Escolar Documentos
Profissional Documentos
Cultura Documentos
net/publication/325426642
CITATION READS
1 368
1 author:
Hagen Borstell
Otto-von-Guericke-Universität Magdeburg
12 PUBLICATIONS 22 CITATIONS
SEE PROFILE
Some of the authors of this publication are also working on these related projects:
All content following this page was uploaded by Hagen Borstell on 29 May 2018.
Although there is a significant trend towards Automation of material handling systems includes,
automation in logistics, the proportion of manual for instance, handling, loading, picking and sorting
operations along the supply chain. Image groceries. In particular, an attempt is made to
processing can support this automation. For supersede code-based ID readers.
unloading operations with robots, the individual – Cameras: Improvements of quality features
packages, sacks or other object types must be (e.g. resolution, privacy protection) lead to
recognized and localized. This can be achieved greater integration of cameras into logistics
by using depth cameras and methods of object processes. In addition to video surveillance
recognition and pose estimation [51]. Similar systems for visualizing processes, cameras
applications are de-palletizing of goods [52] and are also increasingly being used for data
robot-based order picking in warehouses or collection instead of scanners, e.g.
distribution centers [53]. Such technologies are identification, dimensioning.
also suitable to control conveyors, which perform
complex intralogistics tasks such as package Beyond that, tendencies such as the use of
layering or singulation of packages [54][55]. software frameworks and the application of
Laser scanning systems for collision protection methods of digital engineering (e.g. virtual
and camera-based systems for optical track operation) can be identified. The future will show
guidance have long been used successfully in which of these tendencies and trends will make
automated guided vehicles. Recent research is the largest contribution to digitalization of logistics
devoted to obstacle detection for safer and more and to smart logistics zones respectively.
flexible man-machine environments [56] and for
optimization of vehicle routes [57]. In addition to 4 Summary
laser-based systems, camera-based systems are
increasingly being used in these applications, in In this publication, applications and trends of
particular depth cameras are combined with image processing in logistics have been
modern object recognition methods [58]. presented. The identified categories of logistics
applications of image processing illustrate the
2.11 Visual documentation and monitoring significant contribution of these technologies to
digitalization of logistics and to the concept of
Logistics is a network of machine operations and smart logistics zones. Some innovations within
human actions. Humans apply action to the categories, such as (a) volumetric properties of
process in response to current conditions. One goods, (b) manual picking and packing and (c)
way of communicating process states to humans automated handling systems are leading the way
is through visualization. Visualization based on within new technological trends. Which
image data can contain complex content, which is, applications and which trends will gain in
however, very easily decipherable by humans. importance must be further monitored.
Visual documentation of liability transitions can
reduce liability risks and improve risk To determine base functions of image processing
management [59]. When operating large areas and their special characteristics in terms of logistic
such as logistics hubs, passenger terminals or applications represents an important aspect of
event areas, visual monitoring systems based on future research. Base functions, such as pose
heterogeneous sensor systems are ideal for the detection, should act as the smallest building
operator to assess the situation at a glance [60]. blocks for image-based sensor systems,
supporting, in particular, the planning and
3 Trends of image processing in logistics implementation of those systems for logistics
applications.
Trends and their impact are difficult to predict.
However, the current literature review reveals that 5 References
there are certain technologies and methodologies
that are being used to an increasing extent: [1] Krampe, H. et al. (Hrsg.) (2012): Grundlagen
der Logistik: Theorie und Praxis logistischer
– Depth Perception: The availability of Systeme. 4. Auflage. München: HUSS-
consumer depth cameras triggered the VERLAG GmbH.
development of a variety of new systems, e.g. [2] Schenk, M. et al. (Hrsg.) (2015): Produktion
systems for mobile package dimensioning, und Logistik mit Zukunft : Digital Engineering
container unloading, picking assistance or and Operation. Heidelberg: Springer Vieweg.
flexible conveyor controlling. [3] Wegner M. et al. (Hrsg.) (2013): Low-cost
– Embedded Vision: Image processing units Sensor Technology - a DHL Perspective on
are increasingly designed as Internet of Implications and Use Cases for the Logistics
Things (IoT) nodes. They are equipped with Industry. Troisdorf: DHL Customer Solutions
communication modules and do not deliver & Innovation.
pictures, but state data of processes. [4] Kersten, T. et al. (2016): Genauigkeitsunter-
– Deep Learning: Deep learning methods are suchungen handgeführter Scannersysteme.
increasingly used for object recognition in In: Dreiländertagung der DGPF, der OVG
logistics, e.g. robot picking or grab-and-go und der SGPF in Bern, Schweiz - Publi-
kationen der DGPF, Band 25, pp. 271-287.
[5] GS1 Germany (2015): 2D symbols in 21st International Conference on Emerging
distribution and logistics. Technologies and Factory Automation
url: https://www.gs1.org (ETFA). pp. 1–4.
[6] Vitronic Dr.-Ing. Stein Bildverarbeitungs- [19] VLS Engineering GmbH (n.d.): Messen im
systeme GmbH (2012): Technische Bild. url: https://v-l-s.com/messen-im-bild/
Dokumentation - Kamerabasierte Daten- [20] LoadScan (n.d.): Loadscan OverView - Load
erfassung für Warehouse & Distribution. Management Solutions. url:
url: https://www.vitronic.de https://www.loadscan.com/solutions/overview
[7] Shetty, R. et al. (2012): Optical Container [21] Richter, K. et al. (2012): Robust Depth
Code Recognition and its Impact on the Imaging Measurement for Bulk Materials
Maritime Supply Chain. In: Proceedings of Technology. Cement International 01/2012,
the 2012 Industrial and Systems Engineering pp. 66–75.
Research Conference. Florida, USA. [22] Bundesministerium für Wirtschaft und
[8] Kirchner, T. (2016): ProGlove launches their Energie (2016): Transportschäden sicher
first smart Glove for Industry. Workaround identifiziert. url: https://www.zim-
GmbH (ProGlove). bmwi.de/erfolgsbeispiele/transportschaeden-
url: http://www.proglove.de sicher-identifiziert/
[9] Jung, M. et al. (2015): An Accurate and [23] Noceti, N. et al. (2018): A Multi-camera
Efficient Camera-based Indoor Positioning System for Damage and Tampering
Approach for Intralogistic Environments. Detection in a Postal Security Framework. J
Proceedings of the XXI International Image Video Proc. 2018, pp. 11.
Conference MHCL’15. Belgrade: University [24] Wenzel, S. et al. (2011): Condition Monitoring
of Belgrade, Faculty of Mechanical in Logistics – a New Approach for
Engineering, pp 133-138. Maintenance. In: ICEME 2011- 2nd
[10] Borstell, H. et al. (2013): Vehicle Positioning International Conference on Engineering and
System based on Passive Planar Image Meta-Engineering, 27-30 March 2011,
Markers. In: Indoor Positioning and Indoor Orlando, USA.
Navigation (IPIN), 2013 International [25] Cao, L. et al. (2013): Kompakter,
Conference on, pp. 1–9. multifunktionaler Sensor auf Basis von
[11] Lewin, M. et al. (2017): Optimization of Tiefenbildtechnologie für die Schüttgut-
Production-oriented Logistics Processes technik. In: 13./14. Forschungskolloquium am
Through Camera-based Identification and Fraunhofer IFF Forschung vernetzen -
Localization for Cyber-physical Systems. In: Innovationen beschleunigen, pp. 105–112.
Advances in Production Management [26] VLS Engineering GmbH (n.d.): Messen im
Systems, Springer, pp. 168-176. Bild jetzt auch für Lademeterermittlung. url:
[12] IdentPro GmbH (2018): Staplerleitsystem https://v-l-s.com/messen-im-bild-
identplus. url: http://identplus.net/de/das-3d- lademeterermittlung/
staplerleitsystem-identplus/ [27] Borstell, H. et al. (2015): Toward Mobile
[13] Schlüter, M. et al. (2018): Vision-based Monitoring of Cargo Compartment Using 3D
Identification Service for Remanufacturing Sensors for Real-Time Routing. In: Logistics
Sorting. Procedia Manufacturing, 15th Global Management, Lecture Notes in Logistics.
Conference on Sustainable Manufacturing Springer, Cham, pp. 189–200.
21, pp. 384–391. [28] ZIH Corp (2017): Solution Guide: Making
[14] Borstell, H. et al. (2014): Pallet Monitoring Your Loading Operations Smarter and More
System Based on a Heterogeneous Sensor Connected. url: https://www.zebra.com
Network for Transparent Warehouse [29] Amato, G. et al. (2017): Deep learning for
Processes. In: Sensor Data Fusion: Trends, decentralized parking lot occupancy
Solutions, Applications (SDF), pp. 1-6. detection. Expert Systems with Applications
[15] AKL-tec (2017): Datenblatt APACHE portal 72, pp. 327–334.
first choice - Der preiswerte Einstieg in die [30] Borstell, H. et al. (2013): Echtzeitinformatio-
APACHE Frachtvermessung. url: https://akl- nen in sicherheitskritischen GIS-Anwendun-
tec.de/produkt/apache-portal-first-choice/ gen. In: GeoForum MV 2013 - Neue
[16] AKL-tec (2017): Datenblatt APACHE flying Horizonte für Geodateninfrastrukturen - Open
forklift - Eine neue Dimension für das Messen GeoData, Mobility, 3D-Stadt. pp. 181–190.
und Verwiegen „on the fly“. url: https://akl- [31] Özgür, Ç. Et al. (2016): Comparing Sensor-
tec.de/produkt/apache-flying-forklift/ based and Camera-based Approaches to
[17] Borstell, H. et al. (2013): Prozessintegrierte Recognizing the Occupancy Status of the
Volumenerfassung von logistischen Load Handling Device of Forklift Trucks.
Palettenstrukturen auf Basis von Low-Cost- [32] KiwiSecurity (2016): KiwiVision - Privacy
Tiefenbildsensoren. In: 3D NordOst 2013 - Protector. url: https://www.kiwisecurity.com
Tagungsband, Berlin, pp. 115–124. [33] Borstell, H. et al. (2013): Virtual top view:
[18] Fechteler, M. et al. (2016): Prototype for Towards real-time aggregation of videos to
Enhanced Product Data Acquisition based on monitor large areas. In: Computer Analysis of
Inherent Features in Logistics. In: 2016 IEEE
Images and Patterns. 15th International fahrzeuge - Mit Sicherheit weniger Unfälle,
Conference, CAIP 2013. Vol.2. pp. 546–554. 2016. url: http://motec-cameras.com
[34] Kempe, M. et al. (2011): Echtzeitnahe [47] Salzer, S. (2018): Optisches
Analyse des Personenaufkommens in Assistenzsystem zur sichere Handhabung
öffentlichen Bereichen. 9./10. IFF-Kolloquium palettierter Ware. url:
Forschung vernetzen - Innovationen http://www.nekos.exfa.de
beschleunigen Magdeburg, pp. 85–90. [48] Lang, A. et al. (2017): Konzeption eines
[35] Borstell, H. et al. (2012): Image-Based kamerabasierten Kollisionswarnsystems zur
Situation Assessment in Public Space. In: Prävention von Arbeitsunfällen an
Future Security, Communications in Gabelstaplern. In: Logistics Journal:
Computer and Information Science, Berlin: Proceedings 2017.
Springer, pp. 61–64. [49] Trenkle, A. et al. (2013): FiFi – Steuerung
[36] Burrows, P. (2015): Measuring the eines FTF durch Gesten- und Personen-
customer’s journey through London City erkennung. In: Logistics Journal 2013.
Airport. In: Journal of Airport Management 9, [50] Overmeyer, L. et al. (2017): Intelligente
pp. 103–108. Flurförderzeuge durch die Implementierung
[37] Borstell, H. et al. (2012): Security in Supply kognitiver Systeme. In: Handbuch Industrie
Chains in the Scope of Surface Transport of 4.0 Bd.3, Springer Reference Technik. Berlin:
Goods by Secure Information Patterns on the Springer Vieweg, pp. 87-118.
Freight - Trans4Goods. In: Future Security, [51] Thamer, H. et al. (2013): 3D-Bildverarbeitung
Communications in Computer and Informati- für die automatische Entladung von
on Science. Berlin: Springer, pp. 25-28. Standardladungsträgern. In: Schenk, M.
[38] Bohács, G. et al. (2012): Automatische (Hrsg.): 18. Magdeburger Logistiktage -
visuelle Datensammlung aus Sichere und nachhaltige Logistik, pp. 201-
Materialflusssystemen und ihre Anwendung 210.
in Simulationsmodellen. In: Logistics Journal [52] Weichert, F. et al. (2013): Automated
nicht-referierte Veröffentlichungen. Detection of Euro Pallet Loads by Interpreting
[39] Koç, E. et al. (2013): Nutzung von Realdaten PMD Camera Depth Images. Logist. Res. 6,
in Simulationsmodellen durch industrielle 99–118.
Bildverarbeitung. In: Dangelmaier et al. [53] Eppner, C. et al. (2016): Lessons from the
(Hrsg.) Simulation in Produktion und Logistik. Amazon Picking Challenge: Four Aspects of
Paderborn, HNI-Verlagsschriftenreihe 2013, Building Robotic Systems. Presented at the
pp. 349-359. Robotics: Science and Systems XII.
[40] Baechler, A. et al. (2016): The Development [54] Uriarte, C. et al. (2016): Flexible
and Evaluation of an Assistance System for Automatisierung logistischer Prozesse durch
Manual Order Picking - Called Pick-by- modulare Roboter. Logistics Journal :
Projection - with Employees with Cognitive Proceedings 2016.
Disabilities. In: Computers Helping People [55] Cao, L. et al. (2014): Peristaltik-Förderer -
with Special Needs, Lecture Notes in Integriertes Entlade- und Transportkonzept
Computer Science. Springer, pp. 321–328. für Massenströme in der Paketlogistik: In:
[41] Grzeszick, R. et al. (2016). Camera-assisted Schenk, M. (Hrsg.): Forschung vernetzen -
Pick-by-feel. Logistics Journal : Proceedings Innovation beschleunigen: 15. Forschungs-
2016. kolloquium am Fraunhofer IFF, Magdeburg,
[42] Funk, M. et al. (2016): motionEAP: An pp. 7–13.
Overview of 4 Years of Combining Industrial [56] Vatavu, A. et al. (2015): Modeling and
Assembly with Augmented Reality for Tracking of Dynamic Obstacles for Logistic
Industry 4.0. In: Proceedings of the 16th Plants Using Omnidirectional Stereo Vision.
International Conference on Knowledge In: 2015 IEEE/RSJ International Conference
Technologies and Data-Driven Business, I- on Intelligent Robots and Systems (IROS),
KNOW ’16. ACM, New York, NY, USA. pp. 3552–3558.
[43] Hochstein, M. et al. (2017): Konsolidier- [57] Hochstein, M. et al. (2016): Alternatives
assistent - Assistenzsystem für manuelle Linienführungssystem für autonome,
Konsolidier- und Sortierprozesse in fahrerlose Transportsysteme. In: Logistics
Distributionszentren. Logistics Journal: Journal : Proceedings 2016.
Proceedings 2017. [58] TU Chemnitz (n.d.): FOLLOWme - Intra-
[44] Logivations (2018): Kamerabasierte logistiksystem mit Fahrerlosen Transport-
Objekterkennung - Deep Machine Learning in Systemen. url: https://followme-ils.com/
Verbindung mit Computer Vision. url: [59] Rieger, U. (2012): Visualisierung von
http://www.logivations.com Haftungsübergängen. url: http://www.hli-
[45] Qiu, X. et al. (2017): Hand Detection for consulting.de
Grab-and-Go Groceries (Course Project [60] Gebert, B. et al.(2012): Prozessvisualisierung
Reports). Stanford University. auf Basis eines hybriden Sensorsystems. In:
[46] Motec GmbH (2016): Motec Kamera-Monitor- Go-3D 2012. Computergraphik für die Praxis,
Systeme für Transport- und Kommunal- pp. 51–67.