Rapid Deformable Object Detection using Dual-Tree Branch-and-Bound

In this work we use Branch-and-Bound (BB) to efficiently detect objects with deformable part models. Instead of evaluating the classifier score exhaustively over image locations and scales, we use BB to focus on promising image locations. The core problem is to compute bounds that accommodate part deformations; for this we adapt the Dual Trees data structure [7] to our problem. We evaluate our approach using Mixture-of-Deformable Part Models [4]. We obtain exactly the same results but are 10-20 times faster on average. We also develop a multiple-object detection variation of the system, where hypotheses for 20 categories are inserted in a common priority queue. For the problem of finding the strongest category in an image this results in a 100-fold speedup.

[1]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Andrew W. Moore,et al.  Nonparametric Density Estimation: Toward Computational Tractability , 2003, SDM.

[3]  William T. Freeman,et al.  Efficient Multiscale Sampling from Products of Gaussian Mixtures , 2003, NIPS.

[4]  Pietro Perona,et al.  Recognition by Probabilistic Hypothesis Construction , 2004, ECCV.

[5]  Andrew W. Moore,et al.  Dual-Tree Fast Gauss Transforms , 2005, NIPS.

[6]  Long Zhu,et al.  Rapid Inference on a Novel AND/OR graph for Object Detection, Segmentation and Parsing , 2007, NIPS.

[7]  Christoph H. Lampert,et al.  Beyond sliding windows: Object localization by efficient subwindow search , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Andrew Zisserman,et al.  Progressive search space reduction for human pose estimation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Andrew Blake,et al.  Image Segmentation by Branch-and-Mincut , 2008, ECCV.

[11]  Iasonas Kokkinos,et al.  HOP: Hierarchical object parsing , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Christoph H. Lampert.  An efficient divide-and-conquer cascade for nonlinear object detection , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Luc Van Gool,et al.  Fast PRISM: Branch and Bound Hough Transform for Object Class Detection , 2011, International Journal of Computer Vision.

[15]  Iasonas Kokkinos,et al.  Inference and Learning with Hierarchical Shape Models , 2011, International Journal of Computer Vision.

[16]  Ben Taskar,et al.  Cascaded Models for Articulated Pose Estimation , 2010, ECCV.

[17]  David A. McAllester,et al.  Cascade object detection with deformable part models , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Jordi Gonzàlez,et al.  A coarse-to-fine approach for fast deformable object detection , 2011, CVPR 2011.

[19]  Daniel P. Huttenlocher,et al.  Distance Transforms of Sampled Functions , 2012, Theory Comput..