Multi-U-Net: Residual Module under Multisensory Field and Attention Mechanism Based Optimized U-Net for VHR Image Semantic Segmentation

Abstract

As the acquisition of very high resolution (VHR) images becomes easier, the complex characteristics of VHR images pose new challenges to traditional machine learning semantic segmentation methods. As an excellent convolutional neural network (CNN) structure, U-Net does not require manual intervention, and its high-precision features are widely used in image interpretation. However, as an end-to-end fully convolutional network, U-Net has not explored enough information from the full scale, and there is still room for improvement. In this study, we constructed an effective network module: residual module under a multisensory field (RMMF) to extract multiscale features of target and an attention mechanism to optimize feature information. RMMF uses parallel convolutional layers to learn features of different scales in the network and adds shortcut connections between stacked layers to construct residual blocks, combining low-level detailed information with high-level semantic information. RMMF is universal and extensible. The convolutional layer in the U-Net network is replaced with RMMF to improve the network structure. Additionally, the multiscale convolutional network was tested using RMMF on the Gaofen-2 data set and Potsdam data sets. Experiments show that compared to other technologies, this method has better performance in airborne and spaceborne images.

Convolutional Neural Network Algorithms for Semantic Segmentation of Volcanic Ash Plumes Using Visible Camera Imagery

“…The convolutional neural networks (CNN) became popular because they outperformed any other network architecture on computer vision [11]. Specifically, the architecture U-Net is nowadays being routinely and successfully used in image processing, reaching an accuracy similar to or even higher than other existing ANN, for example, of the FCN type [12][13][14], providing multiple applications where pattern recognition and feature extraction play an essential role. CNNs have been applied to find solutions to mitigate risk in different environmental fields, such as for the detection and segmentation of smoke and forest fires [15,16], flood detection [17], and to find solutions regarding global warming, for example, through monitoring of the ice of the poles [18,19].…”

Research on Fault Detection of Belt Conveyor Drum Based on Improved YOLOv8 Network Mode

“…In order to ensure the effectiveness of the dataset, enhance the model's generalization ability, avoid overfitting, and improve the performance of the model, this paper not only employs conventional augmentation techniques such as rotation, translation, cropping, and noise addition, but also utilizes some special algorithms such as HSV, Col_Temp color extraction algorithms, G-Blur, M-Blur, Blend blur algorithms [35]. Multiple algorithms are overlapped and applied to enhance the dataset, as shown in Figure 12.…”

Automatic Pear Extraction from High-Resolution Images by a Visual Attention Mechanism Network

“…Compared to traditional object-oriented and pixel-oriented classification methods [44][45][46], CNN-based networks typically achieve higher classification accuracy. For example, SegNet, FCN8s, and U-Net utilize automatic feature learning to avoid complex feature design, improving the automation and intelligence of remote sensing image segmentation [47]. Consequently, CNNs are gaining increasing attention for feature information extraction in remote sensing applications [7,48,49].…”

“…While CNNs have shown success in classifying high-resolution remote sensing images, several problems remain. Firstly, CNNs depend heavily on the number of input training samples, which are limited for remote sensing images, making generalization difficult [47,50]. Secondly, most models have been trained on natural image datasets and are not suitable for remote sensing images [51].…”