The introduction of digitalization and Industry 4.0 in waste management is still in its early stages. In the forthcoming era, real-time monitoring, data analysis, management, and process control will take precedence at waste treatment plants. Managing mixed waste presents challenges due to disparities in waste quality and variations stemming from material and mechanical factors. This master thesis primarily aims to characterize solid waste particles within a bulk on a conveyor belt, with a specific focus on bulk processing. Real-time characterization of waste on conveyor belts is important for continuous plant optimization. The objective is to implement autonomous and dynamic adjustments to address waste fluctuations. While sensors required for comprehensive characterization are available, they come with significant costs and high safety demands. Consequently, alternative methods like classification through artificial intelligence and cameras are highly sought after. However, these approaches necessitate substantial volumes of highquality labeled training data, which is arduous to obtain for bulk waste processing systems. The creation of such training data using digital techniques such as 3D renderings is being considered as a potential solution, alongside the evaluation of a methodology to ascertain the particles present in a bulk.