The development of Autonomous Underwater Vehicles (AUVs) is essential for the sea bed resources exploration. Vision-based underwater vehicle to robustly detect the underwater target especially in high turbid and low illumination. Visual-based underwater vehicle using 3D perception based move on sensing (3D-MoS) system with dual-eye cameras and 3D marker has been developed. We designed and constructed the active/lighting 3D marker to improve the recognition accuracy for the real time 3D pose estimation. The recognition experiments were conducted in an indoor pool against different turbidity and illumination by adjusting the LED's brightness under day and night environments. The purpose of this research is to choose appropriate currents of LED that was installed in the active/lighting 3D marker for real-time pose recognition against different turbidity and illumination.
