A High-Precision Localization Algorithm by Improved SIFT Key-Points

High-precision localization is getting more and more dependent on computer vision techniques. In this paper a novel high-precision localization algorithm based on improved SIFT (Scale Invariant Feature Transform) key-points is presented. First considering the drawback of original SIFT algorithm and the special application background, the proposed algorithm improves the SIFT key-point description and discards the most time- consuming step of SIFT algorithm. Then the new matching strategy and localization strategy are investigated to ensure the stability and precision of localization. Compared with conven- tional localization algorithm by SIFT key-point, this algorithm increases computation efficiency for about 20% and makes the precision more stable, which reaches 0.1 pixel. I. INTRODUCTION

[1]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[2]  A. Rosenfeld.  Coarse-fine template matching , 1977 .

[3]  Yan Ke,et al.  An efficient parts-based near-duplicate and sub-image retrieval system , 2004, MULTIMEDIA '04.

[4]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, CVPR 2004.

[5]  Mohammad Gharavi-Alkhansari,et al.  A fast globally optimal algorithm for template matching using low-resolution pruning , 2001, IEEE Trans. Image Process..

[6]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Azriel Rosenfeld,et al.  Two-Stage Template Matching , 1977, IEEE Transactions on Computers.

[8]  James J. Little,et al.  Global localization using distinctive visual features , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Sun Minglei,et al.  Locating cross-shaped image feature with subpixel accuracy based on NCCO , 2005 .

[10]  B. S. Manjunath,et al.  Duplicate Image Detection in Large Scale Databases , 2007 .

[11]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[12]  Sebastiano Battiato,et al.  SIFT Features Tracking for Video Stabilization , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[13]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[14]  Feng Wu,et al.  Very Fast Template Matching , 2002, ECCV.

[15]  Antonio Torralba,et al.  Small codes and large image databases for recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[17]  Horst Bischof,et al.  Fast Approximated SIFT , 2006, ACCV.

[18]  Yixu Song,et al.  A high-precision template localization algorithm using SIFT keypoints , 2008, 2008 23rd International Symposium on Computer and Information Sciences.

[19]  SchmidCordelia,et al.  A Performance Evaluation of Local Descriptors , 2005 .

[20]  Yan Ke,et al.  Efficient Near-duplicate Detection and Sub-image Retrieval , 2004 .

[21]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

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

[23]  Jun Jie Foo,et al.  Using Redundant Bit Vectors for Near-Duplicate Image Detection , 2007, DASFAA.