Computer Video Analytics Processor

Abstract

In a method of processing video images, a processor might obtain a video stream, select a set of processing pipelines from a plurality of processing pipelines, apply the set of processing pipelines to the video stream to obtain a data set of analytics data, wherein the pipeline analytics data for a processing pipeline of the set of processing pipelines comprises data about images of the video images, store the pipeline analytics data of each processing pipeline into a queryable data structure, receive queries from a user interface, and return portions of the video stream, or references thereto, in response to the queries.

What is claimed is: 
     
         1 . A method of processing video images, comprising:
 obtaining a video stream;   selecting a set of processing pipelines from a plurality of processing pipelines;   applying the set of processing pipelines to the video stream to obtain a data set of analytics data, wherein pipeline analytics data for a processing pipeline of the set of processing pipelines comprises data about images of the video images;   storing the pipeline analytics data of each processing pipeline into a queryable data structure;   receiving queries from a user interface; and   returning portions of the video stream, or references thereto, in response to the queries.   
     
     
         2 . The method of  claim 1 , wherein a processing pipeline of the set of processing pipelines outputs object analytics data representing objects identified in the video images. 
     
     
         3 . A method of processing data, comprising:
 representing references to video inputs using a markup language;   representing actions to be taken on the video inputs, wherein the actions are represented by data stored in a data object in the markup language;   processing the video inputs according to the actions; and   passing data to one or more of a detector, a classifier, and/or a tracker according to a node structure represented in the data object in the markup language.   
     
     
         4 . The method of  claim 3 , wherein the markup language is organized as a graph of nodes and edges, with edges connecting nodes and each edge representing an output of one node to which the edge is connected and an input of another node or inputs of nodes to which the edge is connected. 
     
     
         5 . The method of  claim 4 , wherein at least one node comprises a nested graph. 
     
     
         6 . The method of  claim 4 , wherein the graph of nodes and edges includes terminal nodes that correspond to physical processes. 
     
     
         7 . The method of  claim 6 , wherein the physical processes include a data transformation process that might be performed by a processor that is processing a markup language file, wherein at a runtime a pipeline execution engine receives the graph of nodes.