Effects of Conveyor Speed and Angle on Potato Volume Estimation Using RGB Cameras and Ultrasonic Sensor Under Controlled Harvester Test Bench Conditions

Accurate, non-destructive estimation of potato volume can support conveyor-based yield monitoring, but individual sensing modalities provide incomplete geometric information. This study developed and evaluated a low-cost sensing approach combining top-view RGB imaging and ultrasonic height measurement under controlled potato-harvester conveyor conditions. One hundred potatoes were evaluated repeatedly under 20 combinations of five conveyor speeds (0.10–0.50 ms−1 and four inclination angles (15–30°). Two RGB cameras provided projected-area measurements across the conveyor width, while an eight-sensor ultrasonic array provided complementary potato-height measurements. Four linear volume-estimation formulations were compared: height only, projected area only, area and height as separate predictors (A+H), and an area–height fusion feature (A×H). The combined models substantially outperformed the single-sensor approaches. The (A+H) model achieved a mean (R2) of 0.88, RMSE of 3.27 cm3, and MAE of 2.54 cm3, while the (A×H) fusion model achieved a mean (R2) of 0.88, RMSE of 3.33 cm3, and MAE of 2.60 cm3. Mixed-effects analysis showed that model type significantly affected estimation error (p < 0.001), confirming the benefit of combining RGB-derived area and ultrasonic height. Conveyor speed had the dominant effect on accuracy (p < 0.001), whereas inclination angle produced a statistically significant but comparatively small effect, and the speed × angle interaction was non-significant. The highest accuracy was obtained at 0.10 ms−1, while performance declined with increasing speed, consistent with reduced RGB and ultrasonic sampling opportunities. These results demonstrate the feasibility of RGB–ultrasonic fusion for potato volume estimation under controlled dynamic conveyor conditions; field-scale robustness remains to be validated under commercial harvesting environments.