Welcome to the Computer Vision and Machine Learning Systems Group

We are interested in interdisciplinary research questions involving the development of novel imaging, computer vision and machine learning technologies yielding new approaches to acquire and analyse data with applications in medicine, biology, ecology, modelling and robotics. This requires a fundamental investigation of how computers perceive and understand complex real-world situations. By examining the entire process from data acquisition (i.e. sensing hardware) to quantitative evaluation (i.e. algorithms) we are seeking for solutions beyond classical image processing and pattern recognition methodologies. Many lessons remain to be learned to tackle the challenges of real-world data which we seek to study and reveal in the coming years to enable and build novel data-driven systems.

Tracked ant (Seville, Spain)
Multiple stitched images showing a trajectory of a desert ant navigating freely in the desert of Seville, Spain. The animal was tracked using our in-field tracking approach.
© Benjamin Risse
  •  Research interests

    Computer Science

    • Computer Vision (esp. 2D/3D tracking, motion compensation, object detection)
    • Machine Learning (esp. deep learning, CNNs, global optimisation)
    • Image Processing (esp. image filtering, transformations, calibration)
    • Computer Graphics (esp. scene reconstruction, virtual reality)
    • Robotics (esp. navigatoin strategies, visual route identification)
    • Computer Systems (esp. embedded systems, microcomputers, client-server)

    Engineering

    • Imaging Techniques (esp. touch techniques, IR / UV/ POL imaging)
    • Sensor Fusion (esp. multi-camera systems, fusion of genetic techniques)
    • 3D Printing (esp. FDM printing, autonomous printing supervision)

    Biomedicine

    • Behavioural Biology (esp. navigation, insect eyes, laboratory / field experiments)
    • Neuroscience (esp. analysis of Drosophila flies / larvae, cell motion analysis)
    • Artificial Life (esp. simulated evolution)
CVMLS
|
PAPER ACCEPTED AT GCPR 2018!
Collision-klemm
© CVMLS

 Our paper "Deep Distance Transform to Segment Visually Indistinguishable Merged Objects" has been accepted at GCPR 2018.

CVMLS
|
PAPER ACCEPTED IN NATURE COMMUNICATIONS!
Larval tracks
© CVMLS

 Our paper "The sulfite oxidase Shopper controls neuronal activity by regulating glutamate homeostasis in Drosophila ensheathing glia" has been accepted in the Nature Communications. You can find the article here.

CVMLS
|
PROMOTION STELLENAUSSCHREIBUNG
The Bukobot Reprap 3d Printer
© Public Domain (by Deezmaker)

Wir suchen ab August einen Promotionsstudenten für ein Projekt im Bereich "Intelligent 3D Printing". Studierende mit Interesse an maschinellem Lernen, Bildanalyse und additiven Fertigungstechniken können sich jederzeit bewerben. Projektpartner ist der Internet-Of-Things Dienstleister tapdo Technologies GmbH. Fragen und Bewerbungen senden Sie bitte direkt an Jun.-Prof. Dr. Benjamin Risse.

CVMLS
|
PAPER ACCEPTED AT MEASURING BEHAVIOR 2018!
Mb2018
© Benjamin Risse

Our paper "Possibilities, Constraints and Limitations of Image-based Animal Tracking in Natural Environments" from Benjamin Risse, Michael Mangan and Barbara Webb has been accepted at the Measuring Behavior 2018 (MB2018) conference.

CVMLS
|
PAPER ACCEPTED IN COMPUT. BIOL. MED.!
Heart beat quantification of Drosophila pupae
© Benjamin Risse

Our paper "Automatic non-invasive heartbeat quantification of Drosophila pupae" from Dimitri Berh, Aaron Scherzinger, Nils Otto, Xiaoyi Jiang, Christian Klämbt and Benjamin Risse has been accepted in the Computers in Biology and Medicine.

CVMLS
|
NEW ELECTRONIC WORKSPACE!
Electronic-workspace
© Benjamin Risse

Our new electronic workspace is now in place. Students interested in micro-computers, low-level programming or working on little hardware projects please contact b.risse@uni-muenster.de.