Pub Date : 2024-10-07DOI: 10.1109/LSP.2024.3475351
Esa Ollila
We propose greedy Capon beamformer (GCB) for direction finding of narrow-band sources present in the array's viewing field. After defining the grid covering the location search space, the algorithm greedily builds the interference-plus-noise covariance matrix by identifying a high-power source on the grid using Capon's principle of maximizing the signal to interference plus noise ratio while enforcing unit gain towards the signal of interest. An estimate of the power of the detected source is derived by exploiting the unit power constraint, which subsequently allows to update the noise covariance matrix by simple rank-1 matrix addition composed of outerproduct of the selected steering matrix with itself scaled by the signal power estimate. Our numerical examples demonstrate effectiveness of the proposed GCB in direction finding where it performs favourably compared to the state-of-the-art algorithms under a broad variety of settings. Furthermore, GCB estimates of direction-of-arrivals (DOAs) are very fast to compute.
{"title":"Greedy Capon Beamformer","authors":"Esa Ollila","doi":"10.1109/LSP.2024.3475351","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475351","url":null,"abstract":"We propose greedy Capon beamformer (GCB) for direction finding of narrow-band sources present in the array's viewing field. After defining the grid covering the location search space, the algorithm greedily builds the interference-plus-noise covariance matrix by identifying a high-power source on the grid using Capon's principle of maximizing the signal to interference plus noise ratio while enforcing unit gain towards the signal of interest. An estimate of the power of the detected source is derived by exploiting the unit power constraint, which subsequently allows to update the noise covariance matrix by simple rank-1 matrix addition composed of outerproduct of the selected steering matrix with itself scaled by the signal power estimate. Our numerical examples demonstrate effectiveness of the proposed GCB in direction finding where it performs favourably compared to the state-of-the-art algorithms under a broad variety of settings. Furthermore, GCB estimates of direction-of-arrivals (DOAs) are very fast to compute.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10706632","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142431890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-07DOI: 10.1109/LSP.2024.3475913
Arghya Sinha;Kunal N. Chaudhury
In the Plug-and-Play (PnP) method, a denoiser is used as a regularizer within classical proximal algorithms for image reconstruction. It is known that a broad class of linear denoisers can be expressed as the proximal operator of a convex regularizer. Consequently, the associated PnP algorithm can be linked to a convex optimization problem $mathcal {P}$ . For such a linear denoiser, we prove that $mathcal {P}$ exhibits strong convexity for linear inverse problems. Specifically, we show that the strong convexity of $mathcal {P}$ can be used to certify objective and iterative convergence of any PnP algorithm derived from classical proximal methods.
{"title":"On the Strong Convexity of PnP Regularization Using Linear Denoisers","authors":"Arghya Sinha;Kunal N. Chaudhury","doi":"10.1109/LSP.2024.3475913","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475913","url":null,"abstract":"In the Plug-and-Play (PnP) method, a denoiser is used as a regularizer within classical proximal algorithms for image reconstruction. It is known that a broad class of linear denoisers can be expressed as the proximal operator of a convex regularizer. Consequently, the associated PnP algorithm can be linked to a convex optimization problem \u0000<inline-formula><tex-math>$mathcal {P}$</tex-math></inline-formula>\u0000. For such a linear denoiser, we prove that \u0000<inline-formula><tex-math>$mathcal {P}$</tex-math></inline-formula>\u0000 exhibits strong convexity for linear inverse problems. Specifically, we show that the strong convexity of \u0000<inline-formula><tex-math>$mathcal {P}$</tex-math></inline-formula>\u0000 can be used to certify objective and iterative convergence of \u0000<italic>any</i>\u0000 PnP algorithm derived from classical proximal methods.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142438595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-07DOI: 10.1109/LSP.2024.3475357
Chao Li;Wujie Zhou;Xi Zhou;Weiqing Yan
Existing salient target detection methods tend to use a single-mirror segmentation strategy, which ignores feature hierarchy information in the frequency domain and lacks fine-grained correspondence. To address these challenges, we propose a new semantic progressive guidance network (SPGNet). To mine sufficient effective information, we propose the wavelet bidirectional focusing (WBF) module to aggregate sub-band features through a bidirectional wavelet transform and fuse them with low-level features to deepen the detail mining. We also introduce the Gaussian fusion complementary (GFC) module, which adopts Gaussian filtering technology to optimize the feature space and then efficiently extracts the contour information through enhanced feature processing. In addition, we propose a global correlation bootstrapping (GCB) module that constructs region-to-pixel correlations from a global perspective to achieve fine-grained correspondence. The proposed model achieves competitive results on a benchmark dataset.
{"title":"Semantic Progressive Guidance Network for RGB-D Mirror Segmentation","authors":"Chao Li;Wujie Zhou;Xi Zhou;Weiqing Yan","doi":"10.1109/LSP.2024.3475357","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475357","url":null,"abstract":"Existing salient target detection methods tend to use a single-mirror segmentation strategy, which ignores feature hierarchy information in the frequency domain and lacks fine-grained correspondence. To address these challenges, we propose a new semantic progressive guidance network (SPGNet). To mine sufficient effective information, we propose the wavelet bidirectional focusing (WBF) module to aggregate sub-band features through a bidirectional wavelet transform and fuse them with low-level features to deepen the detail mining. We also introduce the Gaussian fusion complementary (GFC) module, which adopts Gaussian filtering technology to optimize the feature space and then efficiently extracts the contour information through enhanced feature processing. In addition, we propose a global correlation bootstrapping (GCB) module that constructs region-to-pixel correlations from a global perspective to achieve fine-grained correspondence. The proposed model achieves competitive results on a benchmark dataset.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-07DOI: 10.1109/LSP.2024.3475354
Pei Yan;Shunquan Tan;Miaohui Wang;Jiwu Huang
Malware detection is an effective way to prevent the intrusion of malware into computer systems, and the API-based dynamic analysis method can effectively detect obfuscated and packaged malware. However, existing methods still suffer from limited detection accuracy and weak generalization. To address this issue, this paper presents a gradient attack-based malware dynamic analysis method. Through exerting adversarial noise into the embedding layer, the malware detection model can learn more robust representations of API sequences during training, achieving broader coverage of sample representations. The strategy of normalizing attack noise and recovering attacked representation is designed, which controls the strength of the gradient attack within a reasonable range and prevents a negative impact on the model's detection performance. The proposed method can be applied to existing API-based malware detection models to enhance their detection performance, indicating the strong generality of the proposed method. Experimental results on two benchmark datasets ( i.e. , Aliyun and Catak ) demonstrate the effectiveness of the proposed gradient attack method, which further improves the detection performance of the mainstream API-based models, with an average accuracy increase of 2.80% and 3.66% on these two datasets, respectively.
恶意软件检测是防止恶意软件入侵计算机系统的有效方法，而基于 API 的动态分析方法可以有效地检测出经过混淆和包装的恶意软件。然而，现有方法仍存在检测精度有限、泛化能力弱等问题。针对这一问题，本文提出了一种基于梯度攻击的恶意软件动态分析方法。通过在嵌入层中施加对抗噪声，恶意软件检测模型可以在训练过程中学习到更健壮的 API 序列表示，从而实现更广泛的样本表示覆盖。设计了攻击噪声归一化和恢复被攻击表示的策略，将梯度攻击的强度控制在合理范围内，避免了对模型检测性能的负面影响。所提出的方法可应用于现有的基于 API 的恶意软件检测模型，以提高其检测性能，这表明所提出的方法具有很强的通用性。在两个基准数据集（即阿里云和 Catak）上的实验结果证明了所提梯度攻击方法的有效性，它进一步提高了基于 API 的主流模型的检测性能，在这两个数据集上的平均准确率分别提高了 2.80% 和 3.66%。
{"title":"Enhanced Dynamic Analysis for Malware Detection With Gradient Attack","authors":"Pei Yan;Shunquan Tan;Miaohui Wang;Jiwu Huang","doi":"10.1109/LSP.2024.3475354","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475354","url":null,"abstract":"Malware detection is an effective way to prevent the intrusion of malware into computer systems, and the API-based dynamic analysis method can effectively detect obfuscated and packaged malware. However, existing methods still suffer from limited detection accuracy and weak generalization. To address this issue, this paper presents a gradient attack-based malware dynamic analysis method. Through exerting adversarial noise into the embedding layer, the malware detection model can learn more robust representations of API sequences during training, achieving broader coverage of sample representations. The strategy of normalizing attack noise and recovering attacked representation is designed, which controls the strength of the gradient attack within a reasonable range and prevents a negative impact on the model's detection performance. The proposed method can be applied to existing API-based malware detection models to enhance their detection performance, indicating the strong generality of the proposed method. Experimental results on two benchmark datasets (\u0000<italic>i.e.</i>\u0000, \u0000<italic>Aliyun</i>\u0000 and \u0000<italic>Catak</i>\u0000) demonstrate the effectiveness of the proposed gradient attack method, which further improves the detection performance of the mainstream API-based models, with an average accuracy increase of 2.80% and 3.66% on these two datasets, respectively.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-03DOI: 10.1109/LSP.2024.3472492
Wentao Cheng;Minxing Luo
We introduce a novel method for one-shot object pose estimation. Recent detector-free one-shot methods have achieved promising results for challenging low-textured objects. The features in a query image are directly matched with all features in an object point cloud reconstructed via Structure-from-Motion (SfM) techniques. Rejecting invisible 3D points, as well as associated features, is performed implicitly using a deep neural network that is trained specifically for feature matching. This tightly-coupled strategy is prone to preserve 3D points that are rarely visible from the query view. In contrast, we propose to prune such erroneous points using the explicit image-point relational graph, which is a lightweight by-product of the SfM reconstruction. By injecting the graph-based pruning into stacked feature transformers, our method is able to obtain high quality 2D-3D correspondences through matching with visible points in an early stage. The experiments demonstrate that our method outperforms state-of-the-art model-free one-shot methods with faster speed.
{"title":"MVP: One-Shot Object Pose Estimation by Matching With Visible Points","authors":"Wentao Cheng;Minxing Luo","doi":"10.1109/LSP.2024.3472492","DOIUrl":"https://doi.org/10.1109/LSP.2024.3472492","url":null,"abstract":"We introduce a novel method for one-shot object pose estimation. Recent detector-free one-shot methods have achieved promising results for challenging low-textured objects. The features in a query image are directly matched with all features in an object point cloud reconstructed via Structure-from-Motion (SfM) techniques. Rejecting invisible 3D points, as well as associated features, is performed implicitly using a deep neural network that is trained specifically for feature matching. This tightly-coupled strategy is prone to preserve 3D points that are rarely visible from the query view. In contrast, we propose to prune such erroneous points using the explicit image-point relational graph, which is a lightweight by-product of the SfM reconstruction. By injecting the graph-based pruning into stacked feature transformers, our method is able to obtain high quality 2D-3D correspondences through matching with visible points in an early stage. The experiments demonstrate that our method outperforms state-of-the-art model-free one-shot methods with faster speed.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oriented object detection has broad utilization in many fields, including urban traffic monitoring, land utilization assessment, and environmental monitoring. However, current oriented object detecting methods are limited in leveraging multiscale information, failing to fully exploit the rich scale variation within images and resulting in suboptimal performance when detecting multiscale targets. Herein, an innovative method SH-Net is proposed based on adaptive feature learning and enrichment. First, an adaptive feature learning module (AFLM) is constructed to enhance the feature learning capability for multiscale objects. Second, a high-resolution feature pyramidal network (HRFPN) is constructed to enhance deep feature fusion for dense and small targets. Finally, a rotated proposal generation (RPG) module and rotated box refinement (RBR) module are proposed to generate and refine the bounding box for extracted oriented objects. The experimental results obtained on the DOTA dataset show that SH-Net can achieve a mAP of 82.67% and surpasses most state-of-the-art methods.
{"title":"Oriented Object Detection Based on Adaptive Feature Learning and Enrichment","authors":"Pei Li;Zhongjie Zhu;Yongqiang Bai;Yuer Wang;Lei Zhang","doi":"10.1109/LSP.2024.3472490","DOIUrl":"https://doi.org/10.1109/LSP.2024.3472490","url":null,"abstract":"Oriented object detection has broad utilization in many fields, including urban traffic monitoring, land utilization assessment, and environmental monitoring. However, current oriented object detecting methods are limited in leveraging multiscale information, failing to fully exploit the rich scale variation within images and resulting in suboptimal performance when detecting multiscale targets. Herein, an innovative method SH-Net is proposed based on adaptive feature learning and enrichment. First, an adaptive feature learning module (AFLM) is constructed to enhance the feature learning capability for multiscale objects. Second, a high-resolution feature pyramidal network (HRFPN) is constructed to enhance deep feature fusion for dense and small targets. Finally, a rotated proposal generation (RPG) module and rotated box refinement (RBR) module are proposed to generate and refine the bounding box for extracted oriented objects. The experimental results obtained on the DOTA dataset show that SH-Net can achieve a mAP of 82.67% and surpasses most state-of-the-art methods.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142397085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Automatic modulation classification (AMC), as a key technology of cognitive radio, has become a focal point of research. However, most deep learning-based AMC methods require an extensive number of labeled signals to acquire a comprehensive understanding of modulation types, placing substantial pressure on signal acquisition and labeling. To solve this issue, we propose a few-shot AMC (FSAMC) method to facilitate rapid generalization and recognition with limited data, namely multi-scale feature fusion and distribution similarity network (MS2F-DS). Firstly, we design a multi-scale feature fusion (MS2F) model, which aims to extract features with varying fields of view and boost feature fusion, enabling the derivation of contextual information from the signal. Furthermore, we introduce a distribution similarity (DS) classifier to address the insufficient measurement of current similarity measurement functions by considering both micro and macro perspectives of vectors, further increasing intra-class compactness and inter-class separability. Finally, extensive experiments were conducted on 3-way 1, 3, and 5-shot FSAMC tasks using public datasets RML2016.10a and RML2016.10b, and the results demonstrated the effectiveness of our method.
{"title":"Multi-Scale Feature Fusion and Distribution Similarity Network for Few-Shot Automatic Modulation Classification","authors":"Haoyue Tan;Zhenxi Zhang;Yu Li;Xiaoran Shi;Feng Zhou","doi":"10.1109/LSP.2024.3470762","DOIUrl":"https://doi.org/10.1109/LSP.2024.3470762","url":null,"abstract":"Automatic modulation classification (AMC), as a key technology of cognitive radio, has become a focal point of research. However, most deep learning-based AMC methods require an extensive number of labeled signals to acquire a comprehensive understanding of modulation types, placing substantial pressure on signal acquisition and labeling. To solve this issue, we propose a few-shot AMC (FSAMC) method to facilitate rapid generalization and recognition with limited data, namely multi-scale feature fusion and distribution similarity network (MS2F-DS). Firstly, we design a multi-scale feature fusion (MS2F) model, which aims to extract features with varying fields of view and boost feature fusion, enabling the derivation of contextual information from the signal. Furthermore, we introduce a distribution similarity (DS) classifier to address the insufficient measurement of current similarity measurement functions by considering both micro and macro perspectives of vectors, further increasing intra-class compactness and inter-class separability. Finally, extensive experiments were conducted on 3-way 1, 3, and 5-shot FSAMC tasks using public datasets RML2016.10a and RML2016.10b, and the results demonstrated the effectiveness of our method.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-30DOI: 10.1109/LSP.2024.3470752
Guanhua An;Ao He;Yudong Wang;Jichang Guo
Recently, state space models (SSM) with efficient design, i.e., Mamba, have shown great potential in modeling long-range dependencies with linear complexity. However, the pure SSM-based model yields sub-optimal underwater enhancement performance due to insufficient local details. Given the superiority of convolution in local perception, we propose a hybrid network, named UWMamba, which combines SSM and convolution for underwater image enhancement. We introduce a conv mamba layer (CML) as the foundation layer to combine the visual state space block (VSSB) with convolution. The convolution is used to capture local detailed features, while the VSSB is employed to capture long-range global features, which complement each other. Furthermore, considering underwater images suffer from severe and uneven degradation of spatial regions and color channels, we propose a Mamba Attention Fusion Module (MAFM), which fuses VSSB with an attention mechanism for better perception of channels and spatial regions. Extensive experiments on real-world underwater image datasets demonstrate the promising performance of our method in both objective metrics and subjective comparisons.
{"title":"UWMamba: UnderWater Image Enhancement With State Space Model","authors":"Guanhua An;Ao He;Yudong Wang;Jichang Guo","doi":"10.1109/LSP.2024.3470752","DOIUrl":"https://doi.org/10.1109/LSP.2024.3470752","url":null,"abstract":"Recently, state space models (SSM) with efficient design, i.e., Mamba, have shown great potential in modeling long-range dependencies with linear complexity. However, the pure SSM-based model yields sub-optimal underwater enhancement performance due to insufficient local details. Given the superiority of convolution in local perception, we propose a hybrid network, named UWMamba, which combines SSM and convolution for underwater image enhancement. We introduce a conv mamba layer (CML) as the foundation layer to combine the visual state space block (VSSB) with convolution. The convolution is used to capture local detailed features, while the VSSB is employed to capture long-range global features, which complement each other. Furthermore, considering underwater images suffer from severe and uneven degradation of spatial regions and color channels, we propose a Mamba Attention Fusion Module (MAFM), which fuses VSSB with an attention mechanism for better perception of channels and spatial regions. Extensive experiments on real-world underwater image datasets demonstrate the promising performance of our method in both objective metrics and subjective comparisons.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142397083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pedestrian intrusion detection is crucial to ensuring safe railway operation. Current pedestrian detection algorithms lack consideration for real-world railway scenarios, such as the reflective properties of screen doors and train windows, may mistakenly trigger pedestrian intrusion alerts. Scale variability and pedestrian overlap often lead to detection inaccuracy, making them inadequate for addressing the specific requirements of railway perimeter security. This letter introduces an innovative pedestrian detection algorithm that incorporates Mirror Translation Attention (MTA) and Feature Pooling Enhancement (FPE). MTA, including mirror flipping and offsetting the feature mapping, could significantly mitigate missed detection caused by reflective surfaces. Additionally, we introduce sparsity to the inputs of the self-attention, which significantly enhancing the model's inference speed. A multi-scale approach is adopted to accommodate the diversity in pedestrian sizes, while the FPE addresses occlusion issues across various scales. Compared to the advanced YOLOv8 model, the proposed method improves AP50 by 1.6% to 92.11% and reduces model parameters by 63.55% in our self-built railway pedestrian intrusion dataset.
{"title":"Pedestrian Intrusion Detection in Railway Station Based on Mirror Translation Attention and Feature Pooling Enhancement","authors":"Zhufeng Jiang;Hui Wang;Guoliang Luo;Zizhu Fan;Lu Xu","doi":"10.1109/LSP.2024.3471180","DOIUrl":"https://doi.org/10.1109/LSP.2024.3471180","url":null,"abstract":"Pedestrian intrusion detection is crucial to ensuring safe railway operation. Current pedestrian detection algorithms lack consideration for real-world railway scenarios, such as the reflective properties of screen doors and train windows, may mistakenly trigger pedestrian intrusion alerts. Scale variability and pedestrian overlap often lead to detection inaccuracy, making them inadequate for addressing the specific requirements of railway perimeter security. This letter introduces an innovative pedestrian detection algorithm that incorporates Mirror Translation Attention (MTA) and Feature Pooling Enhancement (FPE). MTA, including mirror flipping and offsetting the feature mapping, could significantly mitigate missed detection caused by reflective surfaces. Additionally, we introduce sparsity to the inputs of the self-attention, which significantly enhancing the model's inference speed. A multi-scale approach is adopted to accommodate the diversity in pedestrian sizes, while the FPE addresses occlusion issues across various scales. Compared to the advanced YOLOv8 model, the proposed method improves AP50 by 1.6% to 92.11% and reduces model parameters by 63.55% in our self-built railway pedestrian intrusion dataset.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142397084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-27DOI: 10.1109/LSP.2024.3469787
Guozheng Nan;Yue Zhao;Chengxing Lin;Qiaolin Ye
The You Only Look Once (YOLO) series of object detection algorithms has attracted considerable attention for its notable advantages in speed and accuracy, resulting in widespread applications in various real-world scenarios. However, achieving outstanding accuracy on remote sensing images with densely arranged small targets and complex backgrounds remains a challenging task. To address this issue, this letter proposes two easily integrated modules suitable for the YOLO architecture, namely global semantic information extraction (GSIE) and adaptive feature fusion (AFF). The GSIE module is designed to overcome the limitation of local information in traditional methods and facilitate global semantic information interaction by introducing multi-angle feature rotation to extend the receptive field. The AFF module effectively captures fine-grained features of objects by dynamically adjusting fusion weights, thereby reducing the loss of deep semantic information during feature transfer and fusion. The experimental results on the VEDAI and LEVIR remote sensing datasets demonstrate that when embedding these two modules into YOLO series algorithms that only use the small-scale detector, there is a significant improvement in performance while reducing computational complexity.
{"title":"General Optimization Methods for YOLO Series Object Detection in Remote Sensing Images","authors":"Guozheng Nan;Yue Zhao;Chengxing Lin;Qiaolin Ye","doi":"10.1109/LSP.2024.3469787","DOIUrl":"https://doi.org/10.1109/LSP.2024.3469787","url":null,"abstract":"The You Only Look Once (YOLO) series of object detection algorithms has attracted considerable attention for its notable advantages in speed and accuracy, resulting in widespread applications in various real-world scenarios. However, achieving outstanding accuracy on remote sensing images with densely arranged small targets and complex backgrounds remains a challenging task. To address this issue, this letter proposes two easily integrated modules suitable for the YOLO architecture, namely global semantic information extraction (GSIE) and adaptive feature fusion (AFF). The GSIE module is designed to overcome the limitation of local information in traditional methods and facilitate global semantic information interaction by introducing multi-angle feature rotation to extend the receptive field. The AFF module effectively captures fine-grained features of objects by dynamically adjusting fusion weights, thereby reducing the loss of deep semantic information during feature transfer and fusion. The experimental results on the VEDAI and LEVIR remote sensing datasets demonstrate that when embedding these two modules into YOLO series algorithms that only use the small-scale detector, there is a significant improvement in performance while reducing computational complexity.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：