Crop segmentation enables the agricultural producers to comprehensively understand the state of their farmland, make more informed management decisions and thereby ensure food security. Unmanned Aerial Vehicle (UAV) remote sensing technology offers cost effective high-resolution imaging for crop segmentation. Deep learning-based methods have continued to improve the accuracy of crop segmentation over time, but accurate edge segmentation remains a challenge. In this letter, we introduce a Convolutional Neural Network (CNN) termed Edge Enhancement Network (EENet) to improve the representation of edge information for crop segmentation in UAV RGB images. Our approach centers on an innovative Edge Enhancement Strategy that augments the learning of edge information during the training phase and refines the representation of edge details during the generation phase. To facilitate the evaluation of our method, we have produced a publicly available dataset for experimentation. Our results, as demonstrated on this self-constructed dataset, illustrate that our proposed approach surpasses competing methods in critical metrics such as mean Intersection over Union (mIoU), F1_score, and model complexity.

Amid the brisk evolution of remote sensing (RS) technology, the domain of RS cross-modal text-image retrieval (RSCTIR) has captivated scholarly interest for its superior adaptability and symbiotic interaction with human operators. However, due to the heterogeneity between image and text data modalities, feature alignment poses a significant challenge. The existing methodologies overlook the sufficient incorporation of structural guidance during the cross-modal feature interaction alignment process to foster alignment between text and image features. In light of this, we propose an innovative approach for RS image-text retrieval task called visual global-salient-guided network (VGSGN), which comprises two branches: the image branch and the text branch. In the image branch, visual global-salient information sensing module (VGSM) is devised to extract visual global and salient features, aiming to enhance the perception capability for complex backgrounds and scenes in RS images. In the text branch, the textual graph enhancement module (TGEM) is crafted to filter out redundant information in the text features and capture the interactions between words within the text. The design of the multiple visual-guided dynamic fusion (MVGF) module aims to leverage the global and salient features of image to guide the text feature, facilitating cross-modal alignment of text and image features. The experimental results on the widely recognized RSICD and RSITMD datasets corroborate the effectiveness and advancement of our proposed VGSGN in tackling the RSCTIR task.

Limited labels and increasing multisource data promote domain adaptation (DA) problem as a challenging study for polarimetric synthetic aperture radar (PolSAR) interpretation. Existing DAs for optical images cannot generalize over PolSAR imagery due to its special side-imaging characteristics and complex distribution shifts. In this letter, a general feature paradigm (GFP) is proposed for unsupervised cross-domain PolSAR image classification. The GFP is based on a key observation that interclass aggregation is optimized after four-step feature transformations. This key observation leads to GFP that not only reduces the domain shifts but also compatible with typical DA methods. The GFPs are conducted on both source and target domain by unsupervised manner, including polarimetric basis extraction, the Wishart clustering, histogram statistics, and dimensionality reduction. After these transformations, the unlabeled target PolSAR image can be classified based on obtained GFP, DA, and limited labeled samples only from the source domain. Extensive unsupervised cross-domain experiments on 27 scenarios verified that GFP leads to at most 93.76% accuracy for full- and dual-polarized synthetic aperture radar (SAR) images’ classification. Moreover, the GFP shed light on extensive cross-domain PolSAR applications about built-up areas, vegetation, and bare land analysis.

Optical remote sensing image (RSI) is easily affected by weather conditions. When the ground target is sheltered by clouds, extracting scene information from the RSI becomes quite challenging. In this work, we propose a distraction-attention-driven adversarial training network (DA2Net) to learn a robust RSI scene classification model. The distraction module employs a gradient-based class activation mapping (GradCAM++) method to produce partially occluded samples. Through feature map visualization, GradCAM++ can quantify the contribution of each region to the network prediction. Regions in the input image are erased and filled with white pixels if the corresponding contribution is higher than a given threshold. In this way, the distraction module enriches the training sample diversity and benefits the network’s robustness and generalization performance. Training with the partially erased samples, the model can extract sufficient information from other regions even though the target with prominent features is occluded. The attention module highlights important features and information. It encourages the network to mine critical features from the uncovered regions. Competition between the two modules drives the network to improve its robustness and overall performance. Extensive experiments show that the DA2Net provides a promising approach for data augmentation and network training. Analysis of cloud-covered scene classification demonstrates the DA2Net’s robust performance.

Change detection (CD) is an essential earth observation technique. It captures the dynamic information of land objects. With the rise of deep learning, convolutional neural networks (CNN) have shown great potential in CD. However, current CNN models introduce backbone architectures that lose detailed information during learning. Moreover, current CNN models are heavy in parameters, which prevents their deployment on edge devices such as UAVs. In this work, we tackle this issue by proposing RDP-Net: a region detail preserving network for CD. We propose an efficient training strategy that constructs the training tasks during the warmup period of CNN training and lets the CNN learn from easy to hard. The training strategy enables CNN to learn more powerful features with fewer FLOPs and achieve better performance. Next, we propose an effective edge loss that increases the penalty for errors on details and improves the network’s attention to details such as boundary regions and small areas. Furthermore, we provide a CNN model with a brand new backbone that achieves the state-of-the-art empirical performance in CD with only 1.70M parameters. We hope our RDP-Net would benefit the practical CD applications on compact devices and could inspire more people to bring change detection to a new level with the efficient training strategy. The code and models are publicly available at https://github.com/Chnja/RDPNet.

The scattering response of polarimetric synthetic aperture radar (PolSAR) data is strongly target orientation-dependent. Formulating the polarimetric matrix as sequential data by rotating the polarimetric matrix along the radar line of sight would provide rich information about land-cover properties. In this work, we propose a composite sequential network (CSN) with polarization orientation angle (POA) attention to model the polarimetric coherency matrix sequence and explore target scattering orientation diversity features. Three major factors strengthen the proposed method for PolSAR image analysis. First, CSN improves the feature comprehensiveness by extending the interpretation mode of PolSAR data from spatial polarization to spatial polarization orientation. In this way, CSN could describe polarimetric response dynamics at different orientations. Second, a two-stream composite network with both real- and complex-valued convolutional long short-term memory (ConvLSTM) network is proposed to process the diagonal and off-diagonal elements of the coherency matrix sequence, respectively. Compared to existing real-/complex-valued networks, the CSN explores the significant phase information of the off-diagonal elements by operations in the complex domain. Meanwhile, CSN prevents padding 0 meaninglessly in the imaginary part of the real-valued diagonal elements. Third, during the sequential modeling of the polarimetric matrix, a POA attention mechanism is proposed. Equipped with POA-sensitive decomposition loss, the CSN attends to substantial POA range derived by targets’ physical scattering mechanism and learns features closely related to the scattering mechanism. Extensive experiments and analysis on land-cover classification demonstrate the proposed method’s robustness and excellence.

Increasing amounts of polarimetric synthetic aperture radar (PolSAR) images from different sensors covering different scenes are available, but limited labeled samples and trained models can hardly work well in these cross-domain data interpretations. Fortunately, domain adaptation (DA) can transfer knowledge in existing images to new yet related images. DA shows attractive potential for PolSAR classification, and it is still challenging due to more complex domain shifts caused by different sensors, imaging conditions, and distributions. Inspired by the widely applicable polarimetric scattering mechanisms and DA ability of subspace alignment (SA), this article is devoted to constructing a robust unsupervised cross-domain PolSAR classification framework, by exploring scattering and statistical characteristics mapping between the source and target domains. First, classical scattering components of both source and target data were extracted, and Wishart clustering was adopted to derive the statistical information of scattering components at patch level. Second, the intrinsic polarimetric scattering components were estimated and extracted, which were called statistical scattering components (SSCs). Third, by applying SA, the source SSC was aligned with target SSC, and domain shift was further reduced. Finally, the target PolSAR image was classified based on labeled samples from source domain, and unsupervised cross-domain classification was achieved by SSC-based SA (SSC-SA). The unsupervised cross-domain experiments are conducted on 49 units among 11 data sets, including Radarsat-2, Gaofen-3, AIRSAR, and Pi-SAR images. With randomly selected labeled samples (about 2%–10%) from source domain, the accuracies of the proposed cross-domain classifications range between 80.20% and 95.64%. Also, the proposed SSC feature pattern is proved extensible for other polarimetric basis and decompositions.

Benefiting from the advantages of flexibility and timeliness, Unmanned Aerial Vehicles (UAVs) play an important role in crop growth monitoring, precision agriculture and intelligent agriculture. This paper focuses on the farmland boundary detection in UAV images. Traditional farmland boundary detection methods have problems such as over-segmentation and discontinuous boundary. To address these problems, we propose a Deep Boundaries Combination (DBC) algorithm for the detection of farmland plots boundaries in UAV remote sensing images. DBC uses deep convolutional networks to obtain edge probability map of farmland images, and then applies Oriented Watershed Transform (OWT) and Ultrametric Contour Map (UCM) to convert edge probability map into closed boundary hierarchy tree, which layers the boundaries by edge probability. We perform experiments on two farmland images acquired by UAV. Experimental results show that our method can extract more accurate farmland boundaries than other methods.

Supervised deep learning models usually need large amounts of labeled data due to the data-driven training strategies, and its applicability to the newly emerging categories that lack annotated images is severely limited. In contrast, few-shot learning aims to recognize novel targets from very few labeled examples, so it will be a promising method for synthetic aperture radar (SAR) image interpretation, where numerous labeled data may not exist. In this paper, we introduced a few-shot learning method based on relation network and graph neural network (GNN). Relation network extracts the feature similarity between query samples and support samples through a convolutional neural network, and it has achieved good performance in few-shot learning problems. GNNs have received increasing attention in recent years, and they have shown superior performance in relation extraction. In this work, we replaced the relation module in the relation network with attention GNN, aiming to model the relationship between the samples more effectively and learn a better metric for feature similarity. Experiments on the MSTAR dataset demonstrate that the proposed method can better extract the relationship between query samples and support samples, thereby improving the performance for few-shot image classification tasks.

Many polarimetric features, including decomposition components, can be extracted from polarimetric synthetic aperture radar (PolSAR) data. The polarimetric features usually reflect the physical mechanisms of ground targets and play an important role in PolSAR image classification. However, the feature values may vary largely due to the differences in system parameters of PolSAR sensors, which result in that the trained classifiers on sample data from one source PolSAR image scene may perform poorly in another source PolSAR image scene. The direct use of polarimetric features can produce wrong identifications. In this letter, we mainly deal with the components extracted by different decomposition methods and proposed a simple but efficient component ratio-based distance (CRD), which is an intracross-component distance, in contrast with component-to-component distances. The combinations with$\mathcal {L}_{1}$distance and$\chi ^{2}$distance can generate$\mathcal {L}_{1}$-CRD and$\chi ^{2}$-CRD and benefit from their robustness to small values. CRDs capture correlations between scattering components with only a linear computational complexity. Finally, we replace the distance measurement in k-nearest neighbor (KNN) with CRDs and employ the improved classifiers to classify PolSAR images. Based on the ratios of scattering components, CRD can also be used for cross-source PolSAR images, ignoring the differences in sensors, acquired time, imaging scenes, and even wavebands. Preliminary experiments on real PolSAR data sets demonstrate promising results of CRDs for image classification.

Accurate built-up area (BA) information plays crucial role for many applications. PolSAR imagery can provide important source for BAs information analysis. However, the BAs with large orientation angles are usually misdetected as vegetation, and labeled BA samples with special orientations are diffi-cult to obtain. In this paper, a PolSAR BA extraction method based on eigenvalue statistical information and PU-Learning is proposed to overcome abovementioned problems. Firstly, the roll invariance of coherency-matrix eigenvalues and the building orientations have been analyzed. Then, by adopting eigenvalue-Wishart unsupervised classification, regional statistical information and rotation invariant property are comprehensively utilized. Finally, the BAs are extracted by combining PU-Learning classifier with only positive samples at same distinguishable orientation. Six experiments on PolSAR imageries show the accuracy of proposed method can reach 92-99% with only a few positive samples, 8-20% higher than classical model decomposition-based PU-Learning method, and the requirement for labeled samples is less than 0.65%.

Interpretation of convolutional neural networks (CNNs) critically influence our understanding of deep learning models’ internal dynamics. In this paper, we demonstrate an interpretable training method, namely class activation mapping guided adversarial training (CAMAT), for two typical remote sensing tasks, land-use classification and object detection. We first generate class activation maps of the current batch training samples. Class activation map is a kind of class-specific saliency map that quantifies the contributions of a particular region in the image to the CNN prediction result. Then, high contribution regions in the training samples are occluded, and we leverage the partial masked images as the inputs for network training. Following this paradigm, the key areas for network learning and decision making are purposefully disturbed in the training phase, thus the trained model could have better performance in robustness and generalization. Experiments conducted on classic remote sensing datasets verified the outperforming effectiveness and efficiency of the proposed CAMAT.

Polarimetric response is strongly target orientation dependent. The observed polarimetric matrices from the same target with different orientations can be quite different. The existence of target scattering orientation diversity contains rich information, and leveraging information of target scattering orientation diversity may help to reveal polarimetric properties of different land cover types. In this work, a robust land cover feature descriptor, dynamic fractal texture, is introduced to capture the stochastic self-similarities of land cover scattering responses in both spatial and rotation domains. We extend the polarimetric matrix to the rotation domain by polarimetric basis transformation. Varying polarization orientation angle (POA) or ellipticity angle (EA), polarimetric responses of land cover under a series of orientations can be obtained. Then, the dynamic fractal texture is formulated by serializing received responses as a polarimetric synthetic-aperture radar (PolSAR) image sequence. Finally, the proposed features are combined with random forest (RF)/support vector machine (SVM) classifier to produce the classification maps on real PolSAR data. Experiment results show that dynamic fractal texture has an advantage in indicating rotation domain information. The proposed method has superior performance in land cover classification and yields accurate classification results.

Polarimetric synthetic aperture radar (PolSAR) image classification is one of the most important applications in Pol-SAR image processing. More and more deep learning methods are applied to PolSAR image classification. As we know, the polarimetric response of a target is related to the orientation of the target, but the features in rotation domain are not fully used in deep learning. We use a convolutional LSTM (ConvLSTM) along with a sequence of polarization coherent matrices in rotation domain for PolSAR image classification. First, nine different polarization orientation angles (POA) are used to generate nine polarization coherent matrices in rotation domain. Second, a deep learning model that stacked with multiple ConvLSTM layers and fully connected layers is proposed for classification. Finally, the sequence of polarization coherent matrices is fed into the ConvLSTM to classify Pol-SAR images. Experiments show that the classification results of ConvLSTM are better than the LeNet-5.

Tracking unexpected warning vehicles is required for quick response to security incident. To realize real-time vehicle tracking in a large-scale video surveillance network, a geospatial and temporal connection (GSTC) model is introduced to model the connection between videos. The transition time between videos is modeled by a Gaussian mixture model (GMM). With the developed plug-ins based on GSTC and GMM, the video streams of defined geospatial neighbors are automatically called in with the video stream that the object appears in during the tracking process. Experiments show that the ratio of success of real-time tracking is largely increased.

This paper presents a novel classification method for high-spatial-resolution satellite scene classification introducing multiset aggregated canonical correlation analysis (MACCA)-based feature fusion to fuse and combine multiple features. Firstly, a superpixel representation of the scene is constructed by employing a high-efficiency linear iterative clustering algorithm. After that, three diverse and complementary visual descriptors are extracted to characterize each superpixel. For taking full advantage of multiset features to yield the effective discriminant information and eliminating the redundancy between multiset features to some extent, MACCA is performed on three different feature sets to acquire fused feature for classification. Experimental analysis on high-spatial-resolution satellite scenes reveals that the suggested method achieves exceedingly promising performance and surpasses other off-the-shelf methods in classification accuracy.

The sensor web is a new method in the earth observation field, comprising sensors that can sense, compute, and correspond with the World Wide Web. The Chinese Integrated Earth Observation Sensor Web (CIEOSW) project is a five-year national basic research program conducted by Wuhan University since 2011 and is aimed to address the following major challenges: (1) the lack of collaboration within the satellite observation system, (2) the absence of a coupling mechanism in heterogeneous spaceborne -- airborne -- ground sensors, and (3) the limited connection between monitoring and decision-support services. For two years, the CIEOSW project has strived to achieve the following: (1) a theory on the coupling and modeling of the Earth observation sensor web (EOSW), (2) an event-driven multi-sensor collaborative observation method, (3) an EOSW fusion and assimilation method, (4) an EOSW-based information extraction and rapid change detection method, (5) a task-oriented EOSW focusing service model, and (6) an epicontinental environment observation and analysis of typical areas in China.

Cooperative spectrum sensing (CSS) is a promising technique in cognitive radio networks (CRNs) that utilises multi‐user diversity to mitigate channel instability and noise uncertainty. In this study, the relationship between ‘cooperation mechanisms’ and ‘spatial‐spectral diversity’ over multiple channels jointly sensing is investigated in the presence of an imperfect reporting channel. The multiple channels are sensed at the receiver built on the filter bank‐based multi‐carrier system. The multi‐channel CSS strategies are modelled by the introduced ‘cooperative ratio’ to balance the requirements on ‘sensing accuracy’, ‘efficiency’ and ‘overhead’, which is quantitatively characterised by the energy consumption. The target of CSS is to maximise the aggregate opportunistic throughput of secondary users (SUs) by jointly considering constraints on sensing overhead and the aggregate interference to primary users (PUs). The optimisation is divided into two sequential sub‐optimisation processes, ‘multi‐user diversity optimisation’ and ‘multi‐channel diversity optimisation’. An approach is developed from generic algorithms to solve the two sub‐problems. Numerical results show that the optimal CSS scheme is effective in improving channel utilisation for SUs with low interference to PUs. This study establishes a valuable cooperative model for the design of multi‐channel spectrum sensing algorithms in CRNs.