Fast image stitching based on improved SURF

This paper presents an improved method based on Speed up Robust Features (SURF) algorithm to achieve fast image stitching. As the variability of scenes lead to instability of features, expecting to obtain accurate number of features is pretty difficult and time-consuming. support vector machine (SVM) applied in this paper to predict primary threshold of determinant of Hessian matrix can conspicuously reduce detected feature points and simplify the process of features matching. This paper also combines an optimized method of image preprocessing-cylindrical projection and image interpolation to weigh the final quality of stitching image and stitching time. Several experiments are conducted to verify the performance of improved SURF.

[1]  Thomas Martin Deserno,et al.  Survey: interpolation methods in medical image processing , 1999, IEEE Transactions on Medical Imaging.

[2]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[3]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[4]  Yueming Hu,et al.  A method for land surveying sampling optimization strategy , 2010, 2010 18th International Conference on Geoinformatics.

[5]  Ken D. Sauer,et al.  Medical image enhancement using resolution synthesis , 2011, Electronic Imaging.

[6]  You Shang.  Research on PSVM Ensemble Algorithm Based on Relief (F) Object to Robot , 2012, 2012 International Conference on Computer Science and Electronics Engineering.

[7]  Cheng-Ming Huang,et al.  Image stitching on the unmanned air vehicle in the indoor environment , 2012, 2012 Proceedings of SICE Annual Conference (SICE).

[8]  Iuliana Chiuchisan.  A new FPGA-based real-time configurable system for medical image processing , 2013, 2013 E-Health and Bioengineering Conference (EHB).

[9]  Yang Fan,et al.  Improved method of automatic image stitching based on SURF , 2013, 2013 First International Symposium on Future Information and Communication Technologies for Ubiquitous HealthCare (Ubi-HealthTech).

[10]  He Xu,et al.  Target tracking control of mobile robot in diversified manoeuvre modes with a low cost embedded vision system , 2013, Ind. Robot.

[11]  Xiangzhi Bai,et al.  Weighted image fusion based on multi-scale top-hat transform: Algorithms and a comparison study , 2013 .

[12]  Ahmad H. Alashaikh,et al.  Modified perspective cylindrical map projection , 2014, Arabian Journal of Geosciences.

[13]  Michael S. Brown,et al.  As-Projective-As-Possible Image Stitching with Moving DLT , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Ying Wang,et al.  A Fast Image Stitching Algorithm Based on Improved SURF , 2014, CIS.

[15]  Wang Ying,et al.  A Fast Image Stitching Algorithm Based on Improved SURF , 2014, 2014 Tenth International Conference on Computational Intelligence and Security.

[16]  Shimon Aburmad.  Panoramic thermal imaging: challenges and tradeoffs , 2014, Defense + Security Symposium.

[17]  Samuel Luz Gomes,et al.  New Analysis Method Application in Metallographic Images through the Construction of Mosaics Via Speeded Up Robust Features and Scale Invariant Feature Transform , 2015, Materials.

[18]  Naif Alajlan,et al.  Multiclass Coarse Analysis for UAV Imagery , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Xiaoming Ma,et al.  A fast affine-invariant features for image stitching under large viewpoint changes , 2015, Neurocomputing.