Automatic detection system for steel skeleton size based on machine vision.

Abstract

Currently, most buildings are constructed using prefabricated concrete slabs supported by a steel skeleton that is generally tied and welded manually. However, if the overall size of the skeleton is incorrect and this error is not noticed before the concrete is poured, then a huge waste is incurred by having to scrap all the prefabricated slabs. Therefore, we propose an automatic system for measuring the frame size needed for prefabricated slabs made of reinforced concrete using LabVIEW and the NI Vision library of machine-vision functions to perform image processing and machine-vision detection. A charge-coupled device camera obtained an overall image, and then, LabVIEW processed the image and extracted its features. The system compared the measured size with the design size and issued a warning if the two differ by more than 0.5cm. From experimental comparison and verification, the maximum measurement error between the test results and the actual size was 2.7% and the root mean square error was 0.66%. This meets the requirements of actual site construction and provides a scientific reference for realizing the automatic detection of the skeleton size for reinforced-concrete precast slabs.