Edge computing method and apparatus, edge device and storage medium

An edge device, comprising:

• a central processor, a graphics processor, a memory and a communication bus, wherein
• the communication bus is configured to implement connection and communication among the central processor, the graphics processor and the memory;
• the central processor and the graphics processor are configured to execute one or more programs stored in the memory, to implement following steps:
• acquiring multiple channels of original videos of a target scenario;
• performing synchronous access processing on the multiple channels of original videos to obtain multiple channels of synchronous videos, and acquiring multiple frames of synchronous images based on the multiple channels of synchronous videos;
• performing computer vision collaborative analysis on the multiple frames of synchronous images to obtain a collaborative processing result;
• and
• performing service logic processing with configuration information synchronized from a cloud server in advance and corresponding to the target scenario, as well as the collaborative processing result to obtain a service processing result;
• wherein for the step of performing the computer vision collaborative analysis on the multiple frames of synchronous images to obtain the collaborative processing result, the central processor and the graphics processor are configured to implement following steps:
• performing computer vision analysis on each frame of image among the multiple frames of synchronous images to obtain multiple image processing results in one-to-one correspondence with the multiple frames of synchronous images;
• and
• performing one of duplication eliminating or both fusion and duplication eliminating on the multiple image processing results to obtain the collaborative processing result.

A non-transitory computer-readable storage medium, storing one or more programs, wherein the one or more programs are executable by one or more processors to:

• acquire multiple channels of original videos of a target scenario;
• perform synchronous access processing on the multiple channels of original videos to obtain multiple channels of synchronous videos, and acquiring multiple frames of synchronous images based on the multiple channels of synchronous videos;
• perform computer vision collaborative analysis on the multiple frames of synchronous images to obtain a collaborative processing result;
• and
• perform service logic processing with configuration information synchronized from a cloud server in advance and corresponding to the target scenario, as well as the collaborative processing result to obtain a service processing result;
• wherein the step of performing the computer vision collaborative analysis on the multiple frames of synchronous images to obtain the collaborative processing result comprises:
• performing computer vision analysis on each frame of image among the multiple frames of synchronous images to obtain multiple image processing results in one-to-one correspondence with the multiple frames of synchronous images;
• and
• performing one of duplication eliminating or both fusion and duplication eliminating on the multiple image processing results to obtain the collaborative processing result.