Visual co-processing method, system, equipment and medium

Abstract

The invention discloses a visual cooperative processing method, system and device and a medium, and relates to the technical field of big data processing, and the method comprises the steps: obtaining a target detection result through detecting a target object in target video data and / or the attribute of the target object; aggregating the target detection results to obtain multi-dimensional object attribute information; for a current frame and a preorder frame in the target video data, judging whether the multi-dimensional object attribute information has a change within a preset range, and obtaining a judgment result; and calling a corresponding processing model according to the judgment result, and outputting a model co-processing result. Complex visual information is decoupled into multiple dimensions, and rich object attribute information is generated. A lightweight model is used in a simple task, and a large model is called in a complex task, so that the balance between high performance and low power consumption is realized. And different task complexities can be flexibly adapted, and efficient operation of the system in a resource-limited environment is ensured.

Images