{
  "id": "2006.16344",
  "version": "v1",
  "published": "2020-06-29T20:06:26.000Z",
  "updated": "2020-06-29T20:06:26.000Z",
  "title": "Material Recognition for Automated Progress Monitoring using Deep Learning Methods",
  "authors": [
    "Navid Ghassemi",
    "Hadi Mahami",
    "Mohammad Tayarani Darbandi",
    "Afshin Shoeibi",
    "Sadiq Hussain",
    "Farnad Nasirzadeh",
    "Roohallah Alizadehsani",
    "Darius Nahavandi",
    "Abbas Khosravi",
    "Saeid Nahavandi"
  ],
  "categories": [
    "cs.CV",
    "stat.ML"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-06-29T20:06:26.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep learning methods",
      "automated progress monitoring",
      "material recognition",
      "create robust systems",
      "create production-ready systems"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}