An Integrated Visual Odometry System for Underwater Vehicles

Underwater navigation is always a challenging problem because of electromagnetic attenuation. The traditional methods involve beacons, inertial sensors, and Doppler velocity log, but they have many shortcomings, such as high cost lengthy setup time. In order to solve underwater problems at low cost, an integrated visual odometry system has been developed discussed in this article. method, two sensors provide acceleration attitude the vehicle, sonar used distance between vehicle seabed, whilst section, optical flow algorithm applied for tracking feature points. With depth provided by sonar, 3-D position points can be calculated. Linear motion then predicted through these dual frames. Finally, nonlinear optimization correct using information. proposed algorithm, trajectory estimated absolute scale single camera; computational complexity reduced dramatically compared other methodologies; allows approach work sparse texture conditions. results from practical experiments demonstrate that method effective it also low-cost solution.