PowerPoint Presentation课件.ppt

Outline Authors Abstract Main contributions Algorithms Experiments Conclusion Authors (1/4) Stefan Walk Experience 2007-, PhD Candidate in Computer Science, Technische Universit?t Darmstadt 2003-2007, Diploma in Physics, Technische Universit?t Darmstadt, Germany 2007 Research interest People Detection Detecting from video data (utilizing motion information) Papers Multi-cue Onboard Pedestrian Detection (CVPR09) Authors (2/4) Nikodem Majer Experience 2007-, PhD Candidate in Computer Science, Technische Universit?t Darmstadt Research interest … Papers … Authors (3/4) Konrad Schindler Experience 2009-: assistant professor, TU Darmstadt, Germany 2007-2008: post-doc, ETH Zurich 2004-2006: post-doc, Monash University, Melbourne/Australia 2001-2003: research assistant, Graz University of Technology, Austria Research interest computer vision (3D scene analysis, biologically inspired vision, tracking) image processing, pattern recognition, machine learning, photogrammetry Papers PAMI10, CVPR10, ICCV10… Authors (4/4) Bernt Schiele Experience 1999-2004, Assistant Professor, ETH Zurich, Switzerland 1997-2000, Postdoctoral Associate and Visiting Assistant Professor, MIT and Cambridge, MA, USA 1994, Visiting researcher at CMU AE of PAMI, IJCV, AC of ECCV’08, CVPR’09, ICCV’09, PC of ICCV 2011 Research interest Perceptual computing, human-computer interfaces Papers … Outline Authors Abstract Main contributions Algorithms Experiments Conclusion Abstract (1/2) Despite impressive progress in people detection the performance on challenging datasets like Caltech Pedestrians or TUD-Brussels is still unsatisfactory In this work we show that motion features derived from optic flow yield substantial improvements on image sequences, if implemented correctly—even in the case of low-quality video and consequently degraded flow fields Furthermore, we introduce a new feature, self-similarity on color channels, which consistently improves detection performance both for static images