Accurate Object Detection with Deformable Shape Models Learnt from Images

We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the accurate boundaries of the objects, rather than just their bounding-boxes. This is made possible by 1) a novel technique for learning a shape model of an object class given images of example instances; 2) the combination of Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately, while needing no segmented examples for training (only bounding-boxes).

[1]  Christopher J. Taylor,et al.  A Method of Non-Rigid Correspondence for AutomaticLandmark Identification , 1996, BMVC.

[2]  Tim Cootes,et al.  An Introduction to Active Shape Models , 2000 .

[3]  D. Cremers,et al.  Diffusion-snakes: combining statistical shape knowledge and image information in a variational framework , 2001, Proceedings IEEE Workshop on Variational and Level Set Methods in Computer Vision.

[4]  Anand Rangarajan,et al.  A new point matching algorithm for non-rigid registration , 2003, Comput. Vis. Image Underst..

[5]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  A. Torralba,et al.  Sharing features: efficient boosting procedures for multiclass object detection , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[7]  Bernt Schiele,et al.  Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search , 2004, DAGM-Symposium.

[8]  C. Schmid,et al.  Scale-invariant shape features for recognition of object categories , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[9]  Jitendra Malik,et al.  Shape matching and object recognition using low distortion correspondences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Andrew Zisserman,et al.  OBJ CUT , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Nebojsa Jojic,et al.  LOCUS: learning object classes with unsupervised segmentation , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[12]  Andrew Blake,et al.  Contour-based learning for object detection , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Pedro F. Felzenszwalb.  Representation and detection of deformable shapes , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[14]  Andrew Zisserman,et al.  A Boundary-Fragment-Model for Object Detection , 2006, ECCV.

[15]  Luc Van Gool,et al.  Object Detection by Contour Segment Networks , 2006, ECCV.

[16]  Narendra Ahuja,et al.  Extracting Subimages of an Unknown Category from a Set of Images , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[17]  Daphne Koller,et al.  Learning Object Shape: From Drawings to Images , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[18]  Antonio Criminisi,et al.  TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation , 2006, ECCV.

[19]  Frédéric Jurie,et al.  Groups of Adjacent Contour Segments for Object Detection , 2008, IEEE Trans. Pattern Anal. Mach. Intell..