Volume Estimation of Oil Tanks Based on 3-D Point Cloud Completion

The measurement of oil tank volume holds significant safety and economic implications. A common method of measurement is the use of 3-D scanning point clouds. However, point cloud data obtained through 3-D scanning may be incomplete and contain certain noise, affecting the accuracy of volume measurement. To address these issues, this article proposes an oil tank volume measurement method based on 3-D point clouds. There are two key innovations. One is the introduction of a stratified truncated cone inner diameter fitting (IDF) method to overcome point cloud measurement noise. The other is the development of a point cloud completion network (BPoinTr) through a bias learning model (BLM). The incomplete bottom point cloud data of the oil tank are completed by BPoinTr and used for subsequent volume calculation. Extensive experiments on actual collected oil tank point cloud data demonstrate that the method proposed in this article can reduce the calculation error of the tank bottom volume to 0.004 m3, merely 0.57 parts per thousand. Furthermore, the mean absolute percentage error (APE) of the calculated tank volume by this method is less than 0.1%.