Research and Experiment of an Underwater Stereo Vision System
Cong Wang, Qifeng Zhang, Sen Lin, Wentao Li, Xiaohui Wang, Yunfei Bai, Qiyan Tian
- Year
- 2019
- Citations
- 16
Abstract
Underwater computer vision is a challenging task due to the severe underwater condition. The underwater optical system can provide more detailed information than the acoustic system. This paper describes a new stereo vision system for underwater object detection and 3D reconstruction. The Stereolabs ZED 2K Stereo Camera and NVIDIA Jetson TX2 are the core components of the system. A USB3.0 optical cable can transmit the high-definition video at the maximum speed of 5.0 GB/s within a distance of 300 meters. All software modules are developed based on ROS (Robot Operating System) middleware. The underwater camera calibration has been carried out to correct the underwater distortion of stereo vision, and underwater 3D reconstruction experiments have proven the validity of the system.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002