Multi-user video stream deep learning sharing computing multiplexing method

Abstract

The invention relates to the computer and video processing. In order to provide a video query service through the technologies, such as target identification, target detection, etc., in a multi-user scene, a multi-user video stream deep learning sharing calculation multiplexing method comprises the following steps of firstly, when a request with a detection operation or an identification operation comes, merging the requests according to the relevance of the spatial dimensions; secondly, according to the relevance of the time dimension, inquiring whether the proper data can be reused or not, and calling a deep learning model with the configured parameters for analysis; for the part for non-multiplexed, firstly, according to the balance relation of the speed and the precision, finding out the most appropriate parameter configuration during the analysis process, then calling a difference detector and a deep learning model to carry out video analysis according to the parameter configuration, finally outputting and storing the analysis result in a data warehouse, and using a lifting module for improving the original result precision in the database to multiple to the high-precision query request. The method is mainly applied to the video processing occasions.

Description

technical field [0001] The invention relates to computer and video processing, in particular to a multi-user video stream deep learning shared computing multiplexing method. Background technique [0002] At present, deep learning has become an important engine to promote the application and popularization of artificial intelligence. Especially in the field of computer vision, the rapid development of deep learning has brought profound changes to the field, the most representative of which is the continuous development of image analysis technologies such as target detection and target recognition. Object detection can be used to classify objects, such as identifying whether there is a dog, a person, or a table in the image, but the name of the person cannot be recognized; object recognition can identify the specific identity of the person. For an image, applying the object detection model can quickly identify all the objects in the image, which brings a huge change to the vi...

AI Technical Summary

Problems solved by technology

And optimize the locality of multi-user video query in a shared computing environment, so that multiple users can share the inference results of deep learning, thereby improving the running speed and solving the problem that the speed of deep learning models is too low when processing video data

At the same time, solve the balance between speed and accuracy caused by sharing

Images