Remote sensing image scene classification is an active and challenging task driven by many applications. More recently, with the advances of deep learning models especially convolutional neural networks (CNNs), the performance of remote sensing image scene classification has been significantly improved due to the powerful feature representations learnt through CNNs. Although great success has been obtained so far, the problems of within-class diversity and between-class similarity are still two big challenges. To address these problems, in this paper, we propose a simple but effective method to learn discriminative CNNs (D-CNNs) to boost the performance of remote sensing image scene classification. Different from the traditional CNN models that minimize only the cross entropy loss, our proposed D-CNN models are trained by optimizing a new discriminative objective function. To this end, apart from minimizing the classification error, we also explicitly impose a metric learning regularization term on the CNN features. The metric learning regularization enforces the D-CNN models to be more discriminative so that, in the new D-CNN feature spaces, the images from the same scene class are mapped closely to each other and the images of different classes are mapped as farther apart as possible. In the experiments, we comprehensively evaluate the proposed method on three publicly available benchmark data sets using three off-the-shelf CNN models. Experimental results demonstrate that our proposed D-CNN methods outperform the existing baseline methods and achieve state-of-the-art results on all three data sets.

When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs

Scene classification of remote sensing images has drawn great attention because of its wide applications. In this paper, with the guidance of the human visual system (HVS), we explore the attention mechanism and propose a novel end-to-end attention recurrent convolutional network (ARCNet) for scene classification. It can learn to focus selectively on some key regions or locations and just process them at high-level features, thereby discarding the noncritical information and promoting the classification performance. The contributions of this paper are threefold. First, we design a novel recurrent attention structure to squeeze high-level semantic and spatial features into several simplex vectors for the reduction of learning parameters. Second, an end-to-end network named ARCNet is proposed to adaptively select a series of attention regions and then to generate powerful predictions by learning to process them sequentially. Third, we construct a new data set named OPTIMAL-31, which contains more categories than popular data sets and gives researchers an extra platform to validate their algorithms. The experimental results demonstrate that our model makes great promotion in comparison with the state-of-the-art approaches.

Scene Classification With Recurrent Attention of VHR Remote Sensing Images

An Archetypal Analysis on

Most of the existing deep-learning-based methods are difficult to effectively deal with the challenges faced for geospatial object detection such as rotation variations and appearance ambiguity. To address these problems, this paper proposes a novel deep-learning-based object detection framework including region proposal network (RPN) and local-contextual feature fusion network designed for remote sensing images. Specifically, the RPN includes additional multiangle anchors besides the conventional multiscale and multiaspect-ratio ones, and thus can deal with the multiangle and multiscale characteristics of geospatial objects. To address the appearance ambiguity problem, we propose a double-channel feature fusion network that can learn local and contextual properties along two independent pathways. The two kinds of features are later combined in the final layers of processing in order to form a powerful joint representation. Comprehensive evaluations on a publicly available ten-class object detection data set demonstrate the effectiveness of the proposed method.

Rotation-Insensitive and Context-Augmented Object Detection in Remote Sensing Images

More recently, remote sensing image classification has been moving from pixel-level interpretation to scene-level semantic understanding, which aims to label each scene image with a specific semantic class. While significant efforts have been made in developing various methods for remote sensing image scene classification, most of them rely on handcrafted features. In this letter, we propose a novel feature representation method for scene classification, named bag of convolutional features (BoCF). Different from the traditional bag of visual words-based methods in which the visual words are usually obtained by using handcrafted feature descriptors, the proposed BoCF generates visual words from deep convolutional features using off-the-shelf convolutional neural networks. Extensive evaluations on a publicly available remote sensing image scene classification benchmark and comparison with the state-of-the-art methods demonstrate the effectiveness of the proposed BoCF method for remote sensing image scene classification.

Remote Sensing Image Scene Classification Using Bag of Convolutional Features

In this paper, a fused global saliency-based multiscale multiresolution multistructure local binary pattern (salM 3LBP) feature and local codebookless model (CLM) feature is proposed for high-resolution image scene classification. First, two different but complementary types of descriptors (pixel intensities and differences) are developed to extract global features, characterizing the dominant spatial features in multiple scale, multiple resolution, and multiple structure manner. The micro/macrostructure information and rotation invariance are guaranteed in the global feature extraction process. For dense local feature extraction, CLM is utilized to model local enrichment scale invariant feature transform descriptor and dimension reduction is conducted via joint low-rank learning with support vector machine. Finally, a fused feature representation between salM3LBP and CLM as the scene descriptor to train a kernel-based extreme learning machine for scene classification is presented. The proposed approach is extensively evaluated on three challenging benchmark scene datasets (the 21-class land-use scene, 19-class satellite scene, and a newly available 30-class aerial scene), and the experimental results show that the proposed approach leads to superior classification performance compared with the state-of-the-art classification methods.

Fusing Local and Global Features for High-Resolution Scene Classification

In this paper, a fast and robust self-representation (FRSR) method is proposed to select a proper band subset from hyperspectral imagery (HSI). The FRSR assumes the separability structure of the HSI band set and transforms the problem of separable nonnegative matrix factorization into the robust self-representation (RSR) model. Then, the FRSR incorporates structured random projections into the RSR model to improve computational efficiency. The solution of FRSR is formulated into optimizing a convex problem and the augmented Lagrangian multipliers are adopted to estimate the proper factorization localizing matrix in the FRSR. The selected band subset is constituted with the bands corresponding to the r largest diagonal entries of the factorization localizing matrix. The experimental results show that FRSR outperforms state-of-the-art techniques in classification accuracy with lower computational cost.

Fast and Robust Self-Representation Method for Hyperspectral Band Selection

This paper proposes a randomized subspace learning based anomaly detector (RSLAD) for hyperspectral imagery (HSI). Improved from robust principal component analysis, the RSLAD assumes that the background matrix is low-rank, and the anomaly matrix is sparse with a small portion of nonzero columns (i.e., column-wise). It also assumes the anomalies do not lie in the column subspace of the background and aims to find a randomized subspace of the background to detect the anomalies. First, random techniques including random sampling and random Hadamard projections are implemented to construct a coarse randomized columns subspace of the background with reduced computational cost. Second, anomaly columns are searched and removed from the coarse randomized column subspace by solving a series of least squares problems, resulting in a purified randomized column subspace. Third, the nonzero columns in the anomaly matrix are located by projecting all the pixels on the orthogonal subspace of the purified subspace, and the anomalies are finally detected based on the L2 norm of the columns in the anomaly matrix. The detection performance of RSLAD is compared with four state-of-the-art methods, including global Reed-Xiaoli (GRX), local RX (LRX), collaborative-representation based detector (CRD), and low-rank and sparse matrix decomposition base anomaly detector (LRaSMD). Experimental results show good detection performance of RSLAD with lower computational cost. Therefore, the proposed RSLAD offers an alternative option for hyperspectral anomaly detection.

/pdf/a-randomized-subspace-learning-based-anomaly-detector-for-3a9n3xeh6k.pdf

A Randomized Subspace Learning Based Anomaly Detector for Hyperspectral Imagery

Hyperspectral images (HSIs) with rich spectral information have been widely used in many fields. Anomaly detection is one of the most interesting and important applications. In this article, a novel Gaussian mixture model (GMM)-based anomaly detection (GMMD) method for HSI is proposed. The main contributions of this article are a new GMM-based extraction approach for extracting the anomaly pixels and an effective GMM-based weighting approach for fusing the extracted anomaly results. Specifically, based on the fact that the spectral values of anomaly pixels in some bands are different from those of background pixels, we propose a GMM-based anomaly extraction approach in which the HSI is characterized by the GMM and the anomaly pixels are extracted by a range prescribed by the GMM parameters. In order to fuse the extracted anomaly results, the GMM-based weighting method is introduced to adaptively construct the detection map. The detection map is rectified by using a guided filter to obtain the final anomaly detection map. Experimental results conducted on four hyperspectral data sets demonstrate the superior performance of the proposed GMMD method.

Anomaly Detection in Hyperspectral Imagery Based on Gaussian Mixture Model

Quasiphase matching (QPM) is a widely used theory in crystal to analyze the character of second-harmonic generation (SHG) emitted from it. Based on the structural features of collagen type I, where the constituted fibrils in collagen function as a crystal which has the structure of two-dimensional (2D) quasicrystalline, in this paper, we use the QPM theory on collagen for SHG emission direction study under the excitation of laser light through a microscope. The effects of numerical aperture NA, as well as the structural parameters, such as QPM order (m,l) and collagen period a=d1+d2 associated with the fibrils diameter (d1), packing density and interfibrils structure (d2), etc., on SHG emission angle φ have been investigated. Our theoretical results show that collagen period a has threshold effect on φ to present forward or backward SHG emission and NA has minor influence on this threshold value a. Collagen period of a has more significant influence on SHG emission angle φ when a is smaller than the thres...

Long Tian

Papers

Fusing Local and Global Features for High-Resolution Scene Classification

Fast and Robust Self-Representation Method for Hyperspectral Band Selection

A Randomized Subspace Learning Based Anomaly Detector for Hyperspectral Imagery

Anomaly Detection in Hyperspectral Imagery Based on Gaussian Mixture Model

Microscopic second-harmonic generation emission direction in fibrillous collagen type I by quasi-phase-matching theory