检索结果-内蒙古大学图书馆

Coupled Dual-Frequency Phase-Shifting Coder for Precise Rotated Angle Representation in oriented object detection

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

作者： Liu, Fei Chen, Renwen Zhang, Junyi Ding, Shanshan Liu, Hao Ma, Shaofei Xing, Kailing Nanjing Univ Aeronaut & Astronaut Coll Aerosp Engn State Key Lab Mech & Control Aerosp Struct Nanjing 210016 Peoples R China ZTE Corp Wired Prod Res & Dev Inst Syst Prod Wired Prod Operat Div Hardware Dev Dept 4 Nanjing 210037 Peoples R China

The classically oriented object detection method often suffers boundary discontinuity and square-like problems, hindering the model's ability to predict orientation accurately. Therefore, in this letter, we introduce a novel angle representation scheme named coupled dual-frequency phase-shifting coder (CDFP) which draws inspiration from optical measurement technology to address the aforementioned issues. Specifically, in the angle encoding stage, we represent the ground-truth (GT) rotation angle as a combination of two five-step phase-shifting at different frequencies and use this representation to supervise the learning of the model's angle branch. In the angle decoding stage, alongside utilizing the corresponding dual-frequency phase-shifting decoding and unwrapping method, we impose additional constraints on the decoding angle range for predicted square-like objects. Extensive experiments on three challenging aerial image datasets using different detectors prove the effectiveness of our approach. Specifically, our RetinaNet-CDFP achieves an average improvement of 2.16% AP50 and 6.83% AP75 on DOTA, and when combined with RTMDet, our RTMDet-R-m-CDFP achieves state-of-the-art (SOTA) detection performance on DIOR-R and DOTA, with 70.11% and 78.77% AP50, respectively. Our codes will be released at https://***/liufeinuaa/***.

关键词： Aerial image deep learning oriented object detection phase-shifting algorithm remote sensing rotated angle coder

来源：评论

学校读者我要写书评

暂无评论

Learning oriented object detection via Naive Geometric Computing

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第8期35卷 10513-10525页

作者： Wang, Yanjie Zhang, Zhijun Xu, Wenhui Chen, Liqun Wang, Guodong Yan, Luxin Zhong, Sheng Zou, Xu Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automation Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430072 Peoples R China Qingdao Univ Sch Comp Sci & Technol Qingdao 266000 Peoples R China

Detecting oriented objects along with estimating their rotation information is one crucial step for image analysis, especially for remote sensing images. Despite that many methods proposed recently have achieved remarkable performance, most of them directly learn to predict object directions under the supervision of only one (e.g., the rotation angle) or a few (e.g., several coordinates) groundtruth (GT) values individually. oriented object detection would be more accurate and robust if extra constraints, with respect to proposal and rotation information regression, are adopted for joint supervision during training. To this end, we propose a mechanism that simultaneously learns the regression of horizontal proposals, oriented proposals, and rotation angles of objects in a consistent manner, via naive geometric computing, as one additional steady constraint. An oriented center prior guided label assignment strategy is proposed for further enhancing the quality of proposals, yielding better performance. Extensive experiments on six datasets demonstrate the model equipped with our idea significantly outperforms the baseline by a large margin and several new state-of-the-art results are achieved without any extra computational burden during inference. Our proposed idea is simple and intuitive that can be readily implemented. Source codes are publicly available at: https://***/wangWilson/***.

关键词： Geometric consistent constraint label assignment oriented object detection remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Dual-Resolution and Deformable Multihead Network for oriented object detection in Remote Sensing Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 930-945页

作者： Yu, Donghang Xu, Qing Liu, Xiangyun Guo, Haitao Lu, Jun Lin, Yuzhun Lv, Liang PLA Strateg Support Force Informat Engn Univ Zhengzhou 450001 Peoples R China Collaborat Innovat Ctr Geoinformat Technol Smart C Zhengzhou 450001 Peoples R China Minist Nat Resources Key Lab Spatiotemporal Percept & Intelligent Proc Zhengzhou 450001 Peoples R China

Compared with general object detection, the scale variations, arbitrary orientations, and complex backgrounds of objects in remote sensing images make it more challenging to detect oriented objects. Especially for oriented objects that have large aspect ratios, it is more difficult to accurately detect their boundary. Many methods show excellent performance on oriented object detection, most of which are anchor-based algorithms. To mitigate the performance gap between anchor-free algorithms and anchor-based algorithms, this article proposes an anchor-free algorithm called dual-resolution and deformable multihead network (DDMNet) for oriented object detection. Specifically, the dual-resolution network with bilateral fusion is adopted to extract high-resolution feature maps which contain both spatial details and multiscale contextual information. Then, the deformable convolution is incorporated into the network to alleviate the misalignment problem of oriented object detection. And a dilated feature fusion module is performed on the deformable feature maps to expand their receptive fields. Finally, box boundary-aware vectors instead of the angle are leveraged to represent the oriented bounding box and the multihead network is designed to get robust predictions. DDMNet is a single-stage oriented object detection method without using anchors and exhibits promising performance on the public challenging benchmarks. DDMNet obtains 90.49%, 93.25%, and 78.66% mean average precision on the HRSC2016, FGSD2021, and DOTA datasets. In particular, DDMNet achieves 79.86% at mAP(75) and 53.85% at mAP(85) on the HRSC2016 dataset, respectively, outperforming the current state-of-the-art methods.

关键词： Feature extraction object detection Remote sensing Inference algorithms Proposals Prediction algorithms Convolution Box boundary-aware vectors deformable feature fusion multihead network oriented object detection remote sensing image

来源：评论

学校读者我要写书评

暂无评论

AO2-DETR: Arbitrary-oriented object detection Transformer

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第5期33卷 2342-2356页

作者： Dai, Linhui Liu, Hong Tang, Hao Wu, Zhiwei Song, Pinhao Peking Univ Shenzhen Grad Sch Key Lab Machine Percept Beijing 100871 Peoples R China Swiss Fed Inst Technol Comp Vis Lab CH-8800 Zurich Switzerland South China Univ Technol Sch Software Engn Guangzhou 511400 Guangdong Peoples R China

Arbitrary-oriented object detection (AOOD) is a challenging task to detect objects in the wild with arbitrary orientations and cluttered arrangements. Existing approaches are mainly based on anchor-based boxes or dense points, which rely on complicated hand-designed processing steps and inductive bias, such as anchor generation, transformation, and non-maximum suppression reasoning. Recently, the emerging transformer-based approaches view object detection as a direct set prediction problem that effectively removes the need for hand-designed components and inductive biases. In this paper, we propose an Arbitrary-oriented object detection TRansformer framework, termed AO2-DETR, which comprises three dedicated components. More precisely, an oriented proposal generation mechanism is proposed to explicitly generate oriented proposals, which provides better positional priors for pooling features to modulate the cross-attention in the transformer decoder. An adaptive oriented proposal refinement module is introduced to extract rotation-invariant region features and eliminate the misalignment between region features and objects. And a rotation-aware set matching loss is used to ensure the one-to-one matching process for direct set prediction without duplicate predictions. Our method considerably simplifies the overall pipeline and presents a new AOOD paradigm. Comprehensive experiments on several challenging datasets show that our method achieves superior performance on the AOOD task.

关键词： Proposals Transformers Feature extraction object detection Detectors Task analysis Pipelines oriented object detection detection transformer oriented proposals feature refinement

来源：评论

学校读者我要写书评

暂无评论

Free³Net: Gliding Free, Orientation Free, and Anchor Free Network for oriented object detection

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2023年 25卷 7089-7100页

作者： Ou, Zhonghong Chen, Zhongjie Shen, Shengyi Fan, Lina Yao, Siyuan Song, Meina Hui, Pan Beijing Univ Posts & Telecommun Beijing 100876 Peoples R China Hong Kong Univ Sci & Technol Computat Media & Arts Trust Area Hong Kong Peoples R China

object detection for aerial images has achieved remarkable progress in recent years. Nevertheless, most exiting studies do not differentiate oriented object detection from horizontal detection. Certain schemes ignore the ambiguity of oriented object representation and leverage label assignment designed for horizontal object detection directly. Consequently, it leads to unstable training and causes performance degradation, because high-quality samples surrounding the oriented bounding boxes can not be leveraged effectively. To address this problem, we propose a gliding Free, orientation Free, and anchor Free Network (Free(3)Net) with high-efficiency for oriented object detection. Specifically, we propose an unambiguous oriented object representation scheme, named FreeGliding, by gliding the projection points of samples on each edge of horizontal bounding boxes. It makes the detection largely free from representation ambiguity and multi-task dependency. To overcome the restrictions of label assignment, we put forward a novel Loss-aware Outer Sample Selection (LOSS) scheme, which takes into consideration spatial information and localization capability to retain high-quality samples surrounding the objects. Moreover, we introduce an oriented Feature Fusion (OFF) scheme to tackle feature alignment by adjusting the receptive field and fusing oriented features dynamically. Experimental results on two large-scale remote sensing datasets HRSC2016 and DOTA demonstrate that Free(3)Net outperforms the state-of-the-art schemes with a large margin. We hope our work can inspire rethinking the design of anchor-free detectors, and serve as a strong baseline for oriented object detection.

关键词： object detection Detectors Feature extraction Location awareness Task analysis Convolution Training oriented object detection anchor-free detector label assignment oriented feature alignment

来源：评论

学校读者我要写书评

暂无评论

PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised oriented object detection

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年

作者： Zhang, Peiyuan Luo, Junwei Yang, Xue Yu, Yi Li, Qingyun Zhou, Yue Jia, Xiaosong Lu, Xudong Chen, Jingdong Li, Xiang Yan, Junchi Li, Yansheng Wuhan Univ Sch Comp Sci Wuhan Peoples R China Wuhan Univ Sch Remote Sensing Informat Engn Wuhan Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai Peoples R China Southeast Univ Sch Automat Nanjing Peoples R China Harbin Inst Technol SEIE Harbin Peoples R China Nanyang Technol Univ S Lab CCDS Jurong Singapore Shanghai Jiao Tong Univ CSE Shanghai Peoples R China Shanghai Jiao Tong Univ SAI Shanghai Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Ant Grp Hangzhou Peoples R China Nankai Univ VCIP CS Tianjin Peoples R China

With the growing demand for oriented object detection (OOD), recent studies on point-supervised OOD have attracted significant interest. In this paper, we propose PointOBB-v3, a stronger single point-supervised OOD framework. Compared to existing methods, it generates pseudo rotated boxes without additional priors and incorporates support for the end-to-end paradigm. PointOBB-v3 functions by integrating three unique image views: the original view, a resized view, and a rotated/flipped (rot/flp) view. Based on the views, a scale augmentation module and an angle acquisition module are constructed. In the first module, a Scale-Sensitive Consistency (SSC) loss and a Scale-Sensitive Feature Fusion (SSFF) module are introduced to improve the model's ability to estimate object scale. To achieve precise angle predictions, the second module employs symmetry-based self-supervised learning. Additionally, we introduce an end-to-end version that eliminates the pseudo-label generation process by integrating a detector branch and introduces an Instance-Aware Weighting (IAW) strategy to focus on high-quality predictions. We conducted extensive experiments on the DIOR-R, DOTA-v1.0/v1.5/v2.0, FAIR1M, STAR, and RSAR datasets. Across all these datasets, our method achieves an average improvement in accuracy of 3.56% in comparison to previous state-of-the-art methods. The code will be available at https://***/ZpyWHU/PointOBB-v3.

关键词： oriented object detection Weakly-supervised learning Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Task interleaving and orientation estimation for high-precision oriented object detection in aerial images

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2023年第1期196卷 241-255页

作者： Ming, Qi Miao, Lingjuan Zhou, Zhiqiang Song, Junjie Dong, Yunpeng Yang, Xue Beijing Inst Technol Sch Automat Beijing Peoples R China Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai Peoples R China

oriented object detection in aerial images has received extensive attention due to its wide range of application scenarios. Although great success has been achieved, current methods still suffer from inferior high-precision detection performance. Firstly, the classification scores cannot truly represent the localization accuracy of the predictions. Secondly, the orientation prediction in these detectors is not accurate enough for high-precision object detection. In this paper, we propose a Task Interleaving and Orientation Estimation Detector (TIOE-Det) for high-quality oriented object detection in aerial images. Specifically, a posterior hierarchical alignment (PHA) label is proposed to optimize the detection pipeline. TIOE-Det adopts PHA label to integrate fine-grained posterior localization guidance into classification task to address the misalignment between classification and localization subtasks. Then, a balanced alignment loss is developed to solve the imbalance localization loss contribution in PHA prediction. Moreover, we propose a progressive orientation estimation (POE) strategy to approximate the orientation of objects with n-ary codes. On this basis, an angular deviation weighting strategy is proposed to achieve accurate evaluation of angle deviation in POE strategy. TIOE-Det achieves significant gains on high-precision detection performance. Extensive experiments on multiple datasets prove the superiority of our approach. Codes are available at https://***/ming71/TIOE.

关键词： oriented object detection Aerial images Convolutional neural network Misaligned tasks Orientation estimation

来源：评论

学校读者我要写书评

暂无评论

Shape-Aware Soft Label Assignment and Context Enhancement for oriented object detection 7th

Shape-Aware Soft Label Assignment and Context Enhancement fo...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Cao, Wang Huang, Zhifu Liu, Yu South China Univ Technol Sch Automat Sci & Engn Guangzhou Peoples R China

ISBN: (纸本)9789819784929;9789819784936

Recently, remote sensing object detection has gained much attention in computer vision. oriented object detection faces additional challenges due to the inherent differences between remote sensing images and those from natural scenes, such as detecting objects with different directions and scales. Recent methods improve the model structure of feature pyramid network (FPN) to solve scale problems, but most of them disregard the default loss of channel information during lateral connections and the semantic gap among different levels of feature maps during fusion. In this paper, we propose a context-enhanced FPN (CEFPN) consisting of an information compensation module and an elaborate fusion to address the aforementioned problems. Specifically, we introduce the Pixel-Shuffle to address the problems of channel information loss and design a novel fusion module to enhance contextual features. In addition, we propose a shape-aware soft label assignment (SSLA) method to alleviate the sensitivity of assignment results to scale variation and angle variation. We design a scoring function to compute a quality score for each anchor box and dynamically select high-quality anchor boxes as positive samples. Moreover, the quality score is utilized to weigh the training samples in the loss function, prioritizing high-quality anchors during the learning process. Experimental results on DOTA and HRSC2016 datasets demonstrate the effectiveness of our proposed method.

关键词： Deep learning oriented object detection Label assignment Feature fusion

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Loss Functions for Arbitrary-oriented object detection in Aerial Images 21

A Comparative Study of Loss Functions for Arbitrary-Oriented...

引用

21st International Joint Conference on Computer Science and Software Engineering (JCSSE)

作者： San, Kaung Htet Kondo, Toshiaki Marukatat, Sanparith Hara-Azumi, Yuko Thammasat Univ Sirindhorn Int Inst Technol Sch ICT Pathum Thani Thailand Natl Elect & Comp Technol Ctr Pathum Thani Thailand Tokyo Inst Technol Ookayama Campus Tokyo Japan

ISBN: (纸本)9798350381771;9798350381764

Detecting objects with specific orientations in aerial imagery is a complex task due to the random rotations and high density of objects within the images. Additionally, boundary discontinuity from regression parametrization poses a major challenge in designing loss functions for rotated object detection. Several bounding box representations and their associated loss functions are being gradually developed to address this challenge. In this study, we compare loss functions for oriented bounding boxes including Probabilistic IoU (ProbIoU), KFIoU and others. The evaluation uses DOTA-PS, a subset of a large scale aerial benchmark dataset DOTAv1.0, which includes two categories, plane and ship. We also introduce Complete Rotated IoU (CRIoU) loss which is improved over Rotated IoU (RIoU) loss. ProbIoU and CRIoU loss achieved mAP score of 93.1% on the test set while RIoU and KFIoU losses got 92.8% and 90.6% respectively. CRIoU demonstrates marginal improvement in oriented bounding box localization, supported by the brief experimental and visual analysis.

关键词： oriented object detection DOTA-PS gaussian-based loss rotated loss CRIoU

来源：评论

学校读者我要写书评

暂无评论

Relational Matching for Weakly Semi-Supervised oriented object detection

Relational Matching for Weakly Semi-Supervised Oriented Obje...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wu, Wenhao Wong, Hau-San Wu, Si Zhang, Tianyou City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou Guangdong Peoples R China

ISBN: (纸本)9798350353006

oriented object detection has witnessed significant progress in recent years. However, the impressive performance of oriented object detectors is at the huge cost of labor-intensive annotations, and deteriorates once the annotated data becomes limited. Semi-supervised learning, in which sufficient unannotated data are utilized to enhance the base detector, is a promising method to address the annotation deficiency problem. Motivated by weakly supervised learning, we introduce annotation-efficient point annotations for unannotated images and propose a weakly semi-supervised method for oriented object detection to balance the detection performance and annotation cost. Specifically, we propose a Rotation-Modulated Relational Graph Matching method to match relations of proposals centered on annotated points between the teacher and student models to alleviate the ambiguity of point annotations in depicting the oriented object. In addition, we further propose a Relational Rank Distribution Matching method to align the rank distribution on classification and regression between different models. Finally, to handle the difficult annotated points that both models are confused about, we introduce weakly supervised learning to impose positive signals for difficult point-induced clusters to the base model, and focus the base model on the occupancy between the predictions and annotated points. We perform extensive experiments on challenging datasets to demonstrate the effectiveness of our proposed weakly semi-supervised method in leveraging point-annotated data for significant performance improvement.

关键词： oriented object detection Semi-Supervised Learning

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：