Cornelia Fermüller is an associate research scientist at the 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.
2011. Active scene recognition with vision and language. 2011 IEEE International Conference on Computer Vision (ICCV). :810-817.
2011. Language Models for Semantic Extraction and Filtering in Video Action Recognition. Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence.
2011. A Corpus-Guided Framework for Robotic Visual Perception. Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence.
2011. Visual Scene Interpretation as a Dialogue between Vision and Language. Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence.
2010. Illusory Lightness Perception Due to Signal Compression and Reconstruction. Journal of VisionJ Vis. 10(7):426-426.
2010. Illusory motion due to causal time filtering. Vision research. 50(3):315-329.
2010. Learning shift-invariant sparse representation of actions. 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). :2630-2637.
2010. An Experimental Study of Color-Based Segmentation Algorithms Based on the Mean-Shift Concept. Computer Vision – ECCV 2010Computer Vision – ECCV 2010. 6312:506-519.
2010. Better Flow Estimation from Color Images-Volume 2007, Article ID 53912, 9 pages. EURASIP Journal on Advances in Signal Processing. 2007(23)
2009. Combining powerful local and global statistics for texture description. IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009. :573-580.
2009. Active segmentation for robotics. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2009. IROS 2009. :3133-3139.
2009. MEASURING 1ST ORDER STRETCH WITH A SINGLE FILTER. Relation. 10(1.132):691-691.
2009. Real-time shape retrieval for robotics using skip Tri-Grams. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2009. IROS 2009. :4731-4738.
2009. Robust Wavelet-Based Super-Resolution Reconstruction: Theory and Algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence. 31(4):649-660.
2009. Viewpoint Invariant Texture Description Using Fractal Analysis. International Journal of Computer Vision. 83(1):85-100.
2008. Bilateral symmetry of object silhouettes under perspective projection. 19th International Conference on Pattern Recognition, 2008. ICPR 2008. :1-4.
2008. A View-Point Invariant Texture Descriptor. Journal of VisionJ Vis. 8(6):354-354.
2008. Measuring 1st order stretchwith a single filter. IEEE International Conference on Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. :909-912.
2007. Combining motion from texture and lines for visual navigation. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007. IROS 2007. :232-239.
2007. Object Detection Using Shape Codebook. British Machine Vision Conference (BMVC'07).
2007. Better flow estimation from color images. EURASIP Journal on Advances in Signal Processing. 2007(1):133-133.
2007. Object detection using a shape codebook. British Machine Vision Conference. 4
2006. Wavelet-Based Super-Resolution Reconstruction: Theory and Algorithm. Computer Vision – ECCV 2006Computer Vision – ECCV 2006. 3954:295-307.
2006. Depth estimation using the compound eye of dipteran flies. Biological Cybernetics. 95(5):487-501.
2006. A 3D shape constraint on video. IEEE Transactions on Pattern Analysis and Machine Intelligence. 28(6):1018-1023.
2006. Noise causes slant underestimation in stereo and motion. Vision Research. 46(19):3105-3120.
2006. A Projective Invariant for Textures. 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2:1932-1939.
2005. On the Anisotropy in the Perception of Stereoscopic Slant. Journal of VisionJ Vis. 5(8):516-516.
2005. Chromatic Induction and Perspective Distortion. Journal of VisionJ Vis. 5(8):1026-1026.
2005. Integration of motion fields through shape. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005. 2:663-669vol.2-663-669vol.2.
2005. Discovering a language for human activity. Proceedings of the AAAI 2005 Fall Symposium on Anticipatory Cognitive Embodied Systems, Washington, DC.
2005. Detecting Independent 3D Movement. Handbook of Geometric ComputingHandbook of Geometric Computing. :383-401.
2005. Motion segmentation using occlusions. IEEE Transactions on Pattern Analysis and Machine Intelligence. 27(6):988-992.
2004. Compound eye sensor for 3D ego motion estimation. 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2004. (IROS 2004). Proceedings. 4:3712-3717vol.4-3712-3717vol.4.
2004. The Argus eye: a new imaging system designed to facilitate robotic tasks of motion. IEEE Robotics & Automation Magazine. 11(4):31-38.
2004. A hierarchy of cameras for 3D photography. Computer Vision and Image Understanding. 96(3):274-293.
2004. Uncertainty in visual processes predicts geometrical optical illusions. Vision Research. 44(7):727-749.
2004. The Argus eye, a new tool for robotics. IEEE Robotics and Automation Magazine. 11(4):31-38.
2004. Bias in Shape Estimation. Computer Vision - ECCV 2004Computer Vision - ECCV 2004. 3023:405-416.
2004. Self-Calibration from Image Derivatives. International Journal of Computer Vision. 48(2):91-114.
2003. Eye design in the plenoptic space of light rays. Ninth IEEE International Conference on Computer Vision, 2003. Proceedings. :1160-1167vol.2-1160-1167vol.2.
2003. Statistical Bias Predicts Many Illusions. Journal of VisionJ Vis. 3(9):636-636.
2003. Plenoptic video geometry. The Visual Computer. 19(6):395-404.
2003. Uncertainty in 3D shape estimation. ICCV Workshop on Statistical and Computational Theories of Vision.
2003. Polydioptric camera design and 3D motion estimation. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. 2:II-294-301vol.2-II-294-301vol.2.
2003. New eyes for robotics. 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2003. (IROS 2003). Proceedings. 1:1018-1023vol.1-1018-1023vol.1.
2002. Eyes form eyes: New cameras for structure from motion. Proceedings Workshop on Omnidirectional Vision (OMNIVIS).
2002. Polydioptric cameras: New eyes for structure from motion. Pattern Recognition. :618-625.
2002. Polydioptric Cameras: New Eyes for Structure from Motion. Pattern RecognitionPattern Recognition. 2449:618-625.
2002. Visual space-time geometry - A tool for perception and the imagination. Proceedings of the IEEE. 90(7):1113-1135.
2002. Eyes from eyes: new cameras for structure from motion. Third Workshop on Omnidirectional Vision, 2002. Proceedings. :19-26.
2002. Bias in visual motion processes: A theory predicting illusions. Statistical Methods in Video Processing.(in conjunction with European Conference on Computer Vision).
2001. The Statistics of Optical Flow. Computer Vision and Image Understanding. 82(1):1-32.
2001. Statistics Explains Geometrical Optical Illusions. Foundations of Image UnderstandingFoundations of Image Understanding. 628:409-445.
2001. Animated heads: From 3d motion fields to action descriptions. Proceedings of the IFIP TC5/WG5. 10:1-11.
2001. Eyes from Eyes. 3D Structure from Images — SMILE 20003D Structure from Images — SMILE 2000. 2018:204-217.
2001. A spherical eye from multiple cameras (makes better models of the world). Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001. CVPR 2001. 1:I-576-I-583vol.1-I-576-I-583vol.1.
2000. Analyzing Action Representations. Algebraic Frames for the Perception-Action CycleAlgebraic Frames for the Perception-Action Cycle. 1888:1-21.
2000. Multi-camera networks: eyes from eyes. IEEE Workshop on Omnidirectional Vision, 2000. Proceedings. :11-18.
2000. The statistics of optical flow: implications for the process of correspondence in vision. 15th International Conference on Pattern Recognition, 2000. Proceedings. 1:119-126vol.1-119-126vol.1.
2000. New eyes for building models from video. Computational Geometry. 15(1–3):3-23.
2000. Structure from motion: Beyond the epipolar constraint. International Journal of Computer Vision. 37(3):231-258.
2000. The Ouchi illusion as an artifact of biased flow estimation. Vision Research. 40(1):77-95.
2000. New Eyes for Shape and Motion Estimation. Biologically Motivated Computer VisionBiologically Motivated Computer Vision. 1811:23-47.
2000. A New Framework for Multi-camera Structure from Motion. Mustererkennung 2000, 22. DAGM-Symposium. :75-82.
2000. Observability of 3D Motion. International Journal of Computer Vision. 37(1):43-63.
1999. Active Perception. Wiley Encyclopedia of Electrical and Electronics EngineeringWiley Encyclopedia of Electrical and Electronics Engineering.
1999. Motion Segmentation: A Synergistic Approach. Computer Vision and Pattern Recognition, IEEE Computer Society Conference on. 2:2226-2226.
1999. Shape from Video. Computer Vision and Pattern Recognition, IEEE Computer Society Conference on. 2:2146-2146.