Deep Learning-Based Semantic Segmentation and Surface Reconstruction for Point Clouds of Offshore Oil Production Equipment

The structural information of offshore oil production equipment is the basis for the functional modification and upgrading of offshore oil drilling platforms. In order to solve the problems of low efficiency in the process of acquiring offshore oil production equipment structure information by traditional measurement methods, we propose a deep learning-based point cloud data processing scheme for offshore oil production equipment. First, a point cloud dataset of offshore oil production equipment for deep learning is constructed, and a deep learning network based on the two-step downsampling method and the local feature aggregation of each point after downsampling is implemented for the semantic segmentation of the dataset. Second, the combined point cloud filtering process based on radius filtering and statistical filtering is implemented on the segmented point cloud data. Third, an implicit surface reconstruction based on contextual prior information is implemented for offshore oil production equipment components. The dataset contains six types of point clouds, including pipelines, flanges, shelves, bends, valves, and oil recovery trees. Based on this dataset for semantic segmentation, the overall segmentation accuracy reaches 98.87% and the mIoU reaches 92.79%. Combined filtering is performed on the segmented offshore oil production equipment data, and the denoising rate can reach 94%. Finally, the denoised point cloud data is utilized for 3-D reconstruction, and the overall consistency accuracy can reach 1.85 mm, which can provide fast, efficient, and reliable data support for the upgrading of offshore oil rigs.