Material Recognition for Automated Progress Monitoring using Deep Learning Methods

TL;DR

This paper advances construction material recognition using deep learning, achieving 97.35% accuracy and providing a new dataset to facilitate further research in robust, real-world construction monitoring systems.

Contribution

The paper introduces a deep learning approach that addresses real-world challenges and provides a new publicly available dataset for construction material recognition.

Findings

Achieved 97.35% accuracy in material classification

Developed a new dataset with 1231 images of 11 classes

Addressed illumination and robustness issues in real-world settings

Abstract

Recent advancements in Artificial intelligence, especially deep learning, has changed many fields irreversibly by introducing state of the art methods for automation. Construction monitoring has not been an exception; as a part of construction monitoring systems, material classification and recognition have drawn the attention of deep learning and machine vision researchers. However, to create production-ready systems, there is still a long path to cover. Real-world problems such as varying illuminations and reaching acceptable accuracies need to be addressed in order to create robust systems. In this paper, we have addressed these issues and reached a state of the art performance, i.e., 97.35% accuracy rate for this task. Also, a new dataset containing 1231 images of 11 classes taken from several construction sites is gathered and publicly published to help other researchers in this field.