检索结果-内蒙古大学图书馆

ASL-OOD:Hierarchical Contextual Feature Fusion with Angle-Sensitive Loss for oriented object detection

Computers, Materials & Continua 2025年第2期82卷 1879-1899页

作者： Kexin Wang Jiancheng Liu Yuqing Lin Tuo Wang Zhipeng Zhang Wanlong Qi Xingye Han Runyuan Wen Northwest Institute of Mechanical and Electrical Engineering Xianyang712099China School of Information Engineering Chang’an UniversityXi’an710064China School of Computer Science and Technology Xidian UniversityXi’an710071China

Detecting oriented targets in remote sensing images amidst complex and heterogeneous backgrounds remains a formidable challenge in the field of object *** frameworks for oriented detection modules are constrained by intrinsic limitations,including excessive computational and memory overheads,discrepancies between predefined anchors and ground truth bounding boxes,intricate training processes,and feature alignment *** overcome these challenges,we present ASL-OOD(Angle-based SIOU Loss for oriented object detection),a novel,efficient,and robust one-stage framework tailored for oriented object *** ASL-OOD framework comprises three core components:the Transformer-based Backbone(TB),the Transformer-based Neck(TN),and the Angle-SIOU(Scylla Intersection over Union)based Decoupled Head(ASDH).By leveraging the Swin Transformer,the TB and TN modules offer several key advantages,such as the capacity to model long-range dependencies,preserve high-resolution feature representations,seamlessly integrate multi-scale features,and enhance parameter *** improvements empower the model to accurately detect objects across varying *** ASDH module further enhances detection performance by incorporating angle-aware optimization based on SIOU,ensuring precise angular consistency and bounding box *** approach effectively harmonizes shape loss and distance loss during the optimization process,thereby significantly boosting detection *** evaluations and ablation studies on standard benchmark datasets such as DOTA with an mAP(mean Average Precision)of 80.16 percent,HRSC2016 with an mAP of 91.07 percent,MAR20 with an mAP of 85.45 percent,and UAVDT with an mAP of 39.7 percent demonstrate the clear superiority of ASL-OOD over state-of-the-art oriented object detection *** findings underscore the model’s efficacy as an advanced solution for challenging remote sensing object detection tasks.

关键词： oriented object detection transformer deep learning

来源：评论

学校读者我要写书评

暂无评论

RQFormer: Rotated Query Transformer for end-to-end oriented object detection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 266卷

作者： Zhao, Jiaqi Ding, Zeyu Zhou, Yong Zhu, Hancheng Du, Wen-Liang Yao, Rui El Saddik, Abdulmotaleb China Univ Min & Technol Sch Comp Sci & Technol Xuzhou 221116 Peoples R China Minist Educ Mine Digitizat Engn Res Ctr Xuzhou 221116 Peoples R China Innovat Res Ctr Disaster Intelligent Prevent & Eme Xuzhou 221116 Peoples R China Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON K1N 6N5 Canada

oriented object detection presents a challenging task due to the presence of object instances with multiple orientations, varying scales, and dense distributions. Recently, end-to-end detectors have made significant strides by employing attention mechanisms and refining a fixed number of queries through consecutive decoder layers. However, existing end-to-end oriented object detectors still face two primary challenges: (1) misalignment between positional queries and keys, leading to inconsistency between classification and localization;and (2) the presence of a large number of similar queries, which complicates one-to-one label assignments and optimization. To address these limitations, we propose an end-to-end oriented detector called the Rotated Query Transformer, which integrates two key technologies: Rotated RoI Attention (RRoI Attention) and Selective Distinct Queries (SDQ). First, RRoI Attention aligns positional queries and keys from oriented regions of interest through cross-attention. Second, SDQ collects queries from intermediate decoder layers and filters out similar ones to generate distinct queries, thereby facilitating the optimization of one-to-one label assignments. Finally, extensive experiments conducted on four remote sensing datasets and one scene text dataset demonstrate the effectiveness of our method. To further validate its generalization capability, we also extend our approach to horizontal object detection. The code is available at https://***/ wokaikaixinxin/RQFormer.

关键词： oriented object detection Transformer End-to-end detectors Attention Query update

来源：评论

学校读者我要写书评

暂无评论

GOOD: Towards domain generalized oriented object detection

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2025年 223卷 207-220页

作者： Bi, Qi Zhou, Beichen Yi, Jingjun Ji, Wei Zhan, Haolan Xia, Gui-Song Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Univ Amsterdam Fac Sci NL-1098XH Amsterdam Netherlands Yale Univ Sch Med New Haven CT 06520 USA Monash Univ Fac Informat Technol Melbourne Vic 3800 Australia

oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution, which is far from reality. In this paper, we propose the task of domain generalized oriented object detection, which intends to explore the generalization of oriented object detectors on arbitrary unseen target domains. Learning domain generalized oriented object detectors is particularly challenging, as the cross-domain style variation not only negatively impacts the content representation, but also leads to unreliable orientation predictions. To address these challenges, we propose a generalized oriented object detector (GOOD). After style hallucination by the emerging contrastive language-image pre-training (CLIP), it consists of two key components, namely, rotation- aware content consistency learning (RAC) and style consistency learning (SEC). The proposed RAC allows the oriented object detector to learn stable orientation representation from style-diversified samples. The proposed SEC further stabilizes the generalization ability of content representation from different image styles. Notably, both learning objectives are simple, straight-forward and easy-to-implement. Extensive experiments on multiple cross-domain settings show the state-of-the-art performance of GOOD. Source code is available at https://***/BiQiWHU/GOOD.

关键词： oriented object detection Domain generalization Rotation consistency Style hallucination

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptive oriented object detection From Optical to SAR Images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Huang, Hailiang Guo, Jingchao Lin, Huangxing Huang, Yue Ding, Xinghao Xiamen Univ Sch Informat Xiamen 361021 Peoples R China Jianghuai Adv Technol Ctr Hefei 230000 Peoples R China Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410073 Peoples R China

oriented object detection in synthetic aperture radar (SAR) images presents significant challenges due to the scarcity of labeled data. In contrast, acquiring labeled optical remote sensing images is considerably easier. This article proposes a domain adaptive oriented object detection (DAOOD) model, termed the pixel-instance information transfer-based model (PITM). PITM aims to transfer knowledge from optical to SAR domains, thereby reducing the dependency of oriented SAR object detection on labels. Given the pronounced domain disparity between optical and SAR images, the efficient migration of both visual content and rotating instances is incorporated to bridge the gap in their information distribution simultaneously. Specifically, regarding pixel-level information transfer, speckle noise from SAR images is mixed into the optical domain to form an intermediate domain, thus compensating for the visual difference between the two domains. For instance-level information transfer, considering the angle diversity of rotating objects, multiscale and multidirectional spatial information extraction is combined with decoupled instance-invariant features, enhancing the cross-domain discernment capacity of rotating instances. Experimental results on four DAOOD benchmarks (i.e., two optical datasets to two SAR datasets) demonstrate that the proposed PITM significantly improves oriented object detection performance, even in the absence of labeled SAR images. Specifically, it individually outperforms two source-only models by 88.16% and 54.62% in average precision (AP).

关键词： object detection Optical sensors Optical imaging Remote sensing Adaptive optics Integrated optics Synthetic aperture radar Radar polarimetry Adaptation models Feature extraction Decoupled instance Gabor convolutional networks (GCNs) oriented object detection synthetic aperture radar (SAR) unsupervised domain adaption

来源：评论

学校读者我要写书评

暂无评论

Dual Teacher: Improving the Reliability of Pseudo Labels for Semi-Supervised oriented object detection

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Fang, Zhenyu Ren, Jinchang Zheng, Jiangbin Chen, Rongjun Zhao, Huimin Northwestern Polytech Univ Sch Software Xian 710060 Peoples R China NPU Yangtze River Delta Res Inst Suzhou 215400 Taicang Peoples R China Guangdong Polytech Normal Univ Sch Comp Sci Guangzhou 510665 Peoples R China Robert Gordon Univ Natl Subsea Ctr Aberdeen AB21 0BH Scotland

oriented object detection in remote sensing is a critical task for accurately location and measurement of the interested targets. Despite of its success in object detection, deep learning-based detectors rely heavily on extensive data annotation. However, variations in object appearance significantly increase the difficulty and the cost of creating large-scale annotated datasets. Semi-supervised learning (SSL) aims to utilize unlabeled data to enhance object detectors. Among these, pseudo-label-based methods have shown promising results recently. Nonetheless, as training progresses, the accumulation of errors in pseudo labels leads to prediction bias without corrections. To tackle this particular challenge, we present a SSL pipeline, named "dual teacher," for improving the reliability of pseudo labels in the semi-supervised oriented object detection. First, to mitigate the bias caused by limited annotated data, a global burn-in (GBI) strategy is introduced at the beginning of training, which guides the student detector to learn the feature extraction on a global scale. In addition, an online bounding box (bbox) correction module is proposed to decrease the occurrence of mislabeled instances and enhance the reliability of detection. These improvements are facilitated by an additional detector, instead of a single teacher model in the teacher-student architecture. Dual teacher reduces the dependency on the quality of pseudo labels related to the model complexity and combines the strengths of both the two-stage and one-stage detectors. With only 20% labeled data, dual teacher outperforms fully supervised rotated fully convolutional one-stage object detection (R-FCOS), you only look once X-small (YOLOX-s), and rotated region-based convolutional neural network (R-RCNN) by up to 2% on both a large-scale dataset for object detection in aerial images (DOTA) and SODA-A datasets. This reveals its potential in reducing labor-intensive tasks and enhancing robustness against env

关键词： Detectors Remote sensing object detection Training Feature extraction Annotations Semisupervised learning Predictive models Supervised learning Interference Consistency learning dual teacher oriented object detection pseudo label semi-supervised learning (SSL)

来源：评论

学校读者我要写书评

暂无评论

GCA2Net: Global-Consolidation and Angle-Adaptive Network for oriented object detection in Aerial Imagery

引用

REMOTE SENSING 2025年第6期17卷 1077-1077页

作者： Zhou, Shenbo Liu, Zhenfei Luo, Hui Qi, Guanglin Liu, Yunfeng Zuo, Haorui Zhang, Jianlin Wei, Yuxing Chinese Acad Sci Natl Key Lab Opt Field Manipulat Sci & Technol Chengdu 610209 Peoples R China Chinese Acad Sci Inst Opt & Elect Chengdu 610209 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Enhancing the detection capabilities of rotated objects in aerial imagery is a vital aspect of the burgeoning field of remote sensing technology. The objective is to identify and localize objects oriented in arbitrary directions within the image. In recent years, the capacity for rotated object detection has seen continuous improvement. However, existing methods largely employ traditional backbone networks, where static convolutions excel at extracting features from objects oriented at a specific angle. In contrast, most objects in aerial imagery are oriented in various directions. This poses a challenge for backbone networks to extract high-quality features from objects of different orientations. In response to the challenge above, we propose the Dynamic Rotational Convolution (DRC) module. By integrating it into the ResNet backbone network, we form the backbone network presented in this paper, DRC-ResNet. Within the proposed DRC module, rotation parameters are predicted by the Adaptive Routing Unit (ARU), employing a data-driven approach to adaptively rotate convolutional kernels to extract features from objects oriented in various directions within different images. Building upon this foundation, we introduce a conditional computation mechanism that enables convolutional kernels to more flexibly and efficiently adapt to the dramatic angular changes of objects within images. To better integrate key information within images after obtaining features rich in angular details, we propose the Multi-Order Spatial-Channel Aggregation Block (MOSCAB) module, which is aimed at enhancing the integration capacity of key information in images through selective focusing and global information aggregation. Meanwhile, considering the significant semantic gap between features at different levels during the feature pyramid fusion process, we propose a new multi-scale fusion network named AugFPN+. This network reduces the semantic gap between different levels before feature fusion,

关键词： oriented object detection feature extraction feature enhancement convolutional neural network remote sensing image

来源：评论

学校读者我要写书评

暂无评论

AG-Yolo: Attention-Guided Yolo for Efficient Remote Sensing oriented object detection

引用

REMOTE SENSING 2025年第6期17卷 1027-1027页

作者： Wang, Xiaofeng Han, Chengshan Huang, Liang Nie, Ting Liu, Xin Liu, Hao Li, Mingxuan Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Remote sensing can efficiently acquire information and is widely used in many areas. object detection is a key component in most applications. But complex backgrounds in remote sensing images severely degrade detection performance. Current methods fail to effectively suppress background interference while maintaining fast detection speeds. This paper proposes Attention-Guided Yolo (AG-Yolo), an efficient oriented object detection (OOD) method tailored for remote sensing. AG-Yolo incorporates an additional rotation parameter into the head of Yolo-v10 and extends its dual label assignment strategy to maintain high efficiency in OOD. An attention branch is further introduced to generate attention maps from shallow input features, guiding feature aggregation to focus on foreground objects and suppress complex background interference. Additionally, derived from the background complexity, a three-stage curriculum learning strategy is designed to train the model from some much easier samples generated from the labeled data. This approach can give the model a better starting point, improving its ability to handle complicated datasets and increasing detection precision. On the DOTA-v1.0 and DOTA-v1.5 datasets, compared with other advanced methods, our algorithm reduces the processing latency from 33.8 ms to 19.7 ms (a roughly 40% decrease) and produces a certain degree of improvement in the mAP metric.

关键词： remote sensing oriented object detection attention curriculum learning

来源：评论

学校读者我要写书评

暂无评论

Center-Symmetry Representation-Based High-Quality Localization Detector for oriented object detection

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Wu, Qin Zhang, Dabin Pan, Yuying Zhou, Haojie Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214200 Peoples R China

Two-stage detectors are widely used in oriented object detection and have achieved high detection accuracy. However, some inconsistency issues in two-stage detectors limit their further improvement. To overcome these issues, this work proposes an effective two-stage center-symmetry representation-based high-quality localization detector (CR-HLDet) for oriented objects in remote sensing images. It improves the three main components of a typical two-stage detector: neck, region proposal network (RPN), and head. Specifically, in the neck, we introduce a feature enhancement block (FEB) to extract multilevel semantic information to solve the inconsistency in feature fusion. And we use a novel center-symmetry representation to generate high-quality oriented proposals in the RPN. Instead of the prediction of the rotated angle, it utilizes the symmetry of the center point to locate any oriented bounding box (OBB) by three points, which gets rid of the inconsistency between proposals and oriented objects. Finally, we design a dual classification detection head (DCDH) to obtain more robust and reasonable classification confidence. It solves the inconsistency between classification confidence and the regression quality by establishing the connection between the classification branch and the regression branch. The effective combination of the above three modules enables our CR-HLDet to accurately locate oriented objects in remote sensing images. Extensive and comprehensive experiments on three challenging remote sensing datasets (DOTA, HRSC2016, and DIOR-R) demonstrate that the proposed method achieves state-of-the-art performance.

关键词： Feature extraction Proposals Detectors object detection Head Location awareness Semantics Accuracy Remote sensing Neck Center-symmetry representation dual classification detection head (DCDH) high-quality localization multilevel semantic information oriented object detection

来源：评论

学校读者我要写书评

暂无评论

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

引用

REMOTE SENSING LETTERS 2025年第5期16卷 494-505页

作者： Wang, Liuqian Zhang, Jing Li, Jiafeng Zhuo, Li Beijing Univ Technol Sch Informat Sci & Technol Beijing 100124 Peoples R China Beijing Univ Technol Beijing Key Lab Computat Intelligence & Intelligen Beijing Peoples R China

oriented object detection (OOD) in remote sensing images (RSIs) is of increasing interest. Since RSIs often contain many oriented objects, it is valuable and challenging to discover geometric invariance of geospatial objects to improve the model's perception of rotation angle and scale. In this paper, we propose a twin-tower detector (T(2)Det) for OOD in RSIs. Specifically, T(2)Det overcomes the challenges posed by the angles and scales of oriented object by developing a self-supervised (SS) branch that exploits geometric invariance based on the main branch. Then, we design a twin-tower (T-2) loss function to enhance the network's ability to perceive the geometric invariance of geospatial object, where a coarse loss function and a fine loss function are introduced for both branches to optimize the model from coarse to fine. In addition, T-2 loss function optimization strategy based on global or refinement modes is developed to achieve the trade-off between the main branch and the SS branch. On three benchmark datasets, including VEDAI, HRSC2016, and NUAA-SIRST, our T(2)Det achieves competitive performance of 85.15%, 90.66% mAP, and 99.28 P-d, respectively, without unnecessary extra features.

关键词： Remote sensing images twin-tower detector oriented object detection geometric invariance self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

ASSK-Net: Automatic Spatial Selection Kernel Network for Faster oriented object detection

引用

JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING 2025年 1-14页

作者： Hu, Yong Jing, Zhengbiao Su, Yun Zhang, Fang Jing, Donglin Chengdu Vocat & Tech Coll Ind Sch Informat Engn Chengdu Peoples R China Chengdu Vocat & Tech Coll Ind Sch Intelligent Mfg & Automot Chengdu Peoples R China Shanghai Aerosp Control Technol Inst Shanghai 201109 Peoples R China China Aerosp Sci & Technol Corp Res & Dev Ctr Infrared Detect Technol Shanghai 201109 Peoples R China

The improvement in existing remote sensing detectors often relies on complex structures and deeper convolutional layers, leading to a significant increase in computational complexity. While previous works have designed various novel lightweight convolutions to improve target feature representation, these structures often overlook the unique prior knowledge of remote sensing scenes when applied to aerial detection tasks, resulting in decreased detection performance. Specifically, this prior knowledge includes: (1) Accurate detection of aerial objects often requires extensive contextual information. (2) The range of contextual information needed for different categories varies greatly. To address this, our paper fully considers this prior knowledge and proposes the Adaptive Spatial Selection Kernel Network (ASSK-Net). We first use large kernel convolution decomposition operations to decouple a series of convolutions with smaller sizes and rapidly expanding dilation rates, constructing diverse receptive fields with different spatial coverage ranges while significantly reducing computation. Based on this, a spatial selection mechanism is used to effectively weight feature maps with different levels of information richness, enhancing the feature differences between targets and backgrounds. Finally, we design an adaptive class equilibrium loss function, increasing the loss weight with rare categories and other easily confused categories with similar classification scores, thus improving the discriminative capability for rare categories. Comprehensive experiments on datasets (such as DOTA, UCAS-AOD, and HRSC2016) indicate that our ASSK-Net achieves optimal performance, effectively balancing computational complexity and detection accuracy.

关键词： Lightweight network oriented object detection Convolution decomposition Sample balance

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：