23 March 2017 in IEEE Transactions on Fuzzy Systems
This paper introduces the popular sparse representation method into the classical fuzzy c-means clustering algorithm, and presents a novel fuzzy clustering algorithm, called fuzzy double c-means based on sparse self-representation (FDCM_SSR). The major characteristic of FDCM_SSR is that it can simultaneously address two datasets with different dimensions, and has two kinds of corresponding cluster centers. The first one is the basic feature set that represents the basic physical property of each sample itself. The second one is learned from the basic feature set by solving a spare self-representation model, referred to as discriminant feature set, which reflects the global structure of the sample set. The spare self-representation model employs dataset itself as dictionary of sparse representation. It has good category distinguishing ability, noise robustness, and data-adaptiveness, which enhance the clustering and generalization performance of FDCM_SSR. Experiments on different datasets and images show that FDCM_SSR is more competitive than other state-of-the-art fuzzy clustering algorithms.
17 August 2021 in IEEE Transactions on Geoscience and Remote Sensing
The remote sensing image captioning has attracted wide spread attention in remote sensing field due to its application potentiality. However, most existing approaches model limited interactions between image content and sentence and fail to exploit special characteristics of the remote sensing images. We introduce a novel recurrent attention and semantic gate (RASG) framework to facilitate the remote sensing image captioning in this article, which integrates competitive visual features and a recurrent attention mechanism to generate a better context vector for the images every time as well as enhances the representations of the current word state. Specifically, we first project each image into competitive visual features by taking the advantage of both static visual features and multiscale features. Then, a novel recurrent attention mechanism is developed to extract the high-level attentive maps from encoded features and nonvisual features, which can help the decoder recognize and focus on the effective information for understanding the complex content of the remote sensing images. Finally, the hidden states from the long short-term memory (LSTM) and other semantic references are incorporated into a semantic gate, which contributes to more comprehensive and precise semantic understanding. Comprehensive experiments on three widely used datasets, Sydney-Captions, UCM-Captions, and Remote Sensing Image Captioning Dataset, have demonstrated the superiority of the proposed RASG over a series of attentive models based on image captioning methods.
19 February 2021 in IEEE Transactions on Geoscience and Remote Sensing
Band selection is an important step in efficient processing of hyperspectral images (HSIs), which can be seen as the combination of powerful band search technique and effective evaluation criterion. The existing deep-learning-based methods make the network parameters sparse to search the spectral bands using threshold-based functions or regularization terms. These methods may lead to an intractable optimization problem. Furthermore, these methods need to repeatedly train deep networks for evaluating candidate band subsets. In this article, we formalize hyperspectral band selection as a reinforcement learning (RL) problem. Band search is regarded as a sequential decision-making process, where each state in the search space is a feasible band subset. To evaluate each state, a semisupervised convolutional neural network (CNN), called EvaluateNet, is constructed by adding the intraclass compactness constraint of both limited labeled and sufficient unlabeled samples. A simple stochastic band sampling method is designed to train EvaluateNet, making it possible to efficiently evaluate without any fine-tuning. In RL, new reward functions are defined by taking the EvaluateNet and the penalty of repeated selection into account. Finally, advantage actor–critic algorithms are designed to explore in the state space and select the band subset according to the expected accumulated reward. The experimental results on HSI data sets demonstrate the effectiveness and efficiency of the proposed algorithms for hyperspectral band selection.
13 January 2021 in IEEE Transactions on Geoscience and Remote Sensing
Anomaly detection of a hyperspectral image without any prior information has attracted much more attention in remote sensing image understanding and interpretation, which aims at determining whether a sample belongs to background or anomaly. Low-rank dictionary learning plays an important role in exploiting the low-rank prior of background for hyperspectral image (HSI) anomaly detection. In this article, the low-rank dictionary learning is introduced to learn a dictionary which can reconstruct the background positively, while anomaly cannot. Considering the high correlation of data especially between the adjacent bands, we resort to spectral-difference low-rank dictionary representation learning for global background modeling which can fully exploit the low-rank prior of background. Then, the residual matrix is used to distinguish anomaly. Different from the existing anomaly detection methods based on dictionary which is constructed or learned in a separated step, our proposed model can simultaneously learn the dictionary and separate anomaly by iterative learning. The experimental results on five real data sets demonstrate the superior performance of the proposed method for hyperspectral anomaly detection compared with other state-of-the-art algorithms.
1 February 2018 in Pattern Recognition
6 October 2022 in Frontiers in Environmental Science
Coordination of rural industrial convergence and ecological environment is an important issue in rural social and economic development. This study aims to introduce a comprehensive evaluation index system and construct an integrated approach to evaluate and predict the coupling coordination between rural industrial convergence and ecological environment. Firstly, an index system including 40 indexes is developed for evaluating the two subsystems, and then entropy weight method is applied to determine the weights. Finally, a coupling coordination model and a grey prediction model are developed using provincial panel data from 2017 to 2021 for 29 provinces in China. There are three main findings: 1) penetration of new technologies and agricultural industrialization are the main driving factors of rural industrial convergence. In the three dimensions of ecological environment, environmental pressure has been the smallest contributor, implying that environmental pressure in rural China still needs attention in the next decade. 2) the coupling coordination between rural industrial convergence and ecological environment shows a fluctuating upward trend in China during the studied period and will continue to rise in the next 12 years. Among the 29 provinces studied, only 4 eastern developed provinces have reached primary coordination. The forecast data suggests that coordination with ecological environment will promote the development of rural industrial convergence. 3) the spatial differences of the coupling coordination are related to the level of economic and cultural development, application of agricultural technology, convergence of information technology, energy consumption structure and stock of natural resources. In conclusion, the research develops a rational index system and an effective approach to measure and predict the coupling coordination between rural industrial convergence and ecological environment, providing a theoretical basis for the environmental considerations in the rural industrial convergence policy-making.