Sub-bottom profiler (SBP) measurements play a very important role in marine pipeline detection and checking. However, sometimes because of bad sea conditions and complex underwater environments, only poor SBP images can be obtained. Pipeline recognition based on a poor SBP image manually is tedious and has low accuracy. In this article, based on the specific hyperbola shapes caused by pipelines on SBP images, a novel method to detect the marine pipelines automatically and robustly is presented. Two main steps are used. First, a comprehensive edge extraction method is proposed, which includes line-like structure enhancement and preliminary edge extraction, local phase calculation and phase edge extraction, final edge extraction, as well as edge processing. By applying this method, interference such as reverberation can be eliminated, and fine hyperbola edges can be obtained. Second, by referencing the theoretical hyperbola and using a buffer zone and a hyperbola contour consistency (HCC) criterion, the location of the pipeline can be determined robustly. This method was implemented and verified using data collected under real conditions. The results show that the proposed method is practicable.

Due to the influence of equipment instability and surveying environment, scattering echoes and other factors, it is sometimes difficult to obtain high-quality sub-bottom profile (SBP) images by traditional denoising methods. In this paper, a novel SBP image denoising method is developed for obtaining underlying clean images based on a non-local low-rank framework. Firstly, to take advantage of the inherent layering structures of the SBP image, a direction image is obtained and used as a guidance image. Secondly, the robust guidance weight for accurately selecting the similar patches is given. A novel denoising method combining the weight and a non-local low-rank filtering framework is proposed. Thirdly, after discussing the filtering parameter settings, the proposed method is tested in actual measurements of sub-bottom, both in deep water and shallow water. Experimental results validate the excellent performance of the proposed method. Finally, the proposed method is verified and compared with other methods quantificationally based on the synthetic images and has achieved the total average peak signal-to-noise ratio (PSNR) of 21.77 and structural similarity index (SSIM) of 0.573, which is far better than other methods.

Traditional manual horizon picking is time-consuming and laborious, while automatic picking methods often suffer from the limited scope of their applications and the discontinuity of picked results. In this paper, we propose a novel method for automatic horizon picking from sub-bottom profiles (SBP) by an improved filtering algorithm. First, a clear and fine SBP image is formed using an intensity transformation method. On this basis, a novel filtering method is proposed by improving the multi-scale enhancement filtering algorithm to obtain clear horizons from an SBP image. The improvement is performed by applying a vertical suppression weighting term based on the form of logistic function, which is constructed by using the eigenvectors from the Hessian matrix. Then, the filtered image is segmented using a threshold method, and the horizon points in the SBP image are picked. After that, a horizon linking method is applied, which uses the horizon directions to refine the picked horizon points. The proposed method has been verified experimentally, and accurate and continuous horizons were obtained. Finally, the proposed method is discussed and some conclusions are drawn.

Manual horizon picking and semiautomatic horizon picking are the traditional methods for data processing of subbottom profiles (SBPs). However, the former is time consuming and laborsome, whereas the latter requires frequent manual intervention and easily suffers from low accuracy and discontinuous picking due to noises. A comprehensive and automatic horizon picking method is proposed by combining the given gray mutation, horizon tracking and filtering, and horizon growth algorithms in this paper. Based on the peaks and valleys corresponding to the strong and weak impedance contrasts in an echo sequence, the gray mutation is used to prepick horizons from a SBP image. According to sediment layer continuity and horizontal resolution, the horizon tracking and filtering are applied to construct discrete horizon segments and remove outliers. In consideration of the correlation of adjacent ping sequences and the horizon orientation, the horizon growth based on the horizon orientation constraints is utilized to connect the discrete horizon segments. Experiments validated the proposed method. The automatic horizon picking results were compared with the bore-hole data and the manual horizon picking results as well, and good consistencies were achieved. The determinations of parameters and the performance of the proposed method are discussed based on the theoretical study and experiments, and some conclusions are drawn.

With the increasing number of underwater pipeline investigation activities, the research on automatic pipeline detection is of great significance. At this stage, object detection algorithms based on Deep Learning (DL) are widely used due to their abilities to deal with various complex scenarios. However, DL algorithms require massive representative samples, which are difficult to obtain for pipeline detection with sub-bottom profiler (SBP) data. In this paper, a zero-shot pipeline detection method is proposed. First, an efficient sample synthesis method based on SBP imaging principles is proposed to generate samples. Then, the generated samples are used to train the YOLOv5s network and a pipeline detection strategy is developed to meet the real-time requirements. Finally, the trained model is tested with the measured data. In the experiment, the trained model achieved a mAP@0.5 of 0.962, and the mean deviation of the predicted pipeline position is 0.23 pixels with a standard deviation of 1.94 pixels in the horizontal direction and 0.34 pixels with a standard deviation of 2.69 pixels in the vertical direction. In addition, the object detection speed also met the real-time requirements. The above results show that the proposed method has the potential to completely replace the manual interpretation and has very high application value.