Hamidi, et al. (2014) proposed a BIM-based demolition waste management system and Park, et al. (2014) developed a BIM-based C&D waste database by analysing the construction material classification system and data available in the ARCHICAD library in Korea.
The associated band gap, magnetic moment, phase, and material classification are also indicated.
This increased flexibility in the image acquisition process prompted the inclusion of the hyper-spectral imaging systems in the development of a wide variety of computer vision systems, such as video surveillance, food inspection, medical imaging, remote sensing, and material classification [2 4].
In such work, a four-layer material classification network with 493,226 trainable weights and biases was able to discern crumbled and chipped concrete from good concrete, as well as other materials such as ballast, rail and fasteners, with an accuracy of 95.02%.
Table 3 displays the material classification results for metal for GoogLeNet, AlexNet, and VGG-16 trained on the MINC dataset.
The material classification experiment results demonstrate that the classification accuracy increases by 10.6%40.8%%, and the fine powder yield increases by 12.5%40.1%%, with an almost changeless cut size.
Besides problems encountered during the measurement, the interpretation of the results and calculation of the activity indices, needed for material classification, may lead to significant mistakes.
The results show that both the dynamic modulus test and the flexural stiffness test can be used in the material classification.
The proposed data decorrelation scheme has been employed to optimally minimize the amount of redundant information contained in the highly correlated hyper-spectral bands and has been comprehensively evaluated in the context of non-ferrous material classification.
