Fabric quality plays a crucial role in modern textile industry processes. How to detect fabric defects quickly and effectively has become the main research goal of researchers. The You Only Look Once (YOLO) series of networks have maintained a dominant position in the field of target detection. However, detecting small-scale objects, such as tiny targets in fabric defects, is still a very challenging task for the YOLOv4 network. To address this challenge, this paper proposed an improved YOLOv4 target detection algorithm: using a combined data augmentation method to expand the dataset and improve the robustness of the algorithm, obtaining the anchors suitable for fabric defect detection by using the k-means algorithm to cluster the ground truth box of the dataset, adding a new prediction layer in yolo_head in order to have a better effect on tiny target detection, integrating a convolutional block attention module into the backbone feature extraction network, and innovatively replacing the CIOU loss function with the CEIOU loss function to achieve accurate classification and localization of defects. Experimental results show that compared with the original YOLOv4 algorithm, the detection accuracy of the improved YOLOv4 algorithm for tiny targets has been greatly increased, the AP value of tiny target detection has increased by 12%, and the overall mean average precision (mAP) has increased by 3%. The prediction results of the proposed algorithm can provide enterprises with more accurate defect positioning, reduce the defect rate of fabric products, and improve their economic effect.

Soil moisture (SM) is a key parameter of the hydrological process, which affects exchanges of water and heat at the land/atmosphere interface. The “trapezoid” (or “triangle”) method has been widely applied to SM monitoring based on the pixel distribution within the thermal and optical remote sensing observations. However, the trapezoid method is a linear empirical model highly related to the retrieval accuracy of the surface temperature. In the article, the moderate-resolution imaging spectroradiometer (MODIS) data were applied to retrieve SM through an improved method over the Tibetan Plateau. The improved method is integrated with the “trapezoid” model and multiple learning techniques, Random Forest (RF) and Extreme Gradient Boosting (XGBoost). Meanwhile, RF and XGBoost were both trained with SM target data (the scale of SM and soil temperature) derived from the Tibetan Plateau observations, and the input variables were derived from MODIS observations. Compared with the SM measured, the results showed the root mean square error, the mean absolute error, and the correlation coefficient of the ensemble retrievals were 0.046-0.081 m ³ m ^-3 , 0.030-0.065 m ³ m ^-3 , and 0.60-0.87, respectively, which is better than that of the separate model. The ideas to implement the combination of traditional inversion algorithms and machine learning methods are helpful for researches in remote sensing fields.

Semantic segmentation using adversarial networks has proved to be effective in image processing fields. However, two problems need to be solved in the field of the road segmentation of unmanned aerial vehicle (UAV) remote sensing images. One is the occupied proportion of road area in UAV remote sensing images; the other is that the constant size of convolutional kernel cannot deal with multiscale feature very well. To solve these two problems, this paper proposed a road segmentation model that combined the adversarial networks with multiscale context aggregation. First, the output feature-maps of three scales (0.5n, 1n, 2n) were obtained, based on an end-to-end training from image segmentation network. Second, after the convolution and deconvolution operations, the processed images were unified to the size scale of original images. Third, with the pixel-by-pixel addition method, the three scales of image feature (0.5n, 1n, 2n) were merged together, then inputted into the discriminative network. Finally, the errors were obtained and propagated backwards compared with the label, and then the parameters of a generative network and a discriminative network could be updated. Further, the segmented results were compared with those from normal adversarial networks, Linknet and D-linknet, and were developed with the morphological operation. The research results show that the proposed model can improve the precision of road segmentation from UAV images with multiscale context aggregation and the regularization property of adversarial networks.

Roads are vital components of infrastructure, the extraction of which has become a topic of significant interest in the field of remote sensing. Because deep learning has been a popular method in image processing and information extraction, researchers have paid more attention to extracting road using neural networks. This article proposes the improvement of neural networks to extract roads from Unmanned Aerial Vehicle (UAV) remote sensing images. D-Linknet was first considered for its high performance; however, the huge scale of the net reduced computational efficiency. With a focus on the low computational efficiency problem of the popular D-LinkNet, this article made some improvements: (1) Replace the initial block with a stem block. (2) Rebuild the entire network based on ResNet units with a new structure, allowing for the construction of an improved neural network D-Linknetplus. (3) Add a 1 × 1 convolution layer before DBlock to reduce the input feature maps, reducing parameters and improving computational efficiency. Add another 1 × 1 convolution layer after DBlock to recover the required number of output channels. Accordingly, another improved neural network B-D-LinknetPlus was built. Comparisons were performed between the neural nets, and the verification were made with the Massachusetts Roads Dataset. The results show improved neural networks are helpful in reducing the network size and developing the precision needed for road extraction.

In current times, reconstruction of remote sensing images using super-resolution is a prominent topic of study. Remote sensing data have a complex spatial distribution. Compared with natural pictures, remote sensing pictures often contain subtler and more complicated information. Most super-resolution reconstruction algorithms cannot restore all the information contained in remote sensing images when reconstructing them. The content of some areas in the reconstructed images may be too smooth, and some areas may even have color changes, resulting in lower quality reconstructed images. In response to the problems presenting in current reconstruction algorithms about super-resolution, this article proposes the SRGAN-MSAM-DRC model (SRGAN model with multi-scale attention mechanism and dense residual connection). This model roots in generative adversarial networks and incorporates multi-scale attention mechanisms and dense residual connections into the generator. Furthermore, residual blocks are incorporated into the discriminator. We use some remote sensing image datasets of real-world data to evaluate this model, and the results indicate the SRGAN-MSAM-DRC model has shown enhancements in three evaluation metrics for reconstructed images about super-resolution. Compared to the basic SRGAN model, the SSIM (structural similarity), PSNR (peak signal-to-noise ratio), and IE (image entropy) increase by 5.0%, 4.0%, and 4.1%, respectively. From the results, we know the quality of the reconstructed images of remote sensing using the SRGAN-MSAM-DRC model is better than basic SRGAN model, and verifies that the model has good applicability and performance in reconstruction of remote sensing images using super-resolution.

With the development of deep learning and remote sensing technologies in recent years, many semantic segmentation methods based on convolutional neural networks (CNNs) have been applied to road extraction. However, previous deep learning-based road extraction methods primarily used RGB imagery as an input and did not take advantage of the spectral information contained in hyperspectral imagery. These methods can produce discontinuous outputs caused by objects with similar spectral signatures to roads. In addition, the images obtained from different Earth remote sensing sensors may have different spatial resolutions, enhancing the difficulty of the joint analysis. This work proposes the Multiscale Fusion Attention Network (MSFANet) to overcome these problems. Compared to traditional road extraction frameworks, the proposed MSFANet fuses information from different spectra at multiple scales. In MSFANet, multispectral remote sensing data is used as an additional input to the network, in addition to RGB remote sensing data, to obtain richer spectral information. The Cross-source Feature Fusion Module (CFFM) is used to calibrate and fuse spectral features at different scales, reducing the impact of noise and redundant features from different inputs. The Multiscale Semantic Aggregation Decoder (MSAD) fuses multiscale features and global context information from the upsampling process layer by layer, reducing information loss during the multiscale feature fusion. The proposed MSFANet network was applied to the SpaceNet dataset and self-annotated images from Chongzhou, a representative city in China. Our MSFANet performs better over the baseline HRNet by a large margin of +6.38 IoU and +5.11 F1-score on the SpaceNet dataset, +3.61 IoU and +2.32 F1-score on the self-annotated dataset (Chongzhou dataset). Moreover, the effectiveness of MSFANet was also proven by comparative experiments with other studies.