Department of Real Estate and Construction, The University of Hong Kong, Pokfulam Road, Hong Kong, China.
J Environ Manage. 2021 May 15;286:112233. doi: 10.1016/j.jenvman.2021.112233. Epub 2021 Mar 5.
There are various scenarios challenging human experts to judge the interior of something based on limited surface information. Likewise, at waste disposal facilities around the world, human inspectors are often challenged to gauge the composition of waste bulks to determine admissibility and chargeable levy. Manual approaches are laborious, hazardous, and prone to carelessness and fatigue, making unattended gauging of construction waste composition using simple surface information highly desired. This research attempts to contribute to automated waste composition gauging by harnessing a valuable dataset from Hong Kong. Firstly, visual features, called visual inert probability (VIP), characterizing inert and non-inert materials are extracted from 1127 photos of waste bulks using a fine-tuned convolutional neural network (CNN). Then, these visual features together with easy-to-obtain physical features (e.g., weight and depth) are fed to a tailor-made support vector machine (SVM) model to determine waste composition as measured by the proportions of inert and non-inert materials. The visual-physical feature hybrid model achieved a waste composition gauging accuracy of 94% in the experiments. This high performance implies that the model, with proper adaption and integration, could replace human inspectors to smooth the operation of the waste disposal facilities.
有各种情况需要人类专家根据有限的表面信息来判断物体的内部。同样，在世界各地的废物处理设施中，人类检查员也经常面临挑战，需要评估废物块的组成，以确定是否可接受和应收取的费用。手动方法既费力又危险，容易出现粗心和疲劳，因此，人们非常希望能够利用简单的表面信息，对建筑废物的组成进行无人值守的测量。本研究旨在通过利用来自香港的有价值数据集，为自动废物成分测量做出贡献。首先，使用经过微调的卷积神经网络（CNN）从 1127 张废物块照片中提取出描述惰性和非惰性材料的视觉特征，称为视觉惰性概率（VIP）。然后，将这些视觉特征与易于获得的物理特征（例如重量和深度）一起输入到定制的支持向量机（SVM）模型中，以确定惰性和非惰性材料的比例来衡量废物的组成。在实验中，视觉-物理特征混合模型实现了 94%的废物成分测量精度。这种高性能表明，该模型经过适当的调整和集成后，可以替代人工检查员，使废物处理设施的运行更加顺畅。
