Exploiting Protrusion Cues for Fast and Effective Shape Modeling via Ellipses

Modeling objects with a set of geometric primitives is a key problem in computer vision and pattern recognition with numerous applications including object detection and retrieval, tracking, motion and action analysis. In this paper, we attempt to represent 2D object shapes with a number of ellipses with semantic meaning (e.g. one ellipse may correspond to an arm, while two other ellipses may represent a bent leg), while maintaining a high coverage of the shapes. We propose a novel ellipse fitting method based on psychology and cognitive science studies on shape decomposition and show that our shape coverage compares well with the state of the art methods, while significantly outperforming them in run-time by as much as 508 times in our evaluation of the methods on over 4000 2D shapes. We also demonstrate the value of our method to higher-level processing via an example application in creating 3D ellipsoid models of PASCAL horses.

[1]  Ben Taskar,et al.  Shape-Based Object Detection via Boundary Structure Segmentation , 2012, International Journal of Computer Vision.

[2]  Donald D. Hoffman,et al.  Parts of Visual Objects: An Experimental Test of the Minima Rule , 1989, Perception.

[3]  R. Venkatesh Babu,et al.  SeamSeg: Video Object Segmentation Using Patch Seams , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Alexander Sorkine-Hornung,et al.  Bilateral Space Video Segmentation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Wenyu Liu,et al.  Convex shape decomposition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Longin Jan Latecki,et al.  Convexity Rule for Shape Decomposition Based on Discrete Contour Evolution , 1999, Comput. Vis. Image Underst..

[7]  Junsong Yuan,et al.  Minimum Near-Convex Shape Decomposition , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Rui Yan,et al.  Dual-ellipse fitting approach for robust gait periodicity detection , 2012, Neurocomputing.

[9]  Xiang Bai,et al.  DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images , 2016, IEEE Transactions on Image Processing.

[10]  Xin Li,et al.  2D Shape Decomposition Based on Combined Skeleton-Boundary Features , 2008, ISVC.

[11]  Zhongyuan Lai,et al.  Shape decomposition and classification by searching optimal part pruning sequence , 2016, Pattern Recognit..

[12]  Nancy M. Amato,et al.  Approximate convex decomposition of polygons , 2004, SCG '04.

[13]  Antonis A. Argyros,et al.  Parameter-free modelling of 2D shapes with ellipses , 2016, Pattern Recognit..

[14]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

[15]  Dani Lischinski,et al.  JumpCut , 2015, ACM Trans. Graph..

[16]  Brian Taylor,et al.  Causal video object segmentation from persistence of occlusions , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Junsong Yuan,et al.  Minimum near-convex decomposition for robust shape representation , 2011, 2011 International Conference on Computer Vision.

[18]  F. Bookstein.  Fitting conic sections to scattered data , 1979 .

[19]  Yan Wang,et al.  DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Iasonas Kokkinos,et al.  Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs , 2014, ICLR.

[21]  Ralph R. Martin,et al.  Faithful Least-Squares Fitting of Spheres, Cylinders, Cones and Tori for Reliable Segmentation , 1998, ECCV.

[22]  Nikolaos Grammalidis,et al.  Head detection and tracking by 2-D and 3-D ellipsoid fitting , 2000, Proceedings Computer Graphics International 2000.

[23]  Benjamin B. Kimia,et al.  Skeleton Search: Category-Specific Object Recognition and Segmentation Using a Skeletal Shape Model , 2011, International Journal of Computer Vision.

[24]  Andrew W. Fitzgibbon,et al.  Direct Least Square Fitting of Ellipses , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[26]  Bogdan Kwolek,et al.  Stereovision-Based Head Tracking Using Color and Ellipse Fitting in a Particle Filter , 2004, ECCV.

[27]  Antonis A. Argyros,et al.  Scalable 3D Tracking of Multiple Interacting Objects , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Richard Y. D. Xu,et al.  Fitting Multiple Connected Ellipses to an Image Silhouette Hierarchically , 2010, IEEE Transactions on Image Processing.

[29]  Georgios Tziritas,et al.  Shape-Based Individual/Group Detection for Sport Videos Categorization , 2008, Int. J. Pattern Recognit. Artif. Intell..

[30]  H. Blum.  Biological shape and visual science (part I) , 1973 .

[31]  Erkki Oja,et al.  Randomized hough transform (rht) : Basic mech-anisms, algorithms, and computational complexities , 1993 .