Zero-Shot Pipeline Detection for Sub-Bottom Profiler Data Based on Imaging Principles

Abstract

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.

Research on the Application of Visual Recognition in the Engine Room of Intelligent Ships

“…It is also an essential part of many other tasks, such as semantic segmentation [ 4 ], object tracking [ 5 ], and scene description [ 6 ]. In recent years, significant breakthroughs have been made In marine and ocean engineering, such as automatic ship identification systems [ 7 ], detection of alien species in ports [ 8 ], undersea exploration [ 9 ], marine farming, and fishing [ 10 ], etc.…”

Shallow mud detection algorithm for submarine channels based on improved YOLOv5s

“…The rapid advancement of acoustic technology has led to the widespread utilization of sub-bottom profilers in the detection of submarine sediment. These profilers are employed in various applications including submarine geological classification [ [20] , [21] , [22] ], research on submarine disasters [ [23] , [24] , [25] ], and exploration of submarine pipelines [ 26 , 27 ]. This is due to their high accuracy, non-immersibility, real-time data display, portability, ease of operation, strong penetration, and relatively minimal attenuation in liquid [ 28 , 29 ].…”

A localization method for subsea pipeline based on active magnetization

“…Lidar, underwater cameras, side-scan sonar and forward sonar can only detect exposed uncovered subsea pipelines and cannot detect buried subsea pipelines [6][7][8][9]. Sub-bottom profiling sonar can penetrate a certain depth of the seabed to detect buried pipelines, and when it moves perpendicular to the pipeline, it can detect the arc profile of the pipeline [10,11]. Sub-bottom profiling sonar cannot locate the pipeline when the carrier AUV moves longitudinally along the pipeline, so it is not used to track subsea pipelines.…”