TrackSort: Predictive tracking for sorting uncooperative bulk materials

Pfaff, Florian; Baum, Marcus; Noack, Benjamin; Hanebeck, Uwe D.; Gruna, Robin; Längle, Thomas; Beyerer, Jürgen

doi:10.1109/mfi.2015.7295737

Cited by 15 publications

(22 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these adaptations have their limits and a considerable variation in the velocities is almost impossible to eliminate. Both the variation in the flight directions of the particles and possible calibration errors can be observed in the evaluation based on real data in [8].…”

Section: Predictive Tracking For Optical Belt Sortersmentioning

confidence: 99%

“…To reduce assumptions about the motion behavior of the particles, we proposed to observe the particles over multiple time steps using an area scan camera [8]. We begin by tracking all particles in a tracking phase, as shown in Fig.…”

Section: Predictive Tracking For Optical Belt Sortersmentioning

confidence: 99%

“…To assess the overall performance of the predictive tracking approach with a constant velocity model, we performed multiple evaluations. Using real image data recorded on an industrial-scale optical belt sorter, we showed that the predictions as to where the particles will pass the array of nozzles are significantly better when using a constant velocity model than when using the old, implicit model assuming movement straight in the transport direction [8]. For further studies, a small experimental (but fully functional) optical belt sorter called TableSort was created.…”

Section: Predictive Tracking For Optical Belt Sortersmentioning

confidence: 99%

“…If the contours of the bulk material particles can be recognized in area scan camera images of the bulk material stream (which may be challenging for high loads), an approach based on area scan cameras can be employed [8]. Using this approach, improved predictions can be generated, which in turn can be used to enhance the separation process.…”

Section: Introductionmentioning

confidence: 99%

“…This problem arises in bulk material sorting tasks as distinguishing all particles on the belt based on visual features is either impossible or computationally too demanding. As described in [8], we use a global nearest neighbor (GNN) [10,Sec. 6.4] as the multitarget tracker and integrate information about the scenario at hand, such as where particles tend to enter and exit the observable area.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Predictive tracking with improved motion models for optical belt sorting

Pfaff

Pieper

Maier

et al. 2020

At - Automatisierungstechnik

Self Cite

View full text Add to dashboard Cite

Optical belt sorters are a versatile means to sort bulk materials. In previous work, we presented a novel design of an optical belt sorter, which includes an area scan camera instead of a line scan camera. Line scan cameras, which are well-established in optical belt sorting, only allow for a single observation of each particle. Using multitarget tracking, the data of the area scan camera can be used to derive a part of the trajectory of each particle. The knowledge of the trajectories can be used to generate accurate predictions as to when and where each particle passes the separation mechanism. Accurate predictions are key to achieve high quality sorting results. The accuracy of the trajectories and the predictions heavily depends on the motion model used. In an evaluation based on a simulation that provides us with ground truth trajectories, we previously identified a bias in the temporal component of the prediction. In this paper, we analyze the simulation-based ground truth data of the motion of different bulk materials and derive models specifically tailored to the generation of accurate predictions for particles traveling on a conveyor belt. The derived models are evaluated using simulation data involving three different bulk materials. The evaluation shows that the constant velocity model and constant acceleration model can be outperformed by utilizing the similarities in the motion behavior of particles of the same type.

show abstract

Section: Predictive Tracking For Optical Belt Sortersmentioning

confidence: 99%

Section: Predictive Tracking For Optical Belt Sortersmentioning

confidence: 99%

Section: Predictive Tracking For Optical Belt Sortersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Predictive tracking with improved motion models for optical belt sorting

Pfaff

Pieper

Maier

et al. 2020

At - Automatisierungstechnik

Self Cite

View full text Add to dashboard Cite

show abstract

An Image‐Based Approach to Automated Recognition of Asbestos‐Containing Components in Wall Demolition Waste

Bauer,

Kruggel‐Emden

2024

Chemie Ingenieur Technik

View full text Add to dashboard Cite

The feasibility to discriminate potentially asbestos‐containing components from asbestos‐free concrete based on camera images using the example of wall demolition waste is investigated. For this, three types of asbestos substitute materials and two types of concrete are crushed and photographed. The classification of the fragment images is carried out with a) morphological and texture features and b) with features automatically extracted by the pretrained MobileNetV3 network. Feret diameters, circularity, and others served as morphological descriptors. The texture was described by measures of grey‐level intensity, as obtained from the grey‐level co‐occurrence matrix. Support vector machines are found to achieve classification accuracies above 99 % based on the automatically extracted features. The presented identification approach is promising to automate the treatment process of asbestos‐containing materials from construction and demolition waste, which is effortful and requires expert knowledge to this day.

show abstract