检索结果-内蒙古大学图书馆

Adaptive Deformation-Learning and Multiscale-Integrated Network for Remote Sensing object detection

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Zhong, Xiyu Zhan, Jialei Xie, Yuhang Zhang, Lingtao Zhou, Guoxiong Liang, Mingyue Yang, Kaitai Guo, Zonghao Li, Liujun Cent South Univ Forestry & Technol Coll Comp & Math Changsha 410004 Peoples R China Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China Xidian Univ Sch Elect Engn Xian 710071 Peoples R China Cent South Univ Forestry & Technol Coll Elect Informat & Phys Changsha 410004 Peoples R China Univ Idaho Dept Soil & Water Syst Moscow ID 83844 USA

Modern human productivity and daily life rely on identifying ground objects using remote sensing images (RSIs). Traditional remote sensing object detection (RSOD) techniques lack timeliness and accuracy and fail to meet practical demands. Existing deep learning algorithms face continued challenges when processing RSIs because of the diverse shapes and extensive scale variations of objects, of which a significant proportion are small scale. To address these challenges, we propose the PSWP-DETR, a transformer-based network that leverages adaptive deformation learning and multiscale integration for enhanced object detection in remote sensing. First, we propose PradatorConv (PdConv) to address the significant shape changes of objects because it adaptively learns the horizontal and vertical deformations to perceive the complex geometric features of RSIs. Second, we propose scale-wise differential modules (SDMs), which comprise multiscale convolution (MSC) and edge captor convolution (ECC). SDM integrates features across various scales and captures edge characteristics and local textures. This is advantageous for detecting multiscale objects, tiny objects with limited feature information. Finally, we propose the whale particle optimization (WPO) algorithm for learning rate optimization, which improves convergence speed and accuracy. Experiments using the VisDrone2019-DET, DIOR, and AI-TOD datasets demonstrated that PSWP-DETR achieves the best accuracy benefits, offering significant insights for future RSOD efforts. The source code will be available at https://***/Get1star/***.

关键词： Remote sensing Shape Transformers Feature extraction object detection Optimization Accuracy Training Sensors Real-time systems Local texture features offset convolution remote sensing object detection (RSOD) transformer-based object detector whale particle optimization (WPO)

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Heterogeneous Geometric Foreground Perception Network for Remote Sensing object detection

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Ren, Dong Liu, Yang Sun, Hang Zhang, Lefei Wan, Jun China Three Gorges Univ Hubei Key Lab Intelligent Vis Based Monitoring Hyd Yichang 443002 Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Zhongnan Univ Econ & Law Sch Informat Engn Wuhan 430073 Peoples R China

Recently, deep learning-based remote sensing object detection (RSOD) has been widely explored and obtained remarkable performance. However, most existing multiscale feature extraction methods neglect exploring the interfering representation of different hierarchical features in the backbone, which is crucial for learning more discriminative features. Moreover, feature pyramid network (FPN) and its variants have difficulty in effectively perceiving the pose and salient information of remote sensing objects, leading to reduced detection accuracy. To address these issues, we propose a hierarchical heterogeneous geometric foreground perception network (HHGFP-Net) for RSOD. Specifically, a hierarchical heterogeneous receptive-field module (HHRM) is proposed to reward and penalize the feature information of the corresponding levels according to the differences between the shallow and deep feature layers in the backbone, improving discriminative feature ability. Furthermore, a geometric foreground perception FPN (GFP-FPN) is developed to refine geometric shapes and enhance foreground contents, providing more precise feature representations for objects, particularly small objects. Experimental results on four challenging RSOD datasets demonstrate that our HHGFP-Net achieves state-of-the-art performance. Codes are available at: https://***/YyLinkWorld/HHGFP-Net.

关键词： Feature extraction Remote sensing object detection Accuracy Shape Semantics Interference Detectors Sensors Sun Foreground enhancing geometric feature perception hierarchical heterogeneous multiscale feature extraction remote sensing object detection (RSOD)

来源：评论

学校读者我要写书评

暂无评论

Fast Quantum Convolutional Neural Networks for Low-Complexity object detection in Autonomous Driving Applications

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第2期24卷 1031-1042页

作者： Roh, Emily Jimin Baek, Hankyul Kim, Donghyeon Kim, Joongheon Korea Univ Dept Elect & Comp Engn Seoul 02841 South Korea Hyundai Motor Co Inst Adv Technol Dev IATD Seoul 06797 South Korea

object detection applications, especially in autonomous driving, have drawn attention due to the advancements in deep learning. Additionally, with continuous improvements in classical convolutional neural networks (CNNs), there has been a notable enhancement in both the efficiency and speed of these applications, making autonomous driving more reliable and effective. However, due to the exponentially rapid growth in the complexity and scale of visual signals used in object detection, there are limitations regarding computation speeds while conducting object detection solely with classical computing. Motivated by this, this paper proposes the quantum object detection engine (QODE), which implements a quantum version of CNN, named QCNN, in object detection. Furthermore, this paper proposes a novel fast quantum convolution algorithm that processes the multi-channel of visual signals based on a small number of qubits and constructs the output channel data, thereby achieving relieved computational complexity. Our QODE, equipped with fast quantum convolution, demonstrates feasibility in object detection with multi-channel data, addressing a limitation of current QCNNs due to the scarcity of qubits in the current era of quantum computing. Moreover, this paper introduces a heterogeneous knowledge distillation training algorithm that enhances the performance of our QODE.

关键词： Autonomous driving object detection quantum convolutional neural network quantum machine learning

来源：评论

学校读者我要写书评

暂无评论

SOFW: A Synergistic Optimization Framework for Indoor 3D object detection

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2025年 27卷 637-651页

作者： Dai, Kun Jiang, Zhiqiang Xie, Tao Wang, Ke Liu, Dedong Fan, Zhendong Li, Ruifeng Zhao, Lijun Omar, Mohamed Harbin Inst Technol State Key Lab Robot & Syst Harbin 150006 Peoples R China State Key Yangtze River Delta HIT Robot Technol Re Wuhu 241000 Peoples R China

In this work, we observe that indoor 3D object detection across varied scene domains encompasses both universal attributes and specific features. Based on this insight, we propose SOFW, a synergistic optimization framework that investigates the feasibility of optimizing 3D object detection tasks concurrently spanning several dataset domains. The core of SOFW is identifying domain-shared parameters to encode universal scene attributes, while employing domain-specific parameters to delve into the particularities of each scene domain. Technically, we introduce a set abstraction alteration strategy (SAAS) that embeds learnable domain-specific features into set abstraction layers, thus empowering the network with a refined comprehension for each scene domain. Besides, we develop an element-wise sharing strategy (ESS) to facilitate fine-grained adaptive discernment between domain-shared and domain-specific parameters for network layers. Benefited from the proposed techniques, SOFW crafts feature representations for each scene domain by learning domain-specific parameters, whilst encoding generic attributes and contextual interdependencies via domain-shared parameters. Built upon the classical detection framework VoteNet without any complicated modules, SOFW delivers impressive performances under multiple benchmarks with much fewer total storage footprint. Additionally, we demonstrate that the proposed ESS is a universal strategy and applying it to a voxels-based approach TR3D can realize cutting-edge detection accuracy on all S3DIS, ScanNet, and SUN RGB-D datasets.

关键词： Three-dimensional displays Feature extraction object detection Point cloud compression Optimization Accuracy Shape Proposals Sun Kernel 3D object detection synergistic optimization deep learning

来源：评论

学校读者我要写书评

暂无评论

LEN-YOLO: a lightweight remote sensing small aircraft object detection model for satellite on-orbit detection

引用

JOURNAL OF REAL-TIME IMAGE PROCESSING 2025年第1期22卷 1-15页

作者： Wu, Jian Zhao, Fanyu Jin, Zhonghe Zhejiang Univ Microsatellite Res Ctr Hangzhou 310027 Peoples R China

The performance of conventional detection algorithms in small aircraft target detection is often unsatisfactory due to the intricate backgrounds of remote sensing images and the diminutive size of aircraft targets. Furthermore, prevalent deep learning algorithms typically prove overly complex for integration into resource-constrained satellite platforms. In response to these challenges, an enhanced algorithm named LEN-YOLO (Lite backbone - Enhanced Neck - YOLO) has been devised to enhance detection accuracy while preserving model simplicity for the detection of small aircraft in satellite on-orbit scenarios. First, the EIoU Loss is adopted for target localization, enabling the network to effectively focus on small aircraft targets. Second, a Lite backbone is designed by discarding high semantic information, using low-semantic feature maps to detect small targets. Finally, a Bidirectional Weighted FPN based on SimAM and GSConv (BSG-FPN) is proposed to fuse feature maps of different scales to increase detailed information. Experimental results on RSOD and DIOR datasets demonstrate compared to the baseline YOLOv5, LEN-YOLO achieves an increase of 5.1% and 4.2% in APs\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\text {AP}_s$$\end{document} respectively. Notably, parameters are reduced by 78.3% and floating-point operations by 33.2%.

关键词： object detection Small aircraft detect Remote sensing Lightweight YOLO

来源：评论

学校读者我要写书评

暂无评论

SARFA-Net: Shape-Aware Label Assignment and Refined Feature Alignment for Arbitrary-Oriented object detection in Remote Sensing Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 8865-8881页

作者： Dong, Yan Wei, Minghong Gao, Guangshuai Li, Chunlei Liu, Zhoufeng Zhongyuan Univ Technol Sch Informat & Commun Engn Zhengzhou 450007 Peoples R China Univ Elect Sci & Technol China Sch Automat Engn Chengdu 610000 Peoples R China

Arbitrary-oriented object detection in remote sensing images has witnessed significant progress in recent years. Numerous excellent detection models perform promising results, however, there are two main tough challenges hinder their performances. On the one hand, current label assignment strategies suffer from an imbalance between positive and negative samples, particularly for large aspect ratio and small-scale objects, leading to the Insufficient High-quality Samples. On the other hand, fixed convolution kernels and coarse sampling positions are not well suited for adapting to rotating objects in complex remote sensing scenes, resulting in Feature Misalignment. To alleviate the above issues, in this article, a novel SARFA-Net is proposed, incorporating a Shape-Aware Label Assignment (SALA) strategy and Refined Feature Alignment module (RFAM). Specifically, SALA is proposed to mitigate the problem of insufficient sampling for extremely shaped objects, the core of which is the Shape-Aware Sampling module, to meticulously select more high-quality positive samples within elliptical regions. To further enhance SALA at extremely limited scales and large aspect ratios, a Threshold Compensation Module is designed, which further utilizes the shape characteristics of the objects. Furthermore, RFAM is developed to adaptively align features by adjusting the sampling positions of the convolution kernels based on the refined anchors. Extensive experiments conducted on five large-scale datasets, DIOR-R, DOTA-v1.0, HRSC2016, FAIR1M-v1.0, and UCAS-AOD achieved mAPs of 68.90%, 80.09%, 90.40%, 46.34%, and 90.01%, respectively, demonstrating the effectiveness of the proposed approach and the superiority compared with state-of-the-arts. Compared with the baseline S(2)A-Net , we have improved by 1.30, 1.57, 0.23, 5.92, and 0.37 points, respectively, without additional data augmentation.

关键词： Feature extraction Shape Remote sensing Convolution object detection Training Synthetic aperture sonar Kernel Sensors Noise Arbitrary-oriented object detection (AOOD) feature misalignment (FM) insufficient high-quality samples label assignment remote sensing images (RSI)

来源：评论

学校读者我要写书评

暂无评论

YOLOCS: object detection based on dense channel compression for feature spatial solidification

引用

KNOWLEDGE-BASED SYSTEMS 2025年 310卷

作者： Huang, Lin Li, Weisheng Tan, Yujuan Shen, Linlin Yu, Jing Fu, Haojie Chongqing Univ Posts & Telecommun 2 Chongwen Rd Chongqing 400065 Peoples R China Chongqing Univ 55 Univ Town South Rd Chongqing 401331 Peoples R China Shenzhen Univ 3688 Nanshan Ave Shenzhen 518061 Peoples R China Inspur Yunzhou Ind Internet Co Ltd 1036 Langchao Rd Jinan 250101 Shandong Peoples R China Guoqi Zhimo Chongqing Technol Co Ltd 5th FloorBldg B15Xiantao Data Valley Chongqing 401122 Peoples R China

In this study, we examine the associations between channel features and convolutional kernels during the processes of feature purification and gradient backpropagation, with a focus on the forward and backward propagation within the network. Consequently, we propose a method called Dense Channel Compression for Feature Spatial Solidification. Drawing upon the central concept of this method, we introduce two innovative modules for backbone and head networks: the Dense Channel Compression for Feature Spatial Solidification Structure (DF) and the Asymmetric Multi-Level Compression Decoupled Head (ADH). When integrated into the YOLOv5 model, these two modules demonstrate exceptional performance, resulting in a modified model referred to as YOLOCS. Evaluated on the MSCOCO dataset, the large, medium, and small YOLOCS models yield AP of 50.1%, 47.6%, and 42.5%, respectively. Maintaining inference speeds remarkably similar to those of the YOLOv5 model, the large, medium, and small YOLOCS models surpass the YOLOv5 model's AP by 1.1%, 2.3%, and 5.2%, respectively.

关键词： Yolo object detection Dense channel compression Feature spatial solidification Decoupled head

来源：评论

学校读者我要写书评

暂无评论

Studying Forgetting in Faster R-CNN for Online object detection: Analysis Scenarios, Localization in the Architecture, and Mitigation

引用

IEEE ACCESS 2025年 13卷 6067-6079页

作者： Wagner, Baptiste Pellerin, Denis Huet, Sylvain Univ Grenoble Alpes GIPSA Lab CNRS Grenoble INP F-38000 Grenoble France

Online object detection (OOD) requires learning new object categories from a stream of images, similar to an agent exploring new environments. In this context, the widely used architecture Faster R-CNN (Region Convolutional Neural Network) faces catastrophic forgetting: the acquisition of new knowledge leads to the loss of previously learned information. In this paper, we investigate the learning and forgetting mechanisms of Faster R-CNN in OOD through three main contributions. First, we observe that the forgetting curves of the Faster R-CNN exhibit patterns similar to those described in human memory studies by Hermann Ebbinghaus: knowledge is lost exponentially over time and recall improves knowledge retention. Second, we present a new methodology to analyse the Faster R-CNN architecture and quantify forgetting across the Faster R-CNN components. We show that forgetting is mainly localised in the Softmax classification layer. Finally, we propose a new training strategy for OOD called Configurable Recall (CR). CR performs recalls on old data using images stored in a memory buffer with variable frequency and recall length to ensure efficient learning. CR also masks the logits of old objects in the softmax classification layer to mitigate forgetting. We evaluate our strategy against state-of-the-art methods on three OOD benchmarks. We analyse the effectiveness of different types of recall in mitigating forgetting and show that CR outperforms existing methods.

关键词： Benchmark testing object detection Training Streaming media Data models Feature extraction Computer architecture Proposals Continuing education object recognition Catastrophic forgetting online object detection faster R-CNN Ebbinghaus forgetting curve natural replay online continual learning

来源：评论

学校读者我要写书评

暂无评论

Open World object detection: A Survey

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第2期35卷 988-1008页

作者： Li, Yiming Wang, Yi Wang, Wenqian Lin, Dan Li, Bingbing Yap, Kim-Hui Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore Hong Kong Polytech Univ Dept Elect & Elect Engn Hong Kong Peoples R China Nanyang Technol Univ Continental NTU Corp Lab Singapore 639798 Singapore Harbin Engn Univ Coll Comp Sci & Technol Harbin 150001 Peoples R China Continental Automot Singapore Pte Ltd Singapore Singapore

Exploring new knowledge is a fundamental human ability that can be mirrored in the development of deep neural networks, especially in the field of object detection. Open world object detection (OWOD) is an emerging area of research that adapts this principle to explore new knowledge. It focuses on recognizing and learning from objects absent from initial training sets, thereby incrementally expanding its knowledge base when new class labels are introduced. This survey paper offers a thorough review of the OWOD domain, covering essential aspects, including problem definitions, benchmark datasets, source codes, evaluation metrics, and a comparative study of existing methods. Additionally, we investigate related areas like open set recognition (OSR) and incremental learning (IL), underlining their relevance to OWOD. Finally, the paper concludes by addressing the limitations and challenges faced by current OWOD algorithms and proposes directions for future research. To our knowledge, this is the first comprehensive survey of the emerging OWOD field with over one hundred references, marking a significant step forward for object detection technology.

关键词： object detection Reviews Surveys Incremental learning Benchmark testing Proposals Training Feature extraction Detectors Measurement Open world object detection incremental learning open set recognition

来源：评论

学校读者我要写书评

暂无评论

Task-Decoupled Learning Strategies for Optimized Multiclass object detection From VHR Optical Remote Sensing Imagery

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 8457-8471页

作者： Zhou, Guangyao Wang, Guanqun Huang, Yu Wang, Wenzhi Qu, Zhi Yin, Chenghan Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Chinese Acad Sci Key Lab Technol Geo Spatial Informat Proc & Applic Beijing 100190 Peoples R China Peking Univ Sch Comp Sci Natl Key Lab Multimedia Informat Proc Beijing 100871 Peoples R China Stonehenge Beijing Technol Co Ltd Beijing 100083 Peoples R China

object detection in remote sensing imagery poses significant challenges due to the vast scale variations and long-tail class distributions inherent in these scenarios. Traditional object detectors often struggle to balance the conflicting requirements of translation invariance for classification and translation equivariance for localization. In this article, we propose a decoupled multiclass object detection (DMOD) framework designed to address these challenges. The DMOD framework introduces a novel decoupling strategy, which separates the optimization of the localization and classification tasks, thereby avoiding the suboptimal solutions that arise from their conflicting demands. Specifically, the decoupled localization branch independently optimizes class-agnostic localization using a dedicated regression head, while the decoupled classification branch focuses on category prediction using translation-invariant features. In addition, a training-independent module (TIM) is incorporated to mitigate the impact of long-tail distributions by leveraging information theory to prioritize informative samples during training. Extensive experiments conducted on the DIOR and NWPU VHR-10 datasets demonstrate that our DMOD framework significantly outperforms existing state-of-the-art methods, achieving superior mean average precision scores of 74.79% and 95.23%, respectively. These results validate the effectiveness of the proposed decoupling strategy in enhancing object detection performance in complex remote sensing scenarios.

关键词： Location awareness object detection Remote sensing Training Heavily-tailed distribution Translation Feature extraction Accuracy Detectors Convolutional neural networks Multiple decoupled detector (MDD) remote sensing images (RSIs)

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：