U_EFF_NET: High-Precision Segmentation of Offshore Farms From High-Resolution SAR Remote Sensing Images

Abstract

Offshore aquaculture promotes the development of aquaculture industry and brings huge economic benefits to fishermen, while seriously affecting the near-coast environment. Accurate access to the range of offshore farms at home and abroad is of great significance for marine disaster warning and coastal management. Remote sensing is a very effective means of observing offshore farms. Offshore farms segmentation technology is more mature in high-resolution optical images. SAR images have the advantage of being available all day and all night. Using SAR images to extract offshore farms has become a recent research hotspot. Gaofen-3 and HISEA-1 satellites have high-resolution marine observation capabilities. Combined with their super observation capabilities, this paper proposes a technical solution to extract offshore farms using Gaofen-3 and HISEA-1 imags. Firstly, the combine-crop component module is proposed to create a new SAR images dataset based the original dataset. Next, common data augmentation methods such as flip, rotate, and copy-paste are used, the online multi-scale resolution image expansion is proposed to enrich the dataset and enlarge the data volume. Finally, the U_EFF_NET model is proposed. The model uses encoder-decoder structure and the light-weight feature extraction network EfficientNet-b0 as backbone. The decoder embeds the attention mechanism. The optimization strategy uses joint loss function to achieve multi-task learning, and the OHEM strategy is added to the joint loss function. The method proposed in this paper has high accuracy and high practicality as the frequency-weight intersection ratio of the extracted results on the test set is 98.12%. And the inference time is at the forefront.

Marine Infrastructure Detection with Satellite Data—A Review

“…The largest share of Deep Learning approaches was represented by the encoder-decoder architecture UNet. With 12 applications [31,39,50,62,[67][68][69]72,73,80,83,115], UNet is the most frequently used technology of all the articles reviewed. The U-Net model, originally developed for biomedical image segmentation [116], gained considerable attention due to its outstanding performance when published and its clear, structured design.…”

“…The fields of application and infrastructures detected with radar data are diverse. Of the total of 32 reviewed articles (35%), aquaculture was identified in 11 [39,49,50,59,62,67,68,70,93,114,115], platforms in 18 [14,17,38,43,[95][96][97][98][99][100][101][104][105][106], OWFs in five [41,42,51,107,108], and bridges in 2 [44,45]. The one study that used hyperspectral satellite data used them to detect aquaculture [64].…”

An Attention-Fused Deep Learning Model for Accurately Monitoring Cage and Raft Aquaculture at Large-Scale Using Sentinel-2 Data

“…For example, Cui et al [23] created a reverse attention module that suppresses seawater features, enabling the learning characteristics for both apparent and inapparent aquaculture sites. Qin et al [24] embedded the convolutional block attention module (CBAM) [25] into the decoder of the network they proposed to gain accurate feature maps for offshore farm extraction, etc.…”