Fused Adaptive Receptive Field Mechanism and Dynamic Multiscale Dilated Convolution for Side-Scan Sonar Image Segmentation
- 24 August 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-17
Abstract
Side-scan sonar (SSS) is a vital sensor for marine survey, which is widely used in military and civilian fields. The accurate segmentation of SSS images is critical in sonar image intelligent interpretation. Existing SSS image segmentation methods have several limitations, such as insufficient feature extraction, relatively worse segmentation results for tiny target categories, and serious interference by seabed reverberation noise and bright shadow region. To overcome these issues, we propose a novel encoder–decoder architecture SSS image segmentation method based on convolution neural network (CNN). First, we extract the multiscale feature information contained in target region using the dynamic multiscale dilated convolution (DMDC_Conv). Second, to further obtain the global and detail feature information, we construct the adaptive receptive field mechanism block (ARFM_Block). Third, we design a feature fusion attention mechanism block (FFAM_Block) to fuse high-level and low-level feature information with different scales and suppress background information interference. Final, we construct a tree structure optimization module (TSOM) to solve the problem of pixel misclassification and obtain refine SSS image segmentation results. Extensive experiments are carried out on the constructed real scene SSS image dataset. The experimental results show that the proposed method achieves 93.24% and 90.82% of mean pixel accuracy (MPA) and mean intersection over union (MIoU), respectively, which outperforms the other state-of-the-art methods and has a substantial advantage in inference speed and calculation parameters.Keywords
Funding Information
- Neural Science Foundation of Shanxi Province (2021JQ-879)
- Jiangsu Innovation and Entrepreneurship Program (184080H10827)
- Shaanxi Key Laboratory of Integrated and Intelligent Navigation open fund (SKLIIN-20180211)
- Shaanxi Province Key Research and Development Program (2021GY-341, 2022GY-118)
This publication has 48 references indexed in Scilit:
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- High-frequency side-scan sonar fish reconnaissance by autonomous underwater vehiclesCanadian Journal of Fisheries and Aquatic Sciences, 2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- A fuzzy clustering image segmentation algorithm based on Hidden Markov Random Field models and Voronoi TessellationPattern Recognition Letters, 2017
- Narrowband Chan-Vese model of sonar image segmentation: A adaptive ladder initialization approachApplied Acoustics, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- A Robust and Fast Method for Sidescan Sonar Image Segmentation Using Nonlocal Despeckling and Active Contour ModelIEEE Transactions on Cybernetics, 2016
- Fully convolutional networks for semantic segmentation2015
- Sonar image segmentation based on GMRF and level-set modelsOcean Engineering, 2010
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007