Global Optimal Multiple Object Detection Using the Fusion of Shape and Color Information

In this work we present a novel method for detecting multiple objects of interest in one image, when the only available information about these objects are their shape and color. To solve this task we use a global optimal variational approach based on total variation. The presented energy functional can be minimized locally due its convex formulation. To improve the runtime of our algorithm we show how this approach can be scheduled in parallel.Our algorithm works fully automatically and does not need any user interaction. In experiments we show the capabilities in non-artificial images, e.g. aerial or bureau images.

[1]  Rachid Deriche,et al.  Implicit Active Shape Models for 3D Segmentation in MR Imaging , 2004, MICCAI.

[2]  Nikos Paragios,et al.  Prior Knowledge, Level Set Representations & Visual Grouping , 2008, International Journal of Computer Vision.

[3]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[4]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[5]  Daniel Cremers,et al.  Fast Matching of Planar Shapes in Sub-cubic Runtime , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Mila Nikolova,et al.  Algorithms for Finding Global Minimizers of Image Segmentation and Denoising Models , 2006, SIAM J. Appl. Math..

[7]  Antonin Chambolle,et al.  Total Variation Minimization and a Class of Binary MRF Models , 2005, EMMCVPR.

[8]  Daniel Cremers,et al.  An Experimental Comparison of Discrete and Continuous Shape Optimization Methods , 2008, ECCV.

[9]  Daniel Cremers,et al.  Shape priors in variational image segmentation: Convexity, Lipschitz continuity and globally optimal solutions , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Daniel Cremers,et al.  Dynamical statistical shape priors for level set-based tracking , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Daniel Cremers,et al.  Diffusion Snakes: Introducing Statistical Shape Knowledge into the Mumford-Shah Functional , 2002, International Journal of Computer Vision.

[12]  Marek Schikora,et al.  A convex formulation for color image segmentation in the context of passive emitter localization , 2009, 2009 12th International Conference on Information Fusion.

[13]  Daniel Cremers,et al.  Efficient planar graph cuts with applications in Computer Vision , 2009, CVPR.