Article detection method, system and device based on image recognition and storage medium

Abstract

The invention discloses an article detection method and system based on image recognition, a computer device and a storage medium. The article detection method comprises the following steps: determining a difference region relative to a background image in a to-be-detected image; identifying the difference region by using an artificial intelligence network; determining whether the difference area contains an article detection target according to the identification result; and determining the position change trajectory of the article detection target according to the position of the difference region including the same article detection target. An artificial intelligence network is used for processing, so that the position change track of the article detection target is obtained; the position change of the article detection target can be visually displayed through the position change track, the observation effect more reliable than that of naked eyes is obtained, and the position and change of the article detection target can be accurately reflected; the final position of the article detection target is determined according to the position change track, thereby facilitating elimination of fault hidden troubles and guaranteeing operation safety. The invention is widely applied to the technical field of image processing.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an object detection method, system, computer device and storage medium based on image recognition. Background technique [0002] In construction sites such as elevator maintenance, smaller items such as wrenches, screwdrivers and spare parts are used. Since these items are inconspicuous, or they are moved to the corner and blocked by rolling or being bumped by the staff, it is easy to ignore these items during the cleaning process, resulting in these items being left behind after the construction is completed. On the one hand, it leads to the property loss of the construction party. On the other hand, these items are easy to cause injuries such as tripping to elevator users and other personnel. Danger. [0003] In the current related technology, the detection of small items on the construction site is still performed manually by construction personnel. Due to the compl...

AI Technical Summary

Problems solved by technology

Since these items are inconspicuous, or they are moved to the corner and blocked by rolling or being bumped by the staff, it is easy to ignore these items during the cleaning process, resulting in these items being left behind after the construction is completed. On the one hand, it leads to the property loss of the construction party. On the other hand, these items are easy to cause injuries such as tripping to elevator users and other personnel. Danger

[0003] In the current related technology, the detection of small items on the construction site is still carried out manually by construction personnel. Due to the complex scene of the construction site, it is difficult to find these small items with the naked eye, so the efficiency is low and the error rate is high.

Images