image denoising is a critical challenge in digital imageprocessing, particularly when dealing with random-value impulse noise (RVIN). Existing methods for RVIN detection and removal often struggle with poor generaliz...
详细信息
image denoising is a critical challenge in digital imageprocessing, particularly when dealing with random-value impulse noise (RVIN). Existing methods for RVIN detection and removal often struggle with poor generalization performance, requiring manual adjustment of detection thresholds or local window information. These approaches have difficulty handling severely damaged images or those with high background noise. To overcome these limitations, a novel fuzzy-based approach has been developed for RVIN detection and denoising in digital photographs. This method combines the power of K-means clustering with fuzzy logic to locate noisy pixels by identifying their closest neighbors. By effectively separating actual signal points from misleading noise signals during the detection phase, the proposed technique ensures precise identification of RVIN. Furthermore, a robust partition decision filter is employed in the elimination phase, effectively removing the identified noise while preserving the underlying signal. The integration of fuzzy techniques enhances the robustness and adaptability of this method, allowing it to handle various noise types and challenging image conditions. Extensive simulations using diverse remote-sensing datasets corrupted with RVIN demonstrated the superior performance of the proposed fuzzy denoising technique. It achieved an impressive 90% success rate in noise detection and maintained high accuracy even at increased noise levels, outperforming other commonly reported methods. This innovative fuzzy-based approach offers a promising solution to the problem of RVIN detection and denoising in digital images. By leveraging the advantages of fuzzy logic and K-means clustering, it provides improved generalization, increased adaptability, and enhanced noise removal capabilities, making it a significant advancement in the field of imageprocessing.
Semantic labelling of remotesensingimages is crucial for various remotesensing applications. However, the dense distribution of man-made and natural objects with similar colours and geographic proximity poses chall...
详细信息
Semantic labelling of remotesensingimages is crucial for various remotesensing applications. However, the dense distribution of man-made and natural objects with similar colours and geographic proximity poses challenges for achieving consistent and accurate labelling results. To address this issue, a novel deep learning model incorporating an octave convolutional neural networks (CNNs) within an end-to-end U-shaped architecture is presented. The approach differs from conventional CNNs in that it employs octave convolutions instead of standard convolutions. This strategy serves to minimize low-frequency information redundancy while maintaining segmentation accuracy. Furthermore, coordination attention is introduced in the encoder module to enhance the network's ability to extract useful features, focusing on spatial and channel dependencies within the feature maps. This attention mechanism enables the network to better capture channel, direction, and location information. In conclusion, the U-shaped network is engineered with a completely symmetric structure that employs skip connections to merge low-resolution information, used for object class recognition, with high-resolution information to enable precise localization. This configuration ultimately improves segmentation accuracy. Experimental results on two public datasets demonstrate that our U-ONet achieves state-of-the-art performance, making it a compelling choice for remotesensingimage semantic labelling applications. Semantic labelling of remotesensingimages is crucial but challenging due to complex object distributions. Our U-ONet model, with octave convolutions and coordination attention, achieves state-of-the-art performance by enhancing feature extraction and precise localization, making it an ideal choice for accurate segmentation tasks. image
Addressing the challenges inherent in remotesensingimage detection, notably the YOLOv5 detector's subpar accuracy due to limited detection target features, intricate detection backgrounds, and predominantly smal...
详细信息
Since last decade, deep learning has made exceptional progress in various fields of artificial intelligence including image and voice recognition, natural language processing. Inspired by these successes, researchers ...
详细信息
Since last decade, deep learning has made exceptional progress in various fields of artificial intelligence including image and voice recognition, natural language processing. Inspired by these successes, researchers are now applying deep learning techniques to classification of scenes in remotesensingimages. The purpose of remotesensingimage scene classification is to classify remotesensing scenes according to their content. These images display a complex structure due to the variety of landforms as well as the distance between the image collection instrument and earth. In our review, we discussed 76 relevant papers published on this topic over the past 6 years. The review conducts a comparison analysis based on the overall accuracy parameter to provide insight into the effectiveness of different methods on different proportions of the dataset. The five classes of techniques we describe are convolutional neural networks, autoencoders, generative adversarial networks, vision transformers, and few-shot learning. Future directions are discussed in this review in order to enhance the effectiveness of deep learning-based scene classification approaches. This article concludes with an overview of the proposed method to enhance the accuracy in classifying remotesensingimages.
Large-format, information-dense satellite-based remotesensing pictures are in conflict with the restricted bandwidth for return transmission to the ground, necessitating the development of appropriate remotesensing ...
详细信息
Change detection (CD) is a fundamental operation in remotesensingimage interpretation. This process employs a range of imageprocessing and recognition techniques to identify semantic alterations in the same geograp...
详细信息
Change detection (CD) is a fundamental operation in remotesensingimage interpretation. This process employs a range of imageprocessing and recognition techniques to identify semantic alterations in the same geographical region across different temporal phases. However, most of existing CD methods rarely utilize the relationship between dual-time phase features. In addition, they tend to overlook the potential benefits of integrating spatial and channel information, which impairs their ability to discern fine details and address pseudochanges. To address these limitations, we propose a cross-perception and hierarchical similarity metric network (CPHSM-Net). The features are first captured using a feature extractor that adds an adaptive spatial channel enhancement (ASCE) strategy to adaptively obtain a more meaningful representation of the features. Then, the relationships between the features of each layer are captured by the cross-perception (CP) module. Finally, the variation feature description is further enhanced by the hierarchical similarity metric (HSM) module, which is designed to capture the variations and differences in the images. The F1 scores obtained by CPHSM-Net in experimental tests on three publicly available datasets (LEVIR-CD, WHU-CD, and DSIFN-CD) were 91.07%, 92.56%, and 65.75%, respectively, which is superior to the state-of-the-art comparison methods.
Landslide identification is an important task in the field of geologic disaster monitoring and early warning, which is of great significance for improving social safety and mitigating the impact of disasters. With the...
详细信息
Landslide identification is an important task in the field of geologic disaster monitoring and early warning, which is of great significance for improving social safety and mitigating the impact of disasters. With the development of computer vision, deep learning is widely used in landslide recognition research. We focus on segmenting landslides from high-resolution optical satellite images using convolutional neural network. Currently, deep learning semantic segmentation models still face issues such as neglecting small objects and incorrectly segmenting terrain features with similar shapes and pixel characteristics. Considering the unbalanced distribution of categories and large differences in scene styles during the extraction of key feature information from remotesensingimages, landslides have diverse and complex backgrounds. We propose a fusion DeepLabv3+ and completed local binary pattern (CLBP) landslide image semantic segmentation method (CLBP-DeepLabv3+), using the improved inverted residual block as the core structure of backbone to extract different levels of image information, and after backbone extracts landslide image features, it connects the improved DenseASPP to fuse the different levels of features to better pay comprehensive attention to local and global features and obtain contextual information at different scales. Then, the texture and edge features of the image are extracted using CLBP, and the multi-level features are merged by introducing the feature aggregation module, which constitutes the CLBP-DeepLabv3+ model. Through ablation experiments and comparative tests on a self-made dataset, the experimental results show that the proposed method performs the best on the validation set, with a mean intersection over union (mIoU) of 88.62%, mean pixel accuracy (mPA) of 94.17%, recall rate of 90.17%, and an intersection over union (IoU) for landslides of 80.53%. Compared with the original DeepLabv3+ model, the improved DeepLabv3+ increased the mI
Target recognition plays a crucial role in the intelligent interpretation of synthetic aperture radar (SAR) images. However, polarimetric information holding great potential in target recognition has not been fully st...
详细信息
Target recognition plays a crucial role in the intelligent interpretation of synthetic aperture radar (SAR) images. However, polarimetric information holding great potential in target recognition has not been fully studied. In this article, we propose a novel method for target recognition in polarimetric SAR (PolSAR) images by using convolutional neural networks (CNNs) to optimize discrete polarimetric correlation pattern. Discrete polarimetric correlation pattern transfers PolSAR images from image domain to rotation domain, and achieves a high-dimensional representation of the target. We then formulate an optimization problem, which is the basis for target recognition, to unfold the low-dimensional embeddings from the raw representations. The optimization problem aims to achieve intraclass compactness and interclass separation of the target embeddings. Interestingly, we employ CNN as a powerful tool to solve it. By combining the rotation domain features with the neural network, we obtain a discriminative representation that reflects the target's polarimetric scattering mechanism, and finally realize high-performance target recognition. Experiments performed on both simulated and real datasets demonstrate that the proposed method outperforms reference methods significantly in almost all metrics. It is worth mentioning that even on low-resolution images, the proposed method can still achieve high-precision recognition performance. In addition, through feature visualization, we gain deeper insights into the network behavior. Finally, feature separability issue is also discussed, further confirming that the optimized features do have the characteristics of intraclass compactness and interclass separation.
Because of the convenience and low cost of obtaining visible remotesensingimages of UAV, it is widely used in agricultural production. In land cover classification, in order to obtain more homogeneous superpixels of...
详细信息
In the field of remotesensing, the scarcity of stereo-matched and particularly lack of accurate ground truth data often hinders the training of deep neural networks. The use of synthetically generated images as an al...
详细信息
ISBN:
(纸本)9798350365474
In the field of remotesensing, the scarcity of stereo-matched and particularly lack of accurate ground truth data often hinders the training of deep neural networks. The use of synthetically generated images as an alternative, alleviates this problem but suffers from the problem of domain generalization. Unifying the capabilities of imageto-image translation and stereo-matching presents an effective solution to address the issue of domain generalization. Current methods involve combining two networks-an unpaired image-to-image translation network and a stereomatching network-while jointly optimizing them. We propose an edge-aware GAN-based network that effectively tackles both tasks simultaneously. We obtain edge maps of input images from the Sobel operator and use it as an additional input to the encoder in the generator to enforce geometric consistency during translation. We additionally include a warping loss calculated from the translated images to maintain the stereo consistency. We demonstrate that our model produces qualitatively and quantitatively superior results than existing models, and its applicability extends to diverse domains, including autonomous driving.
暂无评论