Coral monitoring system based on polarization vision

Coral ecosystem not only breeds abundant organisms, but also deem to be a very important fishery and tourism resources. The reduction of coral will also have a bad impact on the marine. Scattering and absorption leads to complicate the capturing process of a clear image. Aiming to the needs of marine ecological diversity research, in addition to the privilege of underwater polarization imaging, an underwater binocular polarization vision system is proposed in this paper. This system consists of underwater vehicle, vision acquisition system and image processing software. The internal image acquisition hardware module made up out of microcomputer, two polarization camera modules and information transmission module. While the dynamic systems of underwater vehicle consist of six propellers. The proposed system realizes a real-time control and transmit polarization image through cable connected to information transmission module. Due to its autonomous function, it is capable to achieve missions without diver support. After the system is designed and implemented, a large number of underwater coral images are captured and tested at the offshore of Shenzhen to build our polarization image database. This database classified into 15 different kinds of offshore coral, which provides data support for subsequent algorithms such as clear imaging algorithm based on polarization vision. Finally, clear image processing algorithm is carried out with the captured data.