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. Firstly, 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 downsampling 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 stateof-the-arts. The considerable performance on the two challenging benchmarks also proves the powerful generation ability of our method.

is used to capture the abundant word level features, grammatical structure features and semantic features in sentences. The self-learning strategy assisted by domain knowledge can automatically construct the domain training corpus without manual intervention. A set of experiments to verify the effectiveness of the proposed method on an available manually constructed hybrid dataset.

Road networks play an important role in navigation and city planning. However, current methods mainly adopt the supervised strategy that needs paired remote sensing images and segmentation images. These data requirements are difficult to achieve. The pair segmentation images are not easy to prepare. Thus, to alleviate the burden of acquiring large quantities of training images, this study designed an improved generative adversarial network to extract road networks through a weakly supervised process named WSGAN. The proposed method is divided into two steps: generating the mapping image and post-processing the binary image. During the generation of the mapping image, unlike other road extraction methods, this method overcomes the limitations of manually annotated segmentation images and uses mapping images that can be easily obtained from public data sets. The residual network block and Wasserstein generative adversarial network with gradient penalty loss were used in the mapping network to improve the retention of high-frequency information. In the binary image post-processing, this study used the dilation and erosion method to remove salt-and-pepper noise and obtain more accurate results. By comparing the generated road network results, the Intersection over Union scores reached 0.84, the detection accuracy of this method reached 97.83%, the precision reached 92.00%, and the recall rate reached 91.67%. The experiments used a public dataset from Google Earth screenshots. Benefiting from the powerful prediction ability of GAN, the experiments show that the proposed method performs well at extracting road networks from remote sensing images, even if the roads are covered by the shadows of buildings or trees.

Many natural language tasks related to geographic information retrieval (GIR) require toponym recognition, and identifying Chinese toponyms from social media messages to share real-time information is a critical problem for many practical applications, such as natural disaster response and geolocating. In this article, we focused on toponym recognition from social media messages in Chinese. While existing off-the-shelf Chinese named entity recognition (NER) tools could be applied to identify toponyms, these approaches cannot address a variety of language irregularities taken from social media messages, including location name abbreviations, informal sentence structures and combination toponyms. We present a deep neural network named BERT-BiLSTM-CRF, which extends a basic bidirectional recurrent neural network model (BiLSTM) with the pretraining bidirectional encoder representation from transformers (BERT) representation to handle the toponym recognition task in Chinese text. Using three datasets taken from lists of alternative location names, the experimental results showed that the proposed model can significantly outperform previous Chinese NER models/algorithms and a set of state-of-the-art deep learning models.

No abstract