape, or sound change. 
     
     
         28 . The server of  claim 21 , wherein categorizing the threshold-grade event comprises:
 analyzing the threshold-grade event for categorization into the recognized event by an event management system applying event recognition parameters based on the referencing.   
     
     
         29 . The server of  claim 28 , wherein the event management system analyzes at least one of computed pixel values derived from at least one of a parameter from the threshold-grade event by referencing against at least one of a pre-defined, user-defined, or learned reference table of recognized event-computed pixel values. 
     
     
         30 . The server of  claim 28 , wherein the recognized event is at least one of face recognition, object recognition, movement, intrusion, location in designated areas, loitering, vehicle/license plate recognition, impact, and, or aberrant sound,
 wherein the event management system is configured to query an event recognized database, and retrieve any one of a matched recognized event based on at least one of a pixel value, analysis of pixel value, metadata, or hash map from an event bucket in the event recognized database.   
     
     
         31 . The server of  claim 30 , wherein the event management system is configured to:
 run an analysis algorithm for movement tracking and, or movement extrapolating over an array of incoming image frames;   query the event recognized database; and   retrieve any one of a matched recognized event based on movement data from the event bucket in the event recognized database.   
     
     
         32 . The server of  claim 30 , wherein the event management system is configured to:
 determine content of the threshold-grade event based on determining at least one object identity by matching any one of at least scene change, movement, count, shape, sound, metadata, or hashmap characteristics of objects in an event bucket in the event recognized database.   
     
     
         33 . The server of  claim 21 , wherein the operations comprise:
 employing machine learning to update any one of a threshold of computed pixel values for event detection or update any one of a reference analysis of computed pixel values for event recognition.   
     
     
         34 . The server of  claim 33 , wherein the machine learning is at least one of a convolution neural network, associated model, training data set, feed-forward neural network, and, or back-propagated neural network. 
     
     
         35 . The server of  claim 28 , wherein the event management system is configured to perform at least one of an audio, video, and, or image frame upload, save, retrieval, and, or playback in a staged-event driven manner (SEDA), wherein at least one of an upload, save, retrieval, and, or playback is via a serial of audio-video-image segments over a time frame comprising a detected and, or recognized event. 
     
     
         36 . A method comprising:
 accessing an event-detected image frame from a camera;   determining a zone-pixel value from a zone of the event-detected image frame;   detecting a threshold-grade event by referencing the zone-pixel value against a pre-defined reference table of event-recognized pixel values; and   categorizing the threshold-grade event into a recognized event based on the referencing.   
     
     
         37 . The method of  claim 36 , further comprising:
 storing a single stream of the recognized event in a storage of a server;   feeding the single stream from the server to a retrieval cloud-based server; and   overlaying contextual data comprising information of the recognized event on the single stream of the recognized event.   
     
     
         38 . The method of  claim 36 , further comprising:
 transmitting a status message indicating that the camera is operating improperly, in response to determining that the camera is improperly.   
     
     
         39 . The method of  claim 36 , wherein detecting the threshold-grade event comprises:
 detecting the threshold-grade event from audio-video data of a real-world environment captured from the camera by an event management system applying event detection parameters based on the referencing.   
     
     
         40 . A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to:
 accessing an event-detected image frame from a camera;   determining a zone-pixel value from a zone of the event-detected image frame;   detecting a threshold-grade event by referencing the zone-pixel value against a pre-defined reference table of event-recognized pixel values; and   categorizing the threshold-grade event into a recognized event based on the referencing.