Bio-inspired Machine Vision
I received an M.S. from the University of Technology, Graz and a Ph.D. from the Technical University of Vienna, Austria in Applied Mathematics. I am a Research Scientist at the
Center for Automation Research at the Institute for Advanced Computer Studies at UMD. I cofounded the
Autonomy Cognition and Robotics (ARC) Lab and co-lead the
Perception and Robotics Group at UMD. I am the PI of an NSF sponsored Science of Learning Center Network for Neuromporphic Engineering and co-organize the
Neuromorphic Engineering and Cognition Workshop.
My research is in the areas of Computer Vision, Robotics, and Human Vision, focusing on biological-inspired solutions for active vision systems. I have modeled perception problems using tools from geometry, statistics and signal processing
and developed software in the areas of multiple view geometry, motion, navigation, shape, texture, and action recognition. I have also combined computational modeling with psychophysical experiments to gain insights into human motion and low-level
feature perception.
My current work is on robot vision in the following two areas:
1) Integrating perception, action, and high-level reasoning to interpret human manipulation actions with the ultimate goal of advancing collaborative robots and creating robots that visually learn from humans.
2) Motion processing for fast active robots (such as drones) using as input bio-inspired event-based sensors.
By integrating cognitive processes with perception and action execution, we investigate ways of structuring representations of events at multiple time spans, that allow generalization of actions. The main application of this work is to create robots that visually learn from humans.
Read moreDynamic vision sensors, because of their high temporal resolution, low latency, high dynamic range, and high compression, hold promises for autonomous Robotics. We study the advantages of this data for fundamental navigation processes of egomotion, segmentation. and image motion.
Read moreBetween low-level image processing and high-level reasoning are grouping mechanism that implement principles of Gestalt, such as closure, or symmetry. We have developed new 2D image-processing operators and 3D operators that implemet these principles for attention, segmentation and recognition.
Read moreActive vision system compute from video essential information about their environment's spatio-temporal geometry for navigation. In a series of studies, I investigated the recovery 3D motion and scene structure from image motion and implementation in efficient algorithms.
Read moreTaking advantage of the mathematical properties of fractal geometry, we designed texture descriptors that are inavriant to changes in viewpoint, geometric deformation , and illumination, and which encode with very low dimension the essential structure of textures.
Read moreOptical illusions can provide insight into the mechanism of vision. Using geometry and statistics I have uncovered a number of principles explaining limitations in what we can recover from images, and these principles can explain different optical illusions and were used to create new ones.
Read more
June/July 2022: I co-organize the 2022 Telluride Neuromorphic Cognition Engineering Workshop and a project on "Cross-modality signals: auditory, visual and motor"
within the Workshop.
July 2nd, 2022: I co-organize a Forum on Future Directions of Neuromorphic Cognition Engineering
May 2022: Co-PI on a National Multiple Sclerosis Society grant with Daniel Harrison;
Title:
"Development of a Convolutional Neural Network for MRI Prediction of Progression and Treatment Response in Progressive Forms of Multiple Sclerosis"
August 2021: Maryland Innovation Initiative award with Irina Muresanu
Title:
"Artificial Intelligence software for assessment of posture and form in violin instruction."
August 2020: NSF grant on "Accelerating Research on Neuromorphic Perception, Action, and Cognition" This grant will fund network activities, including the
Telluride Neuromorphic Cognition Workshop and fellowships for collaborative work.
May 2019: Provost's Excellence Award for Professional Track Faculty
August 2018: NSF award from the Science of Learning
Title:
Research Coordination Network: Cognitive Functions in the Learning of Symbolic Signals and Systems
March 2018: My work on the Cyberphysical grant on Monitoring Humans was featured in a special issue in
Research Features on Women's day.
November 2019: The paper EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras
will be presented at IROS 2019."
August 2019: Our paper on Topology-Aware Non-Rigid Point Cloud Registration,
was accepted at IEEE Transactions on Pattern Analysis and Machine Intelligence.
June 2019: Invited lecture at Second International Workshop on Event-based Vision and Smart Cameras (CVPR'19).
May 2019: Our paper on Learning sensorimotor control with
neuromorphic sensors: Toward hyperdimensional active perception,
was accepted at Science Robotics.
July 2018: We published a new, efficient library for 3D point cloud processing called cilantro (
paper,
code)
Our work on Vision and Robotics has been sponsored by the following NSF grants in the Cyberphysical program.
Currently I serve for the folllowing journals and conferences
email — fer@cfar.umd.edu
phone — 301 405 1768
office — Iribe Building 4216
ADDRESS (for shipping)
Cornelia Fermüller
Computer Vision Lab, UMIACS
5109 Brendan Iribe Center for Computer Science and Engineering
8125 Paint Branch Dr, College Park, MD 20742