Dr. Chadly Marouane

Dr. Chadly Marouane

Lehrstuhl für Mobile und Verteilte Systeme

Ludwig-Maximilians-Universität München, Institut für Informatik

Oettingenstraße 67
80538 München

Raum G 008

Telefon: +49 89 / 2180-9117

Fax: +49 89 / 2180-9148

Mail: chadly.marouane@ifi.lmu.de

Aufgabengebiet

Computer Vision in Mobile Applications

  • (Indoor-) Positioning
  • visual based Odometry
  • visual based Context Detection

Sprechstunde:
auf Anfrage

Abschlussarbeiten

Ausgeschriebene Abschlussarbeiten

Generell sind nicht alle Themen immer online. Bei Interesse an einer Abschlussarbeit in meinen Themengebieten, gerne einfach eine E-Mail schicken und zu einem Gespräch vorbeikommen. Eigene Ideen für Abschlussarbeiten sind auch jederzeit willkommen.

Publikationen

2016

  • C. Marouane, A. Ebert, C. Linnhoff-Popien, and M. Christil, "Step and activity detection based on the orientation and scale attributes of the SURF algorithm," in 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2016, pp. 1-8.
    [BibTeX]
    @InProceedings{marouane2016step,
    Title = {Step and activity detection based on the orientation and scale attributes of the SURF algorithm},
    Author = {Chadly Marouane and André Ebert and Claudia Linnhoff-Popien and Maximilian Christil},
    Booktitle = {2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN)},
    Year = {2016},
    Organization = {IEEE},
    Pages = {1-8},
    Owner = {cmarouane},
    Timestamp = {2016.11.23}
    }
  • C. Marouane, R. Gutschale, and C. Linnhoff-Popien, "Visual Odometry for pedestrians based on orientation attributes of SURF," in SAI Intelligent Systems Conference 2016, 2016, pp. 727-736.
    [BibTeX]
    @InProceedings{marouane16dvo,
    Title = {Visual Odometry for pedestrians based on orientation attributes of SURF},
    Author = {Chadly Marouane and Robert Gutschale and Claudia Linnhoff-Popien},
    Booktitle = {SAI Intelligent Systems Conference 2016},
    Year = {2016},
    Pages = {727-736},
    Owner = {cmarouane},
    Timestamp = {2016.11.23}
    }
  • C. Marouane, M. Maier, A. Leupold, and C. Linnhoff-Popien, "Visual Odometry using motion vectors from visual feature points," in 7th International Conference on Indoor Positioning and Indoor Navigation (IPIN 2016), 2016, pp. 1-8.
    [BibTeX]
    @InProceedings{marouane2016kompass,
    Title = {Visual Odometry using motion vectors from visual feature points},
    Author = {Chadly Marouane and Marco Maier and Alexander Leupold and Claudia Linnhoff-Popien},
    Booktitle = {7th International Conference on Indoor Positioning and Indoor Navigation (IPIN 2016)},
    Year = {2016},
    Pages = {1-8},
    Owner = {cmarouane},
    Timestamp = {2016.11.25}
    }
  • C. Marouane and B. Rott, "Mobile Authentisierung im Unternehmensalltag," Informatik-Spektrum, vol. 39, iss. 2, pp. 122-130, 2016.
    [BibTeX] [Download PDF]
    @Article{Marouane2016Mobile,
    Title = {Mobile Authentisierung im Unternehmensalltag},
    Author = {Chadly Marouane and Benno Rott},
    Journal = {Informatik-Spektrum},
    Year = {2016},
    Number = {2},
    Pages = {122-130},
    Volume = {39},
    Owner = {cmarouane},
    Timestamp = {2016.04.29},
    Url = {http://rd.springer.com/article/10.1007/s00287-016-0952-y}
    }

2015

  • A. Ebert, C. Marouane, B. Rott, and M. Werner, "KeyPocket - Improving Security and Usability for Provider Independent Login Architectures with Mobile Devices," in EAI 11th International Conference on Security and Privacy in Communication Networks (SecureComm 2015), 2015.
    [BibTeX]
    @InProceedings{keypocket15,
    Title = {KeyPocket - Improving Security and Usability for Provider Independent Login Architectures with Mobile Devices},
    Author = {André Ebert and Chadly Marouane and Benno Rott and Martin Werner},
    Booktitle = {EAI 11th International Conference on Security and Privacy in Communication Networks (SecureComm 2015)},
    Year = {2015},
    Publisher = {EAI},
    Owner = {aebert},
    Timestamp = {2015.09.30}
    }
  • C. Marouane and A. Ebert, "Enabling Pedometers on Basis of Visual Feature Point Conversion," in 1st GI Expert Talk on Localization, 2015, pp. 33-35.
    [BibTeX]
    @InProceedings{marouane15enabling,
    Title = {Enabling Pedometers on Basis of Visual Feature Point Conversion},
    Author = {Chadly Marouane and André Ebert},
    Booktitle = {1st GI Expert Talk on Localization},
    Year = {2015},
    Pages = {33-35},
    Owner = {cmarouane},
    Timestamp = {2015.07.10}
    }
  • C. Marouane and A. Ebert, "SURFLogo - Mobile Tagging with App Icons," in 7th EAI International Conference on Mobile Computing, Applications and Services (MobiCASE 2015), 2015.
    [BibTeX]
    @InProceedings{surflogo15,
    Title = {SURFLogo - Mobile Tagging with App Icons},
    Author = {Chadly Marouane and André Ebert},
    Booktitle = {7th EAI International Conference on Mobile Computing, Applications and Services (MobiCASE 2015)},
    Year = {2015},
    Publisher = {EAI},
    Owner = {cmarouane},
    Timestamp = {2016.01.29}
    }
  • C. Marouane, L. Schauer, and P. Bauer, "Classification of Vehicle Types in Car Parks using Computer Vision Techniques," in 12th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, 2015, pp. 1-9.
    [BibTeX]
    @InProceedings{marouane2015car,
    Title = {Classification of Vehicle Types in Car Parks using Computer Vision Techniques},
    Author = {Chadly Marouane and Lorenz Schauer and Philipp Bauer},
    Booktitle = {12th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services},
    Year = {2015},
    Pages = {1-9},
    Owner = {cmarouane},
    Timestamp = {2015.08.06}
    }

2014

  • M. Maier, C. Marouane, M. Klette, F. Dorfmeister, P. Marcus, and C. Linnhhoff-Popien, "SURFtogether: Towards Context Proximity Detection Using Visual Features," in 3rd International Conference on Context-Aware Systems and Applications (ICCASA 2014), 2014, pp. 86-91.
    [BibTeX]
    @InProceedings{maier2014surftogether,
    Title = {SURFtogether: Towards Context Proximity Detection Using Visual Features},
    Author = {Marco Maier and Chadly Marouane and Manuel Klette and Florian Dorfmeister and Philipp Marcus and Claudia Linnhhoff-Popien},
    Booktitle = {3rd International Conference on Context-Aware Systems and Applications (ICCASA 2014)},
    Year = {2014},
    Pages = {86-91},
    Owner = {mmaier},
    Timestamp = {2015.07.10}
    }
  • M. Maier, C. Marouane, and C. Linnhoff-Popien, "Vis-a-Vis: Offline-Capable Management of Virtual Trust Structures Based on Real-Life Interactions," International Journal On Advances in Life Sciences, vol. 6, iss. 1 and 2, pp. 1-10, 2014.
    [BibTeX] [Abstract] [Download PDF]
    Online services, particularly those aimed at a specific user base such as a company's employees, face the problem of identity management. Especially when the service constitutes some kind of social network, i.e., the validity of the users' identities matters, secure and reliable means for identity verification and authentication are required. In this paper, predicated on our previous work, we propose an identity management concept based on a) verification through physical presence and b) authentication through ownership. Our approach being a hybrid solution between a centralized authority and decentralized trust management is settled on a sweet spot between security and convenience for the users. In this extended version, we present the newly proposed Tree of Trust structure in more detail, and provide a thourough explanation how the system can be used in a technically more distributed manner, even supporting offline operation.
    @Article{visavis2014,
    Title = {Vis-a-Vis: Offline-Capable Management of Virtual Trust Structures Based on Real-Life Interactions},
    Author = {Marco Maier and Chadly Marouane and Claudia Linnhoff-Popien},
    Journal = {International Journal On Advances in Life Sciences},
    Year = {2014},
    Number = {1 and 2},
    Pages = {1-10},
    Volume = {6},
    Abstract = {Online services, particularly those aimed at a specific user base such as a company's employees, face the problem of identity management. Especially when the service constitutes some kind of social network, i.e., the validity of the users' identities matters, secure and reliable means for identity verification and authentication are required. In this paper, predicated on our previous work, we propose an identity management concept based on a) verification through physical presence and b) authentication through ownership. Our approach being a hybrid solution between a centralized authority and decentralized trust management is settled on a sweet spot between security and convenience for the users. In this extended version, we present the newly proposed Tree of Trust structure in more detail, and provide a thourough explanation how the system can be used in a technically more distributed manner, even supporting offline operation.},
    Owner = {mmaier},
    Timestamp = {2014.09.04},
    Url = {http://www.thinkmind.org/download.php?articleid=lifsci_v6_n12_2014_1}
    }
  • C. Marouane, A. Ebert, and B. Rott, "Trends und Chancen beim mobilen Einkaufen," in Marktplätze im Umbruch - Digitale Strategien fuer Services im Mobilen Internet, Springer, 2014, pp. 289-298.
    [BibTeX]
    @InCollection{marouane15trends,
    Title = {Trends und Chancen beim mobilen Einkaufen},
    Author = {Chadly Marouane and André Ebert and Benno Rott},
    Booktitle = {Marktplätze im Umbruch - Digitale Strategien fuer Services im Mobilen Internet},
    Publisher = {Springer},
    Year = {2014},
    Pages = {289-298},
    Owner = {cmarouane},
    Timestamp = {2015.07.10}
    }
  • C. Marouane, M. Maier, S. Feld, and M. Werner, "Visual Positioning Systems - An Extension to MoVIPS," in 5th International Conference on Indoor Positioning and Indoor Navigation (IPIN 2014), 2014, pp. 95-104.
    [BibTeX] [Abstract]
    Due to the increasing popularity of location-based services, the need for reliable and cost-effective indoor positioning methods is rising. As an alternative to radio-based localization methods, in 2011, we introduced MoVIPS (Mobile Visual Indoor Positioning System), which is based on the idea to extract visual feature points from a query image and compare them to those of previously collected geo-referenced images. The general feasibility of positioning by SURF points on a conventional smartphone was already shown in our previous work. However, the system still faced several shortcomings concerning real-world usage such as request times being too high and distance estimation being unreliable because of the employed estimation method not being rotation invariant. In this paper, three extensions are presented that improve the practical applicability of MoVIPS. To speed up request times, both a dead reckoning approach (based on step counting using the accelerometer) and an orientation estimation (based on the smartphone's compass) are introduced to filter relevant images from the database and thus to reduce the amount of images to compare the query image to. Furthermore, the vectors of the SURF points are quantized. For this purpose, clusters are calculated from all SURF points from the database. As a result, each image can be represented by a histogram of cluster frequencies, which can be compared with each other a lot more efficiently. The third extension is an improvement of the distance estimation method, which uses the matched feature points of an image to perform a perspective transformation and to determine the actual position with the aid of the transformation matrix. Employing the first extension, request times are reduced by 84\% percent. The quantization of the SURF points reduces the search time by a factor of 1000. Finally, the distance estimation is now rotation invariant and enables a better position correction.
    @InProceedings{marouane2014visual,
    Title = {Visual Positioning Systems - An Extension to MoVIPS},
    Author = {Chadly Marouane and Marco Maier and Sebastian Feld and Martin Werner},
    Booktitle = {5th International Conference on Indoor Positioning and Indoor Navigation (IPIN 2014)},
    Year = {2014},
    Pages = {95-104},
    Abstract = {Due to the increasing popularity of location-based services, the need for reliable and cost-effective indoor positioning methods is rising. As an alternative to radio-based localization methods, in 2011, we introduced MoVIPS (Mobile Visual Indoor Positioning System), which is based on the idea to extract visual feature points from a query image and compare them to those of previously collected geo-referenced images. The general feasibility of positioning by SURF points on a conventional smartphone was already shown in our previous work. However, the system still faced several shortcomings concerning real-world usage such as request times being too high and distance estimation being unreliable because of the employed estimation method not being rotation invariant. In this paper, three extensions are presented that improve the practical applicability of MoVIPS. To speed up request times, both a dead reckoning approach (based on step counting using the accelerometer) and an orientation estimation (based on the smartphone's compass) are introduced to filter relevant images from the database and thus to reduce the amount of images to compare the query image to. Furthermore, the vectors of the SURF points are quantized. For this purpose, clusters are calculated from all SURF points from the database. As a result, each image can be represented by a histogram of cluster frequencies, which can be compared with each other a lot more efficiently. The third extension is an improvement of the distance estimation method, which uses the matched feature points of an image to perform a perspective transformation and to determine the actual position with the aid of the transformation matrix. Employing the first extension, request times are reduced by 84\% percent. The quantization of the SURF points reduces the search time by a factor of 1000. Finally, the distance estimation is now rotation invariant and enables a better position correction.},
    Owner = {cmarouane}
    }

2013

  • M. Maier, C. Marouane, C. Linnhoff-Popien, B. Rott, and S. A. W. Verclas, "Vis-a-Vis Verification: Social Network Identity Management Through Real World Interactions," in 3rd International Conference on Social Eco-Informatics (SOTICS 2013), 2013, pp. 39-44.
    [BibTeX] [Abstract] [Download PDF]
    Online services, particularly those aimed at a specific user base such as a company's employees, face the problem of identity management. Especially when the service constitutes some kind of social network, i.e., the validity of the users' identities matters, secure and reliable means for identity verification and authentication are required. In this paper, we propose a novel identity management concept based on a) verification through physical presence and b) authentication through ownership. Our approach being a hybrid solution between a centralized authority and decentralized trust management is settled on a sweet spot between security and convenience for the users.
    @InProceedings{visavis,
    Title = {Vis-a-Vis Verification: Social Network Identity Management Through Real World Interactions},
    Author = {Marco Maier and Chadly Marouane and Claudia Linnhoff-Popien and Benno Rott and Stephan A. W. Verclas},
    Booktitle = {3rd International Conference on Social Eco-Informatics (SOTICS 2013)},
    Year = {2013},
    Pages = {39-44},
    Abstract = {Online services, particularly those aimed at a specific user base such as a company's employees, face the problem of identity management. Especially when the service constitutes some kind of social network, i.e., the validity of the users' identities matters, secure and reliable means for identity verification and authentication are required. In this paper, we propose a novel identity management concept based on a) verification through physical presence and b) authentication through ownership. Our approach being a hybrid solution between a centralized authority and decentralized trust management is settled on a sweet spot between security and convenience for the users.},
    Keywords = {identity management systems; authentication; social network services; mobile computing},
    Url = {http://www.thinkmind.org/download.php?articleid=sotics_2013_3_10_30054}
    }
  • S. Rümelin, C. Marouane, and A. Butz, "Free-hand Pointing for Identification and Interaction with Distant Objects," in 5th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2013), New York, NY, USA, 2013, pp. 40-47. doi:10.1145/2516540.2516556
    [BibTeX] [Download PDF]
    @InProceedings{freehandpointing,
    Title = {Free-hand Pointing for Identification and Interaction with Distant Objects},
    Author = {Sonja Rümelin and Chadly Marouane and Andreas Butz},
    Booktitle = {5th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2013)},
    Year = {2013},
    Address = {New York, NY, USA},
    Pages = {40-47},
    Publisher = {ACM},
    Series = {AutomotiveUI '13},
    Acmid = {2516556},
    Doi = {10.1145/2516540.2516556},
    ISBN = {978-1-4503-2478-6},
    Keywords = {camera-based tracking, gesture interaction, pointing},
    Location = {Eindhoven, Netherlands},
    Numpages = {8},
    Url = {http://doi.acm.org/10.1145/2516540.2516556}
    }

2011

  • M. Werner, M. Kessel, and C. Marouane, "Indoor positioning using smartphone camera," in International Conference on Indoor Positioning and Indoor Navigation (IPIN 2011), 2011, pp. 1-6. doi:10.1109/IPIN.2011.6071954
    [BibTeX] [Download PDF]
    @InProceedings{werner2011indoor,
    Title = {Indoor positioning using smartphone camera},
    Author = {Martin Werner and Moritz Kessel and Chadly Marouane},
    Booktitle = {International Conference on Indoor Positioning and Indoor Navigation (IPIN 2011)},
    Year = {2011},
    Pages = {1-6},
    Publisher = {IEEE},
    Doi = {10.1109/IPIN.2011.6071954},
    Url = {http://dx.doi.org/10.1109/IPIN.2011.6071954}
    }