Image recognition method and device based on edge calculation, equipment and storage medium

Abstract

The invention relates to an image recognition method and device based on edge calculation, equipment and a storage medium. The method comprises the following steps: the step 1) carrying out image acquisition, i.e., acquiring an image through a field deployment camera; the step 2), carrying out image recognition, i.e., according to configuration information of a recognition object, recognizing an interested target in each path of video stream based on a yov5 algorithm recognition framework and a customized target detection model; and the step 3), sending an identification result, and sending the identification result for identifying the interested target to an upper computer. Compared with the prior art, the invention has the advantages of high anti-interference performance, high innovativeness and the like.

Description

technical field [0001] The present invention relates to image recognition technology, in particular to an image recognition method, device, equipment and storage medium based on edge computing. Background technique [0002] With the development of machine vision and artificial intelligence technology, artificial intelligence applications based on machine vision have been widely used in various industries, such as face detection, pedestrian tracking, object detection, etc. However, there are still some difficulties in the application of customized artificial intelligence applications in smart construction sites: on the one hand, artificial intelligence scenarios related to vision applications often require GPU server computing resources to support computing power, and the implementation at the deployment end requires the deployment conditions provided by the on-site computer room; on the other hand On the one hand, the customized requirements of smart construction sites (such...

AI Technical Summary

Problems solved by technology

The disadvantages are: 1. The cost is high, and the price of a server plus a graphics card often reaches tens of thousands of yuan; 2. The deployment requirements are high, and the server needs to be deployed in the cabinet of the computer room and the heat dissipation conditions must be guaranteed.

However, this existing patent is a generalized AI machine vision application, which generally includes face recognition, pedestrian recognition, helmet recognition, reflective clothing recognition, etc. It has been widely used, and its performance has been proven to be reliable and stable.

However, in practical application, it also found its existing defects: 1. For the entrance and exit of personnel, there are security guards to maintain the safety and order of the site, and there is no need to wear helmets, and the problem of false alarms needs to be solved; 2. Smart construction sites Workers are required to dress in accordance with safety production regulations and are not allowed to enter the construction site wearing short-sleeved shorts. This requirement is not a general machine vision artificial intelligence scenario

Images