Ocean engineering has recently given a lot of attention to a laser and vision-based underwater range technique. This technique involves the use of lasers to create spot patterns on an object's surface that are then captured on camera. The range might then be determined from the patterns by mapping the correlation between camera spot patterns and real distance. However, the laser paths create "beams" in the camera as a result of backscattering underwater. This impacts the ranging accuracy and makes it challenging to determine the spot position. The Mask R-CNN algorithm-based approach is proposed in this research as a solution to this issue. First, an underwater visual laser ranging system was constructed using a camera, four lasers, and deep learning training with the Mask R-CNN algorithm to recognize and segment the spots in the image. The link between it and the target's distance is then determined by mathematical fitting, using the perimeter of the region the light spot occupies as the geometric feature quantity. Finally, the measured pattern in the camera predicts the object's distance. The findings demonstrate that the measurement accuracy is at the centimeter level, which is beneficial and advantageous for precise underwater ranging.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.