Multiple kernel Gaussian process classification for generic 3D object recognition

We present an approach to generic object recognition with range information obtained using a Time-of-Flight camera and colour images from a visual sensor. Multiple sensor information is fused with Bayesian kernel combination using Gaussian processes (GP) and hyper-parameter optimisation. We study the suitability of approximate GP classification methods for such tasks and present and evaluate different image kernel functions for range and colour images. Experiments show that our approach significantly outperforms previous work on a challenging dataset which boosts the recognition rate from 78% to 88%.

[1]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[2]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, CVPR Workshops.

[3]  Andrea Fusiello,et al.  A Bag of Words Approach for 3D Object Categorization , 2009, MIRAGE.

[4]  Sebastian Thrun,et al.  Real time motion capture using a single time-of-flight camera , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Joachim Denzler,et al.  Combining Appearance and Range Based Information for Multi-class Generic Object Recognition , 2009, CIARP.

[6]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Bernt Schiele,et al.  3D object recognition from range images using local feature histograms , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[8]  Andrea J. van Doorn,et al.  Surface shape and curvature scales , 1992, Image Vis. Comput..

[9]  Robert Lange,et al.  3D time-of-flight distance measurement with custom solid-state image sensors in CMOS/CCD-technology , 2006 .

[10]  Thomas Martinetz,et al.  Scale-invariant range features for time-of-flight camera applications , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[11]  Doaa Abd al-Kareem Mohammed Hegazy,et al.  Boosting for generic 2D/3D object recognition , 2010 .

[12]  Frédéric Jurie,et al.  Fast Discriminative Visual Codebooks using Randomized Clustering Forests , 2006, NIPS.

[13]  J. Paul Siebert,et al.  Local feature extraction and matching on range images: 2.5D SIFT , 2009, Comput. Vis. Image Underst..

[14]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[15]  Yunhong Wang,et al.  Faceprint: Fusion of Local Features for 3D Face Recognition , 2009, ICB.

[16]  Christopher K. I. Williams,et al.  Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) , 2005 .

[17]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[18]  Neil D. Lawrence,et al.  Extensions of the Informative Vector Machine , 2004, Deterministic and Statistical Methods in Machine Learning.

[19]  Igor Guskov,et al.  3D object recognition from range images using pyramid matching , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[20]  Trevor Darrell,et al.  Gaussian Processes for Object Categorization , 2010, International Journal of Computer Vision.

[21]  Yuan Qi,et al.  Predictive automatic relevance determination by expectation propagation , 2004, ICML.

[22]  Sebastian Thrun,et al.  3D shape scanning with a time-of-flight camera , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[23]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).