Underwater image matching with efficient refractive-geometry estimation for measurement in glass-flume experiments

Abstract Computer vision technology has been employed in numerous ocean engineering experiments to measure motions and shapes of target objects. However, when dealing with underwater objects, conventional image matching strategies are less effective because of refractive distortions. In this paper, a new method is proposed for matching underwater images in glass-flume experiments. It leverages the estimation of refractive geometry to refine potential image correspondences that include mismatches and location errors. By analyzing the light paths, the relationship between corresponding points of underwater images is derived. Then, an efficient estimation algorithm is designed to compute the parameters of refractive planes from image correspondences. Finally, an improved matching process is presented by incorporating this algorithm into an outlier removal framework. Extensive experiments on synthetic data and real images demonstrate that the proposed method is effective in calculating the refractive geometry of glass-flume experiments and leads to significantly higher accuracies in underwater image matching.

[1]  Chun-yu Guo,et al.  Experimental study on the wake fields of a Panamax Bulker based on stereo particle image velocimetry , 2018, Ocean Engineering.

[2]  Thomas B. Moeslund,et al.  Camera Calibration for Underwater 3D Reconstruction Based on Ray Tracing Using Snell’s Law , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[3]  Yang Yang,et al.  Non-Rigid Image Registration With Dynamic Gaussian Component Density and Space Curvature Preservation , 2019, IEEE Transactions on Image Processing.

[4]  Kresimir Williams,et al.  A method for computing volumetric fish density using stereo cameras , 2018, Journal of Experimental Marine Biology and Ecology.

[5]  Chao Zhang,et al.  Terahertz Computed Tomography of High-Refractive-Index Objects Based on Refractive Index Matching , 2018, IEEE Photonics Journal.

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

[7]  Hai Du,et al.  The study for particle image velocimetry system based on binocular vision , 2009 .

[8]  Yu‐Chi Chang,et al.  The Development of a Cost-Effective and Optimized DP-SPIV System for Fluid Turbulence Researches , 2014 .

[9]  J. Ortega-Casanova,et al.  Low cost 3D underwater surface reconstruction technique by image processing , 2016 .

[10]  Konrad Schindler,et al.  Variational 3D-PIV with sparse descriptors , 2018, ArXiv.

[11]  Fabio Remondino,et al.  State of the art in high density image matching , 2014 .

[12]  Visesh Chari,et al.  A theory of multi-layer flat refractive geometry , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Zhuowen Tu,et al.  Robust $L_{2}E$ Estimation of Transformation for Non-Rigid Registration , 2015, IEEE Transactions on Signal Processing.

[14]  Dezhi Ning,et al.  Experimental and numerical investigation on coupled motion characteristics of a tunnel element suspended from a twin-barge , 2018 .

[15]  Jiali Wang,et al.  Geometric Distortion Correction for the Underwater Images , 2018, OCEANS 2018 MTS/IEEE Charleston.

[16]  Danping Zou,et al.  CoSLAM: Collaborative Visual SLAM in Dynamic Environments , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Yee-Hong Yang,et al.  Two-View Camera Housing Parameters Calibration for Multi-layer Flat Refractive Interface , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  R. Budwig.  Refractive index matching methods for liquid flow investigations , 1994 .

[20]  Jian Gang Wang,et al.  The Index Matching Method and its Application in V3V Measurements , 2014 .

[21]  Sajid Saleem,et al.  Towards feature points based image matching between satellite imagery and aerial photographs of agriculture land , 2016, Comput. Electron. Agric..

[22]  Z. C. Liu,et al.  Distortion compensation for generalized stereoscopic particle image velocimetry , 1997 .

[23]  Gérard Gréhan,et al.  A digital holography set-up for 3D vortex flow dynamics , 2016 .

[24]  Minh Vo,et al.  Accurate 3D shape measurement of multiple separate objects with stereo vision , 2014 .

[25]  Daniel Berjón,et al.  Fast feature matching for detailed point cloud generation , 2016, 2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA).

[26]  Andriy Myronenko,et al.  Point Set Registration: Coherent Point Drift , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[28]  Yassin A. Hassan,et al.  An investigation of matched index of refraction technique and its application in optical measurements of fluid flow , 2012 .

[29]  Henghua Shen,et al.  Adaptive registration algorithm of color images based on SURF , 2015 .

[30]  Olivier D. Faugeras,et al.  Variational Methods for Multimodal Image Matching , 2002, International Journal of Computer Vision.

[31]  Minh N. Do,et al.  CODE: Coherence Based Decision Boundaries for Feature Correspondence , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[33]  Muguo Li,et al.  Study on the reconstruction method of stereo vision in glass flume , 2016, Adv. Eng. Softw..

[34]  Roland Siegwart,et al.  Target-based calibration of underwater camera housing parameters , 2016, 2016 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).

[35]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.