A Strategy of Subsea Pipeline Identification with Sidescan Sonar based on YOLOV5 Model

Abstract

Accurate identification of pipelines is the basis and prerequisite for tracking and inspection of subsea pipelines with the help of autonomous unmanned vehicles. In this paper, we proposed a strategy based on a deep learning model YOLOV5 to extract the subsea pipeline from acoustic images acquired by a Side scan sonar (SSS). Considering the imaging mechanisms of SSS, the formed bar image by SSS in a short certain period is segmented into many sub-images. Subsequently, these sub-images are fed into a pre-trained identification model based on YOLOV5 to extract the subsea pipelines. This strategy ensures the subsea pipeline could be detected with low time consumption and satisfactory accuracy. The average precision (AP) of our proposed subsea pipeline identification strategy achieved 97.62% with 304ms time consumption for the bar image formed in the 10s period. The experimental results demonstrate that the performance of the proposed subsea pipeline identification strategy is superior comparing with other state-of-the-art models in the performance of both identification and real-time.