In the hyperspectral image (HSI) classification, convolutional neural networks (CNNs)-based approaches often struggle with the scarcity of labeled samples. The letter proposes an HSI classification method based on data expansion and consistency regularization with small samples. Specifically, we leverage the pixel-pair feature (PPF) to expand the dataset, which facilitates the adequate tuning of CNN parameters and alleviates the issue of overfitting. In addition, a designed CNN structure is employed to extract discriminative features from the limited number of labeled PPFs and numerous unlabeled PPFs. The CNN is trained via minimizing the weighted sum of supervised and unsupervised losses, where the supervised loss is calculated through the cross-entropy function while the unsupervised loss is evaluated with the consistency regularization item. Moreover, reliable references required in the consistency regularization item are provided after making an exponential moving average (EMA) on the outputs of CNNs at different training epochs. Ultimately, we conduct experiments on three real HSI datasets, and the results show that the proposed approach gains superior classification accuracy compared to several existing CNN-based approaches.

The classification performance of land features is strongly associated with the quality of samples. However, in the real world, the presence of class noise is inevitable. Class noise may seriously mislead the construction of model and limit the improvement of classifier performance. In response to this situation, a stratified mislabeled instances removal method based on the idea of density spatial clustering optimally (SD-SCM) is proposed. Herein, the convolutional neural network (CNN) is employed to evaluate the effectiveness of the proposed method.Besides, a famous noise filter, KNN-kernel Cluster based technology, is adopted to compare with SD-SCM. The results on two benchmark datasets, Indian Pines and Pavia University, demonstrate the effectiveness of the proposed noise removal method.

The optimization of prediction and update operators plays a prominent role in lifting-based image coding schemes. In this paper, we focus on learning the prediction and update models involved in a recent Fully Connected Neural Network (FCNN)-based lifting structure. While a straightforward approach consists in separately learning the different FCNN models by optimizing appropriate loss functions, jointly learning those models is a more challenging problem. To address this problem, we first consider a statistical model-based entropy loss function that yields a good approximation to the coding rate. Then, we develop a multi-scale optimization technique to learn all the FCNN models simultaneously. For this purpose, two loss functions defined across the different resolution levels of the proposed representation are investigated. While the first function combines standard prediction and update loss functions, the second one aims to obtain a good approximation to the rate-distortion criterion. Experimental results carried out on two standard image datasets, show the benefits of the proposed approaches in the context of lossy and lossless compression.

The classification of hyperspectral image (HSI) has become the focus of the remote sensing field. However, limited training data, which makes the classification task face a major challenge, is inevitable in remote sensing. To eliminate the negative effects of limited labeled samples, an enhanced ensemble method named RoXGBoost, which inherently combines Rotation Forest (RoF) and eXtreme Gradient Boosting (XGBoost) is proposed in this paper. This algorithm could increase the diversity of base classifiers by random feature selection and data transformation. Five ensemble learning methods, Random Forest (RF), AdaBoost, RoF, Rotation Boost and XGBoost, are applied as comparisons. The results on two benchmark datasets, Indian Pines and Pavia University, demonstrate the effectiveness of the RoXGBoost.

An ensemble alignment subspace adaptation method is proposed in this letter for the cross-scene classification. It can settle the problem of both foreign objects in the same spectrum and different spectrums. The algorithm combines the idea of ensemble learning with the domain adaptive (DA) algorithm. Considering the sample imbalance problem of the original data (OD), the source data (SD) is obtained by multiple random sampling of OD according to certain rules and used as input. Then, geometric alignment and statistical alignment of SD and target data (TD) are performed to build a communal subspace, followed by the classification of TD. The classification labels are finally ensembled by counting the multiple classification results with retaining valid information. This technique can reduce the uncertainty and randomness of generating subspace projections. The experimental results on two real datasets show that the proposed algorithm has a terrific accuracy improvement compared with the traditional machine learning and DA methods.

Unmanned Aerial Vehicles (UAVs) are known for their highly dynamic nature, as a result of which their applications demand high design consideration in urban areas. It is imperative to have trajectories that avoid UAV-to-UAV and UAV-to-obstacle collision to ensure the safety of a fleet and people on the ground. Moreover, many applications, like temporary network provision, require continuous backhaul fleet connectivity. This work simultaneously addresses UAVs’ path planning and routing issues to propose connectivity-aware path planning for a fleet of UAVs in an urban environment. The proposed scheme is a graph-based offline path planning with fleet line formation that ensures continuous backhaul connectivity. This feature allows any UAV to play the role of leader and guide the entire fleet according to a desired speed. Thanks to the continuous backhaul connectivity, the Base Station (BS) can disseminate commands to the connected fleet as required. Fleet line formation acts as a backbone network and allows additional UAVs or ground users to become a part of this network. The proposed approach is implemented in MATLAB’s UAV Toolbox and evaluated in a network simulator. The simulation results demonstrate that the proposed scheme provides collision-free trajectories while ensuring continuous BS connectivity.

In this paper, the fusion method of the weighted median filter Gram-Schmidt transform transplants to the digital signal processor (DSP). Image fusion technology has always been a key technology in the field of remote sensing image processing, but the algorithm is rarely implemented on mobile devices, so the scope of use has great limitations. The algorithm in the paper blends multispectral images and panchromatic images in the same location. The multispectral image is filtered by using a weighted median filter, and then the processed image and the panchromatic image are fused through the Gram-Schmidt transform. The filtering process reduces noise interference in the image, and the fused image combines the advantages of both images with high resolution and high color information. Due to the portability of DSP chips, the algorithm can be mounted on many mobile devices. Reduce the process of data transfer and make the image processing process more convenient.

Pine wilt disease is one of the most dangerous forest diseases. Because of its strong infectivity and harm, it is very important to find out and stop it in time. In this paper, a novel spatial-spectral random forest (SRF) algorithm for pine wilt monitoring is proposed, for solving the problem of small manual detection range, long investigation time, and untimely discovery of the diseased tree. The proposed method organically combines spatial features with spectral information to quickly and efficiently mark the location of diseased trees. In this way, the online monitoring of the target area using the data of the Beijing-2 satellite is realized. This paper analyses the location of diseased trees and provides early warnings for disease-prone trees. The accuracy of the proposed algorithm is 86.66%, by the confusion matrix analysis.

International audience

With the continuous progress of computer deep learning technology, convolutional neural network (CNN), as a representative approach, provides a unique solution for hyperspectral image (HSI) classification. However, the parameters of CNN can not be well-tuned when the number of training samples is insufficient, resulting in unsatisfactory classification performance. To tackle the thorny problem, a deep ensemble CNN method based on sample expansion for HSI classification is studied in this paper. Specially, spatial information is first extracted and fused with original spectral bands to help classifiers obtain discriminant spectral-spatial features. Then we use the pixel-pair feature (PPF) to expand the number of training samples so that the parameters of CNN structure can be fully trained. In addition, deep ensemble CNN is employed in this paper, enabling the trained model to obtain better generalization ability and more robust classification results. Ultimately, the proposed method is applied to classify four widely used hyperspectral data sets. Experimental results show that the studied approach yields higher classification accuracy than some CNN-based methods even under the condition of small-size training set.

The objective of this paper is to investigate techniques for learning Fully Connected Network (FCN) models in a lifting based image coding scheme. More precisely, based on a 2D non separable lifting structure composed of three FCN-based prediction stages followed by an FCN-based update one, we first propose to resort to an $\ell_{p}$ loss function, with $p\in\{1,2\}$, to learn the three FCN prediction models. While the latter are separately learned in the first approach, a novel joint learning approach is then developed by minimizing a weighted $\ell_{p}$ loss function related to the global prediction error. Experimental results, carried out on the standard Challenge Learned Image Compression (CLIC) dataset, show the benefits of the proposed techniques in terms of rate-distortion performance.

Recently, convolutional neural network (CNN) is widely used in hyperspectral image classification (HSIC) because of its strong self-learning and efficient feature expression ability. However, the CNN model faces the “overfitting” problem when the number of training samples is small. To improve the classification accuracy of CNN under the condition of limited training set, an ensemble CNN method based on pixel-pair and random feature selection (RFS) for HSIC is proposed in this paper. With the purpose of expanding training samples, the pixel-pair feature (PPF) is used in the presented study. Besides, ensemble CNN based on RFS is applied to further improve the classification performance. Experimental results based on two standard hyperspectral images demonstrate that the proposed method achieves better classification performance than the PPF based on CNN (PPF-CNN) and RFS based on SVM (RFS-SVM) methods.

Convolution neural network (CNN) has been successfully applied to hyperspectral image classification. However, multiclass imbalance is a major problem in the classification of hyper spectral images, and traditional CNN can hardly improve the accuracy of minority classes effectively. In this paper, a new ensemble CNN with enhanced feature subspaces (ECNN-EFSs) algorithm is proposed, which utilizes an imbalanced training set to train the model and achieves accurate classification. Experimental results on two common hyperspectral datasets show that the proposed algorithm outperforms the traditional CNN and ensemble CNN algorithms.

The fusion of hyperspectral image (HSI) and light detection and ranging (LiDAR) data can provide complementary information and improve the accuracy of land cover classification. In this paper, a novel fusion method is proposed to fuse the HSI and LiDAR dataset based on multi-scale feature extraction and total variation. In the method, the extended multi-attribute profile (EMAP) is utilized to automatically extract structural information from HSI and LiDAR elements. The extracted features are then estimated in a lower-dimensional space by multi-scale total variation (MSTV). Finally, the classification map is generated by applying random forest classifiers on the fused data. In the experiment, the performance of the proposed method is evaluated on an urban dataset of Houston. The results demonstrate that classification accuracy could be significantly improved by the proposed method compared with other methods.

In this paper, a novel Synthetic Minority Oversampling Technique based Deep Rotation Forest(SMOTE-DRoF) algorithm is proposed for the classification of imbalanced hyperspectral image data. It builds a multi -level forests cascade model by training a balanced dataset generated by SMOTE. In this model, each level of the random forest produces misclassification information of the data which are used as guidance information to adjust the sample weight adaptively for the next level. Experiment results on the hyperspectral image Indian Pines AVRIS and University of Pavia ROSIS demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined random forest, and SMOTE combined rotation forest in imbalance learning.

The classification is one of the most important tasks of the hyperspectral remote sensing. However, the task always suffers from the curse of dimensionality which makes most classifier models disabled. In this paper, a novel ensemble method named feature separation based rotation forest (FSRoF) is proposed to avoid the influence of high-dimensionality by training a series of independent classifiers with the datasets in a low-dimensionality rotation space and using the out-of-bag instances to select the base classifiers of high quality to construct the final ensemble model. The random forest (RF) and the traditional rotation forest (RoF) are adopted as the comparisons in our experiment.

The presence of noise is often unavoidable and has been a serious nuisance factor that needs to be taken into account in the hyperspectral image classification. Effective noise handling is one of the most difficult problems in data classification. Ensemble-based filtering has been demonstrated successful in dealing with the class noise problem. In this paper, a novel two-step ensemble-based data filtering method is proposed to improve the hyperspectral image classification accuracy in the presence of class noise. The proposed method is a combination of noise redundancy classifiers and sensitive algorithms. The experimental results on two public hyperspectral datasets demonstrate the effectiveness of the proposed approach.

Convolutional neural networks (CNN) can automatically learn features from the hyperspectral image data, which could avoid the difficulty of manually extracting features. However, the number of training set for the classification of hyperspectral images is always limited, making it difficult for CNN to obtain effective features and resulting in low classification accuracy. In this paper, a spectral-spatial feature (SSF) extraction based CNN method is proposed for an accurate classification with a small training set. Experimental results based on two standard hyperspectral images demonstrate the effectiveness of the proposed method.

In this paper, we propose a novel ensemble margin based semi-supervised random forest (EMRF) algorithm for the classification of the hyperspectral image with limited training data. The proposed method tries to improve the effectiveness of the ensemble model via adaptively labeling the unlabeled instances with high classification probability then adding them into the training set. The classification probability of a training instance is reflected by the unsupervised margin value of this instance. The higher ensemble margin of an instance, the higher probability the instance being classified correctly and added into to the training set in the next iteration.

With the recent advances in stereoscopic display technologies, there is a growing demand for designing efficient stereo image compression techniques. For this reason, a great attention should be paid to the disparity/estimation process used to generate the residual image. In this paper, we propose to improve the disparity compensation process in a typical closed-loop-based stereo image coding scheme. A new formulation of this process, based on a block dependent dictionary, is developed. More specifically, the main idea aims to link together the disparities yielding similar compensations and assign a common disparity candidate to each subset of disparities. Experimental results have shown the interest of the proposed method in terms of bitrate saving and quality of reconstruction.