Search

The existing leak detection methods of submarine oil pipelines mainly rely on compositing synthetic aperture radar (SAR) satellite images to detect oil spills on the sea surface or installing underwater cameras to monitor the joints of submarine pipelines manually. The former is poor in timeliness and high in cost, while the latter is inflexible. Aiming at this, this letter studies the underwater image processing method of intelligent oil spill recognition using an underwater camera. Nevertheless, this method is currently faced with challenges, such as poor quality of datasets, unclear goals, and scarce quantity. The U-Net++ algorithm can theoretically reduce the dependence on the number of datasets. However, the pixel feature extraction method used by U-Net++ is difficult to achieve the segmentation effect of oil spill images, so a new network architecture suitable superpixel with texture (SSWT)-UNet++ based on texture superpixel is proposed. In SSWT-UNet++, the input is the oil spill image with texture superpixel division, and the output was changed to the middle layer. In addition, the resolution of each layer and the ratio of up/downsampling were adjusted. This algorithm completes the classification of oil spill texture superpixels and finally realizes oil spill detection according to the minimum bounding rectangle of the classification result of the oil spill region. Experimental verification shows that the final detection effect of the proposed algorithm is higher than that of other algorithms with an average precision (AP) of 0.985. [ABSTRACT FROM AUTHOR]