Faculty Directory

Fermüller, Cornelia

Fermüller, Cornelia

Research Scientist
UMIACS
The Institute for Systems Research
Maryland Robotics Center
Brain and Behavior Institute
4216 Iribe Center

Cornelia Fermüller is a research scientist in the UMIACS Computer Vision Laboratory.

Fermüller’s research is in the areas of computer vision and human vision, and she has written more than 35 articles in journals and 100 publications in refereed conferences and books. In her computer vision work, she has developed many computational models and implemented software solutions for applications in visual navigation and image processing. Fermüller's work on biological vision involves examining the computational constraints, building simulation models, and performing psychophysical experiments to understand the possible computational mechanisms explaining human motion and low-level signal perception.

Many of her studies have been investigating the computational principles underlying multiple view geometry and statistics, and she has discovered a number of basic computational principles in the analysis of visual motion and shape recovery. These include view-invariant texture descriptors, constraints on 3-D motion estimation, 3-D shape and image segmentation, insights on the effects of sensor design on motion estimation, and the findings of statistical bias in low-level processing.

Fermüller has applied these studies in a number of applications, including new imaging sensors for better motion and shape recovery, software for visual motion tasks in navigation and robotics, and various tasks of video computing, such as compression, video manipulation, and image-based rendering.

Her current research interests are centered around developing cognitive robotic systems that integrate, perception with action, reasoning and language. In ongoing projects she develops robots that recognize human manipulation activities and search for an object in a room.

She received a doctorate from the Technical University of Vienna, Austria in 1993 and an M.S. from the University of Technology, Graz, Austria in 1989, both in applied mathematics.

Manipulation actions, event-based vision, mid-level vision, motion analysis, texture, optical illusions


View Dr. Fermüller's publications at Google Scholar.

NSF funding to Fermüller, Muresanu, Shamma for musical instrument distance learning using AI

'VAIolin' is a feedback system to provide advice based on visual and auditory analysis and causal relationships of errors.

MRC Faculty, Researchers, and Students Present 24 Papers at ICRA 2023

MRC researchers have a strong showing at ICRA 2023.

Fermüller and Muresanu VAIolin work featured in Maryland Today

Maria Herd of UMIACS has produced an excellent video about the work.

Seven UMD Grand Challenges projects include ISR and MRC faculty

The $30 million program will accelerate innovative solutions to some of the world's most complex problems.

Levi Burner named a Future Faculty Fellow

The Clark School program prepares engineering and computer science Ph.D. students for careers in academia.

Autonomous drones based on bees use AI to work together

The minute robots could one day provide backup to pollinators.

Chahat Deep Singh named recipient of Wylie Dissertation Fellowship

The computer science student also was named a Clark School Future Faculty Fellow this year.

Chahat Deep Singh named a Future Faculty Fellow

The program prepares Ph.D. students for academic careers in engineering and computer science.

Fermüller, ARC Lab create app to improve violin instruction

School of Music's Irina Muresanu collaborates on 'Arts for All' project

EVPropNet finds drones by detecting their propellers

This deep learning-based solution uses data collected by event camera sensors.

Bee drones featured on new Voice of America video

Active perception is an efficient, fast way for robots to complete task.

Perception and Robotics Group creates hive of ideas for drones

Palm-sized autonomous robots could help bees pollinate flowers, search out survivors and watch patients for problems

Computer vision advances in contact-centered representations, models

Ego-OMG technology comes in first and second in international computer vision challenge.

UMD Researchers to Have a Strong Showing at ICRA 2021

University of Maryland researchers will present 15 papers at the IEEE International Conference on Robotis and Automation (ICRA 2021) to held on May 30 to June 5, 2021.

Ganguly, Fiaz, Suryan are first MRC GRA recipients

The new program is open to mid-career UMD Ph.D. students with Maryland Robotics Center advisors.

'MorphEyes' stereo camera system improves quadrotor UAV navigation

The Perception and Robotics Group is the first to use morphable design to achieve a variable baseline stereo vision system on a quadrotor UAV.

MRC Faculty and Researchers to Present 16 Papers at International Robotics Conference - IROS 2020

International Conference on Intelligent Robots and Systems - From 25 October 2020 until 29 November 2020

Cornelia Fermüller is PI for 'NeuroPacNet,' a $1.75M NSF funding award

The resulting "network of networks" will further the scientific grand challenge of developing neuromorphic artificial intelligence.

Czech prime minister views AI, VR, AR and computer vision research

The visit was hosted by ISR Director William Regli and the university’s Office of International Affairs.

Fermuller, Shamma, Etienne-Cummings receive NSF grant for 'Research Coordination Network'

The network will advance understanding of how biological systems learn complex symbolic signals, and create artificial systems with similar capabilities.