Video analytics encoding for improved efficiency of video processing and compression

Abstract

Embodiments are generally directed to video analytics encoding for improved efficiency of video processing and compression. An embodiment of an apparatus includes a memory to store data, including data for video streaming, and a video processing mechanism, wherein the video processing mechanism is to analyze video data and generate video analytics, generate metadata representing the video analytics and insert the generated video analytics metadata into a message, and transmit the video data and the metadata to a succeeding apparatus or system in a video analytics pipeline, the video data being compressed video data.

1 .- 20 . (canceled) 
     
     
         21 . An apparatus comprising:
 a video processing circuitry to:
 generate video analytics of video data of a video stream, wherein the video analytics represents analysis of the video data; 
 add the video analytics to metadata associated with the video data; and 
 transmit, via a video analytics pipeline, a message having the video data, the video analytics, and the metadata. 
   
     
     
         22 . The apparatus of  claim 21 , further comprising an imaging circuitry to capture the video stream having the video data representing images of a scene, wherein the apparatus further comprises memory to store the video data. 
     
     
         23 . The apparatus of  claim 21 , wherein the video processing circuitry is further to receive at least a portion of the video analytics from a first computing device including a preceding computing device, and wherein the message is transmitted to a second computing device including a subsequent computing device, wherein the video analytics identifies one or more elements associated with the scene, wherein the one or more elements include one or more of individuals, vehicles, objects, or conditions associated with the scene. 
     
     
         24 . The apparatus of  claim 21 , wherein the metadata comprises one or more flags identifying information relating to one or more of user viewing optimization, object motion, or object detection confidence value. 
     
     
         25 . The apparatus of  claim 21 , wherein the message comprises a Supplemental Enhancement Information (SEI) message that is carried in a Network Abstraction Layer (NAL). 
     
     
         26 . The apparatus of  claim 21 , wherein the apparatus comprises one or more of an edge device, a gateway device, or a smart image capturing device. 
     
     
         27 . A method comprising:
 generating, by a computing device, video analytics of video data of a video stream, wherein the video analytics represents analysis of the video data;   adding the video analytics to metadata associated with the video data; and   transmitting a message having the video data, the video analytics, and the metadata.   
     
     
         28 . The method of  claim 27 , further comprising capturing the video stream having the video data representing images of a scene, and storing the video data. 
     
     
         29 . The method of  claim 27 , further comprising receiving at least a portion of the video analytics from a first computing device including a preceding computing device, and wherein the message is transmitted to a second computing device including a subsequent computing device, wherein the video analytics identifies one or more elements associated with the scene, wherein the one or more elements include one or more of individuals, vehicles, objects, or conditions associated with the scene. 
     
     
         30 . The method of  claim 27 , wherein the metadata comprises one or more flags identifying information relating to one or more of user viewing optimization, object motion, or object detection confidence value. 
     
     
         31 . The method of  claim 27 , wherein the message comprises a Supplemental Enhancement Information (SEI) message that is carried in a Network Abstraction Layer (NAL). 
     
     
         32 . The method of  claim 27 , wherein the computing device comprises one or more of an edge device, a gateway device, or a smart image capturing device. 
     
     
         33 . A computer-readable medium having stored thereon instructions which, when executed, cause a computing device to perform operations comprising:
 generating video analytics of video data of a video stream, wherein the video analytics represents analysis of the video data;   adding the video analytics to metadata associated with the video data; and   transmitting a message having the video data, the video analytics, and the metadata.   
     
     
         34 . The computer-readable medium of  claim 33 , wherein the operations further comprise capturing the video stream having the video data representing images of a scene, and storing the video data. 
     
     
         35 . The computer-readable medium of  claim 33 , wherein the operations further comprise receiving at least a portion of the video analytics from a first computing device including a preceding computing device, and wherein the message is transmitted to a second computing device including a subsequent computing device, wherein the video analytics identifies one or more elements associated with the scene, wherein the one or more elements include one or more of individuals, vehicles, objects, or conditions associated with the scene. 
     
     
         36 . The computer-readable medium of  claim 33 , wherein the metadata comprises one or more flags identifying information relating to one or more of user viewing optimization, object motion, or object detection confidence value. 
     
     
         37 . The computer-readable medium of  claim 33 , wherein the message comprises a Supplemental Enhancement Information (SEI) message that is carried in a Network Abstraction Layer (NAL). 
     
     
         38 . The computer-readable medium of  claim 33 , wherein the computing device comprises one or more of an edge device, a gateway device, or a smart image capturing device.