Digital Signal Processing最新文献_第2页

MLE-YOLO: A lightweight and robust vehicle and pedestrian detector for adverse weather in autonomous driving MLE-YOLO：用于自动驾驶恶劣天气的轻型、坚固的车辆和行人探测器

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-25 DOI: 10.1016/j.dsp.2025.105628

Danfeng Du , Mengju Bi , Yuchen Xie , Yang Liu , Guanlin Qi , Yangyang Guo

{"title":"MLE-YOLO: A lightweight and robust vehicle and pedestrian detector for adverse weather in autonomous driving","authors":"Danfeng Du , Mengju Bi , Yuchen Xie , Yang Liu , Guanlin Qi , Yangyang Guo","doi":"10.1016/j.dsp.2025.105628","DOIUrl":"10.1016/j.dsp.2025.105628","url":null,"abstract":"<div><div>Adverse weather poses significant challenges to object detection in autonomous driving, including poor visibility, precipitation interference, and motion blur. Additionally, conventional object detectors often struggle to balance computational efficiency with detection accuracy in such conditions. To address these issues, we propose MLE-YOLO (Multimodal Lightweight Enhanced YOLO), a multimodal fusion framework built upon YOLOv11, optimized for robust vehicle and pedestrian detection in adverse environments. MLE-YOLO integrates four key innovations. The backbone is enhanced with a Multi-Stage Partial Transformer Module (M-SPTM), which combines CNN and Transformer branches to improve detection accuracy in foggy and rainy scenarios while maintaining computational efficiency. The neck adopts a Mixed Aggregation Network (MANet) that leverages depthwise separable convolutions and dynamic cross-layer connections to strengthen multi-scale feature fusion and suppress weather-induced noise. A Lightweight Downsampling Module (LDM) is designed to enhance small-object detection through multi-path feature aggregation, coupled with a compact structure that reduces computational load. Finally, an Efficient Lightweight Detection Head (ELDH) incorporates detail-enhancing convolutions to extract both intensity and gradient features from degraded visual inputs. Extensive experiments on a custom adverse weather dataset demonstrate that MLE-YOLO improves F1 score by 3.6 % and mAP by 3.0 %, while reducing model parameters by 15.8 %, model size by 7.1 %, and FLOPs by 3.2 %. These results validate MLE-YOLO as a lightweight and robust solution for real-time perception in autonomous driving under challenging environmental conditions.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"168 ","pages":"Article 105628"},"PeriodicalIF":3.0,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multiwindow hierarchical range-spread target detection in high-resolution sea clutter 高分辨率海杂波多窗口分层距离扩展目标检测

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-25 DOI: 10.1016/j.dsp.2025.105632

Yu-Fan Xue, Xiao-Jun Zhang, Si-Yuan Chang, Peng-Lang Shui, Shu-Wen Xu

{"title":"Multiwindow hierarchical range-spread target detection in high-resolution sea clutter","authors":"Yu-Fan Xue, Xiao-Jun Zhang, Si-Yuan Chang, Peng-Lang Shui, Shu-Wen Xu","doi":"10.1016/j.dsp.2025.105632","DOIUrl":"10.1016/j.dsp.2025.105632","url":null,"abstract":"<div><div>High-resolution maritime radars often operate on complex scenes with dense small targets and range-spread targets in coastal waters. Traditional range-spread target detectors suffer from significant loss due to the mismatch between the range integration window and target radial sizes, and severe interference from range-spread targets to detection of surrounding small targets. In this paper, a multiwindow hierarchical range-spread target detection method is proposed to address target detection in complex oceanic scenes. High-resolution sea clutter is modelled by the generalized Pareto distribution. Adaptive range-spread generalized likelihood ratio test linearly threshold detectors (GLRT-LTDs) using multiple range integration windows are cooperated to reduce the mismatch loss. The detection results using wider range windows serve as prior information on scenes, aiding detection using narrower range windows in selection of reference cells. The hierarchical utilization of scene information markedly improves detection performance of small targets around range-spread targets. In addition, the mismatch loss of range windows in range-spread GLRT-LTDs are analyzed, and a fast estimation and inversion algorithm of speckle covariance matrices is given to mitigate computational burden of the multiwindow hierarchical detection. Finally, measured data with test small target and simulated range-spread targets is used to verify the effectiveness of the proposed method.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"168 ","pages":"Article 105632"},"PeriodicalIF":3.0,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145264988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improved channel tracking in underwater systems using time-varying sliding window RLS with dual projection framework 基于双投影框架的时变滑动窗RLS改进水下信道跟踪

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-24 DOI: 10.1016/j.dsp.2025.105612

Yi Lou , Zhikuan Chen , Xinqian Mao , Yunjiang Zhao , Zemin Zhou , Zhiquan Zhou

{"title":"Improved channel tracking in underwater systems using time-varying sliding window RLS with dual projection framework","authors":"Yi Lou , Zhikuan Chen , Xinqian Mao , Yunjiang Zhao , Zemin Zhou , Zhiquan Zhou","doi":"10.1016/j.dsp.2025.105612","DOIUrl":"10.1016/j.dsp.2025.105612","url":null,"abstract":"<div><div>The Recursive Least Squares (RLS) algorithm is widely used for channel estimation, but its performance degrades in dynamic and noisy underwater environments. To address this issue, we propose an enhanced RLS variant, the Time-Varying Sliding Window RLS (TVSRLS) algorithm. The TVSRLS algorithm extracts the signal’s frequency features using the Chirplet Transform. The window length is then dynamically adjusted based on changes in the signal’s frequency. Using a rotation matrix, the algorithm projects the signal along the direction with the highest Signal-to-Noise Ratio (SNR), optimizing sensitivity to relevant signals. The window shape is adaptively scaled in that direction using a variable window length and an anisotropic operator. This approach suppresses noise from other directions, further improving SNR. The algorithm applies a second projection using Local Basis Functions to map the signal into the local time-frequency domain. This local time-frequency processing reduces residual noise, further improving signal clarity. Simulations demonstrate that TVSRLS consistently outperforms the traditional Sliding window RLS (SRLS) in various noise conditions, providing more accurate channel estimation.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"168 ","pages":"Article 105612"},"PeriodicalIF":3.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hybrid diffusion model for OCT-angiography vessel segmentation with denoising enhancement 基于去噪增强的oct血管成像血管分割混合扩散模型

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-24 DOI: 10.1016/j.dsp.2025.105620

Xiaoxuan Huang , Yanmei Li , Yu Wu , Zhipeng Li , Hanguang Xiao , Guibin Bian

{"title":"Hybrid diffusion model for OCT-angiography vessel segmentation with denoising enhancement","authors":"Xiaoxuan Huang , Yanmei Li , Yu Wu , Zhipeng Li , Hanguang Xiao , Guibin Bian","doi":"10.1016/j.dsp.2025.105620","DOIUrl":"10.1016/j.dsp.2025.105620","url":null,"abstract":"<div><div>Optical Coherence Tomography Angiography (OCTA) technology provides detailed visualization of the retinal vascular system, where accurate vessel segmentation is crucial for diagnosing vision-related diseases. However, the 3D volume data, affected by inherent modality constraints, contains artifacts and noise, complicating precise vessel extraction in down-sampled images. To address these challenges, this study introduces a hybrid model architecture. The proposed method leverages a diffusion model to learn the underlying noise distribution and regulate the denoising process by controlling the time step. This facilitates noise suppression, vascular structure restoration, and enhanced vessel-background contrast. Furthermore, we design a lightweight segmentation discriminator that utilizes denoised images as conditional inputs. By leveraging wavelet convolution, the discriminator extracts both high- and low-frequency features, enhancing texture representation and detail preservation. This ultimately contributes to more precise vessel segmentation. The diffusion model and segmentation discriminator are incorporated into a unified end-to-end network framework. Extensive experiments on the OCTA-500 and ROSE-1 datasets validate the superiority of our method over state-of-the-art approaches in vessel segmentation.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"168 ","pages":"Article 105620"},"PeriodicalIF":3.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145264985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust Optimization Models for Nonparallel Support Vector Machine 非并行支持向量机的鲁棒优化模型

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-24 DOI: 10.1016/j.dsp.2025.105616

Wendi Zhang , Gang Wang , Jiakang Du

{"title":"Robust Optimization Models for Nonparallel Support Vector Machine","authors":"Wendi Zhang , Gang Wang , Jiakang Du","doi":"10.1016/j.dsp.2025.105616","DOIUrl":"10.1016/j.dsp.2025.105616","url":null,"abstract":"<div><div>To address the classification performance degradation caused by noise-contaminated data in real-world scenarios, we propose a robust Nonparallel Support Vector Machine (NPSVM) framework based on uncertainty sets. The suggested framework innovatively overcomes the limitation of precise-label dependency in traditional methods by employing two tactically deployed nonparallel hyperplanes that ensure robust classification performance in noisy environments. Four fundamental innovations distinguish our approach. First, the multi-parameter penalty mechanism compensates for class imbalance, improving classification accuracy. Second, the <span><math><mrow><mi>ε</mi></mrow></math></span>-insensitive loss function provides inherent noise resistance and preserves model sparsity. Third, rigorous robustness is ensured by our convex optimization-based uncertainty quantification employing hyper-rectangle and hyper-ellipsoid sets. Finally, the proposed model has computational efficiency by solving two smaller convex sub-problems. Experimental validation on UCI benchmark datasets demonstrates the superior performance of our method compared to conventional algorithms with the hyper-ellipsoidal uncertainty set-based classifier exhibiting particularly outstanding results.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"168 ","pages":"Article 105616"},"PeriodicalIF":3.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Novel graph neural network and GNN-C-Transformer model construction for direction of arrival estimation 新型图神经网络及GNN-C-Transformer到达方向估计模型的构建

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-23 DOI: 10.1016/j.dsp.2025.105619

Hongxi Zhao , Yiran Shi , Wenchao He , Hewei Sun , Haoran Wang , Jiahao Liu , Lin Gui

{"title":"Novel graph neural network and GNN-C-Transformer model construction for direction of arrival estimation","authors":"Hongxi Zhao , Yiran Shi , Wenchao He , Hewei Sun , Haoran Wang , Jiahao Liu , Lin Gui","doi":"10.1016/j.dsp.2025.105619","DOIUrl":"10.1016/j.dsp.2025.105619","url":null,"abstract":"<div><div>Direction of Arrival (DOA) estimation is essential in radar, sonar, wireless communications, and speech processing. Traditional methods like MUSIC and ESPRIT provide high resolution but suffer from high computational complexity and poor performance in low signal-to-noise ratio (SNR) environments. Recent advances in neural networks, particularly Convolutional Neural Networks (CNN), improve accuracy and robustness; however, CNNs’ ability to reduce time complexity and improving robustness under low SNR conditions remains insufficient.</div><div>This paper presents a novel framework for DOA estimation in sparse arrays based on Graph Neural Networks (GNN) and proposes an entirely new array-based graph connectivity structure. By modeling the array geometry as a graph, our GNN approach captures spatial relationships effectively, addressing the challenges of time complexity and low SNR. We further integrate Transformer layers to capture both spatial and temporal dependencies, enhancing the model’s performance. Experimental results demonstrate that, at SNRs <span><math><mrow><mo>≤</mo><mn>5</mn><mspace></mspace><mrow><mi>dB</mi></mrow></mrow></math></span>, our GNN-based framework and the GNN-C-Transformer model developed thereon achieve superior accuracy compared to existing methods, while exhibiting lower computational complexity than all other algorithms except ESPRIT. This work advances the application of GNN-based DOA estimation by providing a scalable solution for large-scale, multi-dimensional signal processing in both dense and sparse array configurations.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"168 ","pages":"Article 105619"},"PeriodicalIF":3.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An adaptive virtual measurement STGP algorithm for self-occluded 3D extended object tracking with time-varying shapes 一种时变形状自遮挡三维扩展目标跟踪的自适应虚拟测量STGP算法

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-23 DOI: 10.1016/j.dsp.2025.105622

Hua Su, Yunfei Guo, Anke Xue, Yun Chen

引用次数: 0

Sample unbalanced HRRP ground target recognition based on improved Lightgbm 基于改进Lightgbm的样本不平衡HRRP地面目标识别

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-23 DOI: 10.1016/j.dsp.2025.105624

Di Wu , Shuwen Xu , Hui Liu , Pengcheng Guo

{"title":"Sample unbalanced HRRP ground target recognition based on improved Lightgbm","authors":"Di Wu , Shuwen Xu , Hui Liu , Pengcheng Guo","doi":"10.1016/j.dsp.2025.105624","DOIUrl":"10.1016/j.dsp.2025.105624","url":null,"abstract":"<div><div>Radar-based ground target recognition faces significant challenges, including complex terrain, diverse target types, high recognition difficulty, and low accuracy. Moreover, the non-cooperative nature of military targets limits access to comprehensive target data, leading to sample imbalances that further degrade recognition performance. Addressing these issues, this paper proposes a target recognition method based on LightGBM, which balances model complexity and recognition accuracy. This method integrates a weighted focal loss function with dual-stage ground clutter suppression and enhancement techniques. Initially, during the data preprocessing phase, spherical hypothesis clustering, coupled with the local outlier factor algorithm, is utilized to mitigate ground target clutter. Subsequently, in the training phase for target recognition, the weights of imbalanced samples are dynamically adjusted to augment the model's learning capacity and heighten its focus on challenging targets. This approach dynamically adjusts the weights of imbalanced samples, thereby enhancing the model's learning ability and increasing its attention to difficult-to-classify instances. Additionally, to better accommodate complex backgrounds and bolster the model's robustness, an adaptive weighting coefficient adjustment mechanism is incorporated. Ultimately, ground targets are identified using a LightGBM multi-classifier. Simulations based on actual radar seeker data have validated the effectiveness of this method, and the recognition performance for six distinct target types has been evaluated. Comparative analyses with other classifiers demonstrate that this method exhibits superior performance in ground target recognition under conditions of imbalanced samples.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"168 ","pages":"Article 105624"},"PeriodicalIF":3.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intra-group neighborhood relationship-aware channel pruning 组内邻域关系感知的通道修剪

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-23 DOI: 10.1016/j.dsp.2025.105615

Yu Pan, Ning Chen, Hongqing Zhu, Zhiying Zhu

{"title":"Intra-group neighborhood relationship-aware channel pruning","authors":"Yu Pan, Ning Chen, Hongqing Zhu, Zhiying Zhu","doi":"10.1016/j.dsp.2025.105615","DOIUrl":"10.1016/j.dsp.2025.105615","url":null,"abstract":"<div><div>The high computational and memory requirements of Convolutional Neural Networks (CNNs) limit the deployment of CNN-based image processing models on edge computing devices. To this end, the clustering-based structural pruning methods have been studied to prune the redundant channels. However, the conventional clustering-based pruning methods may not achieve satisfactory performances for the following reasons. First, the clustering is performed only based on the feature of the current layer, which is not enough to identify the importance of each channel precisely. Second, the K-Means or K-Means++ clustering-based pruning methods may be affected by abnormal channels easily. Third, the strategy of pruning the channels around centroids may prune important channels. Fourth, the number of clusters needs to be set manually, which may affect the flexibility and generalization. To solve these issues, an intro-group neighborhood relationship-aware (IGNRA) channel pruning method is proposed. First, DepGraph is adopted to construct the dependency graph, based on which the global-level importance of each channel is assessed. Second, K-Medoids is adopted to perform clustering to reduce the influence of abnormal channels. Third, the centroids of clusters with multiple channels are viewed as redundant channels and pruned directly, while the centroids of those with a single channel are retained due to their unique roles in the downstream tasks. Fourth, the number of the clusters is set according to the pruning ratio automatically to enhance the method’s flexibility and generalization. Extensive experimental results on 9 models for two image processing tasks on 6 datasets demonstrate that the proposed method outperforms the state-of-the-art pruning methods, and each key module contributes to the performance enhancement.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"168 ","pages":"Article 105615"},"PeriodicalIF":3.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Maritime image dehazing based on Omni-Directional Perception and frequency-guided fusion 基于全方位感知和频导融合的海洋图像去雾

IF 3 3区工程技术

Digital Signal Processing Pub Date : 2025-09-22 DOI: 10.1016/j.dsp.2025.105611

Jingang Wang , Shikai Wu , Peng Liu

{"title":"Maritime image dehazing based on Omni-Directional Perception and frequency-guided fusion","authors":"Jingang Wang , Shikai Wu , Peng Liu","doi":"10.1016/j.dsp.2025.105611","DOIUrl":"10.1016/j.dsp.2025.105611","url":null,"abstract":"<div><div>Maritime image dehazing plays a crucial role in visual navigation and environmental perception. While existing methods based on physical models and deep learning have achieved certain progress in enhancing image contrast and detail restoration, they still face challenges in insufficient target detail extraction and over-smoothed backgrounds in complex maritime scenarios. To address these issues, this paper proposes an innovative network architecture featuring parallel feature perception and frequency-guided fusion, which improves dehazing performance through three aspects: feature extraction, feature fusion, and information optimization. Specifically, the Omni-Directional Perception Module enhances the perception of complex features by strengthening high-frequency target detail and low-frequency background feature extraction. The Frequency-Guided Feature Fusion Module achieves efficient local-global feature fusion through frequency decomposition and dynamic weighting mechanisms. The Discrete Entropy Constraint Loss further improves the naturalness and detail fidelity of dehazed results by optimizing image information distribution. Experimental results demonstrate that our method significantly enhances detail representation and background naturalness in complex scenarios, providing a promising solution for marine image dehazing.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"168 ","pages":"Article 105611"},"PeriodicalIF":3.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145134648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0