Eagle-Eye-Inspired Attention for Object Detection in Remote Sensing

Recent studies in remote sensing object detection have made excellent progress and shown promising performance. However, most current detectors only explore rotation-invariant feature extraction but disregard the valuable spatial and semantic prior knowledge in remote sensing images (RSIs), which limits the detection performance when encountering blurred or heavy occluded objects. To address this issue, we propose a mask-reconstruction relation learning (MRRL) framework to learn such prior knowledge among objects and a consistency-reasoning transformer over relation proposals (CTRP) to recognize objects with limited visual features via consistency reasoning. Specifically, MRRL framework applies random mask to some objects in the training dataset and performs masked objects reconstruction to guide the network to learn the distribution consistency of objects. CTRP is the core component of the MRRL framework, which models the interaction between spatial and semantic priors, and uses easy detected objects to reason hard detected objects. The trained CTRP can be integrated into the existing detector to improve the ability of object detection with limited visual features in RSIs. Extensive experiments on widely-used datasets for two distinct tasks, namely remote sensing object detection task and occluded object detection task, demonstrate the effectiveness of the proposed method. Source code is available at https://github.com/sunpeng96/CTRP_mmrotate.

With the development of remote sensing technology, remote sensing object detection has been widely applied in various fields, but it still faces some thorny challenges, such as the following: 1) the complexity of object scale changes in remote sensing images makes it difficult to improve the performance of small object detection and 2) remote sensing images have complex backgrounds and densely arranged small and weak objects, which pose a serious problem of feature interference. To alleviate these challenges, we propose an end-to-end adaptive feature separation network called AFSNet, which includes a scale-aware module (SAM) and a class-aware module (CAM). The SAM mainly enables feature maps of different resolutions to detect objects of different scales. Shallow feature maps mainly suppress the features of large objects they contain to focus on small object detection, while deep feature maps increase the detailed features of large objects they contain to focus on large object detection. The CAM is mainly used to distinguish the features in the feature map by category, separating the features of different categories into different channels, thus mitigating the problem of inter class feature interference, and blocking background interference. The effectiveness of this article has been proven on the NWPU VHR-10, IPIU-M, DIOR, and DOTA2.0 datasets. It can be widely applied in civilian, military, and other fields. Through experimental verification, our AFSNet achieved 97.70% mAP on the NWPU VHR-10 dataset, 78.9% mAP on the DIOR dataset, and 58.22% mAP on the DOTA2.0 dataset. Our code is available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Xidian-AIGroup190726/AFSNet</uri>.

Applications of remote sensing images in both defense and civilian sectors have spurred substantial research interest. In the field of remote sensing, object detection confronts challenges such as complex backgrounds, scale diversity, and the presence of dense small objects. To address these issues, we propose an improved deep learning-based model, the Global Multi-scale Fusion Self-calibration Network, which is expected to contribute to alleviating the challenges. It consists of three main components: the hierarchical feature aggregation backbone, which uses improved modules such as the receptive field context-aware feature extraction module, the global information acquisition module, and the simple parameter-free attention module to extract key features and minimize the background interference. To couple multi-scale features, we enhanced the fusing component and designed the multi-scale enhanced pyramid structure integrating the proposed new modules. During the detection phase, especially when focusing on small object detection, we designed a novel convolutional attention feature fusion head. This head is constructed to integrate local and global branches for feature extraction by leveraging channel shuffling and multi-head attention mechanisms for efficient and accurate detection. Experiments on the Detection in Optical Remote Sensing Images (DIOR), Northwestern Polytechnical University Very High-Resolution‐10 (NWPU VHR‐10), remote sensing object detection (RSOD), and DOTAv1.0 data sets show that our method achieves mAP50(mean average precision at 50% intersection over union) of 69.7%, 91.3%, 94.2%, and 70.0%, respectively, outperforming existing comparative methods. The proposed network is expected to provide new perspectives for remote sensing tasks and possible solutions for relevant applications in the image domain.

Object detection plays a crucial role in scene understanding and has extensive practical applications. In the field of remote sensing object detection, both detection accuracy and robustness are of significant concern. Existing methods heavily rely on sophisticated adversarial training strategies that tend to improve robustness at the expense of accuracy. However, detection robustness is not always indicative of improved accuracy. Therefore, in this paper, we research how to enhance robustness, while still preserving high accuracy, or even improve both simultaneously, with simple vanilla adversarial training or even in the absence thereof. In pursuit of a solution, we first conduct an exploratory investigation by shifting our attention from adversarial training, referred to as adversarial fine-tuning, to adversarial pretraining. Specifically, we propose a novel pretraining paradigm, namely structured adversarial self-supervised (SASS) pretraining, to strengthen both clean accuracy and adversarial robustness for object detection in remote sensing images. At a high level, SASS pretraining aims to unify adversarial learning and self-supervised learning into pretraining and encode structured knowledge into pretrained representations for powerful transferability to downstream detection. Moreover, to fully explore the inherent robustness of vision Transformers and facilitate their pretraining efficiency, by leveraging the recent masked image modeling (MIM) as the pretext task, we further instantiate SASS pretraining into a concise end-to-end framework, named structured adversarial MIM (SA-MIM). SA-MIM consists of two pivotal components, structured adversarial attack and structured MIM (S-MIM). The former establishes structured adversaries for the context of adversarial pretraining, while the latter introduces a structured local-sampling global-masking strategy to adapt to hierarchical encoder architectures. Comprehensive experiments on three different datasets have demonstrated the significant superiority of the proposed pretraining paradigm over previous counterparts for remote sensing object detection. More importantly, regardless of with or without adversarial fine-tuning, it enables simultaneous improvements on detection accuracy and robustness as expected, promisingly alleviating the dependence on complicated adversarial fine-tuning.

With the wide application of remote sensing images (RSIs) in military and civil fields, remote sensing object detection (RSOD) has gradually become a hot research direction. However, we observe two main challenges for remote sensing object detection, namely the complicated background and the small objects issues. Given the different appearances of generic objects and remote sensing objects, the detection algorithms designed for the former usually cannot perform well for the latter. We propose a novel global to local scale-aware detection network (GLSANet) for remote sensing object detection, aiming to solve the above mentioned two challenges. Firstly, we design a global semantic information interaction module (GSIIM) to excavate and reinforce the high-level semantic information in the deep feature map, which alleviates the obstacles of complex background on foreground objects. Secondly, we optimize the feature pyramid network to improve the performance of multiscale object detection in RSIs. Finally, a local attention pyramid (LAP) is introduced to highlight the feature representation of small objects gradually while suppressing the background and noise in the shallower feature maps. Extensive experiments on three public datasets demonstrate that the proposed method achieves superior performance compared with the state-of-the-art detectors, especially on small object detection dataset. Specifically, our algorithm reaches 94.57% mAP on NWPU VHR-10 dataset, 95.93% mAP on RSOD dataset and 77.9% mAP on DIOR dataset, respectively.

Object detection in remote sensing images is a major challenge because of the complex background and diverse appearance of remote sensing images. At the same time, targets may have different sizes and densely distributed targets in the image. To address these challenges, we propose an enhanced YOLOv8 model that integrates three key components: dynamic convolution (DyConv), which replaces the ordinary convolutional layer in the C2F module in the backbone network, and adaptively adjusts the convolution filter according to the input features to enhance the model’s ability to deal with objects of different scales and appearance. Dual level Routing Attention (BRA) was used to process the high-level features of the backbone network, suppress irrelevant background information, emphasize effective features and establish semantic correlation. Asymptotic Feature Pyramid Network (AFPN) improves multi-scale feature fusion to ensure the effective fusion of small object details in the low level and high-level semantic information. Through experiments on the Remote Sensing Object Detection (RSOD) dataset, our improved YOLOv8 model shows significant performance improvement over the original model, achieving 65.4% of the mAP50-95 score, an improvement of 3.3%. Compared with the mainstream single-stage, two-stage and DETR models, our proposed model achieves the improvement of detection accuracy while ensuring computational efficiency.

Object detection in remote sensing images (RSIs) requires the locating and classifying of objects of interest, which is a hot topic in RSI analysis research. With the development of deep learning (DL) technology, which has accelerated in recent years, numerous intelligent and efficient detection algorithms have been proposed. Meanwhile, the performance of remote sensing imaging hardware has also evolved significantly. The detection technology used with high-resolution RSIs has been pushed to unprecedented heights, making important contributions in practical applications such as urban detection, building planning, and disaster prediction. However, although some scholars have authored reviews on DL-based object detection systems, the leading DL-based object detection improvement strategies have never been summarized in detail. In this paper, we first briefly review the recent history of remote sensing object detection (RSOD) techniques, including traditional methods as well as DL-based methods. Then, we systematically summarize the procedures used in DL-based detection algorithms. Most importantly, starting from the problems of complex object features, complex background information, tedious sample annotation that will be faced by high-resolution RSI object detection, we introduce a taxonomy based on various detection methods, which focuses on summarizing and classifying the existing attention mechanisms, multi-scale feature fusion, super-resolution and other major improvement strategies. We also introduce recognized open-source remote sensing detection benchmarks and evaluation metrics. Finally, based on the current state of the technology, we conclude by discussing the challenges and potential trends in the field of RSOD in order to provide a reference for researchers who have just entered the field.

Most current researches primarily focus on improving experimental accuracy using large models, often neglecting the deployment challenges. There is a growing need for lightweight algorithms in certain remote sensing devices. Moreover, remote sensing images (RSIs) often contain numerous small, densely distributed targets, which pose significant detection challenges. To address these issues, we have improved the YOLOv8s network and developed a lightweight remote sensing object detection (RSOD) network based on multiscale features fusion and context information (MFFCI–YOLOv8). This network combines multiscale feature fusion and contextual information to accurately detect objects in RSIs. First, we introduce the lightweight CSP bottleneck with attention module, which utilizes partial convolution calculation and SimAM attention mechanisms to decrease the number of parameters and computational complexity while enhancing feature extraction capabilities. Second, we design the gate spatial pyramid pooling fast module to enhance the model's perception of scale and contextual information, thus improving the detection of small objects. Last, we employ the multiscale fusion lightweight neck module for more efficient multiscale feature fusion, preventing the loss of small objects. Compared to YOLOv8s, our overall model reduces the number of parameters by 7.7% and FLOPs by 11.9%. We validated the accuracy of MFFCI–YOLOv8 on two remote sensing datasets, NWPU VHR-10 and VisDrone. The experimental results demonstrate that our model offers a low computational cost and high detection accuracy compared to other RSOD models and other YOLO models.

BiF-DETR:Remote sensing object detection based on Bidirectional information fusion

Remote sensing object detection (RSOD) models play an increasingly important role in modern remote sensing systems. However, during model delivery, sharing, and deployment, RSOD models face increasing risks of unauthorized redistribution, illegal replication, and intellectual property infringement. To mitigate these threats, this paper proposes a white-box watermarking framework for RSOD models that enables reliable copyright verification while preserving the performance of the primary detection task. Specifically, a gradient-based sensitivity analysis of the detection loss is first performed to adaptively identify model parameters that minimally affect detection performance, which are then selected as watermark carriers. Subsequently, a parameter-ranking-based watermark encoding scheme is developed, where watermark bits are embedded by enforcing relative ordering constraints between parameter pairs. To further improve robustness under practical deployment conditions, an attack-simulation-driven training strategy is introduced, in which common perturbations and watermark removal attacks are simulated during the embedding process. In addition, a stealthiness enhancement strategy based on statistical distribution constraints is designed to maintain consistency between the distribution of watermarked parameters and those of the original model, thereby reducing the risk of watermark exposure and localization. Extensive experiments across multiple RSOD datasets and detection architectures demonstrate that the proposed method achieves a high copyright verification success rate with negligible impact on detection accuracy and exhibits strong robustness and stealthiness against a variety of watermark removal attacks.

Remote sensing image object detection and instance segmentation are widely valued research fields. A convolutional neural network (CNN) has shown defects in the object detection of remote sensing images. In recent years, the number of studies on transformer-based models increased, and these studies achieved good results. However, transformers still suffer from poor small object detection and unsatisfactory edge detail segmentation. In order to solve these problems, we improved the Swin transformer based on the advantages of transformers and CNNs, and designed a local perception Swin transformer (LPSW) backbone to enhance the local perception of the network and to improve the detection accuracy of small-scale objects. We also designed a spatial attention interleaved execution cascade (SAIEC) network framework, which helped to strengthen the segmentation accuracy of the network. Due to the lack of remote sensing mask datasets, the MRS-1800 remote sensing mask dataset was created. Finally, we combined the proposed backbone with the new network framework and conducted experiments on this MRS-1800 dataset. Compared with the Swin transformer, the proposed model improved the mask AP by 1.7%, mask APS by 3.6%, AP by 1.1% and APS by 4.6%, demonstrating its effectiveness and feasibility.

The presence of shadows in high-resolution (HR) remote-sensing images reduces object detection accuracy. To address this problem, in this paper, we proposed a deep neural network algorithm for shadow detection by using the AISD and SSAD remote-sensing shadow image datasets. To improve the ability to extract spatial information from feature maps, we developed a cross-spatial attention module that focuses on semantic information in the horizontal and vertical directions at each position point on the remote-sensing image. This module overcomes the limitations of existing technologies in accurately judging small areas and suspected shadow areas and in missing or incorrectly detected shadow areas. In addition, to improve the ability to extract shadow features and the accuracy of shadow detection in remote-sensing images, we developed a channel attention module that assigns more attention to channels that conform to the shadow color characteristics. The network architecture comprises an encoder – decoder structure, with ResNeXt50 used as the backbone for the encoder and a multi resolution parallel fusion (MRPF) designed for the decoder; cross-spatial and channel attention were incorporated into the decoder unit. Experimental results demonstrated the superior performance of the proposed algorithm, with an F1 score of 92.6% for the shadow category on the test set, thus, outperforming other algorithms and making the proposed method an effective solution for shadow detection in HR remote-sensing images.

The study of remote sensing image object detection has excellent research value in environmental protection and public safety. However, the performance of the detectors is unsatisfactory due to the large variability of object size and complex background noise in remote sensing images. Therefore, it is essential to improve the detection performance of the detectors. Inspired by the idea of "divide and conquer", we proposed a Multiple Receptive Field Attention(MRFA) to solve these problems and which is a plug-and-play attention method. First, we use the method of multiple receptive field feature map generation to convert the input feature map into four feature maps with different receptive fields. In this way, the small, medium, large, and immense objects in the input feature maps are "seen" in these feature maps, respectively. Then, we used the multiple attention map fusion method to focus objects of different sizes separately, which can effectively suppress noise in the background of remote sensing images. Experiments on remote sensing object detection datasets DIOR and HRRSD demonstrate that the performance of our method is better than other state-of-the-art attention modules. At the same time, the experiments on remote sensing image semantic segmentation dataset WHDLD and classification dataset AID prove the generalization and superiority of our method.

Object detection in remote sensing imagery presents challenges due to low resolution, complex backgrounds, occlusions, and scale variations, which are critical in disaster response, environmental monitoring, and surveillance. This study proposes a robust object detection framework integrating super-resolution techniques with advanced feature extraction algorithms for remote sensing images. The hybrid model combines Advanced StyleGAN and Swin Transformer. Advanced StyleGAN enhances image resolution, facilitating the detection of small and occluded objects, while Swin Transformer employs hierarchical attention mechanisms for effective feature extraction. Preprocessing techniques, including data augmentation, are incorporated to improve the diversity and accuracy of the training dataset. Evaluation on datasets such as VEDAI-VISIBLE and VEDAI-IR demonstrated exceptional performance, achieving an mAP@0.5 of 97.2%, mAP@0.5:0.95 of 72.8%, and F1-Score of 0.93, with an inference time of 42 ms. The framework maintained robustness under challenging conditions, such as low light and fog, outperforming YOLOv9-S, YOLOv9-E, and DCNN-based methods. Furthermore, it surpassed state-of-the-art models on RSOD and NWPU VHR-10 datasets, achieving superior detection accuracy and robustness. This framework offers a significant advancement in remote sensing object detection, providing an effective solution for complex scenarios. Future work may focus on optimizing computational efficiency and expanding the framework to multimodal or dynamic object detection tasks.

With the wide applications of remote sensing technology in engineering, the demands of efficient object detection algorithms for remote sensing images have also been significantly increased in recent years. Traditional detection methods have the shortcomings of low accuracy and poor robustness, which is difficult to be applied to remote sensing images with complex background and varieties of objects. Recently, the deep convolutional neural networks have already shown great advances in object detection and outperformed many traditional methods. In this work, we study the performance of a region proposal-based method, Mask R-CNN, for detecting airplane and ship in remote sensing images. Specifically, we add an FPN module to improve the accuracy of small objects detection, and a mask branch is used to describe the shape of objects. In addition, we used a series of data augmentation strategies during training for meeting the CNN’s requirement of training samples diversity. The experimental results show that our model has superior performance in object detection of remote sensing images.