Combining Segmentation Network and Nonsubsampled Contourlet Transform for Automatic Marine Raft Aquaculture Area Extraction from Sentinel-1 Images

Abstract

Marine raft aquaculture (MFA) plays an important role in the marine economy and ecosystem. With the characteristics of covering a large area and being sparsely distributed in sea area, MFA monitoring suffers from the low efficiency of field survey and poor data of optical satellite imagery. Synthetic aperture radar (SAR) satellite imagery is currently considered to be an effective data source, while the state-of-the-art methods require manual parameter tuning under the guidance of professional experience. To preclude the limitation, this paper proposes a segmentation network combined with nonsubsampled contourlet transform (NSCT) to extract MFA areas using Sentinel-1 images. The proposed method is highlighted by several improvements based on the feature analysis of MFA. First, the NSCT was applied to enhance the contour and orientation features. Second, multiscale and asymmetric convolutions were introduced to fit the multisize and strip-like features more effectively. Third, both channel and spatial attention modules were adopted in the network architecture to overcome the problems of boundary fuzziness and area incompleteness. Experiments showed that the method can effectively extract marine raft culture areas. Although further research is needed to overcome the problem of interference caused by excessive waves, this paper provides a promising approach for periodical monitoring MFA in a large area with high efficiency and acceptable accuracy.

Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement

“…Liu et al [20] introduced a change detection method based on mathematical morphology and a k-means clustering model, and the accuracy of the change detection improved. The nonsubsampled contourlet transform (NSCT) and nonsubsampled shearlet transform (NSST) are widely used in image fusion and denoising [21][22][23][24][25][26][27]. Chen et al [28] introduced the NSCT-hidden Markov tree (NSCT-HMT) model to the remote sensing image change detection; Li et al [29] proposed a multitemporal remote sensing image change detection algorithm based on the NSCT denoising model.…”

Mapping Aquaculture Areas with Multi-Source Spectral and Texture Features: A Case Study in the Pearl River Basin (Guangdong), China

“…Synthetic aperture radar (SAR) images are also used for aquaculture mapping [14,29]. For examples, Hu et al [29] detected floating raft aquaculture from SAR image using statistical region merging and contour feature; Ottinger et al [14] employed time series Sentinel-1 images and object-based approach to map aquaculture ponds over river basins; and Zhang et al [30] mapped marine raft aquaculture areas using a deep learning approach by enhancing the contour and orientation features of Sentinel-1 images.…”

Editorial for the Special Issue “Remote Sensing of the Oceans: Blue Economy and Marine Pollution”

“…Detection of targets such as marine raft aquaculture, moving vessels, and the shoreline [1][2][3]; • Observation of spatio-temporal pattern of oil spills and coastal marine litter [4][5][6]; • Study of natural sea processes, including typhoon-induced storm surges, sub-mesoscale eddies and migration of the along-slope counter-flow [7][8][9]; • Analysis of scattering and spectral properties of the sea surface [10,11].…”

“…Those goals have been pursued using multi-platform and multi-frequency remote sensing tools together with theoretical models, numerical simulations, and in-situ measurements. Most of the study exploited satellite data, including microwave-synthetic aperture radar (SAR) imagery collected in single-, dual-and quad-polarimetric imaging modes, radar altimeters [1][2][3][4][5]7,11], and optical-spin-scanning radiometers and spectroradiometers [7,8]. Other studies used airborne or shore-based sensors, including UAV cameras and high-frequency (HF) coastal radars [6,9].…”

“…In [1], single-polarization (under vertical transmit) C-band Sentinel-1 SAR satellite data are exploited to detect marine raft aquaculture in coastal areas. To this aim, a segmentation network combined with a non-subsampled contourlet transform is proposed to extract the sea area covered by the raft aquacultures.…”