Three Birds, One Stone: Unified Laser-Based 3-D Reconstruction Across Different Media

The laser-based 3-D reconstruction is crucial for autonomous manipulation and resource exploration in both the air and underwater scenarios, due to its accurate precision and robustness to disturbances. However, most current laser-based 3-D reconstruction sensors cannot be applied across different media without recalibration directly, e.g., air, air<inline-formula> <tex-math notation="LaTeX">$\rightarrow $ </tex-math></inline-formula>glass<inline-formula> <tex-math notation="LaTeX">$\rightarrow $ </tex-math></inline-formula>air, and air<inline-formula> <tex-math notation="LaTeX">$\rightarrow $ </tex-math></inline-formula>glass<inline-formula> <tex-math notation="LaTeX">$\rightarrow $ </tex-math></inline-formula>water, which is called killing three birds with one stone. This is because the variation of the medium density could change the sensor calibration parameters and further make the sensor suffer from a systematic geometric bias. To address these challenges, a unified laser-based 3-D reconstruction method is proposed in order that the laser-based scanner could be used across different media without recalibration, where we first explicitly model the refraction of the underwater vision systems and transform it across different media into a unified sensor reference frame. More specifically, an underwater refractive camera calibration model is designed to calibrate the orientation and position of the refractive interface, which can improve the accuracy of underwater reconstruction for the laser-based scanner, and we then present a refractive pose estimation model with a unified sensor reference frame, which can help the sensor to be applied across different scenarios directly. For the experiments, we validate the performance of our method on our underwater 3-D scanner prototype. Several reconstruction results on different objects and scenarios demonstrate the effectiveness of our proposed method and the practicality of our designed sensor.

[1]  João Paulo Costeira,et al.  Stereo Reconstruction of a Submerged Scene , 2005, IbPRIA.

[2]  Yee-Hong Yang,et al.  A Closed-Form Solution to Single Underwater Camera Calibration Using Triple Wavelength Dispersion and Its Application to Single Camera 3D Reconstruction , 2017, IEEE Transactions on Image Processing.

[3]  Gan Sun,et al.  Environment Driven Underwater Camera-IMU Calibration for Monocular Visual-Inertial SLAM , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[4]  Juntong Xi,et al.  Modeling and Calibration of a Novel One-Mirror Galvanometric Laser Scanner , 2017, Sensors.

[5]  Pere Ridao,et al.  Underwater Laser Scanner: Ray-Based Model and Calibration , 2019, IEEE/ASME Transactions on Mechatronics.

[6]  Soon-Jo Chung,et al.  The Visual–Inertial Canoe Dataset , 2018, Int. J. Robotics Res..

[7]  Sébastien Ourselin,et al.  Refractive Structure-from-Motion Through a Flat Refractive Interface , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[8]  Pere Ridao,et al.  3D Laser Scanner for Underwater Manipulation , 2018, Sensors.

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

[10]  Dongdong Hou,et al.  Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[11]  T. Ura,et al.  Instruments and Methods for Acoustic and Visual Survey of Manganese Crusts , 2013, IEEE Journal of Oceanic Engineering.

[12]  Pere Ridao,et al.  State of the Art of Underwater Active Optical 3D Scanners , 2019, Sensors.

[13]  Jiebo Luo,et al.  Novel event analysis for human-machine collaborative underwater exploration , 2019, Pattern Recognit..

[14]  Xiaowei Xu,et al.  What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Yan Peng,et al.  Motion-based pose estimation via free falling , 2018, 2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC).

[16]  Andrea Trucco,et al.  Devising an Affordable Sonar System for Underwater 3-D Vision , 2008, IEEE Transactions on Instrumentation and Measurement.

[17]  Andrea Trucco,et al.  Acoustic imaging of underwater embedded objects: signal simulation for three-dimensional sonar instrumentation , 2006, IEEE Transactions on Instrumentation and Measurement.

[18]  Tamaki Ura,et al.  Generation of High‐resolution Three‐dimensional Reconstructions of the Seafloor in Color using a Single Camera and Structured Light , 2017, J. Field Robotics.

[19]  Kalle Åström,et al.  Absolute pose for cameras under flat refractive interfaces , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Refractive Structure-from-Motion on Underwater Images , 2013, 2013 IEEE International Conference on Computer Vision.

[21]  Pauline Trouvé-Peloux,et al.  AQUALOC: An underwater dataset for visual–inertial–pressure localization , 2019, Int. J. Robotics Res..

[22]  Qianqian Wang,et al.  Visual Tactile Fusion Object Clustering , 2020, AAAI.

[23]  José Luis Lázaro,et al.  Calibration of a High-Accuracy 3-D Coordinate Measurement Sensor Based on Laser Beam and CMOS Camera , 2009, IEEE Transactions on Instrumentation and Measurement.

[24]  Xiaohui Wang,et al.  Research and Experiment of an Underwater Stereo Vision System , 2019, OCEANS 2019 - Marseille.

[25]  Pere Ridao,et al.  Inspection of an underwater structure using point‐cloud SLAM with an AUV and a laser scanner , 2019, J. Field Robotics.

[26]  Songyang Lao,et al.  Two-view underwater 3D reconstruction for cameras with unknown poses under flat refractive interfaces , 2017, Pattern Recognit..

[27]  Jinwhan Kim,et al.  In‐water visual ship hull inspection using a hover‐capable underwater vehicle with stereo vision , 2018, J. Field Robotics.

[28]  Minglun Gong,et al.  Underwater Camera Calibration Using Wavelength Triangulation , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Ismail Lazoglu,et al.  Design and analysis of a 3D laser scanner , 2017 .

[30]  Klaus Schilling,et al.  STRUCTURED-LIGHT BASED 3D LASER SCANNING OF SEMI-SUBMERGED STRUCTURES , 2018, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[31]  Andreas Birk,et al.  The Pinax-model for accurate and efficient refraction correction of underwater cameras in flat-pane housings , 2017 .

[32]  Anne Jordt,et al.  Refractive 3D reconstruction on underwater images , 2016 .

[33]  Danail Stoyanov,et al.  Refractive Two-View Reconstruction for Underwater 3D Vision , 2019, International Journal of Computer Vision.

[34]  Shaojie Shen,et al.  VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator , 2017, IEEE Transactions on Robotics.

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

[36]  Disai Yang,et al.  An Extrinsic Calibration Method With Closed-Form Solution for Underwater Opti-Acoustic Imaging System , 2020, IEEE Transactions on Instrumentation and Measurement.

[37]  Michael Kaess,et al.  Degeneracy-Aware Imaging Sonar Simultaneous Localization and Mapping , 2020, IEEE Journal of Oceanic Engineering.

[38]  Jan-Michael Frahm,et al.  The Misty Three Point Algorithm for Relative Pose , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Junzhi Yu,et al.  A NSGA-II-Based Calibration Algorithm for Underwater Binocular Vision Measurement System , 2020, IEEE Transactions on Instrumentation and Measurement.