A Coarse-to-Fine Framework for Oil–Water Interface Measurement in Small-Caliber Transparent Test Tubes

Accurate oil–water interface measurement in small transparent test tubes is important for subsequent volume readout in laboratory analysis. However, manual observation and conventional vision-based methods are easily affected by illumination variation, wall stains, and bubbles, while deep learning detectors alone usually provide only coarse semantic perception. To address this issue, a coarse-to-fine framework is proposed for robust oil–water interface measurement. In the coarse stage, YOLOv8n is used to provide semantic constraints for subsequent processing. In the fine stage, a Fisher-discriminative chromatic-weighted brightness feature is constructed from RGB information, where the RGB weights are derived from the Fisher criterion to enhance oil–water chromatic separability rather than using fixed grayscale or empirical channel weights. This feature is then fused with a SobelY-based vertical-gradient feature to improve interface localization. A stain-aware row-aggregation strategy with effective-pixel compensation is further introduced to suppress artefact interference. The validated interface position is finally converted into a volume readout, with additional correction for bubble-induced bias. The framework was validated on sampled frames from a complete shale-oil core pressing process conducted under mixed-lighting conditions. Stage-wise evaluation and ablation results indicate that the proposed design improves readout stability under stains, bubbles, and illumination variation, achieving a mean absolute error of 0.0159 mL and keeping the maximum error below 0.03 mL in the current experimental setup.