Automatic detection and classification of EOL-concrete and resulting recovered products by hyperspectral imaging

Abstract

The recovery of materials from Demolition Waste (DW) represents one of the main target of the recycling industry and the its characterization is important in order to set up efficient sorting and/or quality control systems. End-Of-Life (EOL) concrete materials identification is necessary to maximize DW conversion into useful secondary raw materials, so it is fundamental to develop strategies for the implementation of an automatic recognition system of the recovered products. In this paper, HyperSpectral Imaging (HSI) technique was applied in order to detect DW composition. Hyperspectral images were acquired by a laboratory device equipped with a HSI sensing device working in the near infrared range (1000-1700 nm): NIR Spectral Camera™, embedding an ImSpector™ N17E (SPECIM Ltd, Finland). Acquired spectral data were analyzed adopting the PLS-Toolbox (Version 7.5, Eigenvector Research, Inc.) under Matlab® environment (Version 7.11.1, The Mathworks, Inc.), applying different chemometric methods: Principal Component Analysis (PCA) for exploratory data approach and Partial Least Square- Discriminant Analysis (PLS-DA) to build classification models. Results showed that it is possible to recognize DW materials, distinguishing recycled aggregates from contaminants (e.g. bricks, gypsum, plastics, wood, foam, etc.). The developed procedure is cheap, fast and non-destructive: it could be used to make some steps of the recycling process more efficient and less expensive

Extending Effective Dynamic Range of Hyperspectral Line Cameras for Short Wave Infrared Imaging

“…The detection of plastic in food waste was chosen as a test application for this study. Many studies have proposed the use of spectral imaging to detect and classify plastic in waste [23][24][25]. It is important to separate plastic from food waste to prevent it from being trapped in transportation channels when it is moved to gasification tanks, which stops the entire process.…”

Quality assessment for recycling aggregates from construction and demolition waste: An image-based approach for particle size estimation

“…Da Fonseca Martins Gomes et al (2010) for instance developed a machine vision system based on shape features for detecting mortar, ceramic and concrete within C&D. Gokyuu et al (2011) used colour features and Bayesian classification to sort byproducts of different size and shape from C&D. Likewise, Anding et al (2013) proposed a computer vision system based on colour imaging and support vector classification for differentiating phenotypically similar materials such as concrete, aerated concrete, lightweight concrete, porous brick and dense brick. More recently, Palmieri et al (2014) described a system based on hyperspectral imaging for detecting unwanted contaminants like brick, gypsum, wood and plastics in C&D.…”

Hyperspectral imaging applied to end-of-life (EOL) concrete recycling

“…Experimental set-up 1: the training sample set. Particles of brick (2 particles), aggregates (3 particles), wood (1 particle), gypsum (3 particles), foam (3 particles) and plastic (4 particles), arranged in 7 lines, were acquired generating a training image sample set used to build the classification model (Figure 12.1) [7]. Experimental set-up 2: validation sample set.…”