Remote sensing image scene classification refers to assigning semantic labels according to the content of the remote sensing scenes. Most machine learning-based scene classification methods assume that training and testing data share the same distributions. However, in real application scenarios, this assumption is difficult to guarantee. Domain adaptation (DA) is a promising approach to address this problem by aligning the feature distribution of training and testing data. Inspired by the idea DA, in this article, we propose a correlation subspace dynamic distribution alignment (CS-DDA) method for remote sensing image scene classification. Aiming at the characteristics of remote sensing scenes, we introduce two strategies to balance the effects of source and target domains: subspace correlation maximization (SCM) and dynamic statistical distribution alignment (DSDA). On the one hand, SCM tries to avoid mapping source domain data into irrelevant subspace to preserve the representation information of the source domain. On the other hand, DSDA is proposed to reduce the data distribution discrepancy between aligned source and target domains. Specifically, DSDA is a dynamic adjustment process where an adaptive factor is learned to balance the interclass and intraclass distribution between domains. Moreover, we integrate SCM and DSDA into a uniform optimization framework, and the optimal solution can be converted to the generalized eigendecomposition problem by derivation. The experimental results indicate that the proposed method can generate better results when compared with other feature distribution alignment methods.

In remote sensing images, the backgrounds of objects include crucial contextual information that may contribute to distinguishing objects. However, there are at least two issues that should be addressed: not all the backgrounds are beneficial, and object information may be suppressed by backgrounds. To address these problems, in this paper, we propose the contextual bidirectional enhancement (CBD-E) method to simultaneously remove unexpected background information and enhance objects features. CBD-E integrates the features of different background regions sequentially in two directions. On the one hand, a gate function is used to filter out unexpected information in the background and thus improve the recall of detection. On the other hand, a spatial-group-based visual attention mechanism is adopted to enhance the features of objects to reduce the false alarm. The gate function provides an approach to selecting meaningful information in the background, while the spatial-group-based visual attention mechanism enhances the information control ability of the gate function. In the experiments, we have validated the effectiveness of both the gate function and the visual attention mechanism and further demonstrated that the proposed contextual fusion strategy performs well on two published data sets.

In order to solve the problem of low accuracy of the U-Net in cardiac ventricular segmentation, we propose an improved U-net named LU-Net by the following three methods. Firstly, in order to improve the efficiency and effectiveness of extracting the features of the original image, we combine U-net with SE-Net model. This model reweights the channels of feature map, which can give higher weight to the useful information and lower weight to the invalid information. Secondly, in order to alleviate the extent of losing the pixel-location information when use the encoder to dawn sample, we combine multiscale input with U-net’s encoder. Thirdly, in order to solve the problem of low accuracy in traditional U-net, we replace the transposed convolution layer, used by the traditional U-Net,s encoder during upsampling, with unsampling layer. During the process of unsampling, it can put pixels to their original location using the pixel-location information reserved by the encoder during sampling process, which can reduce errors caused by losing pixel-location information. Besides, using unsampling layer during unsampling can also avoid producing checkerboard artifacts during transposed convolution and improve the segmentation accuracy. To verify the effectiveness of LU-Net, we apply it to the ACDC Stacom 2017 dataset. The experiment results show that the evaluation criteria of prediction results are 92.4%, 86.4%and 92.5% on Dice coefficient,Jaccard similarity coefficient and F1-ccore respectively, which are better than U-Net, SegNet, IU-Net and remarkably better than the traditional neural convolution network model, FCN8s.

Remote sensing image scene classification aims to automatically assign semantic labels for remote sensing images. Recently, to overcome the distribution discrepancy of training data and test data, domain adaptation has been applied to remote sensing image scene classification. Most domain adaptation approaches usually explore transferability under the assumption that the source domain and target domain have common classes. However, in real applications, new categories may appear in the target domain. Besides, only considering the transferability will degrade the classification performance due to the strong interclass similarity of remote sensing images. In this article, we present an open set domain adaptation algorithm via exploring transferability and discriminability (OSDA-ETD) for remote sensing image scene classification. To be specific, we propose the transferability technology, which aims at the high interdomain variations and high intraclass diversity of remote sensing images. The purpose of transferability is to reduce the global distribution difference of domains and the local distribution discrepancy of the same classes in different domains. For high interclass similarity in remote sensing images, we adopt the discriminability strategy. The discriminability intends to enlarge the distribution discrepancy of different classes in different domains. To further promote the effectiveness of scene classification, we integrate the transferability and the discriminability into a framework. Moreover, we prove that the algorithm has a unique optimizer.

Ship detection from Synthetic Aperture Radar (SAR) images is a hot topic, but the difficulty in collecting labeled SAR images may hinder the development of deep learning based detection methods. Inspired by the idea of domain adaptation, in this paper, we propose a Hierarchical Similarity Alignment neural Network (HSANet) for ship detection in SAR images, which is a domain adaptive approach with optical remote sensing images as training samples. The kernel target of HSANet is to mine and align both the global structure and the local instance information between SAR and optical images, where two modules, Structural Alignment Module (SAM) and Prototype Alignment Module (PAM), are designed to respectively conduct two hierarchies of alignment process. In general, SAM attempts to extract the global structure similarity which exists in image-level feature representation, while PAM tends to extract the local shape similarity which is instance-level representation. To be specific, SAM is developed by Fourier-based feature alignment, which tries to describe the similar structural relation between optical and SAR images. Meanwhile, PAM is proposed based on the conjoint confidence analysis where the instance-level ship representations of the source and target domains is aligned. SAM and PAM work together to construct a hierarchical domain adaptation network for SAR ship detection. Experiments on several public datasets may indicate the effectiveness of the proposed method.

Multi-object tracking in unmanned aerial vehicle (UAV) scenes is a crucial task with numerous applications across various domains. The goal of this task is to track multiple objects such as people and vehicles over time as they move through the scene, often captured by cameras mounted on UAV. However, tracking objects in UAV scenes can be challenging due to several factors, including the scale variance of objects as they move through the scene and the frequent occlusions caused by complex scenes. To address these issues, we propose a Global-Local and Occlusion Awareness (GLOA) tracking network for unmanned aerial vehicles. It comprises two main components: global-local awareness detector (GLA-D) and the occlusion awareness data association (OADA). The GLA-D uses our specially designed global-local awareness block to extract scale variance feature information from the input frames. It then outputs more discriminative identity information by adding identity embedding branches to the prediction head. The GLA-D is designed to better handle scale variance issues and improve object tracking accuracy. The OADA method used different metrics for high and low scoring detection frames was to alleviate occlusion problems in tracking scenarios. By combining these two components, the GLOA provides a more robust and effective solution for multi-object tracking in UAV scenes. Experiments on two public datasets may indicate the effectiveness of the proposed method.