检索结果-内蒙古大学图书馆

MINIAOD: Lightweight Aerial Image object detection

IEEE SENSORS JOURNAL 2025年第5期25卷 9167-9184页

作者： Wang, Huiying Wang, Chunping Fu, Qiang Si, Binqiang Zhang, Dongdong Kou, Renke Yu, Ying Feng, Changfeng Army Engn Univ PLA Dept Elect & Opt Engn Shijiazhuang 050003 Peoples R China Beijing Informat Sci & Technol Univ Sch Instrument Sci & Optoelect Engn Beijing 100192 Peoples R China

Identifying challenging samples in real-time aerial images captured by the unmanned aerial vehicles (UAVs) is currently a difficult task. Lightweight network designs often utilize lightweight modules or employ methods such as network pruning, quantization, and distillation for real-time detection on embedded devices. However, these approaches are inadequate for complex background aerial images. In this article, we propose a real-time object detection algorithm specifically designed for complex aerial images, named MINIAOD. First, we use Ghost convolution to build a lightweight backbone network, which improves the detection speed without compromising the feature extraction capability. In addition, we utilize the GSConv module to construct a feature enhancement network and develop the C3 module with integrated GSConv convolution and ECA attention mechanism (GSC3ECA) module to improve the network's learning capability for challenging targets, while also decreasing computational complexity. To boost the network's focus on small and medium-sized targets and mitigate interference from complex backgrounds, we incorporate the ECA attention mechanism in the small and medium-sized target detection branch to elevate the focus on difficult-to-detect samples. Finally, we design the rotation detection head to characterize the target directionality of aerial images. We perform extensive experiments on multiple publicly available datasets and the proposed method demonstrates a favorable balance between accuracy and speed when compared to the current leading models.

关键词： object detection Feature extraction Computational modeling Real-time systems Accuracy YOLO Visualization Convolution Attention mechanisms Silicon Aerial images attention mechanism oriented object detection real-time detection

来源：评论

学校读者我要写书评

暂无评论

Empowering object detection: Unleashing the Potential of Decoupled and Interactive Distillation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第1期26卷 544-557页

作者： Qian, Fulan Hong, Jiacheng Yan, Huanqian Chen, Hai Zhang, Chonghao Su, Hang Zhao, Shu Anhui Univ Artificial Intelligence Inst Sch Comp Sci & Technol Hefei 230601 Peoples R China Anhui Univ Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230601 Peoples R China Beihang Univ Dept Comp Sci & Technol Beijing 100191 Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing 100190 Peoples R China

Deploying state-of-the-art object detectors on resource-limited devices presents significant challenges. Knowledge distillation is an efficient and streamlined lightweight technique to improve the accuracy of compact detectors. However, its effectiveness is limited by the redundancy of different types of semantics on the feature map and the closure of same level's feature distillation. To alleviate this problem, we propose Decoupled and Interactive Distillation, an effective and versatile method to improve knowledge distillation in some complex object detection tasks. The method has two key components. A knowledge decoupled module captures category awareness and localization awareness features. A multi-level feature interaction distillation can aggregate feature distillations from shallow to deep levels, facilitating the collaboration between feature transfers at different levels. The relevant experiments in traffic-related, 3D, rotated object detection have verified the effectiveness of the proposed method, particularly in challenging scenes.

关键词： Lightweight network knowledge distillation 3D object detection oriented object detection

来源：评论

学校读者我要写书评

暂无评论

Anchor-Free oriented Proposal Generator for object detection

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2022年 60卷 1页

作者： Cheng, Gong Wang, Jiabao Li, Ke Xie, Xingxing Lang, Chunbo Yao, Yanqing Han, Junwei Northwestern Polytech Univ Sch Automat Xian 710129 Peoples R China Zhengzhou Inst Surveying & Mapping Zhengzhou 450052 Peoples R China

oriented object detection is a practical and challenging task in remote sensing image interpretation. Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them. However, the horizontal boxes are inclined to get small Intersection-over-Unions (IoUs) with ground truths, which may have some undesirable effects, such as introducing redundant noise, mismatching with ground truths, and detracting from the robustness of detectors. In this article, we propose a novel anchor-free oriented proposal generator (AOPG) that abandons horizontal box-related operations from the network architecture. AOPG first produces coarse oriented boxes by a coarse location module (CLM) in an anchor-free manner and then refines them into high-quality oriented proposals. After AOPG, we apply a Fast Region-based Convolutional Neural Network (R-CNN) head to produce the final detection results. Furthermore, the shortage of large-scale datasets is also a hindrance to the development of oriented object detection. To alleviate the data insufficiency, we release a new dataset on the basis of our DIOR dataset and name it DIOR-R. Massive experiments demonstrate the effectiveness of AOPG. Particularly, without bells and whistles, we achieve the accuracy of 64.41%, 75.24%, and 96.22% mAP on the DIOR-R, DOTA, and HRSC2016 datasets, respectively. Code and models are available at https://***/jbwang1997/AOPG.

关键词： Proposals Detectors object detection Generators Feature extraction Remote sensing Shape Anchor-free oriented proposal generator (AOPG) oriented object detection oriented proposal generation

来源：评论

学校读者我要写书评

暂无评论

Multi-oriented Rotation-Equivariant Network for object detection on Remote Sensing Images

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷 1页

作者： Zhu, Kun Zhang, Xiaodong Chen, Guanzhou Li, Xianwei Cai, Peihua Liao, Puyun Wang, Tong Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China Yangtze Univ Sch Geosci Wuhan 430100 Peoples R China

object detection has attracted a lot of attention in the field of image automatic interpretation. Detectors based on convolution neural networks (CNNs) applied in natural scene images encode detection results with horizontal bounding boxes (HBBs), which can not accurately calibrate the position and shape of the arbitrary-orientation objects on remote sensing images (RSIs). To solve these issues, we propose an object detection framework named multi-oriented rotation-equivariant network (MORE-Net) in this letter. The MORE-Net consists of a multi-oriented rotating filter (MORF) and a multi-oriented ground objects detector. The MORF generates rotation-equivariant features by rotating canonical filter according to the predefined discrete directions. Equipped with MORF, the multi-oriented ground objects detector extracts rotation-invariant semantic representations for each decoded rotated region of interest (RRoI). We also propose area smooth (AS) L1 loss to impose tighter shape and position constraints to the RROIs. Extensive experiments and comprehensive evaluations on the large-scale DOTA dataset demonstrate the effectiveness of the proposed framework, which achieves a mean average precision (mAP) value of 81.27 on the DOTA-v1.0 dataset and a mAP value of 78.03 on the DOTA-v1.5 dataset.

关键词： Feature extraction Detectors Convolution Shape object detection Training Remote sensing oriented object detection remote sensing image (RSI) rotation-equivariant rotation-invariant

来源：评论

学校读者我要写书评

暂无评论

Gaussian Aware Anchor-Free Rotated Detector for Aerial object detection

引用

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

作者： Zhang, Shuai Zhang, Cunyuan Yu, Lijian Ji, Wenyu Zhi, Xiyang Jilin Univ Coll Phys Changchun 130012 Peoples R China Harbin Inst Technol Sch astronaut Harbin 150006 Peoples R China

object detection in specific scenarios has received increasing attention for many applications. However, the feature inconsistencies of localization and classification branches in remote sensing models may degrade the detection performance. Furthermore, the existing IoU-based label assignment strategy cannot accurately capture objects' shape and oriented information. We propose an anchor-free detector called the Gaussian aware rotated detector (GARDet) to address the above issues. It contains two improvements: the feature alignment module (FAM) and the Gaussian dynamic label assignment (GDLA) strategy. FAM consists of oriented feature alignment (OFA) convolutions sensitive to orientation-invariant features inside objects and spatial feature alignment convolutions sensitive to spatial coordinate information. GDLA uses a Gaussian matching confidence (GMC) based on the Gaussian distance to measure the quality of the predicted bounding boxes and dynamically assigns positive and negative samples for training. Extensive experiments on remote sensing object detection datasets (DOTAv1.0 and HRSC2016) demonstrate that the proposed model can achieve competitive performance.

关键词： Feature extraction Location awareness Remote sensing Training object detection Detectors Task analysis Aerial images anchor-free detector oriented object detection remote sensing

来源：评论

学校读者我要写书评

暂无评论

Lightweight Transformer with Adaptive Rotational Convolutions for Aerial object detection

引用

APPLIED SCIENCES-BASEL 2025年第9期15卷 5212-5212页

作者： Umirzakova, Sabina Muksimova, Shakhnoza Qizi, Abrayeva Mahliyo Olimjon Cho, Young Im Gachon Univ Dept Comp Engn Seongnam Si 13120 South Korea Tashkent State Univ Econ Dept Informat Syst & Technol Tashkent 100066 Uzbekistan

oriented object detection in aerial imagery presents unique challenges due to the arbitrary orientations, diverse scales, and limited availability of labeled data. In response to these issues, we propose RASST-a lightweight Rotationally Aware Semi-Supervised Transformer framework designed to achieve high-precision detection under fully and semi-supervised conditions. RASST integrates a hybrid Vision Transformer architecture augmented with rotationally aware patch embeddings, adaptive rotational convolutions, and a multi-scale feature fusion (MSFF) module that employs cross-scale attention to enhance detection across object sizes. To address the scarcity of labeled data, we introduce a novel Pseudo-Label Guided Learning (PGL) framework, which refines pseudo-labels through Rotation-Aware Adaptive Weighting (RAW) and Global Consistency (GC) losses, thereby improving generalization and robustness against noisy supervision. Despite its lightweight design, RASST achieves superior performance on the DOTA-v1.5 benchmark, outperforming existing state-of-the-art methods in supervised and semi-supervised settings. The proposed framework demonstrates high scalability, precise orientation sensitivity, and effective utilization of unlabeled data, establishing a new benchmark for efficient oriented object detection in remote sensing imagery.

关键词： lightweight vision transformer oriented object detection semi-supervised learning rotational invariance pseudo-labeling adaptive rotational convolution multi-scale feature fusion global consistency loss

来源：评论

学校读者我要写书评

暂无评论

Learning an anchor-free network with angle attention for remote sensing object detection

引用

REMOTE SENSING LETTERS 2023年第9期14卷 934-944页

作者： Li, Yufeng Chen, Hongming Kong, Caihua Dai, Longgang Chen, Xiang Shenyang Aerosp Univ Coll Elect Informat Engn Shenyang Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Peoples R China

Rotation object detection has achieved significance progress in the community of remote sensing image processing. In contrast to horizontal bounding boxes, rotating bounding boxes require an accurate angle parameter to position the object. However, angle regression accuracy remains an urgent challenge due to the arbitrary orientation, large aspect ratio, and dense alignment of aerial images. To solve this problem, we propose an anchor-free network with angle attention (FAA-Net), which delicately develops two core designs, i.e, angle feature extraction (AFE) module and angle prediction head (APH) module. Specifically, the AFE module performs feature extraction and angle selection to reduce the negative effects of angle adaptation. In addition, APH module is further employed to better predict the object orientation by introducing the frequency attention and integral operation. Extensive experiments on two classical benchmark datasets have demonstrated that our method can effectively boost detection performance against several start-of-the-art approaches.

关键词： oriented object detection anchor-free detector angle attention remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Dynamic Pyramid Attention Networks for multi-orientation object detection

引用

JOURNAL OF INTERNET TECHNOLOGY 2022年第1期23卷 79-90页

作者： Yuan, Hongchun Zhou, Hui Cai, Zhenyu Zhang, Shuo Wu, Ruoyou Shanghai Ocean Univ Coll Informat Technol Shanghai Peoples R China Minist Agr Key Lab Fisheries Informat Beijing Peoples R China

The objects in remote sensing images often appeared in any direction, and thus multi-orientation object detection has received considerable attention. However, most existing oriented object detection methods rely on increasing the network layers, which wastes many computing resources while only bringing a slight improvement. We find that a few pixels around the convolution kernel participate in the calculation when extracting image features in the convolution network. If we can incorporate the global information into the feature map, the model's performance will be significantly improved. In this paper, we proposed the dynamic pyramid attention network (DPANet) for remote sensing images, which consists of the self-attention feature pyramid network (SAFPN) and the dynamic feature map selection module (DFMS). The SAFPN employs the self-attention mechanism learn the correlation between each pixel value and the global pixel in different feature layers by downsampling the upper feature layers to the lower one. Furthermore, the DFMS module dynamically selects feature maps to further expand the receptive field by weighing the effectiveness of different feature layers and reducing the interference of unnecessary feature maps. The remote sensing datasets HRSC2016, UCAS_AOD and NWPU_VHR are used to evaluate the performance of DPANet and the experiment results show that the proposed network outperforms the benchmark models significantly.

关键词： oriented object detection Remote sensing images Self-attention Feature layer selection

来源：评论

学校读者我要写书评

暂无评论

object detection in Aerial Images: A Large-Scale Benchmark and Challenges

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第11期44卷 7778-7796页

作者： Ding, Jian Xue, Nan Xia, Gui-Song Bai, Xiang Yang, Wen Yang, Michael Ying Belongie, Serge Luo, Jiebo Datcu, Mihai Pelillo, Marcello Zhang, Liangpei Wuhan Univ State Key Lab LIESMARS Wuhan 430079 Hubei Peoples R China Wuhan Univ Natl Engn Res Ctr Multimedia Software Sch Comp Sci & Inst Artificial Intelligence Wuhan 430072 Hubei Peoples R China Natl Engn Res Ctr Multimedia Software Sch Comp Sci Wuhan Peoples R China Natl Engn Res Ctr Multimedia Software Inst Artificial Intelligence Wuhan Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat Wuhan 430072 Hubei Peoples R China Wuhan Univ Sch Elect Informat Wuhan 430072 Hubei Peoples R China Univ Twente Fac Geoinformat Sci & Earth Observat ITC NL-7522 NB Enschede Netherlands Cornell Univ Dept Comp Sci Ithaca NY 14853 USA Cornell Tech Ithaca NY 14853 USA Univ Rochester Dept Comp Sci Rochester NY 14627 USA German Aerosp Ctr DLR Remote Sensing Technol Inst NRW D-82234 Cologne Germany Univ POLITEHN Bucharest UPB Bucharest 060042 Romania Ca Foscari Univ Venice DAIS Venice Italy

In he past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become a major obstacle to the development of object detection in aerial images (ODAI). In this paper, we present a large-scale Dataset of object detection in Aerial images (DOTA) and comprehensive baselines for ODAI. The proposed DOTA dataset contains 1,793,658 object instances of 18 categories of oriented-bounding-box annotations collected from 11,268 aerial images. Based on this large-scale and well-annotated dataset, we build baselines covering 10 state-of-the-art algorithms with over 70 configurations, where the speed and accuracy performances of each model have been evaluated. Furthermore, we provide a code library for ODAI and build a website for evaluating different algorithms. Previous challenges run on DOTA have attracted more than 1300 teams worldwide. We believe that the expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.

关键词： object detection Earth Libraries Codes Task analysis Software algorithms Software object detection remote sensing aerial images oriented object detection benchmark dataset

来源：评论

学校读者我要写书评

暂无评论

S4Det: Breadth and Accurate Sine Single-Stage Ship detection for Remote Sense SAR Imagery

引用

REMOTE SENSING 2025年第5期17卷 900-900页

作者： Zhang, Mingjin Zhu, Yingfeng Li, Longyi Guo, Jie Liu, Zhengkun Li, Yunsong Xidian Univ Sch Telecommun Engn Xian 710071 Peoples R China China Acad Aerosp Sci & Innovat Beijing 100088 Peoples R China

Synthetic Aperture Radar (SAR) is a remote sensing technology that can realize all-weather and all-day monitoring, and it is widely used in ocean ship monitoring tasks. Recently, many oriented detectors were used for ship detection in SAR images. However, these methods often found it difficult to balance the detection accuracy and speed, and the noise around the target in the inshore scene of SAR images led to a poor detection network performance. In addition, the rotation representation still has the problem of boundary discontinuity. To address these issues, we propose S4Det, a Sinusoidal Single-Stage SAR image detection method that enables real-time oriented ship target detection. Two key mechanisms were designed to address inshore scene processing and angle regression challenges. Specifically, a Breadth Search Compensation Module (BSCM) resolved the limited detection capability issue observed within inshore scenarios. Neural Discrete Codebook Learning was strategically integrated with Multi-scale Large Kernel Attention, capturing context information around the target and mitigating the information loss inherent in dilated convolutions. To tackle boundary discontinuity arising from the periodic nature of the target regression angle, we developed a Sine Fourier Transform Coding (SFTC) technique. The angle is represented using diverse sine components, and the discrete Fourier transform is applied to convert these periodic components to the frequency domain for processing. Finally, the experimental results of our S4Det on the RSSDD dataset achieved 92.2% mAP and 31+ FPS on an RTXA5000 GPU, which outperformed the prevalent mainstream of the oriented detection network. The robustness of the proposed S4Det was also verified on another public RSDD dataset.

关键词： remote sensing SAR image oriented object detection context information boundary discontinuity

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：