Real-time Depth Estimation for Underwater Inspection Using Dual Laser and Camera

Nowadays, the ocean plays a fundamental role in the global economy, mainly due to oil extraction industry. It makes this environment be populated with human-made structures that needs to be inspected and maintained. In this context, this paper details a system for real-time detecting an underwater flat target using computer vision algorithms and a dual laser emitter. This enable an underwater vehicle to track the target, as well as control distance between the target to be inspected and the vehicle. The system could be used to assist a human operator during inspection tasks. This work is concluded with a series of tests and analyses aiming to the system validation.