Otto-von-Guericke-Universität Magdeburg

 
 
 
 
 
 
 
 

Content-based Image Retrieval

 SFB/TRR 62 is an interdisciplinary research activity to
investigate the communication between technical sys-
tems and human users. It is particularly focused on the
consideration of so-called Companion-features - proper-
ties like individuality, adaptivity, accessibility, cooper-
ativity, trustworthyness, and the ability to react to the
user’s emotions appropriately and individually. The re-
search program comprises the theoretical and exper-
imental investigation as well as the practical imple-
mentation of advanced cognitive processes in order to
achieve Companion-like behavior of technical systems.
With that, it will lay the foundations for a technology
which opens a completely new dimension of interac-
tion between man and technical systems. The Neuro-Information Technology (NIT) group contributes to following
subprojects:
C1 - Environment perception: A companion sy-
stem must perform its surroundings, interpreting, to
recognize the user groups and communicate with him,
involving the facial expressions, language and gesture.
In this sub-project, the important tasks of this area de-
tection and environment modeling that based on ges-
ture recognition are solved. To capture the environ-
ment, methods for multi-sensor fusion, information fu-
sion and temporal filtering are investigated based on the
finite set theory, and further allow the simultaneous es-
timation of object and existence of the object state.
The detection, tracking and classification of persons
and other objects made using multi-sensory data and
the classification of user gestures is purely image based
on the use of hidden Markov models (HMMs). For a ro-
bust gestures classification, static and dynamic features
characteristics that are appropriate for their extraction
as a result of recent research can be used, also color
information. The segmentation using color information
and 3D information provides a high degree of robust-
ness to disturbances, occlusions, brightness variations
and background perturbations. (S. Handrich
A. Al-Hamadi -18709)

 

 

Letzte Änderung: 08.11.2017 - Ansprechpartner: Dipl.-Ing. Arno Krüger
 
 
 
 
image_pose
Video: Head pose and orientation
 
 
 
 
v01_winglets
Video: Particle Tracking
 
 
 
 
Johanniskirche_1_300x240
Video: Multi-object tracking
 
 
 
 
Test_584
Video: Gestures and intention
 
 
 
 
Kinect-pose-ayoub1-logo
Video: Pose and Face detection using Kinect
 
 
 
 
kinect_pose
Video: HCI Face Attention
 
 
 
 
mimik-flow1
Video: Static and dynamic features
 
 
 
 
Motionblobs-gut
Video: Trisectional Multi-object tracking
 
 
 
 
s8
Video: Ephestia Parasitization