Title: Automatic classification method of construction waste based on machine vision

Authors: Lei Zhang

Addresses: Department of Civil and Architecture Engineering, Jiaozuo University, Jiaozuo, 454000, China

Abstract: In order to solve the problems of low accuracy and low efficiency of existing automatic classification methods of construction waste, an automatic classification method of construction waste based on machine vision was proposed. Firstly, the CCD camera is used to collect the image and enhance the image. Then, the maximum entropy method is used to obtain the optimal segmentation threshold of the image, and the construction waste image is segmented. Finally, the gradient information is used to obtain the image features of construction waste, and the automatic classification of construction waste is realised by combining with the SVM algorithm. The experimental results show that the classification accuracy of the proposed method is between 90% and 98%. When the number of construction waste images is 1,000, the classification time is 13 min, which indicates that the proposed method has high classification accuracy, high efficiency and good application performance.

Keywords: machine vision; construction waste; automatic classification; histogram; maximum entropy segmentation.

DOI: 10.1504/IJETM.2025.144506

International Journal of Environmental Technology and Management, 2025 Vol.28 No.1/2/3, pp.19 - 31

Received: 28 Feb 2024
Accepted: 12 Jun 2024
Published online: 17 Feb 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article