An appraisal of backscatter removal and refraction calibration models for improving the performance of vision-based mapping and navigation in shallow underwater environments

Abstract

• Underwater Vision-Based Mapping (VbM) encounters distortion and noise resulting from refraction between different mediums, along with non-uniform light illumination due to the variable properties of water. • The integration of visual-inertial capabilities into GoPro cameras aids in restoring the precise metrics of VbM. • Real-time fusion of refraction correction is achieved using the Pinhole-Axial (Pinax) camera model, which considers multi-layer geometry, particularly beneficial for flat port camera housings. • Underwater image enhancement, coupled with backscatter removal, expedites feature detection and matching within VbM across diverse states of water properties. Vision-based mapping (VbM) is one of the fundamental origins of automation in remote and autonomous spatial data acquisitions. Complexity in obtaining accurate data arises when such a method is applied in the underwater environment. Non-uniform illumination and refraction distortion are the most common problems encountered in underwater VbM. This study addresses this by employing backscatter removal to enhance image clarity and a pinhole-axial (Pinax) camera model to adjust the refraction distortion. In particular, the methods are computed in the robot operating system (ROS), publishing the enhanced images as separated image nodes in real-time and enabling seamless integration to the VbM pipeline. It is argued that the proposed VbM-dedicated models can significantly improve the feature detection method and conformity of objects’ positions underwater around the camera's motion. Simulation datasets are generated to evaluate the sensitivity to varying turbidity levels to test the method's sensitivity. Additionally, field experiments with GoPro 10 hardware in Pramuka Island Waters, Indonesia, offer real-world context for the study's relevance to distinct underwater circumstances. Furthermore, additional visual-inertial datasets quantify the overall performance, especially in retrieving metric positioning information. The research shows efficient backscatter removal improves feature detection robustness, especially in murky water conditions. Refraction correction eliminates the bowing effect from missing ground control points in underwater environments. The study is significant because it emphasizes how vital image enhancement and refraction calibration are to obtaining less than 4% trajectory error of VbM. Overall, the proposed VbM pipeline can maintain less than 5 cm trajectory error compared to the standard VbM pipeline. The results highlight the need for a comprehensive strategy to advance underwater mapping and navigation technology to deliver accurate and dependable outcomes in various underwater situations.