An underwater stereo vision system: From design to deployment and dataset acquisition

This paper describes the hardware setup of a stereovision system for underwater 3D object detection and a camera calibration method that does not require complex underwater procedures. The vision system has been developed within the MARIS Italian national project for underwater cooperative intervention tasks. The hardware architecture is based upon state of the art technologies. The software modules of the system are based on the ROS middleware. A dataset of underwater stereo images of cylindrical pipes has been collected and is made publicly available.

[1]  Duane C. Brown,et al.  Close-Range Camera Calibration , 1971 .

[2]  Carlos H. Llanos,et al.  Development of a stereo vision measurement architecture for an underwater robot , 2013, 2013 IEEE 4th Latin American Symposium on Circuits and Systems (LASCAS).

[3]  Weijian Cong,et al.  Automatic radial distortion correction for endoscope image , 2013, 2013 6th International Congress on Image and Signal Processing (CISP).

[4]  Matthias Wehkamp,et al.  A practical guide to the use of consumer-level digital still cameras for precise stereogrammetric in situ assessments in aquatic environments , 2014 .

[5]  S Negahdaripour,et al.  Performance assessment in solving the correspondence problem in underwater stereo imagery , 2010, OCEANS 2010 MTS/IEEE SEATTLE.

[6]  D Gonzalez-Aguilera,et al.  An Automatic Approach for Radial Lens Distortion Correction From a Single Image , 2011, IEEE Sensors Journal.

[7]  Shahriar Negahdaripour,et al.  Stereovision imaging on submersible platforms for 3-D mapping of benthic habitats and sea-floor structures , 2003 .

[8]  C. J. Prabhakar,et al.  Stereo correspondence for underwater images using adaptive weight-based cross-correlation , 2013, 2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[9]  E. Malis,et al.  3D Reconstruction of Natural Underwater Scenes Using the Stereovision System IRIS , 2007, OCEANS 2007 - Europe.

[10]  Nicholas Krouglicof,et al.  Calibration of an underwater stereoscopic vision system , 2013, 2013 OCEANS - San Diego.

[11]  Massimo Caccia,et al.  MARIS: A national project on marine robotics for interventions , 2014, 22nd Mediterranean Conference on Control and Automation.

[12]  Pere Ridao,et al.  Grasping for the Seabed: Developing a New Underwater Robot Arm for Shallow-Water Intervention , 2013, IEEE Robotics & Automation Magazine.

[13]  Oleari Fabio,et al.  Performance Evaluation of a Low-Cost Stereo Vision System for Underwater Object Detection , 2014 .

[14]  Shang-Hong Lai,et al.  Automatic Distortion Correction of Endoscopic Images Captured With Wide-Angle Zoom Lens , 2013, IEEE Transactions on Biomedical Engineering.

[15]  Andreas Geiger,et al.  Simultaneous underwater visibility assessment, enhancement and improved stereo , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[16]  E. Malis,et al.  D Reconstruction of Natural Underwater Scenes Using the Stereovision System , 2022 .

[17]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[18]  Gabriel Oliver,et al.  A vision system for an underwater cable tracker , 2002, Machine Vision and Applications.