Indoor place recognition based on set operation of keypoints databases

In this paper, we proposed a new algorithm based on independent keypoints databases for indoor place recognition. In analogy with set operation, a new kind of operations for keypoints sets are defined to describe the process of independent keypoints database establishment and place classification. To obtain the databases, keypoints are firstly extracted from sample images whose class are known, and then they are processed by set operation. A serious of experiments are conducted to test the influence from the parameters of the algorithm on the effect of the algorithm based on the INDECS database and verified that the algorithm is not sensitive to parameters and changing environment. Then an integrated experiment was developed to test the performance of this algorithm, and verified that it is a robust algorithm with high precision.

[1]  Giulio Sandini,et al.  On-line independent support vector machines , 2010, Pattern Recognit..

[2]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[3]  Trevor Darrell,et al.  Pyramid Match Kernels: Discriminative Classification with Sets of Image Features (version 2) , 2006 .

[4]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[5]  Barbara Caputo,et al.  Recognition with local features: the kernel recipe , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[7]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[8]  Wolfram Burgard,et al.  Supervised Learning of Places from Range Data using AdaBoost , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[9]  Trevor Darrell,et al.  The pyramid match kernel: discriminative classification with sets of image features , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[10]  Chiou-Ting Hsu,et al.  Content-based image retrieval by interest-point matching and geometric hashing , 2002, SPIE/COS Photonics Asia.

[11]  Antonio Torralba,et al.  Recognizing indoor scenes , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Özgür Ulusoy,et al.  Nearest-Neighbor based Metric Functions for indoor scene recognition , 2011, Comput. Vis. Image Underst..

[13]  Ana Cristina Murillo,et al.  SURF features for efficient robot localization with omnidirectional images , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[14]  Barbara Caputo,et al.  A realistic benchmark for visual indoor place recognition , 2010, Robotics Auton. Syst..

[15]  Francesco Orabona,et al.  Indoor Place Recognition using Online Independent Support Vector Machines , 2007, BMVC.