Vision-based automated waste audits: a use case from the window manufacturing industry

Waste auditing is one of the tools used to quantify waste generation in construction processes, especially industrialized building facilities that aim reduce waste. These audits are organized following a regular schedule monitor manufacturing activities with respect generated. However, identification and quantification through occasional at any particular workstation remains biased, manual, error-prone, monotonous task. This paper proposes automation facilities, using as case study cutting station on window line. The generated during process quantified contour-based image processing algorithms, material determined by optimized deep learning classification models. approach allows continuous acquisition data level enables data-driven management decision-making has potential support reduction facilities.