Bio: Xiaoguang Mei is an academic researcher from Wuhan University. The author has contributed to research in topics: Hyperspectral imaging & Computer science. The author has an hindex of 14, co-authored 60 publications receiving 920 citations. Previous affiliations of Xiaoguang Mei include Huazhong University of Science and Technology & Central China Normal University.
TL;DR: A new end-to-end model, termed as dual-discriminator conditional generative adversarial network (DDcGAN), for fusing infrared and visible images of different resolutions, which establishes an adversarial game between a generator and two discriminators.
Abstract: In this paper, we proposed a new end-to-end model, termed as dual-discriminator conditional generative adversarial network (DDcGAN), for fusing infrared and visible images of different resolutions. Our method establishes an adversarial game between a generator and two discriminators. The generator aims to generate a real-like fused image based on a specifically designed content loss to fool the two discriminators, while the two discriminators aim to distinguish the structure differences between the fused image and two source images, respectively, in addition to the content loss. Consequently, the fused image is forced to simultaneously keep the thermal radiation in the infrared image and the texture details in the visible image. Moreover, to fuse source images of different resolutions, e.g. , a low-resolution infrared image and a high-resolution visible image, our DDcGAN constrains the downsampled fused image to have similar property with the infrared image. This can avoid causing thermal radiation information blurring or visible texture detail loss, which typically happens in traditional methods. In addition, we also apply our DDcGAN to fusing multi-modality medical images of different resolutions, e.g. , a low-resolution positron emission tomography image and a high-resolution magnetic resonance image. The qualitative and quantitative experiments on publicly available datasets demonstrate the superiority of our DDcGAN over the state-of-the-art, in terms of both visual effect and quantitative metrics. Our code is publicly available at https://github.com/jiayi-ma/DDcGAN .
TL;DR: Qualitative and quantitative experimental results on publicly available datasets demonstrate that the proposed target-enhanced multiscale transform (MST) decomposition model for infrared and visible image fusion can generate fused images with clearly highlighted targets and abundant details.
Abstract: In this study, we propose a target-enhanced multiscale transform (MST) decomposition model for infrared and visible image fusion to simultaneously enhance the thermal target in infrared images and preserve the texture details in visible images. The Laplacian pyramid is initially used to separately decompose two pre-registered source images into low- and high-frequency bands. The common “max-absolute” fusion rule is performed for fusion for high-frequency bands. We use the decomposed infrared low-frequency information to determine the fusion weight of low-frequency bands and highlight the target. Meanwhile, a regularization parameter is introduced to dominate the proportion of the infrared features in a gentle manner, which can be further adjusted according to user requirements. Finally, we use inverse transform with the Laplacian pyramid (LP) to reconstruct the fused image. Qualitative and quantitative experimental results on publicly available datasets demonstrate that the proposed method can generate fused images with clearly highlighted targets and abundant details. These images exhibit better visual effects and objective metric values than those of five other commonly used MST decomposition methods.
TL;DR: Experimental results demonstrate that the proposed spectral-spatial attention network for hyperspectral image classification can fully utilize the spectral and spatial information to obtain competitive performance.
Abstract: Many deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN), have been successfully applied to extracting deep features for hyperspectral tasks. Hyperspectral image classification allows distinguishing the characterization of land covers by utilizing their abundant information. Motivated by the attention mechanism of the human visual system, in this study, we propose a spectral-spatial attention network for hyperspectral image classification. In our method, RNN with attention can learn inner spectral correlations within a continuous spectrum, while CNN with attention is designed to focus on saliency features and spatial relevance between neighboring pixels in the spatial dimension. Experimental results demonstrate that our method can fully utilize the spectral and spatial information to obtain competitive performance.
TL;DR: This paper integrates superpixel segmentation (SS) into LRR and proposes a novel denoising method called SSLRR, which excavate the spatial-spectral information of HSI by combining PCA with SS, and is better than simply dividing the HSI into square patches.
Abstract: Recently, low-rank representation (LRR) based hyperspectral image (HSI) restoration method has been proven to be a powerful tool for simultaneously removing different types of noise, such as Gaussian, dead pixels and impulse noise. However, the LRR based method just adopts the square patch denoising strategy, which makes it not able to excavate the spatial information in HSI. This paper integrates superpixel segmentation (SS) into LRR and proposes a novel denoising method called SSLRR. First, the principal component analysis (PCA) is adopted to obtain the first principal component of HSI. Then the SS is adopted to the first principal component of HSI to get the homogeneous regions. Since we excavate the spatial-spectral information of HSI by combining PCA with SS, it is better than simply dividing the HSI into square patches. Finally, we employ the LRR to each homogeneous region of HSI, which enable us to remove all the above mentioned different types of noise simultaneously. Extensive experiments conducted on synthetic and real HSIs indicate that the SSLRR is efficient for HSI denoising.
TL;DR: The difference of Gabor (DoGb) filters is proposed and improved (IDoGb), which is an extension of DoG but is sensitive to orientations and can better suppress the complex background edges, then achieves a lower false alarm rate.
Abstract: Infrared (IR) small target detection with high detection rate, low false alarm rate, and multiscale detection ability is a challenging task since raw IR images usually have low contrast and complex background. In recent years, robust human visual system (HVS) properties have been introduced into the IR small target detection field. However, existing algorithms based on HVS, such as difference of Gaussians (DoG) filters, are sensitive to not only real small targets but also background edges, which results in a high false alarm rate. In this letter, the difference of Gabor (DoGb) filters is proposed and improved (IDoGb), which is an extension of DoG but is sensitive to orientations and can better suppress the complex background edges, then achieves a lower false alarm rate. In addition, multiscale detection can be also achieved. Experimental results show that the IDoGb filter produces less false alarms at the same detection rate, while consuming only about 0.1 s for a single frame.
01 Jan 2006
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.
TL;DR: This survey comprehensively survey the existing methods and applications for the fusion of infrared and visible images, which can serve as a reference for researchers inrared and visible image fusion and related fields.
Abstract: Infrared images can distinguish targets from their backgrounds based on the radiation difference, which works well in all-weather and all-day/night conditions. By contrast, visible images can provide texture details with high spatial resolution and definition in a manner consistent with the human visual system. Therefore, it is desirable to fuse these two types of images, which can combine the advantages of thermal radiation information in infrared images and detailed texture information in visible images. In this work, we comprehensively survey the existing methods and applications for the fusion of infrared and visible images. First, infrared and visible image fusion methods are reviewed in detail. Meanwhile, image registration, as a prerequisite of image fusion, is briefly introduced. Second, we provide an overview of the main applications of infrared and visible image fusion. Third, the evaluation metrics of fusion performance are discussed and summarized. Fourth, we select eighteen representative methods and nine assessment metrics to conduct qualitative and quantitative experiments, which can provide an objective performance reference for different fusion methods and thus support relative engineering with credible and solid evidence. Finally, we conclude with the current status of infrared and visible image fusion and deliver insightful discussions and prospects for future work. This survey can serve as a reference for researchers in infrared and visible image fusion and related fields.
TL;DR: A comprehensive review of the current-state-of-the-art in DL for HSI classification, analyzing the strengths and weaknesses of the most widely used classifiers in the literature is provided, providing an exhaustive comparison of the discussed techniques.
Abstract: Advances in computing technology have fostered the development of new and powerful deep learning (DL) techniques, which have demonstrated promising results in a wide range of applications. Particularly, DL methods have been successfully used to classify remotely sensed data collected by Earth Observation (EO) instruments. Hyperspectral imaging (HSI) is a hot topic in remote sensing data analysis due to the vast amount of information comprised by this kind of images, which allows for a better characterization and exploitation of the Earth surface by combining rich spectral and spatial information. However, HSI poses major challenges for supervised classification methods due to the high dimensionality of the data and the limited availability of training samples. These issues, together with the high intraclass variability (and interclass similarity) –often present in HSI data– may hamper the effectiveness of classifiers. In order to solve these limitations, several DL-based architectures have been recently developed, exhibiting great potential in HSI data interpretation. This paper provides a comprehensive review of the current-state-of-the-art in DL for HSI classification, analyzing the strengths and weaknesses of the most widely used classifiers in the literature. For each discussed method, we provide quantitative results using several well-known and widely used HSI scenes, thus providing an exhaustive comparison of the discussed techniques. The paper concludes with some remarks and hints about future challenges in the application of DL techniques to HSI classification. The source codes of the methods discussed in this paper are available from: https://github.com/mhaut/hyperspectral_deeplearning_review .
TL;DR: This survey introduces feature detection, description, and matching techniques from handcrafted methods to trainable ones and provides an analysis of the development of these methods in theory and practice, and briefly introduces several typical image matching-based applications.
Abstract: As a fundamental and critical task in various visual applications, image matching can identify then correspond the same or similar structure/content from two or more images. Over the past decades, growing amount and diversity of methods have been proposed for image matching, particularly with the development of deep learning techniques over the recent years. However, it may leave several open questions about which method would be a suitable choice for specific applications with respect to different scenarios and task requirements and how to design better image matching methods with superior performance in accuracy, robustness and efficiency. This encourages us to conduct a comprehensive and systematic review and analysis for those classical and latest techniques. Following the feature-based image matching pipeline, we first introduce feature detection, description, and matching techniques from handcrafted methods to trainable ones and provide an analysis of the development of these methods in theory and practice. Secondly, we briefly introduce several typical image matching-based applications for a comprehensive understanding of the significance of image matching. In addition, we also provide a comprehensive and objective comparison of these classical and latest techniques through extensive experiments on representative datasets. Finally, we conclude with the current status of image matching technologies and deliver insightful discussions and prospects for future works. This survey can serve as a reference for (but not limited to) researchers and engineers in image matching and related fields.
TL;DR: A concept of spatial dependency system that involves pixel dependency and label dependency, with two main factors: neighborhood covering and neighborhood importance is developed, and several representative spectral–spatial classification methods are applied on real-world hyperspectral data.
Abstract: Imaging spectroscopy, also known as hyperspectral imaging, has been transformed in the last four decades from being a sparse research tool into a commodity product available to a broad user community. Specially, in the last 10 years, a large number of new techniques able to take into account the special properties of hyperspectral data have been introduced for hyperspectral data processing, where hyperspectral image classification, as one of the most active topics, has drawn massive attentions. Spectral–spatial hyperspectral image classification can achieve better classification performance than its pixel-wise counterpart, since the former utilizes not only the information of spectral signature but also that from spatial domain. In this paper, we provide a comprehensive overview on the methods belonging to the category of spectral–spatial classification in a relatively unified context. First, we develop a concept of spatial dependency system that involves pixel dependency and label dependency, with two main factors: neighborhood covering and neighborhood importance. In terms of the way that the neighborhood information is used, the spatial dependency systems can be classified into fixed, adaptive, and global systems, which can accommodate various kinds of existing spectral–spatial methods. Based on such, the categorizations of single-dependency, bilayer-dependency, and multiple-dependency systems are further introduced. Second, we categorize the performings of existing spectral–spatial methods into four paradigms according to the different fusion stages wherein spatial information takes effect, i.e., preprocessing-based, integrated, postprocessing-based, and hybrid classifications. Then, typical methodologies are outlined. Finally, several representative spectral–spatial classification methods are applied on real-world hyperspectral data in our experiments.