5 Recent Publications

5 Recent Publications            J. F. P. Kooij, G. Englebienne and D. M. Gavrila. Mixture of Switching Linear Dynamics to Discover Behavior Patterns in Object Tracks. IEEE Trans. on Pattern Analysis and Machine Intelligence., DOI 10.1109/TPAMI.2015.2443801, 2015.  J. P. F. Kooij, G. Englebienne and D. M. Gavrila. Identifying Multiple Objects from their Appearance in Inaccurate Detections. Computer Vision and Image Understanding, vol.136, July, pp.103-116, 2015.  F. Flohr, M. Dumitru-Guzu, J. F. P. Kooij and D. M. Gavrila. A probabilistic framework for joint pedestrian head and body orientation estimation. IEEE Trans. on Intelligent Transportation Systems, vol.16, nr.4, pp.1872-1882, 2015. M. C. Liem and D. M. Gavrila. Coupled Person Orientation Estimation and Appearance Modeling using Spherical Harmonics, Image and Vision Computing, vol.32, nr.10, pp.728-738, 2014. M. C. Liem and D. M. Gavrila. Joint Multi-person Detection and Tracking from Overlapping Cameras. Computer Vision and Image Understanding, nr.128, pp.36-50, 2014.

5 Selected Publications

C. G. Keller and D.M. Gavrila. Will the Pedestrian Cross? A Study on Pedestrian Path Prediction. IEEE Trans. on Intelligent Transportation Systems. vol.15, nr.2, pp.494-506, 2014. M. Hofmann and D.M. Gavrila. Multi-view 3D Human Pose Estimation in Complex Environment. International Journal of Computer Vision (IJCV), vol.96, nr.1, pp.103-124, 2012. M. Enzweiler and D. M. Gavrila.  A Multi-Level Mixture-of-Experts Framework for Pedestrian Classification. IEEE Trans. on Image Processing, vol.20, nr.10, pp.2967-2979, 2011. C. Keller, M. Enzweiler, M. Rohrbach, D.-F. Llorca, C. Schnörr and D.M. Gavrila. The Benefits of Dense Stereo for Pedestrian Detection. IEEE Trans. on Intelligent Transportation Systems, vol.12, nr.4, pp.1096-1106, 2011. J. P. F. Kooij, G. Englebienne and D.M. Gavrila. A Non-parametric Hierarchical Model to Discover Behavior Dynamics from Tracks. Proc. of the European Conference on Computer Vision, vol. 6, pp.270-283, Florence, Italy, 2012.

	Ph.D. Thesis

	D. M. Gavrila, Vision-based 3-D Tracking of Humans in Action, Ph.D. Thesis, Department of Computer Science, University of Maryland, College Park, 1996.

	Book Chapters

T. Dang, J. Desens, U. Franke, D. M. Gavrila, L. Schaefers, and W. Ziegler Steering and Evasion Assist. In Handbook of Intelligent Vehicles, Ed. Eskandarian, Springer Verlag, 2012. U. Franke, D. M. Gavrila, A. Gern, S. Görzig, R. Janssen, F. Paetzold and C. Wöhler,From Door to Door - Principles and Applications of Computer Vision for Driver Assistant Systems, chapter 6 in Intelligent Vehicle Technologies, eds. L. Vlacic and F. Harashima and M. Parent, Butterworth Heinemann, Oxford, 2001 Y. Yacoob, L. Davis, M. Black, D. M. Gavrila, T. Horprasert and C. Marimoto, Looking at People in Action - An Overview, in Computer Vision for Human-Machine Interaction,eds. R. Cipolla and A. Pentland, Cambridge University Press, 1998.   U. Franke, D. M. Gavrila, S. Görzig, F. Lindner, F. Paetzold and C. Wöhler,Bildverstehen im Innerstädtischen Verkehr (in German), in Autonome Mobile Systeme, eds. H. Wörn, R. Dillmann and D. Heinrich, Springer Verlag, 1998.   D. M. Gavrila, 3-D Model-based Tracking of Humans in Action, in Advances in Image Understanding, eds. K. Bowyer and N. Ahuja, IEEE Computer Society Press, 1996.   D. M. Gavrila, R-Tree Index Optimization, in Advances in GIS Research, eds. T. Waugh and R. Healey, Taylor and Francis, 1994. Also, CS-TR-3292, University of Maryland, College Park, 1994.

	Journals

	J. F. P. Kooij, G. Englebienne and D. M. Gavrila. Mixture of Switching Linear Dynamics to Discover Behavior Patterns in Object Tracks. IEEE Trans. on Pattern Analysis and Machine Intelligence., DOI 10.1109/TPAMI.2015.2443801, 2015.  J. P. F. Kooij, G. Englebienne and D. M. Gavrila. Identifying Multiple Objects from their Appearance in Inaccurate Detections. Computer Vision and Image Understanding, vol.136, July, pp.103-116, 2015.  F. Flohr, M. Dumitru-Guzu, J. F. P. Kooij and D. M. Gavrila. A probabilistic framework for joint pedestrian head and body orientation estimation. IEEE Trans. on Intelligent Transportation Systems, vol.16, nr.4, pp.1872-1882, 2015. M. C. Liem and D. M. Gavrila. Joint Multi-person Detection and Tracking from Overlapping Cameras. Computer Vision and Image Understanding, nr.128, pp.36-50, 2014. M. C. Liem and D. M. Gavrila. Coupled Person Orientation Estimation and Appearance Modeling using Spherical Harmonics, Image and Vision Computing, vol.32, nr.10, pp.728-738, 2014. C. Keller and D.M. Gavrila. Will the Pedestrian Cross? A Study on Pedestrian Path Prediction. IEEE Transactions on Intelligent Transportation Systems. vol.15, nr.2, pp.494-506, 2014. M. Hofmann and D.M. Gavrila. Multi-view 3D Human Pose Estimation in Complex Environment. International Journal of Computer Vision, vol.96, nr.1, pp.103-124, 2012. M. Enzweiler and D. M. Gavrila.  A Multi-Level Mixture-of-Experts Framework for Pedestrian Classification. IEEE Trans. on Image Processing, vol.20, nr.10, pp.2967-2979, 2011. M. Hofmann and D.M. Gavrila. 3D Human Shape Model Adaptation by Automatic Frame Selection and Batch-Mode Optimization. Computer Vision Image Understanding, vol.115, nr.11, pp.1559-1570, 2011. C. Keller, M. Enzweiler, M. Rohrbach, D.-F. Llorca, C. Schnörr and D.M. Gavrila. The Benefits of Dense Stereo for Pedestrian Detection. IEEE Trans. on Intelligent Transportation Systems, vol.12, nr.4, pp.1096-1106, 2011. C. Keller, T. Dang, A. Joos, C. Rabe, H. Fritz, and D.M. Gavrila, Active Pedestrian Safety by Automatic Braking and Evasive Steering, IEEE Trans. on Intelligent Transportation Systems, vol.12, nr.4, pp.1292-1304, 2011. M. Enzweiler and D. M. Gavrila. Monocular Pedestrian Detection: Survey and Experiments. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.31, no.12, pp.2179-2195, 2009. S. Munder, C. Schnörr and D.M. Gavrila. Pedestrian Detection and Tracking Using a Mixture of View-Based Shape-Texture Models. IEEE Transactions on Intelligent Transportation Systems, vol.9, nr.2, pp.333-343, 2008. D. M. Gavrila. A Bayesian, Exemplar-based Approach to Hierarchical Shape Matching.IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.29, no.8 (August), 2007. D. M. Gavrila and S. Munder. Multi-Cue Pedestrian Detection and Tracking from a Moving Vehicle. International Journal of Computer Vision, Springer Verlag, vol.73, no.1 (June), pp.41-59, 2007. S. Munder and D. M. Gavrila. An Experimental Study on Pedestrian Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.28, nr 11, pp. 1863-1868, 2006.  W. van der Mark and D. M. Gavrila. Real-Time Dense Stereo for Intelligent Vehicles.IEEE Transactions on Intelligent Transportation Systems, vol. 7, nr 1, pp.38-50, March 2006. D. M. Gavrila, Sensor-based Pedestrian Protection, IEEE Intelligent Systems, vol.16, nr.6, pp.77-81, 2001. D. M. Gavrila, U. Franke, S. Görzig and C. Wöhler, Real-time Vision for Intelligent Vehicles, IEEE Instrumentation and Measurement Magazine, vol.4, nr.2, pp.22-27, June, 2001.   D. M. Gavrila, The Visual Analysis of Human Movement: A Survey, Computer Vision and Image Understanding, Academic Press, vol. 73, nr. 1, pp. 82-98, 1999. U. Franke, D. M. Gavrila, S. Görzig, F. Lindner, F. Paetzold and C. Wöhler, Autonomous Driving goes Downtown, IEEE Intelligent Systems, vol.13, nr.6, pp. 40-48, 1998. D. M. Gavrila and F. C. A. Groen, 3-D Object recognition from 2-D Images using Geometric Hashing, Pattern Recognition Letters, vol. 13, nr. 4, pp. 263-278, 1992.

	Conferences and Symposia

J. F. P. Kooij, N. Schneider, F. Flohr and D. M. Gavrila. Context-based Pedestrian Path Prediction. Proc. of the ECCV, Part VI, LNCS, vol.8694, pp.618-633, Springer, 2014. V. Evers; N. Menezes, L. Merino, D. Gavrila; F. Nabais, M. Pantic, P. Alvito and D. Karreman. The Development and Real-World Deployment of FROG; the Fun Robotic Outdoor Guide. Proc. of the ACM/IEEE International Conference on Human-Robot Interaction, 2014  J.F.P. Kooij, N. Schneider and D.M. Gavrila. Analysis of Pedestrian Dynamics form a Vehicle Perspective. In Proc. of the IEEE Intelligent Vehicles Symposium (IV), Dearborn, USA, 2014.  F. Flohr, M. Dumitru-Guzu, J.F.P. Kooij and D.M. Gavrila. Joint probabilistic head and body orientation estimation. In Proc. of the IEEE Intelligent Vehicles Symposium (IV), Dearborn, USA, 2014. M. Liem and D. M. Gavrila. A comparative study on multi-person tracking using overlapping cameras. Proc. of the International Conference on Computer Vision Systems (St.Petersburg, Russia), Lecture Notes in Computer Science, vol. 7963, 2013. M. Liem and D. M. Gavrila. Person Appearance Modeling and Orientation Estimation using Spherical Harmonics. Proc. of the IEEE International Conference on Automatic Face & Gesture, Shanghai, China, 2013. FG2013 Best Student Paper Honorable Mention Award. F. Flohr and D. M. Gavrila. PedCut: an iterative framework for pedestrian segmentation combining shape models and multiple data cues. Proc. of the British Machine Vision Conference, Bristol, UK, 2013. N. Schneider and D. M. Gavrila. Pedestrian Path Prediction with Recursive Bayesian Filters: A Comparative Study. In Lecture Notes in Computer Science: Proc. of the German Conference on Pattern Recognition (GCPR), vol. 8142, Springer, 2013 J. P. F. Kooij, G. Englebienne and D.M. Gavrila. A Non-parametric Hierarchical Model to Discover Behavior Dynamics from Tracks. Proc. of the European Conference on Computer Vision, vol. 6, pp.270-283, Florence, Italy, 2012. C. Keller, C. Hermes and D.M. Gavrila. Will the pedestrian cross? Probabilistic Path Prediction based on Learned Motion Features. In “Pattern Recognition: DAGM Symposium: Frankfurt”, Lecture Notes in Computer Science, vol. 6835, pp. 386-395, 2011.  DAGM PRIZE M. Liem and D. M. Gavrila. Multi-Person Localization and Track Assignment in Overlapping Camera Views. In “Pattern Recognition: DAGM Symposium: Frankfurt”,Lecture Notes in Computer Science, vol. 6835, pp. 173-183, 2011. C. Keller, M. Enzweiler, and D. M. Gavrila. A New Benchmark for Stereo-based Pedestrian Detection. Proc. of the IEEE Intelligent Vehicles Symposium, Baden-Baden, 2011. M. Enzweiler and D.M. Gavrila. Integrated Pedestrian Classification and Orientation Estimation. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, USA, pp.982-989, 2010 M. Enzweiler, A. Eigenstetter, B. Schiele and D.M. Gavrila. Multi-Cue Pedestrian Classification with Partial Occlusion Handling. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, USA, 2010. M. Hofmann and D.M. Gavrila. Multi-view 3D Human Upper Body Pose Estimation combining Single-frame Recovery, Temporal Integration and Model Adaptation. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009 M. Liem and D. M. Gavrila. Multi-person tracking with overlapping cameras in complex, dynamic environments. Proc. of the British Machine Vision Conference (BMVC), London, 2009. M. Rohrbach, M. Enzweiler and D.M. Gavrila. High-Level Fusion of Depth and Intensity for Pedestrian Classification. In “Pattern Recognition: DAGM Symposium Jena“,Lecture Notes in Computer Science, vol. 5748, pp.101-110, 2009. C. Keller, D. Fernandez-Llorca and D.M. Gavrila. Dense Stereo-based ROI Generation for Pedestrian Detection. In “Pattern Recognition: DAGM Symposium Jena“, Lecture Notes in Computer Science, vol. 5748, pp.81-90, 2009. M. Hofmann and D.M. Gavrila, Single-frame 3D Human Pose Recovery from Multiple Views. In “Pattern Recognition: DAGM Symposium Jena“, Lecture Notes in Computer Science, vol. 5748, pp.71-80, 2009.   M. Enzweiler, P. Kanter and D. M. Gavrila. Monocular Pedestrian Recognition Using Motion Parallax. Proc. of the IEEE Intelligent Vehicles Symposium, Eindhoven, The Netherlands, 2008. M. Enzweiler and D. M. Gavrila. A Mixed Generative-Discriminative Framework for Pedestrian Classification. Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, USA, 2008. W. Zajdel, D. Krijnders, T. Andringa and D.M. Gavrila. CASSANDRA: Audio-Video Sensor Fusion for Aggression Detection. IEEE Int. Conf. on Advanced Video and Signal based Surveillance (AVSS), London (UK), 2007. BEST PAPER AWARD L. Andreone, A. Guarise, F. Lilli, D. M. Gavrila and M. Pieve. “Cooperative Systems for vulnerable road users: The Concept Of The WATCH-OVER Project”, ITS World Congress 2006   M. Mählisch, M. Oberländer, O. Löhlein, D. M. Gavrila and W. Ritter. A Multiple Detector Approach to Low-Resolution FIR Pedestrian Recognition. Proc. of the IEEE Intelligent Vehicles Symposium, Las Vegas, USA, 2005. J. Giebel, D. M. Gavrila and C. Schnörr. A Bayesian Framework for Multi-Cue 3D Object Tracking, Proc. of the European Conference on Computer Vision, Prague, Czech Republic, 2004. D. M. Gavrila, J. Giebel and S. Munder. Vision-based Pedestrian Detection: the PROTECTOR System, Proc. of the IEEE Intelligent Vehicles Symposium, Parma, Italy, 2004. See more recentIJCV’07 article H. Sunyoto, W. van der Mark and D. M. Gavrila. A Comparative Study of Fast Dense Stereo Vision Algorithms, Proc. of the IEEE Intelligent Vehicles Symposium, Parma, Italy, 2004. See more recent Trans onITS ’06 article P. Marchal, D. M. Gavrila, L. Letellier, M.-M. Meinecke, R. Morris and M. Töns.SAVE-U: An innovative sensor platform for Vulnerable Road User protection, Proc. of the World Congress on Intelligent Transportation Systems (ITS), Madrid, Spain, 2003. R. Cicilloni, S. J. Deutschle, K. M. Oltersdorf and D. M. Gavrila. Results of Vulnerable Road User Protection Systems in PROTECTOR. Proc. of the World Congress on Intelligent Transportation Systems (ITS). Madrid, Spain, 2003. M.-M. Meinecke, M. Obojski, M. Töns, R. Dörfler, P. Marchal, L. Letellier, D. M. Gavrila and R. Morris. Approach for Protection of Vulnerable Road Users using Sensor Fusion Techniques, Proc. of the International Radar Symposium, Dresden, Germany, 2003. C. von Bank, D. M. Gavrila and C. Wöhler. A Visual Quality Inspection System Based on a Hierarchical 3D Pose Estimation Algorithm, In “Pattern Recognition: DAGM Symposium Magdeburg”, Lecture Notes in Computer Science, vol. 2781, pp.179-186, 2003. J. Giebel and D. M. Gavrila. Multimodal Shape Tracking using Point Distribution Models. In “Pattern Recognition: DAGM Symposium Zürich”, ed. L. van Gool. Lecture Notes on Computer Science, vol. 2449, pp. 1-8, 2002. D. M. Gavrila and J. Giebel. Shape-based Pedestrian Detection and Tracking. Proc. of the IEEE Intelligent Vehicles Symposium, Paris, France, 2002. See more recentIJCV’07 article S. Hezel, D. M. Gavrila, A. Kugel and R. Männer. FPGA-based Template Matching using Distance Transforms. Proc. of the IEEE Symposium on Field-Programmable Custom Computing Machines, Napa, U.S.A., 2002. D. M. Gavrila and J. Giebel, Virtual Sample Generation for Template-based Shape Matching, Proc. of IEEE Conference on Computer Vision and Pattern Recognition, vol. I, pp. 676-681, Kauai, U.S.A., 2001. D. M. Gavrila, M. Kunert and U. Lages, A multi-sensor approach for the protection of vulnerable traffic participants - the PROTECTOR project, Proc. of the IEEE Instrumentation and Measurement Technology Conference, vol. 3, pp. 2044-2048, Budapest, Hungary, 2001. D. M. Gavrila, J. Giebel and H. Neumann, Learning Shape Models from Examples, In “Pattern Recognition: DAGM Symposium Münich”, Lecture Notes on Computer Science, vol. 2449, pp. 369-376, 2001 D. M. Gavrila, Pedestrian Detection from a Moving Vehicle, Proc. of European Conference on Computer Vision, pp. 37-49, Dublin, Ireland, 2000 U. Franke, D. M. Gavrila and S. Görzig,  Vision-based Driver Assistance in Urban Traffic, Proc. of World Congress on Intelligent Transportation Systems (ITS), Turin, Italy, 2000.   D. M. Gavrila, U. Franke, S. Görzig and C. Wöhler, Visual Object Recognition for Intelligent Vehicles, Proc. of the 9-th Aachen Colloquium, vol. I, pp. 589-598, Aachen, Germany, 2000.   D. M. Gavrila and V. Philomin, Real-time Object Detection for Smart Vehicles, Proc. of IEEE International Conference on Computer Vision, pp. 87-93, Kerkyra, Greece, 1999. Please cite the earlierIV’98 paper D. M. Gavrila, Traffic Sign Recognition Revisited, Proc. of the 21st DAGM Symposium für Mustererkennung, pp. 86-93, Springer Verlag, Bonn, Germany, 1999. D. M. Gavrila, Multi-feature Hierarchical Template Matching Using Distance Transforms, Proc. of IEEE International Conference on Pattern Recognition, pp. 439-444, Brisbane, Australia, 1998. D. M. Gavrila and V. Philomin, Real-time Object Detection using Distance Transforms,Proc. of IEEE Intelligent Vehicles Symposium, pp. 274-279, Stuttgart, Germany, 1998. D. M. Gavrila and L. S. Davis, 3-D Model-based Tracking of Humans in Action: a Multi-view Approach, Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 73-80, San Francisco, U.S.A., 1996. Please cite my more extensivePhD. Thesis D. M. Gavrila, Hermite Deformable Contours, Proc. of IEEE International Conference on Pattern Recognition, pp. 130-135, Vienna, Austria, 1996. D. M. Gavrila and L. S. Davis, 3-D Model-based Tracking of Human Upper Body Movement, Proc. of the IEEE International Symposium on Computer Vision, pp. 253-258,Coral Gables, U.S.A., 1995.

	Workshops

D. M. Gavrila, The Analysis of Human Motion and its Application for Visual Surveillance, Proc. of the 2nd IEEE International Workshop on Visual Surveillance, pp. 3-5, Fort Collins, U.S.A., 1999.   D. M. Gavrila and L. S. Davis, Tracking Humans in Action: A 3-D Model-based Approach,Proc. of the ARPA Image Understanding Workshop, pp. 737-746, Palm Springs, U.S.A., 1996.   D. M. Gavrila and L. S. Davis, Towards 3-D Model-based Tracking and Recognition of Human Movement, Proc. of the IEEE International Workshop on Face and Gesture Recognition, pp. 272-277, Zurich, Switzerland, 1995.   D. M. Gavrila and L. S. Davis, Fast Correlation Matching in Large (Edge) Image Databases, Proc. of the 23rd AIPR Workshop, Washington D.C., U.S.A., 1994. Also, CS-TR-3334, University of Maryland, College Park, 1994.