Experimental Evaluation of a Novel Sensor-Based Sorting Approach Featuring Predictive Real-Time Multiobject Tracking

Abstract

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. Index Terms-Automated visual inspection, machine vision, real-time multiobject tracking, sensor-based sorting.

A General Framework for Sorting Large Data Sets Using Independent Subarrays of Approximately Equal Length

“…The distance between the locations that need swap has also decreased. In contrast, for a large number of divisions, which do not apply to inequality (27), the serial realization of the proposed framework will be slower than the conventional serial realization. By comparing serial and parallel realizations of the proposed framework, the speedup factor, T P S T P P , is as…”

“…Therefore, when the number of processors is not too large, the proposed algorithm will be preferable because of time complexity order, the required running time, and the number of swaps. For data sets with 2 10 , 2 13 , 2 15 , 2 17 , 2 20 , 2 24 , 2 27 , and 2 30 elements, the maximum number of processors that the proposed algorithm of this work is less complex and faster than the previous algorithm are 32, 128, 256, 512, 2048, 8192, 32768, and 65536 (or equivalently, the number of divisions equal to 5, 7, 8, 9, 11, 13, 15, and 16), respectively.…”

Recovery of Raw Materials from Ceramic Waste Materials for the Refractory Industry

“…Therefore, the fragmented material was sorted by optical sorting, meaning by differences in color and translucency. The sorting was carried out with a laboratory system for optical bulk material sorting (TableSort), which was developed at the Fraunhofer IOSB [13,14]. Equipped with a RGB filter camera and a filigree blow-out device, this system is suitable for small amounts of material.…”

Motion-based visual inspection of optically indiscernible defects on the example of hazelnuts

“…In other words, we exploit the knowledge that there is always at least one image without detection between two runs. It is important to note that although the test objects are fed individually into the system and our data acquisition system considers only one test object at a time, the system can be extended, for instance by integrating a real-time multiobject tracking system for sensor-based sorting as presented in [35], to handle multiple test objects occurring in the same frame. We further require that the number of points associated with an sample, i.e., | |, is greater than a certain threshold which is based on the average number of points associated to the extracted samples.…”