Sensor-based sorting describes a family of systems that enable the removal of individual objects from a material stream. The technology is widely used in various industries such as agriculture, food, mining, and recycling. Examples of sorting tasks include the removal of fungus-infested grains, the enrichment of copper content in copper mining or the sorting of plastic waste according to the type of plastic. Sorting decisions are made based on information acquired by one or more sensors. A particular strength of the technology is the flexibility in sorting decisions, which is achieved by using various sensors and programming the data analysis. However, a comprehensive understanding of the process is necessary for the development of new sorting systems that can address previously unresolved tasks. This survey is aimed at innovative researchers and practitioners who are unfamiliar with sensor-based sorting or have only encountered certain aspects of the overall process. The references provided serve as starting points for further exploration of specific topics.

Sensor-based sorting is a machine vision application that has found industrial application in various fields. An accept-or-reject task is executed by separating a material stream into two fractions. Current systems use line-scanning sensors, which is convenient as the material is perceived during transportation. However, line-scanning sensors yield a single observation of each object and no information about their movement. Due to a delay between localization and separation, assumptions regarding the location and point in time for separation need to be made based on the prior localization. Hence, it is necessary to ensure that all objects are transported at uniform velocities. This is often a complex and costly solution. In this paper, we propose a new method for reliably separating particles at non-uniform velocities. The problem is transferred from a mechanical to an algorithmic level. Our novel advanced image processing approach includes equipping the sorter with an area-scan camera in combination with a real-time multiobject tracking system, which enables predictions of the location of individual objects for separation. For the experimental validation of our approach, we present a modular sorting system, which allows comparing sorting results using a line-scan and area-scan camera. Results show that our approach performs reliable separation and hence increases sorting efficiency.

The ongoing digitization of industry and agriculture can benefit significantly from optical spectroscopy. In many cases, optical spectroscopy enables the estimation of properties such as substance concentrations and compositions. Spectral data can be acquired and evaluated in real time, and the results can be integrated directly into process and automation units, saving resources and costs. Multivariate data analysis is needed to integrate optical spectrometers as sensors. Therefore, a spectrometer with integrated artificial intelligence (AI) called SmartSpectrometer and its interface is presented. The advantages of the SmartSpectrometer are exemplified by its integration into a harvesting vehicle, where quality is determined by predicting sugar and acid in grapes in the field.

A polarization state detector (PSD) measures the state of polarization of the detected light. The state of polarization is fully described by the Stokes vector containing four Stokes parameters. A division-of-amplitude photopolarimeter (DOAP) measures the four Stokes parameters by simultaneously acquiring four intensities using photodetectors. A key component of the DOAP is the first beam splitter, which splits up the incoming beam into two beams. The effect of the beam splitter on the state of polarization of the reflected (r) and transmitted (t) beam is determined by six parameters: R, T, ψ_r, ψ_t, Δ_r, and Δ_t. R and T are the reflectance and transmittance, and (ψ_r, Δ_r) and (ψ_t, Δ_t) are the ellipsometric parameters of the beam splitter in reflection and transmission, respectively. To measure the Stokes vector with high accuracy, the six optical parameters must be chosen appropriately. In previous work, the optimal parameters of the beam splitter have been determined as R = T = 1/2, cos² 2ψ_r = 1/3, ψ_t = π/2 - ψ_r, and Δ_r-Δ_t modulo π=π/2 by calculating the maximum of the absolute value of determinant of the instrument matrix. Using additional quarter-wave plates eliminates the constraint on the retardance and hence simplifies the manufacturing process of the beam splitter, especially when broadband application is intended. To compensate a suboptimal value of Δ_r-Δ_t, the azimuthal angles of the principal axes of the retarders must be adjusted, for which we provide analytic formulas. Hence, a DOAP with retarders is also optimal in the sense that the same values for the determinant and condition number of the instrument matrix are obtained. When using two additional retarders, it is necessary to install both on the same light path in order to obtain an optimal DOAP. We will show that is also possible to get an optimal DOAP with only one additional quarter-wave plate instead of two, if one of the Wollaston prisms is rotated.

In optical sorting of bulk material, the composition of particles may frequently change. State-of-the-art sorting approaches rely on tuning physical models of the particle motion. The aim of this work is to increase the prediction accuracy in complex fast-changing sorting scenarios with data-driven approaches. In this article, we propose two neural network (NN) experts for accurate prediction of a priori known particle types. To handle the large variety of particle types that can occur in real-world sorting scenarios, we introduce a simple but effective mixture of experts’ approach that combines NNs with hand-crafted motion models. Our new method not only improves the prediction accuracy for bulk material consisting of many particle classes, but also proves to be very adaptive and robust to new particle types.