Deep learning, which represents data by a hierarchical network, has proven to be efficient in computer vision. To investigate the effect of deep features in hyperspectral image (HSI) classification, this paper focuses on how to extract and utilize deep features in HSI classification framework. First, in order to extract spectral-spatial information, an improved deep network, spatial updated deep auto-encoder (SDAE), is proposed. SDAE, which is an improved deep auto-encoder (DAE), considers sample similarity by adding a regularization term in the energy function, and updates features by integrating contextual information. Second, in order to deal with the small training set using deep features, a collaborative representation-based classification is applied. Moreover, in order to suppress salt-and-pepper noise and smooth the result, we compute the residual of collaborative representation of all samples as a residual matrix, which can be effectively used in a graph-cut-based spatial regularization. The proposed method inherits the advantages of deep learning and has solutions to add spatial information of HSI in the learning network. Using collaborative representation-based classification with deep features makes the proposed classifier extremely robust under a small training set. Extensive experiments demonstrate that the proposed method provides encouraging results compared with some related techniques.

Change detection is an important task to identify land-cover changes between the acquisitions at different times. For synthetic aperture radar (SAR) images, inherent speckle noise of the images can lead to false changed points, which affects the change detection performance. Besides, the supervised classifier in change detection framework requires numerous training samples, which are generally obtained by manual labeling. In this paper, a novel unsupervised method named saliency-guided deep neural networks (SGDNNs) is proposed for SAR image change detection. In the proposed method, to weaken the influence of speckle noise, a salient region that probably belongs to the changed object is extracted from the difference image. To obtain pseudotraining samples automatically, hierarchical fuzzy C-means (HFCM) clustering is developed to select samples with higher probabilities to be changed and unchanged. Moreover, to enhance the discrimination of sample features, DNNs based on the nonnegative- and Fisher-constrained autoencoder are applied for final detection. Experimental results on five real SAR data sets demonstrate the effectiveness of the proposed approach.

Many emerging applications, such as security surveillance and smart healthcare, have incubated the device-free localization (DFL) technique which could estimate the location of a target without equipping any device. However, current DFL system needs labor-intensive training to learn the influence of the target on surrounding wireless signals, so as to provide model parameters or radio maps for the location estimation algorithm. To address this issue, we develop a novel robust training-free DFL system, named DeFi, which could directly estimate the target location by refining the angle-of-arrival (AOA) of the target reflection path based on WiFi channel state information. We analyze the characteristics of the static paths and the motion paths, eliminate the static paths using a background elimination algorithm, and separate out the target reflection path from the motion paths according to the AOA and equivalent time-of-flight measurements. With the AOA of the target reflection path as observation information, we robustly estimate the target location based on a particle filter algorithm. We implement the proposed DeFi system on commodity off-the-shelf WiFi devices and validate its performance in two indoor scenarios. Experimental results show that DeFi achieves a median error of less than 0.6m.

Convolution neural network (CNN) utilizes alternating convolutional and pooling layers to learn representative spatial information when the training samples are sufficient. However, for pixelwise classification of hyperspectral image, some important information is neglected by CNN, such as the erased information by the pooling operation and the appearance information from lower layers. Moreover, the lack of training samples is a common situation in remote sensing area, which afflicts CNN with overfitting problem. To address the aforementioned issues, this paper designs an end-to-end deconvolution network with skip architecture to learn the spectral-spatial features. The proposed network starts with two branches, i.e., the spatial branch and spectral branch. In the spatial branch, a band selection layer is designed to reduce parameters and remit the overfitting problem, unpooling and deconvolution operations are utilized to recover the erased information of the pooling layers and learn pixelwise spatial representation hierarchically, and the skip architecture is constructed for merging the deep semantic information with the shallow appearance information. In the spectral branch, a contextual deep network is employed for learning deep spectral features. Experimental results on three benchmark data sets reveal the competitive performance of the proposed approach over several related methods.

Hyperspectral target detection (HTD) is an important issue in earth observation, with applications in both military and civilian domains. However, conventional representation-based detectors are hindered by the reliance on the unknown background dictionary, the limited ability to capture nonlinear representations using the linear mixing model (LMM), and the insufficient background-target recognition based on handcrafted priors. To address these problems, this paper proposes an interpretable representation network that intuitively realizes LMM for HTD, making nonlinear feature expression and physical interpretability compatible. Specifically, a subspace representation network is designed to separate the background and target components, where the background subspace can be adaptively learned. In addition, to further enhance the nonlinear representation and more accurately learn the coefficients, a lightweight multi-scale Transformer is proposed by modeling long-distance feature dependencies between channels. Furthermore, to supplement the depiction for target-background discrimination, a constrained energy minimization (CEM) loss is tailored by minimizing the output background energy and maximizing the target response. The effectiveness of the proposed method is demonstrated on four benchmark datasets, showing its superiority over state-of-the-art methods. The code for this work is available at https://github.com/shendb2022/HTD-IRN for reproducibility purposes.