检索结果-内蒙古大学图书馆

Bounding Box Vectorization for oriented object detection With Tanimoto Coefficient Regression

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 5181-5193页

作者： Wang, Linfei Zhan, Yibing Liu, Wei Yu, Baosheng Tao, Dapeng Yunnan Univ Sch Informat Sci & Engn FIST LAB Kunming 650091 Peoples R China Yunnan United Vis Innovat Technol Co Ltd Kunming 650504 Peoples R China JD Explore Acad Beijing 100000 Peoples R China Tencent AI Lab Shenzhen 518000 Peoples R China Univ Sydney Camperdown NSW 2006 Australia Yunnan Key Lab Media Convergence Kunming 650032 Yunnan Peoples R China

Current oriented object detection methods mainly utilize a vanilla coordinate-angle representation for bounding box regression, which usually suffers from inconsistency between the bounding box regression losses and prediction errors induced with respect to different rotation angles, aspect ratios, and scales. Therefore, although the existing oriented object detectors have achieved very good performances under coarse evaluation metrics such as AP(50), their performance significantly degrades when using stricter evaluation metric such as AP(75). To address the abovementioned issues, we propose a new regression method with bounding box vectorization that implicitly represents the shape and orientation of an object with a set of orthogonal vectors. By doing this, the proposed method delicately avoids the inconsistency issues encountered in oriented bounding box regression. During training, we introduce the Tanimoto coefficient to evaluate the similarity of the bounding box vector in a shape- and orientation-aware manner, and we refer to the proposed box-to-vector loss as the B2V loss. In addition to 2D object detection, the proposed method can be easily generalized to 3D scenarios involving orientation estimation, such as autonomous driving. We evaluate the proposed method through extensive experiments conducted on four popular oriented object detection datasets, including both 2D and 3D datasets, where the proposed method significantly outperforms the recently developed state-of-the-art methods when using a more accurate evaluation metric.

关键词： object detection Detectors Measurement Three-dimensional displays Task analysis Shape Convergence Bounding box regression implicit vector representation oriented object detection

来源：评论

学校读者我要写书评

暂无评论

FADL-Net: Frequency-Assisted Dynamic Learning Network for oriented object detection in Remote Sensing Images

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第8期20卷 9939-9951页

作者： Fu, Ronghao Chen, Chengcheng Yan, Shuang Zhang, Rui Wang, Xianchang Chen, Huiling Jilin Univ Coll Comp Sci & Technol Changchun 130021 Peoples R China Minist Educ Key Lab Symbol Computat & Knowledge Engn Changchun 130021 Peoples R China Shenyang Aerosp Univ Sch Comp Sci Shenyang 110136 Peoples R China Jilin Univ Coll Instrumentat & Elect Engn Changchun 130021 Peoples R China Wenzhou Univ Coll Comp Sci & Artificial Intelligence Wenzhou 325035 Peoples R China

In the field of Earth observation and computer vision, oriented object detection for remotesensing images is a crucial task that aims to locate objects more accurately in complex scenes containing a large number of densely arranged, large aspect ratio, and arbitrarily oriented objects. Although recently proposed methods have achieved remarkable performance, there are still several challenges to address: 1) interference from complex backgrounds, 2) imbalanced and mismatched label assignments caused by tiny objects and objects with large aspect ratios, and 3) misalignment between the tasks of classification and localization. In this article, we propose a frequency-assisted dynamic learning network (FADL-Net) to overcome the crucial challenges. Concretely, we introduce a spatial-spectral feature pyramid network to adaptively capture global long-range dependency feature representations containing various frequency domains. Meanwhile, to produce more reliable training samples for objects with extreme shapes, we design a geometric aware dynamic label assignment to dynamically mitigate the imbalance and mismatch in label assignment in a coarse-to-fine manner, thereby achieving more stable optimization during the training process. Moreover, we propose a joint-learning rotated quality loss that addresses the inconsistency between classification and localization by dynamically adapting the weights of different samples in the training stage. Extensive experiments on several public remote sensing datasets demonstrate that our method performs favorably against state-of-the-art detection approaches.

关键词： Feature extraction object detection Location awareness Frequency-domain analysis Training Interference Detectors Feature representation label assignment oriented object detection remote sensing

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

Cross-Grid Label Assignment for Arbitrary-oriented object detection in Aerial Images

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2024年 21卷 1页

作者： Rao, Xiaohan Zhou, Liming Harbin Inst Technol Sch Elect & Informat Engn Harbin 150001 Peoples R China Henan Univ Coll Comp & Informat Engn Kaifeng 475001 Peoples R China

As a challenging task in the field of remote sensing, object detection has attracted widespread attention from researchers. However, for aerial images with an imbalanced foreground-background distribution, the existing label assignment assigns insufficient positive samples to aerial objects, severely limiting detection performance. In this letter, we propose the cross-grid label assignment (CLA) to add high-quality positive samples used for training and loss calculation, thereby alleviating the issue of imbalanced positive and negative samples. Furthermore, the feature refinement head (FRHead), which extracts object-oriented features and guiding semantic enhancement, is used to address the inconsistent between classification scores and localization accuracy. Extensive experiments have shown that our method has superior detection performance, with 90.50% and 73.69% mAP on the HRSC2016 and DOTA datasets, respectively.

关键词： Feature extraction Training Kernel object detection Head Shape Semantics Aerial images anchor-based detector feature alignment label assignment oriented object detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic weighting label assignment for oriented object detection

引用

MEMETIC COMPUTING 2024年第3期16卷 285-297页

作者： Zhu, Yunhui Huang, Buliao Nanjing Audit Univ Sch Comp Sci 86 Yushan Rd (W) Nanjing 211815 Jiangsu Peoples R China Jinling Inst Technol Sch Comp Sci & Engn 99 Hongjing Ave Nanjing 211169 Jiangsu Peoples R China

oriented object detection has garnered significant attention for its broad applications in remote sensing image processing. Most oriented detectors perform dense predictions on a set of predefined anchors to generate oriented bounding boxes, where these anchors require classification (cls) and localization (loc) labels for detector training. Recent advancements in label assignment utilize the overall quality score of cls and loc predictions to determine positive and negative samples for each oriented object. However, these methods typically establish the overall quality score by assigning fixed weights to cls and loc quality scores. This approach may not be optimal, as fixed weights fail to dynamically balance cls and loc performance during model optimization, thereby constraining detection efficacy. Motivated by this observation, this paper proposes a Dynamic Weighting Label Assignment (DWLA) algorithm. DWLA dynamically adjusts the weights of individual quality scores based on the current model state to continuously balance cls and loc performance. Additionally, to mitigate the impact of unreliable predictions and achieve more stable training, this paper proposes a level-wise positive sample selection scheme and an object-adaptive scheme for constructing initial candidates of positive samples, respectively. Comprehensive experiments on the DOTA and UCAS-AOD datasets have validated the effectiveness of the proposed DWLA.

关键词： oriented object detection Label assignment Deep learning Remote sensing image

来源：评论

学校读者我要写书评

暂无评论

Feature Enhancement and Alignment for oriented object detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 778-787页

作者： Xie, Xu You, Zhi-Hui Chen, Si-Bao Huang, Li-Li Tang, Jin Luo, Bin Anhui Univ Sch Comp Sci & Technol IMIS Lab Anhui Prov Anhui Prov Key Lab Multimodal Cognit Computat Hefei 230601 Peoples R China

Over the last few years, developments in fields such as aviation and remote sensing have drawn increasing attention to the detection of rotated objects. Unlike general object detection, rotated object detection requires overcoming certain challenges, such as detecting objects with different directions and high aspect ratios. Recently proposed rotated object detectors have achieved good results, but most of them rely on hand-designed anchors, which require manual adjustment of the anchors settings in different scenarios. On the contrary, this article presents a method called FEADet, an anchor-free detector that utilizes feature enhancement and alignment to achieve competitive performance, without the use of anchors. Specifically, in order to better fuse features across different layers, we design an attention feature fusion (AAF) module to reduce the aliasing effect produced by the fusion of different layers. To deal with feature misalignment in detecting objects with orientation, we propose an adaptive alignconv (AAC) module, which is implemented by the constrained deformable convolution and align convolution. The ACC module can efficiently extract object features according to the decoded boxes and predicted constrained offsets. On the two benchmark datasets, dataset for object detection in aerial images (DOTA) and high resolution ship collection 2016 (HRSC2016), a comprehensive evaluation of our method has been conducted to demonstrate the effectiveness of these method in comparison with state-of-the-art methods.

关键词： Deep learning feature alignment feature enhancement oriented object detection remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Rethinking Label Assignment and Sampling Strategies for Two-Stage oriented object detection

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Qian, Jinjin Liu, Chengxu Ai, Yubin Zhao, Guoshuai Qian, Xueming Xi An Jiao Tong Univ Sch Software Engn Xian 710049 Peoples R China Xi An Jiao Tong Univ Sch Informat & Commun Engn Xian 710049 Peoples R China

oriented object detection seeks to determine both the position and orientation of objects, yet angle periodicity often limits performance. To solve this issue, we rethink label assignment and sampling strategies and propose a pair of orientation-aware assigner and sampler (OAS) for a two-stage detector. The orientation-aware assigner (OA) incorporates angle and location to improve positive and negative sample assignment, while the orientation-aware sampler (OS) ranks positive samples by their angular difference from ground truth, adjusting learning weights by soft sampling. Such a design significantly mitigates the angle periodicity problem and enables detector focusing on high-quality samples with a more consistent orientation for training. Experimental results on two challenging oriented object detection benchmarks demonstrate that OAS can consistently boost the detection accuracy based on many existing two-stage detectors (e.g., oriented R-CNN and RPGAOD) without additional cost. Both code and pretrained models are available at https://***/skyandkibo/OAS.

关键词： Proposals object detection Residual neural networks Training Detectors Head Artificial intelligence Measurement Data mining Accuracy Angle periodicity oriented object detection sample assignment sample learning

来源：评论

学校读者我要写书评

暂无评论

detection in Optical Remote Sensing Images of Transmission Tower Based on oriented object detection

引用

CSEE Journal of Power and Energy Systems 2025年第1期11卷 217-226页

作者： Yuanpeng Tan Fei Jiao Wenhao Mo Haiying Liu Xiaojing Bai Jiaxiu Ma China Electric Power Research Institute Beijing 100192China China Electric Power Research Institute and North China Electric Power University Beijing100192China China Electric Power Research Institute and State Grid Corporation of China Information and Communication Branch Beijing100192China

Transmission towers play a crucial role in overhead transmission line systems and are the key target of transmission line *** the help of remote sensing technology,transmission towers can be effectively detected in wide areas at reasonable costs and in a relatively short time ***,it is difficult to identify the type of transmission towers in optical remote sensing images due to detail degradation caused by long-distance and high-altitude *** paper proposes a transmission tower detection method in optical remote sensing images using an oriented object detector and object and shadow joint *** enrich the information,the transmission towers and their shadows are jointly detected through a CenterNet detector with an orientation prediction *** improve the detection accuracy of difficult objects,attention and deformable convolutional network modules are introduced to the backbone and orientation prediction branches,*** the orientation and the aspect ratio of the objects and shadows,a focal loss function with an aspect ratio is employed to further improve the *** and shadow joint detection are separately realized through the one-box and multi-box detection strategies.A transmission tower dataset RSITT labeled with horizontal and oriented boxes is *** conducted on the RSITT dataset have demonstrated that the detection accuracy and recall rate of the proposed joint detection algorithm reached 73.2%and 95.2%.

关键词： oriented object detection remote sensing image transmission projection transmission tower detection

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Multi-layer Feature Aggregation and Rotated Anchor Matching for oriented object detection in Remote Sensing Images

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2024年第9期49卷 12935-12951页

作者： Jin, Chuan Zheng, Anqi Wu, Zhaoying Tong, Changqing Hangzhou Dianzi Univ Sch Sci Hangzhou 310018 Zhejiang Peoples R China Southeast Univ Southeast Monash Joint Grad Suzhou 210096 Jiangsu Peoples R China

object detection has made significant progress in computer vision. However, challenges remain in detecting small, arbitrarily oriented, and densely distributed objects, especially in aerial remote sensing images. This paper presents MATDet, an end-to-end encoder-decoder detection network based on the Transformer designed for oriented object detection. The network employs multi-layer feature aggregation and rotated anchor matching methods to improve oriented small and densely distributed object detection accuracy. Specifically, the encoder is responsible for encoding labeled image blocks using convolutional neural network (CNN) feature maps. It efficiently fuses these blocks with higher resolution multi-scale features through cross-layer connections, facilitating the extraction of global contextual information. The decoder then performs an upsampling of the encoded features, effectively recovering the full spatial resolution of the feature maps to capture essential local-global semantic features for accurate object localization. In addition, high quality proposed anchor boxes are generated by refined convolution, and the convolved features are adaptively aligned according to the anchor boxes to reduce redundant computation. The proposed MATDet achieves mAPs of 80.35%, 78.83%, 73.60%, and 98.01% on the DOTAv1.0, DOTAv1.5, DIOR, and HRSC2016 datasets, respectively, proving that it outperforms the baseline model for oriented object detection. This validation confirms the feasibility and effectiveness of the proposed methods.

关键词： Remote sensing oriented object detection Transformer Multi-layer feature aggregation Rotated anchor matching

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：