Utilisation of Vision Systems and Digital Twin for Maintaining Cleanliness in Public Spaces

TL;DR

The utilisation of advanced vision surveillance systems and the Digital Twin technology in cleanliness management is presented, using a railway station as an example, based on an actual 3D model in the Nvidia Omniverse Isaac Sim simulator.

Abstract

Nowadays, the increasing demand for maintaining high cleanliness standards in public spaces results in the search for innovative solutions. The deployment of CCTV systems equipped with modern cameras and software enables not only real-time monitoring of the cleanliness status but also automatic detection of impurities and optimisation of cleaning schedules. The Digital Twin technology allows for the creation of a virtual model of the space, facilitating the simulation, training, and testing of cleanliness management strategies before implementation in the real world. In this paper, we present the utilisation of advanced vision surveillance systems and the Digital Twin technology in cleanliness management, using a railway station as an example. The Digital Twin was created based on an actual 3D model in the Nvidia Omniverse Isaac Sim simulator. A litter detector, bin occupancy level detector, stain segmentation, and a human detector (including the cleaning crew) along with their movement analysis were implemented. A preliminary assessment was conducted, and potential modifications for further enhancement and future development of the system were identified.

Figures (8)

• Figure 1: 3D model of the railway station: \ref{['fig:image_revit']} designed in Autodesk Revit and \ref{['fig:image_isaac']} Digital Twin based on the 3D model with added materials and textures.
• Figure 2: Generated simple 3D objects, arranged on a regular grid, 1 metre apart, to analyse cameras placement and video surveillance coverage of the station area.
• Figure 3: Examples of prepared litter models.
• Figure 4: Comparison of the performance of the trained YOLOv8x network model with the additional use of the SAHI method for small object detection.
• Figure 5: Comparison of the view from the same camera on \ref{['fig:KoszPusty']} empty and \ref{['fig:KoszPelny']} full bin.