Depth Estimation of an Underwater Object Using a Single Camera

Abstract

<p>Underwater robotics is currently a growing field. To be able to autonomously find and collect objects on the land and in the air is a complicated problem, which is only compounded within the underwater setting. Different techniques have been developed over the years to attempt to solve this problem, many of which involve the use of expensive sensors. This paper explores a method to find the depth of an object within the underwater setting, using a single camera source and a known object. Once this known object has been found, information about other unknown objects surrounding this point can be determined, and therefore the objects can be collected.</p>

Fish-inspired robotic algorithm: mimicking behaviour and communication of schooling fish

“…For this study, the robot uses the camera sensor, as it has been shown in the literature that cameras can be used to get the distance and position of objects relative to themselves [38,74].…”

“…The first is by using two cameras next to one another and calculating the distance of an object within the two camera feeds. A single-camera approach offers an alternative solution that, despite its complexity, enables distance estimation by leveraging pixel density and object size information [74]. For the simulation, the distance to an object was determined using the ray cast function within Unity to reduce the computation and complexity.…”