Augmented Vision DFKI
Bionic – IFA Berlin 09.19

Thanks to the team members who travelled to Berlin for presenting the Bionic Project on the IFA.

For more informations about the project :

EASY-IMP Promotional Video
EASY IMP – Promotional Video

EASY-IMP is a large initiative started in September 2013. It regroups 12 partners from seven different countries to develop new methodologies for designing and producing intelligent wearable products as Meta-Products.

We propose a Cloud-enabled framework for Collaborative Design and Development of Personalised Products and Services, combining embedded (Internet of things paradigm) and mobile devices with facilities for joint open development of enabling downloadable applications.

Application of smart clothes in mobile exercise monitoring
Application of smart clothes in mobile exercise monitoring
This video shows the application of smart clothes for squat monitoring.
Multiple miniaturized inertial measurement units (IMUs) are integrated into a pair of pants using textile cables. This results in a light-weight and easy to use platform providing comfortableness and maximal movement flexibility for the user. A customized firmware for energy-efficient data acquisition, in addition to a selection of low-power components extends the autonomous operation time compared to traditional approaches.The mobile application provides:

  • Real time estimation of hip and knee joint angles with visualization
  • Detection of eccentric(downward) and concentric(upward) phases of squat
  • Counting the repetitions with visual and audio feedback

for more information please contact

AlterEgo Preview
Das EU Forschungsprojekt AlterEGO hat sich zum Ziel gesetzt, eine Rehabilitationsmethode für Patienten zu entwickeln, die unter sozialen Defiziten in der Interaktion mit anderen Menschen leiden. Durch den Einsatz von Robotik und Virtueller Realität sollen Kommunikationshemmnisse abgebaut und die soziale Interaktionsfähigkeit langfristig verbessert werden. Die Rehabilitationsmethode basiert dabei auf neusten Erkenntnissen der Kognitionswissenschaft, nach denen eine soziale Interaktion mit selbstähnlichen Personen bevorzugt wird. Im Projekt wird dabei eine Ähnlichkeit in Aussehen, Verhalten und Bewegung genutzt und im Laufe der Rehabilitation kontinuierlich verfremdet, um die Interaktion mit unbekannten Personen zu verbessern.In einer ersten Projektphase wird ein virtueller Agent des Patienten mit größtmöglicher Ähnlichkeit erstellt. Dazu werden animierbare 3D Modelle extrahiert, Bewegungssequenzen erfasst und Verhaltensmodelle extrahiert. Diese Modelle werden zur Zeit im Rahmen einer ersten Studie mit Patienten und Kontrollpersonen im Krankenhaus in Montpellier / Frankreich evaluiert.

Vehicle tracking for traffic analysis
Video-based vehicle tracking for smart traffic analysis
Researchers from the Augmented Vision group at DFKI have developed a novel approach for automatic video-based traffic analysis. First, entry and exit zones of complex crossroads or roundabouts are defined interactively. Then, each car is tracked individually by computing the trajectory based solely on the video content. This provides unique data for traffic analysis and in particular for supporting simulations for improved traffic solutions.
AR-Handbook 2013
Nils Petersen and Didier Stricker, ‘Learning Task Structure from Video Examples for Workflow Tracking and Authoring’, in Proceedings of the International Symposium on Mixed and Augmented Reality (ISMAR), 2012
Wireless Full-Body Capturing for Sport Analytics
Wireless Full Body Motion Capturing for Sport Analytics

With 11 inertial measurement units, the full body motion of a person is tracked during climbing. Potential applications are sports analysis and coaching. Further research will focus on detecting the limbs and body parts in the head mounted camera and use this as additional information for obtaining more precise tracking results. The system has been developed within the European project COGNITO (

Kinect Avatar
We present a novel scanning system for capturing a full 3D human body model using just a single depth camera and no auxiliary equipment. We claim that data captured from a single Kinect is sufficient to produce a good quality full 3D human model. In this setting, the challenges we face are the sensor’s low resolution with random noise and the subject’s non-rigid movement when capturing the data. To overcome these challenges, we develop an improved superresolution algorithm that takes color constraints into account. We then align the super-resolved scans using a combination of automatic rigid and non-rigid registration. As the system is of low price and obtains impressive results in several minutes, full 3D human body scanning technology can now become more accessible to everyday users at home
OnEye Tracking Framework
OnEye Tracking Framework
OnEye Generic Object Tracking Framework – Tracking examples – 2011-2012 – Clothes tracking (Catwalk sequence 1)


  1. “OnEye — Producing and broadcasting generalized interactive video”, Alain Pagani and Christian Bailer and Didier Stricker, Proceedings of the Networked and Electronic Media Summit (NEM Summit), 2013
  2. “A user supported tracking framework for interactive video production”, Christian Bailer and Alain Pagani and Didier Stricker, Proceedings of the European Conference on Visual Media Production (CVMP) 2013