Dorin received Ph.D. degrees in electrical engineering from the
Polytechnic University of Bucharest in 1995 and Rutgers University in 1999. He has since been with Siemens
Corporate Research, serving both as a scientist and manager.
Since 2004 he is the head of the Integrated Data Systems Department, with offices in Princeton, New Jersey and Erlangen, Germany.
Under his leadership the department has quadrupled in size, by refocusing on disruptive and high impact research.
Dorin's scientific interests include robust computer vision, motion estimation,
information fusion, discriminative methods for medical imaging, biomedical informatics, and
content-based access to visual data. He holds 24 US patents, has co-authored more than 80 patent applications, and more than 140 papers,
conference papers, and book chapters in the area of visual information
processing. He has received the Best Paper Award at the IEEE Conference on
Computer Vision and Pattern Recognition 2000 and is a co-author of the upcoming book Nonparametric Analysis of Visual Data:
The Mean Shift Paradigm. For his innovations in the areas of medical imaging
and intelligent vehicles he has received the 2004 Siemens Inventor of the Year Award, the highest technical
recognition of Siemens AG
worldwide. He has been featured in the book Innovative Minds and has given numerous invited speeches.
Dorin leads the scientific direction of one of the largest European projects
in biomedical informatics, Health-e-Child, and is one of the main architects of MEDICO, a project focussed on the next generation of semantic, scalable search engines for medical imaging. He serves as an Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence.
Acknowledgement: I gratefully acknowledge the contributions of my former and current collaborators. I enjoyed working along the years with great and wonderful minds from whom I constantly learned. The technologies we created together are helping the society in many ways. This is the greatest reward a scientist can have.
Variable Bandwidth Density-based Fusion (VBDF). The most significant mode
of the data is selected by mode tracking across scales. Read the CVPR'03
paper.
Some old, but popular sequences. Read the PAMI'03
paper.
D. Comaniciu, V. Ramesh, P. Meer: Kernel-Based
Object Tracking, IEEE Trans. Pattern Analysis Machine Intell., Vol.
25, No. 5, 564-575, 2003
D. Comaniciu: Bayesian
Kernel Tracking, Annual Conf. of the German Society for Pattern
Recognition (DAGM'02), Zurich, Switzerland, 438-445, 2002
D. Comaniciu, V. Ramesh, P. Meer: Real-Time
Tracking of Non-Rigid Objects using Mean Shift, BEST PAPER AWARD, IEEE
Conf. Computer Vision and Pattern Recognition (CVPR'00), Hilton Head Island,
South Carolina, Vol. 2, 142-149, 2000
L. Yang, B. Georgescu, Y. Zheng, D.J. Foran, D. Comaniciu: A Fast and Accurate Tracking Algorithm of Left Ventricle in 3D Echocardiography, IEEE Int'l Symposium Biomedical Imaging (ISBI'08), Paris, France, 2008
X.S. Zhou, D. Comaniciu, S. Krishnan: Coupled-Contour Tracking through Non-orthogonal Projections and
Fusion for Echocardiography, European Conf. Computer Vision
(ECCV'04), Prague, Czech Republic, 2004
J. Zhang, S.k. Zhou, L. McMillan, D. Comaniciu: Discriminative Learning for Deformable Shape Segmentation: A Comparative Study, European Conf. Computer Vision (ECCV'08), Marseille, France, 2008
Y. Zheng, X.S. Zhou, B. Georgescu, S.K. Zhou, D. Comaniciu: Example Based Non-rigid Shape Detection, European Conf. Computer Vision (ECCV'06), Graz, Austria, 2006
D. Comaniciu, P. Meer: Robust Analysis of Feature
Spaces: Color Image Segmentation, IEEE Conf. Computer Vision and
Pattern Recognition (CVPR'97), San Juan, Puerto Rico, 750-755, 1997
K. Okada, D. Comaniciu, N. Dalal, A. Krishnan: A
Robust Algorithm for Characterizing Anisotropic Local Structures,
European Conf. Computer Vision (ECCV'04), Prague, Czech Republic, 2004
Information Fusion
D. Comaniciu: Robust Information Fusion using
Variable-Bandwidth Density Estimation, 6th ISIF/IEEE Int. Conf.
Information Fusion (Fusion'03), Cairns, Queensland, Australia, 2003
D. Barash, D. Comaniciu: A Common View Point on
Broad Kernel Filtering and Nonlinear Diffusion, Int. Conf.
Scale-Space Theories in Computer Vision, Isle of Skye, Scotland, 683-689, 2003
T. Chen, W. Yin, X.S. Zhou,
D. Comaniciu, T.S. Huang: Illumination Normalization
for Face Recognition and Uneven Background Correction Using Total Variation
Based Image Models, IEEE Conf. Computer Vision and Pattern
Recognition (CVPR'05), San Diego, CA, 2005
O. Javed, M. Shah, D. Comaniciu: A Probabilistic
Framework for Object Recognition in Video, IEEE Int'l Conf. Image
Processing (ICIP'04), Singapore, 2004
B. Han, D. Comaniciu, L. Davis: Sequential Kernel
Density Approximation through Mode Propagation: Applications to Background
Modeling, Asian Conf. Computer Vision (ACCV'04), Jeju Island,
Korea, 2004
M. Greiffenhagen, D. Comaniciu, H. Niemann, V. Ramesh: Design, Analysis and Engineering of Video Monitoring Systems: An
Approach and a Case Study, Proceedings of the IEEE on Third
Generation Surveillance Systems, Vol. 89, No. 10, 1498-1517, 2001
J. Rosca, S. Sudarsky, R. Balan, D. Comaniciu, Mobile Interaction with Remote Worlds: The Acoustic
Periscope, AAAI Workshop Artificial Intelligence in Mobile Systems,
Seattle, Washington, 2001
L.Lu, A. Barbu, M. Wolf, J. Liang, L. Bogoni, M. Salganicoff, D. Comaniciu: Simultaneous Detection and Registration for Ileocecal Valve Detection in 3D CT Colonography, European Conf. Computer Vision (ECCV'08), Marseille, France, 2008
J. Williams, H. Tek, D. Comaniciu: 3-Dimensional
Interactive Vascular Postprocessing Techniques: Industrial
Perspective, (Invited), in Angiography and Plaque Imaging:
Advanced Segmentation Techniques, Suri and Laxminarayan (Eds), CRC Press,
2002
D. Comaniciu, P. Meer: Cell Image Segmentation for
Diagnostic Pathology, (Invited), in Advanced Algorithmic
Approaches to Medical Image Segmentation, Suri, Setarehdan, and Singh
(Eds), ISBN: 1-85233-389-8, Springer, 2002
Y. Zheng, A. Barbu, B. Georgescu, M. Scheuering, D. Comaniciu: Four-Chamber Heart Modeling and Automatic Segmentation for 3D Cardiac CT Volumes using Marginal Space Learning and Steerable Features, IEEE Trans.
Medical Imaging, 2008 
