Very high resolution (VHR) remote sensing imagery has been used for land cover classification, and it tends to a transition from land-use classification to pixel-level semantic segmentation. Inspired by the recent success of deep learning and the filter method in computer vision, this work provides a segmentation model, which designs an image segmentation neural network based on the deep residual networks and uses a guided filter to extract buildings in remote sensing imagery. Our method includes the following steps: first, the VHR remote sensing imagery is preprocessed and some hand-crafted features are calculated. Second, a designed deep network architecture is trained with the urban district remote sensing image to extract buildings at the pixel level. Third, a guided filter is employed to optimize the classification map produced by deep learning; at the same time, some salt-and-pepper noise is removed. Experimental results based on the Vaihingen and Potsdam datasets demonstrate that our method, which benefits from neural networks and guided filtering, achieves a higher overall accuracy when compared with other machine learning and deep learning methods. The method proposed shows outstanding performance in terms of the building extraction from diversified objects in the urban district.

The road network plays an important role in the modern traffic system; as development occurs, the road structure changes frequently. Owing to the advancements in the field of high-resolution remote sensing, and the success of semantic segmentation success using deep learning in computer version, extracting the road network from high-resolution remote sensing imagery is becoming increasingly popular, and has become a new tool to update the geospatial database. Considering that the training dataset of the deep convolutional neural network will be clipped to a fixed size, which lead to the roads run through each sample, and that different kinds of road types have different widths, this work provides a segmentation model that was designed based on densely connected convolutional networks (DenseNet) and introduces the local and global attention units. The aim of this work is to propose a novel road extraction method that can efficiently extract the road network from remote sensing imagery with local and global information. A dataset from Google Earth was used to validate the method, and experiments showed that the proposed deep convolutional neural network can extract the road network accurately and effectively. This method also achieves a harmonic mean of precision and recall higher than other machine learning and deep learning methods.

Recent advances in deep-learning methods have shown extraordinary performance in road extraction from high resolution satellite imagery. However, most existing deep-learning network models yield discontinuous and incomplete results because of shadows and occlusions. To address this problem, a dual-attention road extraction network (DA-RoadNet) with a certain semantic reasoning ability is proposed. First, DA-RoadNet is designed based on a shallow encoder-to-decoder network with densely connected blocks, which can minimize the loss of road structure information caused by multiple down-sampling operations. Moreover, by constructing a novel attention mechanism module, the proposed network is able to explore and integrate the invisible correlations among road features with their global dependency in spatial and channel dimension respectively. Finally, considering that the proportion of road samples is small in the satellite imagery, a hybrid loss function is appended to handle class imbalance, which enables the network model to train stablely and avoid local optimum. The validation experiments using two open road datasets demonstrate that the proposed DA-RoadNet can effectively solve discontinuous problems and preserve integrity of the extracted roads, thus resulting in a higher accuracy of road extraction compared with other developed state-of-the-arts. The considerable performance on the two challenging benchmarks also proves the powerful generation ability of our method.

Resolution is a comprehensive reflection and evaluation index for the visual quality of remote sensing images. Super-resolution processing has been widely applied for extracting information from remote sensing images. Recently, deep learning methods have found increasing application in the super-resolution processing of remote sensing images. However, issues such as blurry object edges and existing artifacts persist. To overcome these issues, this study proposes an improved generative adversarial network with self-attention and texture enhancement (TE-SAGAN) for remote sensing super-resolution images. We first designed an improved generator based on the residual dense block with a self-attention mechanism and weight normalization. The generator gains the feature extraction capability and enhances the training model stability to improve edge contour and texture. Subsequently, a joint loss, which is a combination of L1-norm, perceptual, and texture losses, is designed to optimize the training process and remove artifacts. The L1-norm loss is designed to ensure the consistency of low-frequency pixels; perceptual loss is used to entrench medium- and high-frequency details; and texture loss provides the local features for the super-resolution process. The results of experiments using a publicly available dataset (UC Merced Land Use dataset) and our dataset show that the proposed TE-SAGAN yields clear edges and textures in the super-resolution reconstruction of remote sensing images.

Volunteered geographic information (VGI), OpenStreetMap (OSM), has been used in many applications, especially when official spatial data are unavailable or outdated. However, the quality of VGI remains a valid concern. In this paper, we use the matched results between OSM building footprints and official data as the samples for training an autoencoder network, which encodes and reconstructs the sample populations according to unknown complex multivariate probability distributions. Then, the OSM data are assessed based on the theory that small probability samples contribute little to the autoencoder network and that they can be recognized by the higher reconstructed errors during training. In the method described here, the selected measures, including data completeness, positional accuracy, shape accuracy, semantic accuracy and orientation consistency between OSM and official data, are used as the inputs for a deep autoencoder network. Finally, building footprint data from Toronto, Canada, are evaluated, and experiments show that the proposed method can assess the OSM data comprehensively, objectively and accurately.

One major limitation of remote-sensing images is bad weather conditions, such as haze. Haze significantly reduces the accuracy of satellite image interpretation. To solve this problem, this paper proposes a novel unsupervised method to remove haze from high-resolution optical remote-sensing images. The proposed method, based on cycle generative adversarial networks, is called the edge-sharpening cycle-consistent adversarial network (ES-CCGAN). Most importantly, unlike existing methods, this approach does not require prior information; the training data are unsupervised, which mitigates the pressure of preparing the training data set. To enhance the ability to extract ground-object information, the generative network replaces a residual neural network (ResNet) with a dense convolutional network (DenseNet). The edge-sharpening loss function of the deep-learning model is designed to recover clear ground-object edges and obtain more detailed information from hazy images. In the high-frequency information extraction model, this study re-trained the Visual Geometry Group (VGG) network using remote-sensing images. Experimental results reveal that the proposed method can recover different kinds of scenes from hazy images successfully and obtain excellent color consistency. Moreover, the ability of the proposed method to obtain clear edges and rich texture feature information makes it superior to the existing methods.