SlumpGuard: An AI-Powered Real-Time System for Automated Concrete Slump Prediction via Video Analysis

2025-07-14

AI Summary

Traditional concrete slump testing suffers from heavy reliance on manual operation, low efficiency, poor repeatability, and inability to support real-time quality monitoring. To address this, this paper proposes the first video-based, full-batch automated workability monitoring system for concrete. Methodologically, we construct a dedicated in-the-wild construction-site video dataset and design an end-to-end flow-behavior analysis model that integrates computer vision with lightweight deep learning to directly regress slump values from raw video frames. The system is deployed in real-world construction environments and operates autonomously, delivering continuous, real-time quantitative outputs without human intervention. Experimental results demonstrate over a 10× improvement in detection efficiency and a prediction error of ≤5 mm—significantly outperforming current manual standards. This work establishes a practical, deployable technical pathway for closed-loop quality control of concrete in intelligent construction.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Intelligent Robots: State Estimation
• Machine Learning: Feature Construction/Reformulation

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Concrete workability is essential for construction quality, with the slump test being the most common on-site method for its assessment. However, traditional slump testing is manual, time-consuming, and prone to inconsistency, limiting its applicability for real-time monitoring. To address these challenges, we propose SlumpGuard, an AI-powered, video-based system that automatically analyzes concrete flow from the truck chute to assess workability in real time. Our system enables full-batch inspection without manual intervention, improving both the accuracy and efficiency of quality control. We present the system design, a the construction of a dedicated dataset, and empirical results from real-world deployment, demonstrating the effectiveness of SlumpGuard as a practical solution for modern concrete quality assurance.

Problem

• Automating concrete slump testing to replace manual methods
• Real-time monitoring of concrete workability via video analysis
• Improving accuracy and efficiency in construction quality control

Innovation

• AI-powered real-time video analysis system
• Automated concrete slump prediction
• Full-batch inspection without manual intervention