Learning Hough regression models via bridge partial least squares for object detection

Popular Hough Transform-based object detection approaches usually construct an appearance codebook by clustering local image features. However, how to choose appropriate values for the parameters used in the clustering step remains an open problem. Moreover, some popular histogram features extracted from overlapping image blocks may cause a high degree of redundancy and multicollinearity. In this paper, we propose a novel Hough Transform-based object detection approach. First, to address the above issues, we exploit a Bridge Partial Least Squares (BPLS) technique to establish context-encoded Hough Regression Models (HRMs), which are linear regression models that cast probabilistic Hough votes to predict object locations. BPLS is an efficient variant of Partial Least Squares (PLS). PLS-based regression techniques (including BPLS) can reduce the redundancy and eliminate the multicollinearity of a feature set. And the appropriate value of the only parameter used in PLS (i.e., the number of latent components) can be determined by using a cross-validation procedure. Second, to efficiently handle object scale changes, we propose a novel multi-scale voting scheme. In this scheme, multiple Hough images corresponding to multiple object scales can be obtained simultaneously. Third, an object in a test image may correspond to multiple true and false positive hypotheses at different scales. Based on the proposed multi-scale voting scheme, a principled strategy is proposed to fuse hypotheses to reduce false positives by evaluating normalized pointwise mutual information between hypotheses. In the experiments, we also compare the proposed HRM approach with its several variants to evaluate the influences of its components on its performance. Experimental results show that the proposed HRM approach has achieved desirable performances on popular benchmark datasets.

[1]  Subhransu Maji,et al.  Object detection using a max-margin Hough transform , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Larry S. Davis,et al.  Vehicle Detection Using Partial Least Squares , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Guodong Guo,et al.  Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression , 2011, CVPR 2011.

[4]  Bernt Schiele,et al.  Robust Object Detection with Interleaved Categorization and Segmentation , 2008, International Journal of Computer Vision.

[5]  Larry S. Davis,et al.  On partial least squares in head pose estimation: How to simultaneously deal with misalignment , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Jitendra Malik,et al.  Multi-scale object detection by clustering lines , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[7]  Bernt Schiele,et al.  Integrating representative and discriminant models for object category detection , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[8]  Aaron D. Wyner,et al.  Prediction and Entropy of Printed English , 1993 .

[9]  L. Davis,et al.  Kernel PLS regression for robust monocular pose estimation , 2011, CVPR 2011 WORKSHOPS.

[10]  Luc Van Gool,et al.  Latent Hough Transform for Object Detection , 2012, ECCV.

[11]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[12]  Hans Stødkilde-Jørgensen,et al.  Bridge–PLS regression: two‐block bilinear regression without deflation , 2004 .

[13]  Anton van den Hengel,et al.  Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features , 2014, ECCV.

[14]  Hanzi Wang,et al.  Semantic Hough Transform based object detection with Partial Least Squares , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[15]  Larry S. Davis,et al.  A data-driven detection optimization framework , 2013, Neurocomputing.

[16]  Claude E. Shannon,et al.  Prediction and Entropy of Printed English , 1951 .

[17]  Björn Ommer,et al.  Voting by Grouping Dependent Parts , 2010, ECCV.

[18]  R. Manne Analysis of two partial-least-squares algorithms for multivariate calibration , 1987 .

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

[20]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[21]  Francesc Moreno-Noguer,et al.  Efficient rotation invariant object detection using boosted Random Ferns , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  Giovanni Montana,et al.  Sparse partial least squares regression for on‐line variable selection with multivariate data streams , 2010, Stat. Anal. Data Min..

[23]  Ryuzo Okada,et al.  Discriminative generalized hough transform for object dectection , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[24]  S. Wold,et al.  A PLS kernel algorithm for data sets with many variables and fewer objects. Part 1: Theory and algorithm , 1994 .

[25]  Larry S. Davis,et al.  Human detection using partial least squares analysis , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[26]  Stefan Roth,et al.  People-tracking-by-detection and people-detection-by-tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Roman Rosipal,et al.  Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space , 2002, J. Mach. Learn. Res..

[28]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[29]  Ieee Xplore,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence Information for Authors , 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Gerlof Bouma,et al.  Normalized (pointwise) mutual information in collocation extraction , 2009 .

[31]  Bernt Schiele,et al.  Cross-Articulation Learning for Robust Detection of Pedestrians , 2006, DAGM-Symposium.

[32]  Juergen Gall,et al.  Class-specific Hough forests for object detection , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[34]  Pushmeet Kohli,et al.  On Detection of Multiple Object Instances Using Hough Transforms , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.