Band selection is an effective method to reduce redundancy in a hyperspectral image (HSI) without compromising the original contents. Popular band selection methods usually use strong assumptions, such as linear or nonlinear assumptions with simple predefined Kernel functions, to model the correlations between bands. However, this kind of strong assumption may not valid in the real environment due to the complex interactions between bands. In this letter, we treat hyperspectral band selection as a spectral reconstruction task. By assuming that an HSI can be sparsely reconstructed from a few informative bands, we propose an attention-based autoencoder to model the underlying nonlinear interdependencies between bands. The proposed model consists of two parts: an attention module and an autoencoder. The attention module is used to produce the attention mask which selects the most informative bands for every pixel. The autoencoder uses these informative bands to reconstruct the raw HSI. The final band selection is conducted via clustering column vectors of the attention mask and exploring the most representative band for each cluster. Different from most of the existing band selection methods, the proposed method directly learns global nonlinear correlations between bands without strong assumptions. The proposed model is easy to implement and all the parameters can be jointly optimized using the stochastic gradient descend algorithm. Experiments on three open public data sets show that the proposed method offers the promising results.

Hyperspectral unmixing, which estimates end-members and their corresponding abundance fractions simultaneously, is an important task for hyperspectral applications. In this article, we propose a new autoencoder-based hyperspectral unmixing model with three novel components. First, we propose a new sparse prior to abundance maps. The proposed prior, called orthogonal sparse prior (OSP), is based on the observations that different abundance maps are close to orthogonal because, generally, no more than two end-members are mixed within one pixel. As opposed to the conventional norm-based sparse prior that assumes the abundance maps are independent, the proposed OSP explores the orthogonality between the abundance maps. Second, we propose the hyper-Laplacian loss to model the reconstruction error. The key observation is that the reconstruction error distribution usually has a heavy-tailed shape, which is better modeled by the hyper-Laplacian distribution rather than the commonly used Gaussian distribution. Third, to ease the side effect of outliers for end-member initializations, we develop a data-driven approach to detect outliers from the raw hyperspectral images. Extensive experiments on both synthetic and real-world data sets show that the proposed method significantly and consistently outperforms the compared state-of-the-art methods, with up to more than 50% improvements.

With the growing threat of unmanned aerial vehicle (UAV) intrusions, the topic of anti-UAV tracking has received widespread attention from the community. Traditional Siamese trackers struggle with small UAV targets and are plagued by model degradation issues. To mitigate this, we propose a novel searching region-free and template-free Siamese network (SiamSRT) to track UAV targets in thermal infrared (TIR) videos. The proposed tracker builds a two-stage Siamese architecture with the former providing detection of the first-frame ground truth by using a cross-correlated region proposal network (C-C RPN) and the latter providing detection of previous-frame predictions via a similarity-learning region convolutional neural network (S-L RCNN). In both stage, global proposals are acquired by region of interest (ROI) alignment operation to break the limitation of searching region. Then, a spatial location consistency function is introduced to suppress background thermal distractors and a temporal memory bank (TMB) is utilized to avoid template update degradation problem. Further, a single-category foreground detector (SCFD) is designed to independently predict the position of the UAV target. SCFD can re-initialize the tracker without the given target in the first frame, which can help to recover the tracking failures. Comprehensive experiments demonstrate that SiamSRT achieves the best performance compared to the most advanced algorithms in the anti-UAV tracking missions.

We present a new regularizer for image smoothing which is particularly effective for diminishing insignificant details, while preserving salient edges. The proposed regularizer relates in spirit to total variation (TV) which penalizes all the gradients, while our method just penalizes part of the gradients and leaves the significant edges unchanged. Though the proposed regularizer is a piecewise function, which is hard to optimize, we can unify it to a mathematically sound penalty. The unified penalty term is easy to optimize using recent fast solvers and hard thresholding operation. We show some potential applications of the proposed regularizer, including texture removal and compression artifact restoration. The results show the efficiency of the proposed regularizer.

GF-(Gaofen- means high resolution in Chinese) satellite launched in 2015 is the first geosynchronous orbit remote sensing satellite in China. To evaluate the on-orbit modulation transfer function (MTF) of the space-borne panchromatic camera in GF-4, a modified pulse target is proposed. This new type target is laid in the uniform low-reflection background region whose center region is a high-reflection square with the size of 3 ~4 ground sampled distance (GSD), and then two low-reflection rectangle stripes are extended along the center square toward both ends with the length over 4 GSD. In consideration of the staring imaging mechanism of GF-4, the target image sequences are accessed with relative random distance taken by the space-borne camera in a short period to reduce accidental error of one sampling and enhance the accuracy of estimation. Based on the multi-sampling calibrating images, maximum a posteriori estimation model and gradient descent solution with grid searching method are used to fit the pulse response function (PRF) when taking the target center positions as references. MTF is then calculated from PRF via Fourier transformation. Numerical simulation results reveal our method can keep the accuracy stable despite of different kinds of noise. Actual calibration result using this method shows that on-orbit MTF of GF-4 camera at Nyquist frequency is 0.1473.

Blind deconvolution is a highly ill-posed problem for the restoration of degraded images and requires prior knowledge or regularization. Recently, various priors have been proposed and the models based on these priors have achieved state-of-the-art performances. In this paper, we present a blind image deblurring method based on a computationally efficient and effective image regularizer. The proposed regularizer is motivated by the fact that the success of recent priors mainly stems from their properties, which implicitly generate an unnatural latent image suppressing insignificant structures and preserving only salient edges. These salient edges guide the models to estimate an accurate kernel. In this paper, the proposed regularizer termed smoothing-enhancing regularizer, not only assures that only salient structures in the image are preserved but also enhances these salient structures to help the model estimate the more accurate kernel. To efficiently solve the proposed model, we develop an efficient numerical approach based on the half-quadratic splitting algorithm and the lagged-fixed-point iteration scheme. The optimization scheme only requires a few additional shrinkage operations compared with the original half-quadratic splitting algorithm, making our method much faster than recent leading methods. The qualitative and quantitative experimental results show that our algorithm achieves the state-of-the-art results and can be extended to other challenging deblurring tasks, such as those involving text, face, and low-illuminated images. Furthermore, the proposed method is much more computationally efficient than the recent state-of-the-art algorithms with up to more than 10× faster execution time.