UAV-based pipeline leakage detection via acoustics with owl auditory-inspired OPEI representation

To address the low sensitivity of visual UAV inspection in leakage detection for above-ground natural gas pipelines, an acoustic detection method inspired by the owl auditory mechanism was developed. An innovative oscillatory positional encoding imaging (OPEI) technique was proposed, through which one-dimensional acoustic signals were converted into two-dimensional image representations incorporating time-domain, frequency-domain, and amplitude information. Recognition accuracy of 97.38% for OPEI images on the testing dataset was achieved by the EfficientNetV2 cascade model. The results demonstrated that the biomimetic design enhanced acoustic signal sensitivity and enabled fine-grained recognition of pipeline leakage apertures (1/5/10 mm). This study proposes a novel acoustic signal processing method, providing a theoretical foundation for ensuring the reliability and safety of natural gas pipeline transportation.