Remote sensing has become a primary technology for monitoring raft aquaculture products. However, due to the complexity of the marine aquaculture environment, the boundaries of the raft aquaculture areas in remote sensing images are often blurred, which will result in ‘adhesion’ phenomenon in the raft aquaculture areas extraction. The fully convolutional network (FCN) based methods have made great progress in the field of remote sensing in recent years. In this paper, we proposed an FCN-based end-to-end raft aquaculture areas extraction model (which is called UPS-Net) to overcome the ‘adhesion’ phenomenon. The UPS-Net contains an improved U-Net and a PSE structure. The improved U-Net can simultaneously capture boundary and contextual information of raft aquaculture areas from remote sensing images. The PSE structure can adaptively fuse the boundary and contextual information to reduce the ‘adhesion’ phenomenon. We selected laver raft aquaculture areas in eastern Lianyungang in China as the research region to verify the effectiveness of our model. The experimental results show that compared with several state-of-the-art models, the proposed UPS-Net model performs better at extracting raft aquaculture areas and can significantly reduce the ‘adhesion’ phenomenon.

Sea-land segmentation of remote sensing images is of great significance to the dynamic monitoring of coastlines. However, the types of objects in the coastal zone are complex, and their spectra, textures, shapes, and distribution features are different. Therefore, sea-land segmentation for various types of coastlines is still a challenging task. In this paper, a scale-adaptive semantic segmentation network, called SANet, is proposed for sea-land segmentation of remote sensing images. SANet has made two innovations on the basis of the classic encoder-decoder structure. First, to integrate the spectral, textural and semantic features of ground objects at different scales, we designed an adaptive multi-scale feature learning module (AML) to replace the conventional serial convolution operation. The AML module mainly contains a multi-scale feature extraction unit and an adaptive feature fusion unit. The former can capture the multi-scale detailed information and contextual semantic information of objects from an early stage, while the latter can adaptively fuse feature maps of different scales. Second, we adopted the squeeze-and-excitation module to bridge the corresponding layers of the codec so that SANet can selectively emphasize the features of the weak sea-land boundaries. Experiments on a set of Gaofen-1 remote sensing images demonstrated that SANet achieved more accurate segmentation results and obtained sharper boundaries than other methods for various natural and artificial coastlines.

Due to the phenomenon of mixed pixels in low-resolution remote sensing images, the green tide spectral features with low Enteromorpha coverage are not obvious. Super-resolution technology based on deep learning can supplement more detailed information for subsequent semantic segmentation tasks. In this paper, a novel green tide extraction method for MODIS images based on super-resolution and a deep semantic segmentation network was proposed. Inspired by the idea of transfer learning, a super-resolution model (i.e., WDSR) is first pre-trained with high spatial resolution GF1-WFV images, and then the representations learned in the GF1-WFV image domain are transferred to the MODIS image domain. The improvement of remote sensing image resolution enables us to better distinguish the green tide patches from the surrounding seawater. As a result, a deep semantic segmentation network (SRSe-Net) suitable for large-scale green tide information extraction is proposed. The SRSe-Net introduced the dense connection mechanism on the basis of U-Net and replaces the convolution operations with dense blocks, which effectively obtained the detailed green tide boundary information by strengthening the propagation and reusing features. In addition, the SRSe-Net reducs the pooling layer and adds a bridge module in the final stage of the encoder. The experimental results show that a SRSe-Net can obtain more accurate segmentation results with fewer network parameters.

Semi-supervised classification methods result in higher performance for hyperspectral images, because they can utilize the relationship between unlabeled samples and labeled samples to obtain pseudo-labeled samples. However, how generating an effective training sample set is a major challenge for semi-supervised methods, In this paper, we propose a novel semi-supervised classification method based on extended label propagation (ELP) and a rolling guidance filter (RGF) called ELP-RGF, in which ELP is a new two-step process to make full use of unlabeled samples. The first step is to implement the graph-based label propagation algorithm to propagate the label information from labeled samples to the neighboring unlabeled samples. This is then followed by the second step, which uses superpixel propagation to assign the same labels to all pixels within the superpixels that are generated by the image segmentation method, so that some labels wrongly labeled by the above step can be modified. As a result, so obtained pseudo-labeled samples could be used to improve the performance of the classifier. Subsequently, an effective feature extraction method, i.e., RGF is further used to remove the noise and the small texture structures to optimize the features of the initial hyperspectral image. Finally, these produced initial labeled samples and high-confidence pseudo-labeled samples are used as a training set for support vector machine (SVM). The experimental results show that the proposed method can produce better classification performance for three widely-used real hyperspectral datasets, particularly when the number of training samples is relatively small.

Hyperspectral image classification methods may not achieve good performance when a limited number of training samples are provided. However, labeling sufficient samples of hyperspectral images to achieve adequate training is quite expensive and difficult. In this paper, we propose a novel sample pseudo-labeling method based on sparse representation (SRSPL) for hyperspectral image classification, in which sparse representation is used to select the purest samples to extend the training set. The proposed method consists of the following three steps. First, intrinsic image decomposition is used to obtain the reflectance components of hyperspectral images. Second, hyperspectral pixels are sparsely represented using an overcomplete dictionary composed of all training samples. Finally, information entropy is defined for the vectorized sparse representation, and then the pixels with low information entropy are selected as pseudo-labeled samples to augment the training set. The quality of the generated pseudo-labeled samples is evaluated based on classification accuracy, i.e., overall accuracy, average accuracy, and Kappa coefficient. Experimental results on four real hyperspectral data sets demonstrate excellent classification performance using the new added pseudo-labeled samples, which indicates that the generated samples are of high confidence.

The coastline extraction from remote-sensing images is of great significance to the dynamic monitoring of the coastal zone. The types of coastlines are complex and diverse, and they show different spectrum, texture, and shape features, so accurately extracting coastlines is still a challenging task. The semantic segmentation model based on deep learning has good generalization ability. However, the down sampling operation will lose the location of boundary information, resulting in the location offset between the extracted coastlines and the actual coastlines. A multi-task network, called the joint learning network of boundary and segmentation (BS-Net), was proposed in this letter. BS-Net adds a coastline positioning stream to supervise the location of the coastlines. Moreover, this letter designed a boundary-segmentation interaction (BSI) module for the mutual guidance of information between the coastline positioning stream and the sea-land segmentation stream to correct the coastline features and enhance the segmentation boundary. The experimental results on a set of Gaofen-1 remote sensing images showed that, for various natural coastlines and artificial coastlines, coastlines extracted based on BS-Net were more accurate than those extracted by other methods. Code is available at: https://github.com/weiAI1996/BS-Net.