Spatial-temporal Analysis for Automated Concrete Workability Estimation

TL;DR

This paper presents a computer vision-based approach using deep neural networks to objectively estimate concrete workability during mixing, aiming to reduce human error and improve construction efficiency.

Contribution

It introduces a novel application of spatial-temporal deep learning models for real-time concrete workability estimation from video data.

Findings

Deep neural networks can effectively predict workability from video

The approach reduces subjective assessment errors

Potential for real-time application in construction sites

Abstract

Concrete workability measure is mostly determined based on subjective assessment of a certified assessor with visual inspections. The potential human error in measuring the workability and the resulting unnecessary adjustments for the workability is a major challenge faced by the construction industry, leading to significant costs, material waste and delay. In this paper, we try to apply computer vision techniques to observe the concrete mixing process and estimate the workability. Specifically, we collected the video data and then built three different deep neural networks for spatial-temporal regression. The pilot study demonstrates a practical application with computer vision techniques to estimate the concrete workability during the mixing process.