Deep learning models are widely employed in hyperspectral image processing to integrate both spatial features and spectral features, but the correlations between them are rarely taken into consideration. However, in hyperspectral mineral identification, not only the spectral and spatial features of minerals need to be considered, but also the correlations between them are crucial to further promote identification accuracy. In this paper, we propose hierarchical spatial-spectral feature extraction with long short term memory (HSS-LSTM) to explore correlations between spatial features and spectral features and obtain hierarchical intrinsic features for mineral identification. In the proposed model, the fusion spatial-spectral feature is primarily extracted by stacking local spatial features obtained by a convolution neural network (CNN)-based model and spectral information together. To better exploit spatial features and spectral features, an LSTM-based model is proposed to capture correlations and obtain hierarchical features for accurate mineral identification. Specifically, the proposed model shares a uniform objective function, so that all the parameters in the network can be optimized in the meantime. Experimental results on the hyperspectral data collected by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) in the Nevada mining area show that HSS-LSTM achieves an overall accuracy of 94.70% and outperforms other commonly used identification methods.

When detecting a target over the diurnal cycle, a conventional infrared thermal sensor might lose the target due to the thermal crossover, which could happen at any time throughout the day when the infrared image contrast between target and background in a scene is indistinguishable due to the temperature variation. In this paper, the benefits of using a multispectral-based infrared sensor over the diurnal cycle have been shown. Firstly, a brief theoretical analysis on how the thermal crossover influences a conventional thermal sensor, within the conditions where the thermal crossover would happen and why the mid-infrared (3~5 μm) multispectral technology is effective, is presented. Furthermore, the effectiveness of this technology is also described and we describe how the prototype design and multispectral technology is employed to help solve the thermal crossover detection problem. Thirdly, several targets are set up outside and imaged in the field experiment over a 24-h period. The experimental results show that the multispectral infrared imaging system can enhance the contrast of the detected images and effectively solve the failure of the conventional infrared sensor during the diurnal cycle, which is of great significance for infrared surveillance applications.

Airborne lidar provides accurate height information of objects on the earth and has been recognized as a reliable and accurate surveying tool in many applications. In particular, lidar data offer vital and significant features for urban land-cover classification, which is an important task in urban land-use studies. In this article, we present an effective approach in which lidar data fused with its co-registered images (i.e. aerial colour images containing red, green and blue (RGB) bands and near-infrared (NIR) images) and other derived features are used effectively for accurate urban land-cover classification. The proposed approach begins with an initial classification performed by the Dempster–Shafer theory of evidence with a specifically designed basic probability assignment function. It outputs two results, i.e. the initial classification and pseudo-training samples, which are selected automatically according to the combined probability masses. Second, a support vector machine (SVM)-based probability estimator is adopted to compute the class conditional probability (CCP) for each pixel from the pseudo-training samples. Finally, a Markov random field (MRF) model is established to combine spatial contextual information into the classification. In this stage, the initial classification result and the CCP are exploited. An efficient belief propagation (EBP) algorithm is developed to search for the global minimum-energy solution for the maximum a posteriori (MAP)-MRF framework in which three techniques are developed to speed up the standard belief propagation (BP) algorithm. Lidar and its co-registered data acquired by Toposys Falcon II are used in performance tests. The experimental results prove that fusing the height data and optical images is particularly suited for urban land-cover classification. There is no training sample needed in the proposed approach, and the computational cost is relatively low. An average classification accuracy of 93.63% is achieved.

Weakly supervised visible-to-infrared image translation in remote sensing scenes is a challenging task that attempts to generate corresponding infrared images from visible images with cross-model manner, thus tackling the acute scarcity of infrared data in certain crucial task scenes. Existing methods frequently concentrate solely on style transfer, resulting in stylistic similarity but physical inconsistency, which limits the authenticity of cross-modal translation. Infrared thermal features stemming from brightness and darkness contrasts among distinct regions due to temperature disparities, are associated with visual representations in foreground objects in visible images. Therefore, this paper proposes ThermalMask, a framework for infrared image generation guided by thermal features, aiming to make the generated images more closely with infrared features in remote sensing. Specifically, a saliency mask generation network (SMGN) and a semantic attention generation network (SAGN) are designed in the generator. The SMGN is used to generate background and foreground masks to preserve the background and most prominent features of the input remote sensing image. Meanwhile, the SAGN generates attention maps through pyramid non-local attention mechanism, guiding the network to adaptively focus on salient regions within both visible and infrared feature maps. In addition, to refine the generated infrared features, a pixel-spectrum multi-spatial constraint (PSC) targeting high-frequency components is designed, enabling the generative network to focus more on expressing infrared features. Extensive experiment results have shown that our method has good performance in visible-to-infrared image translation within remote sensing scenes, surpassing existing state-of-the-art image translation methods. Moreover, it holds promise for application in downstream tasks where infrared data is insufficient.

A multi parameter optimization model is proposed for the mineral mapping of hyperspectral imagery. This model can provide guidance for selecting system parameters when a new sensor is designed or offer performance estimation in mineral mapping with a given imaging system. A multivariate regression analysis is performed to investigate the quantitative relationship between mineral identification capability and imaging spectrometer parameters. The objective function of the proposed optimization model is set to maximize performance with the constraint on system parameters due to user requirements and technology maturity. The number of minerals identified is selected to measure the data usefulness. The parameters of an imaging system include ground sample distance, signal-to-noise ratio, modulation transfer function, and spectral resolution. A set of evaluation experiments is conducted using hyperspectral data collected in Dongtianshan area, Xinjiang, China. The predicted error is less than 15%, and the best mineral mapping can be obtained using the optimized system parameters.

Various minerals present distinct spectra due to different constituent ions or groups. However, variable imaging conditions of hyperspectral imagery greatly affect the mineral spectra, which makes it difficult to identify minerals. Attenuation spectral absorption index (ASAI) is suggested to extract absorption features from mineral diagnostic bands, which combines spectral absorption index (SAI) with absorption position and resists variations in external factors. To integrate intrinsic features of mineral spectra, the ASAI vector is formed by the ASAIes of diagnostic absorption bands corresponding to all identified minerals, which depicts mineral contents to a certain extent. In this letter, a multilayer perceptron (MLP) model based on attenuation spectral absorption index vector (ASMLP) is proposed to obtain hierarchical features for accurate mineral identification. The hyperspectral data of the Nevada mining area collected by Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) are applied to illuminate the performance of the proposed model. The results show that ASMLP achieves an overall accuracy of 93.62% and outperforms other identification methods.