Recent advances in deep learning have shown remarkable performance in road segmentation from remotely sensed images. However, these methods based on convolutional neural networks (CNNs) cannot obtain long-range dependency and global contextual information because of the intrinsic inductive biases. Motivated by the success of Transformer in computer vision (CV), excellent models based on Transformer are emerging endlessly. However, patches with a fixed scale limit the further improvement of the model performance. To address this problem, a dual-resolution road segmentation network (DCS-TransUperNet) with a features fusion module (FFM) was proposed for road segmentation. Firstly, the encoder of DCS-TransUperNet was designed based on CSwin Transformer, which uses dual subnetwork encoders of different scales to obtain the coarse and fine-grained feature representations. Secondly, a new FFM was constructed to build enhanced feature representation with global dependencies, using different scale features from the subnetwork encoders. Thirdly, a mixed loss function was designed to avoid the local optimum caused by the imbalance between road and background pixels. Experiments using the Massachusetts dataset and DeepGlobe dataset showed that the proposed DCS-TransUperNet could effectively solve the discontinuity problem and preserve the integrity of the road segmentation results, achieving a higher IoU (65.36% on Massachusetts dataset and 56.74% on DeepGlobe) of road segmentation compared to other state-of-the-art methods. The considerable performance also proves the powerful generation ability of our method.

Cloud detection is an important step in the processing of optical satellite remote-sensing data. In recent years, deep learning methods have achieved excellent results in cloud detection tasks. However, most of the current models have difficulties to accurately classify similar objects (e.g., clouds and snow) and to accurately detect clouds that occupy a few pixels in an image. To solve these problems, a cloud-detection framework (Cloudformer) combining CNN and Transformer is being proposed to achieve high-precision cloud detection in optical remote-sensing images. The framework achieves accurate detection of thin and small clouds using a pyramidal structure encoder. It also achieves accurate classification of similar objects using a dual-path decoder structure of CNN and Transformer, reducing the rate of missed detections and false alarms. In addition, since the Transformer model lacks the perception of location information, an asynchronous position-encoding method is being proposed to enhance the position information of the data entering the Transformer module and to optimize the detection results. Cloudformer is experimented on two datasets, AIR-CD and 38-Cloud, and the results show that it has state-of-the-art performance.

In this study, the indoor air quality (IAQ) was investigated in a subway station with fully enclosed platform screen doors in Beijing, China. Eight indoor air pollutants, including PM_2.5, PM₁₀, SO₂ (sulfur dioxide), NO₂ (nitrogen dioxide), NH₃ (ammonia), CO (carbon monoxide), CH₂O (formaldehyde) and TVOC (total volatile organic compound), were measured for six consecutive days in October 2019. The results indicated that the IAQ in the subway station was basically stable at good levels for most times during the whole measurement period. All eight indoor air pollutants were far below their corresponding maximum allowable concentrations, except for the PM_2.5 concentrations, which occasionally exceeded the concentration limits. The concentrations of indoor air pollutants in the subway station were basically within the corresponding standards. The correlation analyses showed that outdoor air pollutants have important influences on indoor air pollutants. The concentrations of PM₁₀, PM_2.5, SO₂, NO₂ and CO in the subway station were positively correlated with their corresponding outdoor concentrations. PM₁₀ was statistically significantly correlated with the passenger flow and train frequency, but the other air pollutants were less impacted by the passenger flow and train frequency.

In the era of remote sensing big data, synthetic aperture radar (SAR) image interpretation is a great scientific application challenge [1]. The automatic detection and identification of targets are the hot spots and focuses of this research field. In general, the SAR image detection and recognition method require multiple independent steps such as filtering, edge extraction, image segmentation and target recognition. The complexity of the process not only reduces the efficiency of target detection and recognition of SAR images, but also loses a lot of key image features to a certain extent, which makes it difficult to further process SAR images and restrain the accuracy of detection and recognition. Therefore, this paper presents a method for automatic detection and recognition of SAR image targets based on convolution neural network (CNN). By using the CNN model to conduct target detection and recognition experiment on the moving and stationary target acquisition and recognition (MSTAR) benchmark dataset, we verify the validity of the deep neural network in the field of SAR image target recognition, which lays the foundation for further research in this field.

In recent years, the application of semantic segmentation methods based on the remote sensing of images has become increasingly prevalent across a diverse range of domains, including but not limited to forest detection, water body detection, urban rail transportation planning, and building extraction. With the incorporation of the Transformer model into computer vision, the efficacy and accuracy of these algorithms have been significantly enhanced. Nevertheless, the Transformer model’s high computational complexity and dependence on a pre-training weight of large datasets leads to a slow convergence during the training for remote sensing segmentation tasks. Motivated by the success of the adapter module in the field of natural language processing, this paper presents a novel adapter module (ResAttn) for improving the model training speed for remote sensing segmentation. The ResAttn adopts a dual-attention structure in order to capture the interdependencies between sets of features, thereby improving its global modeling capabilities, and introduces a Swin Transformer-like down-sampling method to reduce information loss and retain the original architecture while reducing the resolution. In addition, the existing Transformer model is limited in its ability to capture local high-frequency information, which can lead to an inadequate extraction of edge and texture features. To address these issues, this paper proposes a Local Feature Extractor (LFE) module, which is based on a convolutional neural network (CNN), and incorporates multi-scale feature extraction and residual structure to effectively overcome this limitation. Further, a mask-based segmentation method is employed and a residual-enhanced deformable attention block (Deformer Block) is incorporated to improve the small target segmentation accuracy. Finally, a sufficient number of experiments were performed on the ISPRS Potsdam datasets. The experimental results demonstrate the superior performance of the model described in this paper.

Road segmentation is one of the essential tasks in remote sensing. Large-scale high-resolution remote sensing images originally have larger pixel sizes than natural images, while the existing models based on Transformer have the high computational cost of square complexity, leading to more extended model training and inference time. Inspired by the long text Transformer model, this paper proposes a novel hybrid attention mechanism to improve the inference speed of the model. By calculating several diagonals and random blocks of the attention matrix, hybrid attention achieves linear time complexity in the token sequence. Using the superposition of adjacent and random attention, hybrid attention introduces the inductive bias similar to convolutional neural networks (CNNs) and retains the ability to acquire long-distance dependence. In addition, the dense road segmentation result of remote sensing image still has the problem of insufficient continuity. However, multiscale feature representation is an effective means in the network based on CNNs. Inspired by this, we propose a multi-scale patch embedding module, which divides images by patches with different scales to obtain coarse-to-fine feature representations. Experiments on the Massachusetts dataset show that the proposed HA-RoadFormer could effectively preserve the integrity of the road segmentation results, achieving a higher Intersection over Union (IoU) 67.36% of road segmentation compared to other state-of-the-art (SOTA) methods. At the same time, the inference speed has also been greatly improved compared with other Transformer based models.