Research activities of Christian Wöhler
Short scientific CV
Overview of research activities in the Image Analysis Group at TU Dortmund (since April 2010)
(examples also include previous research work at Daimler AG, Group Research
and Advanced Engineering)
- Image-based 3D reconstruction methods for industrial inspection and metrology
3D reconstruction of a plaster figure painted with bright enamel and a housing part based on the combined analysis of noisy depth data obtained by fringe projection with image intensity information. The reflectance parameters, which were assumed to be constant across the surface, were inferred from the same data. The lateral resolution corresponds to 0.042 mm per pixel (from Herbort et al., ISPRS Journal of Photogrammetry and Remote Sensing, 2013).
3D reconstruction of a surface part part of a dumbbell consisting
of dark cast iron, obtained based on a combination of photometric stereo and fringe
projection based active range scanning (lateral resolution is 0.042 mm per pixel)
(from Herbort and Wöhler, VISAPP 2012).
- Pattern recognition methods
Detection of US traffic signs using resource optimised
cascaded perceptron classifiers (from Staudenmaier et al., CI 2010).
Recognition of working actions based on a non-stationary
HMM framework. Top: Spatio-temporal 3D pose estimation of the hand-forearm
limb with the Shape Flow algorithm. Bottom: Results of action recognition.
Blue: transfer motion; red: screw_1; black: screw_2; green: clean; ochre:
plug; white: unknown action; GT: ground truth (from Hahn et al., HCRS 2009).
Recognition and prediction of a situation involving two vehicles
turning left at a road intersection. The true future trajectories are denoted by
dashed lines, while the solid lines correspond to the motion hypotheses of the
vehicles (from Käfer et al., ICRA 2010).
- Methods for image-based 3D reconstruction and analysis of hyperspectral data for remote sensing applications
Petrographic map of the lunar crater Aristillus, overlaid on
a DEM of high lateral resolution. The map reveals the relative abundances of
the three most important lunar rock types (red channel: basalt; green channel:
Mg-rich rock; blue channel: ferroan anorthosite). The central peak mainly
consists of Mg-rich rock, probably norite, while the northern part of the
crater rim is covered by anorthositic ejecta material (from Grumpe et al.,
Result of automatic lunar crater detection using a DEM of high
lateral resolution obtained based on a photometric approach using Chandrayaan-1 M3
imagery in combination with LOLA data. Green: previous LU60645GT catalogue; yellow:
additionally detected craters (from Salamunićcar et al., ISPA 2011).
DEM of high lateral resolution of the eastern part of the lunar
crater Alphonsus (left) and of the lunar crater Menelaus (right), obtained based on a
photometric approach using Chandrayaan-1 M3 imagery in combination with LOLA data
(from Herbort et al., ICIP 2011 and Grumpe and Wöhler, ISPA 2011,
For detailed information see list of publications.
A result of technology transfer: SafetyEYE
A research project for which my former colleague Dr. Lars Krüger and I were
responsible at Daimler AG, Group Research and Advanced Engineering, has led to the
development of the vision-based SafetyEYE system for three-dimensional surveillance
of working areas in industrial production. This system has been created
in cooperation between Daimler and the company Pilz GmbH & Co. KG,
a specialist for safe automation.
SafetyEYE's trinocular camera sensor
General information about the functionality of SafetyEYE (cf. published press material):
The SafetyEYE system consists of three calibrated cameras which monitor
the protection area around a machine, e. g. an industrial robot, and two
high-performance industrial PCs. The implemented stereoscopic algorithms
determine the three-dimensional structure of the scene being surveyed.
As soon as a potentially hazardous situation is about to occur, the system
initiates the protective measures necessary to prevent an accident, either
by slowing down or by stopping the machine. An important advantage of the
SafetyEYE system is the fact that it can be installed quickly and efficiently.
While setting up a traditional safety system consisting of several components
such as metal fences, light barriers, and laser scanners may take as long as
one day, only a few hours are needed to configure SafetyEYE's three-dimensional
protection areas. For the future, it is intended to increase the system
capabilities towards a distinction between persons and objects. This will
be a step towards collaborative working environments in which persons and
machines are able to work simultaneously on the same workpiece.
SafetyEYE has received the Automation Award 2006.
For more information about the system, see the
SafetyEYE product website and the website of the system supplier
Pilz GmbH & Co. KG.
- Guest editor of the special issue "Image Processing and Analysis in Space Science" of the journal Advances in Space Research
- Member of the editorial board of the Springer journal 3D Research,
editor of the topical
issue "3D Computer Vision" (September 2010)
- Reviewer for the journals Pattern Recognition Letters,
Image and Vision Computing, Earth and Planetary Science Letters, and Planetary and Space Science
- Co-organiser of the special session "Image Processing and Analysis
in Lunar and Planetary Science" of the 7th
International Symposium on Image and Signal Processing and Analysis (ISPA 2011),
Dubrovnik, Croatia, September 4-6, 2011
- Member of the programme committee of the
International Conference on Computer
Vision Theory and Applications (VISAPP) 2011 and 2012
- Co-organiser of the symposium Oldenburger 3D-Tage 2009
- Member of the programme committee of the 2nd Workshop
Vision 2008, Auckland, New Zealand, February 18-20, 2008
- Member of the programme committee of the
International Conference on Computer Vision
Systems (ICVS) 2008, Santorini, Greece, May 12-14, 2008
- Member of the programme committee, exhibition and industrial
relations chair of the International
Conference on Computer Vision Systems (ICVS) 2007, Bielefeld, Germany,
March 21-24, 2007
- Organisation of the workshop "Camera Calibration Methods for
Computer Vision Systems (CCMVS 2007)" in conjunction with ICVS 2007
Back to main page