An algorithm of image mosaic based on binary tree and eliminating distortion error

The traditional image mosaic result based on SIFT feature points extraction, to some extent, has distortion errors: the larger the input image set, the greater the spliced panoramic distortion. To achieve the goal of creating a high-quality panorama, a new and improved algorithm based on the A-KAZE feature is proposed in this paper. This includes changing the way reference image are selected and putting forward a method for selecting a reference image based on the binary tree model, which takes the input image set as the leaf node set of a binary tree and uses the bottom-up approach to construct a complete binary tree. The root node image of the binary tree is the ultimate panorama obtained by stitching. Compared with the traditional way, the novel method improves the accuracy of feature points detection and enhances the stitching quality of the panorama. Additionally, the improved method proposes an automatic image straightening model to rectify the panorama, which further improves the panoramic distortion. The experimental results show that the proposed method cannot only enhance the efficiency of image stitching processing, but also reduce the panoramic distortion errors and obtain a better quality panoramic result.

[1]  Yiannis Andreopoulos,et al.  Voronoi-Based Compact Image Descriptors: Efficient Region-of-Interest Retrieval With VLAD and Deep-Learning-Based Descriptors , 2016, IEEE Transactions on Multimedia.

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

[3]  Jing Li,et al.  Parallax-Tolerant Image Stitching Based on Robust Elastic Warping , 2018, IEEE Transactions on Multimedia.

[4]  Judith Redi,et al.  Effects of task and image properties on visual-attention deployment in image-quality assessment , 2015, J. Electronic Imaging.

[5]  Xavier Maldague,et al.  Multisensor image fusion approach utilizing hybrid pre-enhancement and double nonsubsampled contourlet transform , 2017, J. Electronic Imaging.

[6]  Cheng-Ming Huang,et al.  Efficient Image Stitching of Continuous Image Sequence With Image and Seam Selections , 2015, IEEE Sensors Journal.

[7]  Baohua Zhang,et al.  Multi-focus image fusion algorithm based on focused region extraction , 2016, Neurocomputing.

[8]  Hsien-Chou Liao,et al.  De-ghosting Method for Image Stitching , 2012 .

[9]  Ling Liu,et al.  Image seamless stitching and straightening based on the image block , 2018, IET Image Process..

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

[11]  Zhong Qu,et al.  The Improved Algorithm of Fast Panorama Stitching for Image Sequence and Reducing the Distortion Errors , 2015 .

[12]  Yufei Chen,et al.  An automatic panoramic image mosaic method based on graph model , 2015, Multimedia Tools and Applications.

[13]  Takeshi Ikenaga,et al.  Ghost-free high dynamic range imaging via moving objects detection and extension , 2015, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

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

[15]  Yu Liu,et al.  Dense SIFT for ghost-free multi-exposure fusion , 2015, J. Vis. Commun. Image Represent..

[16]  Kristin J. Dana,et al.  Automated Crack Detection on Concrete Bridges , 2016, IEEE Transactions on Automation Science and Engineering.

[17]  Bin Lu,et al.  An Automatic Video Image Mosaic Algorithm Based on SIFT Feature Matching , 2013 .

[18]  Mohammad Shorif Uddin,et al.  Feature-based image stitching algorithms , 2016, 2016 International Workshop on Computational Intelligence (IWCI).

[19]  Qi Zhang,et al.  Study in Ultrasonic Flaw Detection for Small-Diameter Steel Pipe with Thick Wall , 2012 .

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

[21]  Sim Heng Ong,et al.  Remote Sensing Image Registration Using Multiple Image Features , 2017, Remote. Sens..

[22]  Karimov Abdusamat Ismonovich,et al.  Mathematical Modeling of Heat Flux Distribution in Raw Cotton Stored in Bunt , 2020 .

[23]  Pan Lin,et al.  Multiple Visual Features Measurement With Gradient Domain Guided Filtering for Multisensor Image Fusion , 2017, IEEE Transactions on Instrumentation and Measurement.

[24]  Marcelo Resende Pereira,et al.  AUMENTO DE PRODUTIVIDADE E REDUÇÃO NO CONSUMO DE COMBUSTÍVEL ATRAVÉS DA UTILIZAÇÃO DE PELOTAS NO ALTO-FORNO 02 DA SAINT-GOBAIN CANALIZAÇÃO , 2005 .

[25]  Adrien Bartoli,et al.  Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces , 2013, BMVC.

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

[27]  Chul Lee,et al.  Ghost-Free High Dynamic Range Imaging via Rank Minimization , 2014, IEEE Signal Processing Letters.

[28]  Yifang Xu,et al.  Quasi-Homography Warps in Image Stitching , 2017, IEEE Transactions on Multimedia.

[29]  Guorong Yu,et al.  A new image registration algorithm using SDTR , 2017, Neurocomputing.

[30]  Yu-Sheng Chen,et al.  Natural Image Stitching with the Global Similarity Prior , 2016, ECCV.

[31]  King Ngi Ngan,et al.  No-Reference Retargeted Image Quality Assessment Based on Pairwise Rank Learning , 2016, IEEE Transactions on Multimedia.

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

[33]  Masatoshi Okutomi,et al.  Versatile visible and near-infrared image fusion based on high visibility area selection , 2016, J. Electronic Imaging.

[34]  Volkan Isler,et al.  Large Scale Image Mosaic Construction for Agricultural Applications , 2016, IEEE Robotics and Automation Letters.

[35]  Adrien Bartoli,et al.  KAZE Features , 2012, ECCV.

[36]  Huiqian Du,et al.  Structure tensor and nonsubsampled shearlet transform based algorithm for CT and MRI image fusion , 2017, Neurocomputing.

[37]  Mohammed Bennamoun,et al.  An Accurate and Robust Range Image Registration Algorithm for 3D Object Modeling , 2014, IEEE Transactions on Multimedia.