Search

Recent advancements in computer vision, particularly in detection, segmentation, and classification, have significantly impacted various domains. However, these advancements are tied to RGB-based systems, which are insufficient for applications in industries like waste sorting, pharmaceuticals, and defense, where advanced object characterization beyond shape or color is necessary. Hyperspectral (HS) imaging, capturing both spectral and spatial information, addresses these limitations and offers advantages over conventional technologies such as X-ray fluorescence and Raman spectroscopy, particularly in terms of speed, cost, and safety. This study evaluates the potential of combining HS imaging with deep learning for material characterization. The research involves: i) designing an experimental setup with HS camera, conveyor, and controlled lighting; ii) generating a multi-object dataset of various plastics (HDPE, PET, PP, PS) with semi-automated mask generation and Raman spectroscopy-based labeling; and iii) developing a deep learning model trained on HS images for pixel-level material classification. The model achieved 99.94\% classification accuracy, demonstrating robustness in color, size, and shape invariance, and effectively handling material overlap. Limitations, such as challenges with black objects, are also discussed. Extending computer vision beyond RGB to HS imaging proves feasible, overcoming major limitations of traditional methods and showing strong potential for future applications., Comment: 13 pages, 15 figures, 6 equations

Information and communication technology (ICT) is an enabler for establishing automated vehicles (AVs) in today's traffic systems. By providing complementary and/or redundant information via radio communication to the AV's perception by on-board sensors, higher levels of automated driving become more comfortable, safer, or even possible without interaction by the driver, especially in complex scenarios. Additionally, communication between vehicles and/or a central service can improve the efficiency of traffic flow. This paper presents a reference architecture for such an infrastructure-based support of AVs. The architecture combines innovative concepts and technologies from different technological fields like communication, IT environment and data flows, and cyber-security and privacy. Being the basis for the EU-funded project ICT4CART, exemplary implementations of this architecture will show its power for a variety of use cases on highways and in urban areas in test sites in Austria, Germany, and Italy, including cross-border interoperability., Comment: Proceedings of 8th Transport Research Arena TRA 2020 (Conference cancelled), April 27-30, 2020, Helsinki, Finland