T2Det: twin-tower detector with geometric invariance for oriented object detection

Remote sensing images are blurred due to large and wide imaging, long shooting distance, fast scanning speed, interference from external light, etc. At the same time, because of that remote sensing images have the characteristics of diverse and dense shooting objects, deblurring remote sensing images is a major problem in remote sensing research. Therefore, we propose a remote sensing image deblurring algorithm, which based on WGAN. The algorithm is different from the traditional method in estimating the blur kernel of image. What’s more our method does not require an explicit estimation of the blur kernel, and it implements an end-to-end image deblurring process. We use a WGAN-based deblurring model. First, the training images are processed in pairs. Then, in order to increase the generalization ability, a image of 256 * 256 that is a sub-region cropped at the random position in the original image is chosen as the input image. Finally, to achieve a better deblurring effect, a content loss function and a perceptual loss function are added to the loss function to achieve the specific implementation. The remote sensing image deblurring model trained by the proposed method has achieved better results on the remote sensing image dataset. The experimental results show that the proposed algorithm have better performance than the traditional method in filtering out the blur of remote sensing images, which could optimize the overall visual effect subjectively and improve the peak signal-to-noise ratio of the image objectively.

Deep learning technology plays an important role in land cover change detection (LCCD) with bitemporal remote sensing images (RSIs). In particular, the classical UNet can provide promising detection accuracies and visual performance for LCCD with RSIs. This study proposes a novel change detection approach named difference feature guidance and multi-scale feature-fusion (DFG-MFF) network based on UNet to further improve the performance of LCCD with RSIs. First, a difference feature module is adopted to guide the change feature learning process. A multi-scale fusion module is then developed to capture the multi-scale features of ground targets with various shapes and sizes. Finally, a composite loss function composed of dice loss function, focal loss function and mean squared error loss function is utilized to train the DFG-MFF network. Experiments are performed on one pairwise homogeneous dataset and two pairs of heterogeneous datasets, and the comparison with eight state-of-the-art methods well demonstrated the feasibility and advantages of the proposed network for LCCD with RSIs.

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Light-weight neural networks for remote sensing (RS) visual analysis must overcome two inherent redundancies: spatial redundancy from vast, homogeneous backgrounds, and channel redundancy, where extreme scale variations render a single feature space inefficient. Existing models, often designed for natural images, fail to address this dual challenge in RS scenarios. To bridge this gap, we propose LWGANet, a light-weight backbone engineered for RS-specific properties. LWGANet introduces two core innovations: a Top-K Global Feature Interaction (TGFI) module that mitigates spatial redundancy by focusing computation on salient regions, and a Light-Weight Grouped Attention (LWGA) module that resolves channel redundancy by partitioning channels into specialized, scale-specific pathways. By synergistically resolving these core inefficiencies, LWGANet achieves a superior trade-off between feature representation quality and computational cost. Extensive experiments on twelve diverse datasets across four major RS tasks—scene classification, oriented object detection, semantic segmentation, and change detection—demonstrate that LWGANet consistently outperforms state-of-the-art light-weight backbones in both accuracy and efficiency. Our work establishes a new, robust baseline for efficient visual analysis in RS images.

The past years have witnessed great progress on remote sensing (RS) image interpretation and its wide applications. With RS images becoming more accessible than ever before, there is an increasing demand for the automatic interpretation of these images. In this context, the benchmark datasets serve as an essential prerequisites for developing and testing intelligent interpretation algorithms. After reviewing existing benchmark datasets in the research community of RS image interpretation, this article discusses the problem of how to efficiently prepare a suitable benchmark dataset for RS image interpretation. Specifically, we first analyze the current challenges of developing intelligent algorithms for RS image interpretation with bibliometric investigations. We then present the general guidances on creating benchmark datasets in efficient manners. Following the presented guidances, we also provide an example on building RS image dataset, i.e., Million Aerial Image Dataset (Online. Available: https://captain-whu.github.io/DiRS/0 ), a new large-scale benchmark dataset containing a million instances for RS image scene classification. Several challenges and perspectives in RS image annotation are finally discussed to facilitate the research in benchmark dataset construction. We do hope this article will provide the RS community an overall perspective on constructing large-scale and practical image datasets for further research, especially data-driven ones.

Object detection has a great significance to remote sensing image recognition. Conventional object detection methods by using horizontal bounding box have shown good performance in general images. However, because of looking down perspective of remote sensing images, rotation bounding box is more suitable and precise for object detection. Although rotation bounding box has been researched by some works for remote sensing images, most of them are still two stages. In this paper, by improvement of YOLO architecture, we propose an one-stage object detection method to predict rotation bounding box for remote sensing images. Firstly, in the data preprocessing stage, an image cropping operation is utilized instead of zooming operation to generate suitable input data for network. Meanwhile, in order to avoid an object from being divided, an overlapping band is set during cropping. Secondly, a novel rotation bounding box representation method is introduced, and a corresponding loss function is designed in training process. Experiments on the Dota dataset demonstrate that our method outperforms state-of-the-art rotation objects detection methods, in terms of mAP, our method achieves 73.50%mAP, which is higher than methods based on rotation bounding box by 2.0%.

How to represent the object more appropriately in oriented object detection is an essential problem to be solved, there are many solutions for the object represented. It is a relatively novel approach to represent objects as a number of sample points useful for both localization and recognition. However, the current point-set-based representation methods do not effectively supervise all points for learning, and the internal information of the convex hull in the point set cannot be effectively learned. Therefore, this letter proposes point set distance (PSD) loss, which learns set-to-set supervision of objects to effectively represent objects. Besides, most of the current sample selection strategies are based on the Intersection over Union (IoU), but these methods cannot comprehensively measure candidate samples quality. To select high-quality point sets, we propose to use the probability distribution of point sets to select the positive samples. Our probabilistic point set sample selection (PPSS) scheme effectively exploits the classification information, regression information, and the distribution characteristics of the point set. Experimental results on remote sensing image datasets including DOTA, DIOR-R, and HRSC2016, demonstrate the proposed method for arbitrary-oriented object detection achieves consistent and substantial improvements.

Oriented object detection in remote sensing images remains a challenging task due to arbitrary target rotations, extreme scale variations, and complex backgrounds. However, current rotated detectors still face several limitations: insufficient orientation-sensitive feature representation, feature misalignment for rotated proposals, and unstable optimization of rotation parameters. To address these issues, this paper proposes an enhanced Rotation-Sensitive Feature Pyramid Network (RSFPN) framework. Building upon the effective Oriented R-CNN paradigm, we introduce three novel core components: (1) a Dynamic Adaptive Feature Pyramid Network (DAFPN) that enables bidirectional multi-scale feature fusion through semantic-guided upsampling and structure-enhanced downsampling paths; (2) an Angle-Aware Collaborative Attention (AACA) module that incorporates orientation priors to guide feature refinement; (3) a Geometrically Consistent Multi-Task Loss (GC-MTL) that unifies the regression of rotation parameters with periodic smoothing and adaptive weight mechanisms. Comprehensive experiments on the DOTA-v1.0 and HRSC2016 benchmarks show that our RSFPN achieves superior performance. It attains a state-of-the-art mAP of 77.42% on DOTA-v1.0 and 91.85% on HRSC2016, while maintaining efficient inference at 14.5 FPS, demonstrating a favorable accuracy-efficiency trade-off. Visual analysis confirms that our method produces concentrated, rotation-aware feature responses and effectively suppresses background interference. The proposed approach provides a robust solution for detecting multi-oriented objects in high-resolution remote sensing imagery, with significant practical value for urban planning, environmental monitoring, and security applications.

Detecting oriented objects in optical remote sensing images has been consistently challenging due to difficulties in bounding boxes localization. The cascaded regression framework, widely employed for high-quality bounding box refinement, has demonstrated effectiveness in this domain. However, our experiments reveal a discontinuity issue in bounding box optimization in cascaded regression framework. As a result, performance gain is not guaranteed across all stages in this framework. In this paper, we propose a Distribution Discriminative Detector(DDDet) to address the above issues and enhance the optimization of bounding boxes in oriented object detection. Specifically, a novel Conditional Anchor Refinement Framework(CARF) is designed to improve cascaded regression structure. CARF distinguishes bounding boxes with different distributions, adaptively optimizing them within the well-assigned regressors. Subsequently, the Aligned Convolution Module(ACM) is integrated into each regressor, facilitating the continuous alignment between features and refined anchors. Furthermore, the Geometry-guided Training Sample Selection(GTSS) method is incorporated into CARF to assign labels based on object shape priors. Experimental results show that DDDet obtains state-of-the-art performance on mainstream datasets for oriented object detection in remote sensing image, which demonstrates the effectiveness of the proposed method. Our method surpasses many current single-stage detectors, two-stage detectors, and refine-stage detectors, achieving the mAP of 79.41% on DOTA dataset, and 44.15% on FAIR1M dataset.

Multispectral oriented object detection faces challenges due to both inter-modal and intra-modal discrepancies. Recent studies often rely on transformer-based models to address these issues and achieve cross-modal fusion detection. However, the quadratic computational complexity of transformers limits their performance in remote sensing imagery. Inspired by the efficiency and lower complexity of Mamba in long sequence tasks, we propose Disparity-guided Multispectral Mamba (DMM), a multispectral oriented object detection framework comprised of a Disparity-guided Cross-modal Fusion Mamba (DCFM) module, a Multi-scale Target-aware Attention (MTA) module, and a Target-Prior Aware (TPA) auxiliary task. The DCFM module leverages disparity information between modalities to adaptively merge features from RGB and IR images, mitigating inter-modal conflicts. The MTA module aims to enhance feature representation by focusing on relevant target regions within the RGB modality, addressing intra-modal variations. The TPA auxiliary task utilizes single-modal labels to guide the optimization of the MTA module, ensuring it focuses on targets and their local context. Extensive experiments on the DroneVehicle and VEDAI datasets demonstrate the effectiveness of our method, which outperforms state-of-the-art methods while maintaining computational efficiency. Code will be available at https://github.com/Another-0/DMM.

Remote sensing images are inevitably affected by the degradation of haze with complex appearance and non-uniform distribution, which remarkably affects the effectiveness of downstream remote sensing visual tasks. However, most current methods principally operate in the original pixel space of the image, which hinders the exploration of the frequency characteristics of remote sensing images, resulting in these models failing to fully exploit their representation ability to produce high-quality images. This paper proposes a frequency-oriented remote sensing dehazing Transformer named FOTformer, to explore information in the frequency domain to eliminate disturbances caused by haze in remote sensing images. It contains three components. Specifically, we developed a frequency-prompt attention evaluator to estimate the self-correlation of features in the frequency domain rather than the spatial domain, improving the image restoration performance. We propose a content reconstruction feed-forward network that captures information between different scales in features and integrates and processes global frequency domain information and local multi-scale spatial information in Fourier space to reconstruct the global content under the guidance of the amplitude spectrum. We designed a spatial-frequency aggregation block to exchange and fuse features from the frequency domain and spatial domain of the encoder and decoder to facilitate the propagation of features from the encoder stream to the decoder and alleviate the problem of information loss in the network. The experimental results show that the FOTformer achieved a more competitive performance against other remote sensing dehazing methods on commonly used benchmark datasets.

The development of technological devices, such as satellites and drones, has made it easier to collect images and videos from above. With rich and diverse data sources, the problem of detecting objects in aerial images is formed to serve real-life situations: rescue missions, social scenarios, security needs, and more. This issue attracts a lot of attention from researchers in computer vision because of its high applicability in real life. However, object detection in images collected from drones faces many significant challenges due to the complex factors of real-life environments. To overcome these difficulties, many studies focus on developing effective models for detecting and tracking objects from UAV systems. In this paper, our primary emphasis is comprehensive survey of methodologies pertaining to horizontal and oriented object detection. We analyzed and compared existing approaches such as CNN-based vs. Transformer-based, Anchor-based vs. Anchor-free. Moreover, we also learned about ways to represent objects using bounding boxes in oriented object detection. After researching many practical and innovative techniques in different approaches, we have carefully selected 15 methods for horizontal object detection and 18 for oriented object detection that were recently researched and developed to conduct classifications, surveys and assessments. We also provide a taxonomy mind map to assist readers in gaining an overview of the methods we surveyed. Additional, we examine 17 aerial image datasets collected from platforms and in various locations worldwide. These are typical datasets used to serve two primary tasks: Horizontal Object Detection and Oriented Object Detection. Then, we compared the experimental resultsof the previously introduced methods on four typical datasets: VisDrone, UAVDT, DOTAv1.0, and HRSC2016. The above datasets present diversity in the number of classes and the complexity of real-life conditions. Furthermore, they have been tested with various methods and shown remarkable results. For the reasons mentioned, we have enough basis to confirm that the comparison results are objective so that other research groups can make accurate comments and assessments on experimental methods on each dataset. We believe that updating and synthesizing the latest research will provide complete and comprehensive information, helping researchers to have more survey material for the development of the field of object detection in the future.

In recent years, there has been a significant increase in the production of high-resolution aerial and satellite imagery. Analyzing and extracting urban features from these images, especially building components, is a significant challenge in photogrammetry and remote sensing. Meanwhile, deep convolution neural networks have been used as a powerful model in the semantic segmentation of building features. However, due to the structure of these types of deep convolution networks, accurate retrieval of building boundary information during training will be difficult, and this will lead to ambiguous boundary areas. On the other hand, the use of distributed-based loss functions, such as the binary cross-entropy loss alone cannot improve the segmentation accuracy in the boundary areas of building features. Accordingly, in this paper, a derivative boundary loss function is introduced to optimize and enhance the extraction of buildings in border areas. To calculate the proposed boundary loss function, distance transform image (DTI), is obtained from ground-truth images and predicted images, that derived from the segmentation network. In this paper, a derivative method for calculating DTI is presented. Another advantage of the proposed loss function is its ability to be used in a wide range of deep convolution segmentation networks. The proposed method was investigated and tested using the ISPRS Potsdam and Vaihingen data sets. The results of this implementation show the superiority in the criteria of evaluation and improvement of buildings extraction if the proposed boundary loss function is used along with the distributed-based loss function.

As an important link between human and nature, land use/land cover change (LUCC) has become a research hotspot since the first day of the issue initiated. Remote sensing observation supplies important data source for LUCC research. With the constant improvement of the remote sensed image spatial resolution and the continuous development of computer scientific algorithms and models, the study of semantic segmentation in the field of automatic interpretation of remote sensed images has promoted quickly. There have been a number of achievements focusing on the one-class extraction of LUCC classification system, but limited progress in multi-class classifying mission when facing high resolution remote sensing data by using semantic segmentation model, because of its sophisticated structure, the phenomenon of synonyms spectrum and foreign body with spectrum in images. Additionally, the limitation of the semantic segmentation model is a crucial issue which needs to be solv for precision of classification in class recognition and the perfection of semantic segmentation on pixel level as well. The High-Resolution network (HRnet) model was used and improved in the study for semantic segmentation because it has the advantage of low resolution loss. In the LUCC classification work, the distribution of classes (such as cultivated land, woodland, grassland, other land, water, etc.) are usually extremely imbalanced, that leads to the limited classification recognition results of land types when using HRnet. So a combined Loss function of Lovasz Softmax Loss+Cross Entropy Loss was used in HRnet to classify the land cover of remote sensing images, to meet the requirements of high-resolution image classification not only in terms of low resolution loss but also in terms of class recognition. The combined loss function provided the direction of the model, and the appropriate loss function improved the performance of the model when faced with the imbalanced distribution of land classes. The results are as follows: 1) Compared with Deeplab and Unet, HRnet model performed better in segmentation results; 2) HRnet model with combined Loss function Lovasz Softmax Loss+Cross Entropy Loss (HRnet+) had better performance, and its test accuracy PA(Pixel Accuracy) value was 0.9577, MIOU (Mean Intersection over Union) value was 0.8801, and Kappa value was 0.9455. This indicated that the HRnet model with low loss of resolution could achieve better results in the automatic segmentation of high-resolution remote sensing images, and the combined loss function constructed in this study could effectively solve the problem of imbalanced distribution of classes in remote sensing images, and the edge optimization ability was also more significant.

In recent years, oriented object detection has garnered significant attention due to its broad applicability and the high performance of recent models. Due to the high resolution of remote-sensing images, object detection models typically require substantial computational resources and time. To address this problem, this paper introduces sparse attention module to the oriented object detector that improves the efficiency by selective calculating attention on foreground features. We have refined the key components to make the pipeline more suitable for remote sensing images and oriented object detection. Based on the improvements in this paper, our model achieves significant performance improvements of 2% mAP50 on DIOR-R and 1.2% mAP50 on DOTAv1 compared to baseline ARS-DETR, as well as a 10.9% improvement in FPS and a 24.2% reduction in FLOPs.