Concrete pouring amount estimation method based on artificial intelligence video analysis

Abstract

The invention provides a concrete pouring amount estimation method based on artificial intelligence video analysis. The method includes: carrying out efficient event segmentation judgment on a video stream uploaded in real time through a deep learning method CoViAR-Mobile-V3 algorithm; analyzing a scene and an event type of the time window video; respectively finishing pouring of commercial premixed concrete and pouring of self-mixed concrete; after the current pouring amount is estimated and pouring is completed, estimating the overall pouring amount, comparing output information with a set standard value, giving out an early warning for events with risks, estimating the pouring amount at some specific moments, providing a basis for corresponding related supervision projects, carrying outnecessary pouring amount estimation, and completing risk early warning of the link. According to the invention, full-flow intelligent side station supervision is adopted, potential risks caused by human factors of a supervisor are avoided, online real-time risk early warning is realized, only a small number of supervision experts are needed, the risk of system early warning is remotely analyzed and judged, and the human efficiency of side station supervision and management is improved.

Description

Technical field [0001] The invention relates to the technical field of construction engineering, in particular to a method for estimating the pouring amount in concrete pouring based on artificial intelligence video analysis. Background technique [0002] Concrete pouring quality management is an important part of site supervision work. In the process of pouring quality management, the overall pouring amount and certain links need to be provided with necessary information support for the supervision of related projects through the pouring amount. In the process of management depth supervision, it is necessary to use the current pouring amount information to estimate the current concrete depth in the final hole. In the current manual supervision process, professional supervisors estimate the current pouring volume based on relevant information on the spot. Specifically: in the commercial concrete scenario, using the on-site attention information, the single-car loading volume and ...

AI Technical Summary

Problems solved by technology

[0003] Under the existing manual on-site supervision and management mode, its shortcomings are more obvious. The specific developments are as follows: the quality of side station supervision and management has the following high-risk problems: the quality of side station supervisors is uneven, and it is impossible to fully grasp the side station supervision. The key points of the side station will easily lead to the loss of control of the side station process; the supervisors have great discretion, and the lack of image data support for the side station process and side station management resul...

Images