Abstract
Automatic detection of underwater objects by sonar images is an important and challenging topic in applications of Autonomous Underwater Vehicle (AUV) under the complex marine environment. A detection method is proposed based on Multi-Scale Multi-Column Convolution Neural Networks (MSMC-CNNs). Firstly, the Multi-Scale Multi-Column CNNs is used to form an encoder network for extracting multi-scale features of the sonar image. Secondly, the bicubic linear interpolation algorithm is used as the deconvolution process of the decoder networks to restore the sonar image size and resolution. Moreover, a novel transfer learning manner based on progressive fine-tuning to accelerate the model training. Finally, the proposed method is validated on the sonar image dataset and is compared with other existing detection methods. The pixel accuracy (PA) of MSMC-CNNs for different categories sonar image is over 95%. The experiment results show that the MSMC-CNNs model has better detection effect and more robustness to noise.
Highlights
In Europe, the United States, and China pay much attention to marine research and have a deep foundation, and have conducted much research on the detection and localization of the underwater target
We proposed novel neural network MSMC-Convolutional neural networks (CNNs) for detection of underwater sonar image
To enhance the feature extraction capability of the encoder network, the multi-scale multi-column CNNs architecture is used to extract the features of sonar image
Summary
In Europe, the United States, and China pay much attention to marine research and have a deep foundation, and have conducted much research on the detection and localization of the underwater target. According to the imaging characteristics of the sonar target, Xie et al [18] establish the segmentation constraint condition, make use of the small gray mean ratio of the shadow to the target to carry on the initial segmentation, and remove the false target according to the width difference between the segmented target and the shadow This method takes into account the dependence between adjacent pixels and has the advantages of strong anti-noise and accurate segmentation. The parametric active contour model based on the local information of the image, which is affected by noise and the initial test curve must be close to the edge of the target in order to get the correct segmentation results [20].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
