An Adaptive Image Thresholding Algorithm Using Fuzzy Logic for Autonomous Underwater Vehicle Navigation

Breakthroughs in autonomous vehicle technology have ignited diverse topics within engineering research. Among these, the focus on conducting inspections through autonomous underwater vehicles (AUVs) stands out as particularly influential, owing to the substantial investments directed towards offshore infrastructures. Leveraging the capabilities of onboard sensors, AUVs hold the potential to adeptly trace and examine pipelines with high levels of accuracy. However, the complicated and varying underwater environment presents a formidable challenge to ensuring the robustness of the localization and navigation framework. In response to these challenges, this study introduces a novel GPS-denied, adaptive, vision-based navigation framework tailored specifically for AUV inspection tasks. Different from conventional approaches involving manual parameter tuning, this framework dynamically adjusts contrast enhancement and edge detection functions based on incoming frame data. Fuzzy inference systems (FIS) have been harnessed within both image processing and the navigation algorithm, strengthening the overall robustness of the system. The verification of the proposed framework took place within a simulation environment. Through the implemented algorithm, the AUV adeptly identified, approached, and traversed the pipeline. Additionally, the framework distinctly showcased its capacity to dynamically adjust parameters, reduce processing time, and uphold consistency amid diverse illuminations and levels of noise.