Signal Processing最新文献_第10页

LSCANet: Differential features guided long–short cross attention network for infrared and visible image fusion

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-09 DOI: 10.1016/j.sigpro.2025.109889

Baofeng Guo , Hongtao Huo , Xiaowen Liu , Bowen Zheng , Jing Li

{"title":"LSCANet: Differential features guided long–short cross attention network for infrared and visible image fusion","authors":"Baofeng Guo , Hongtao Huo , Xiaowen Liu , Bowen Zheng , Jing Li","doi":"10.1016/j.sigpro.2025.109889","DOIUrl":"10.1016/j.sigpro.2025.109889","url":null,"abstract":"<div><div>Infrared and visible image fusion can generate images that not only highlight prominent targets, but also contain rich details and texture information. However, directly fusing the features of infrared and visible images can diminish the correlation information between source images. To address this, we propose a differential features guided long–short cross attention network for infrared and visible image fusion (LSCANet). Specifically, a differential feature cross attention network (DCAN) is designed to achieve cross modal multi-scale interaction of differential features in the feature extraction process. Cross modal feature interaction before infrared and visible features fusion can enhance deep feature relationships between cross modal features, thereby preserving more correlation information between source images. Besides, a long–short differential feature attention network (LSDAN) is proposed to achieve the integration of multi-scale cross-modal differential features, which can preserve details and texture information while reducing the artifacts and noise introduced during the integration process. Moreover, the loss function is introduced to impel the network retain more details and texture information while preserving thermal radiation information. Ablation experiments were conducted to validate the effectiveness of LSCANet. Extensive qualitative and quantitative experiments conducted on cross dataset benchmarks have demonstrated that LSCANet outperforms eight state-of-the-art methods. The source code is available at <span><span>https://github.com/Pinot-30/LSCANet/tree/main</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"231 ","pages":"Article 109889"},"PeriodicalIF":3.4,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143138411","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}

引用次数: 0

High-order chirplet transform for efficient reconstruction of multicomponent signals with amplitude modulated crossing ridges

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-08 DOI: 10.1016/j.sigpro.2025.109887

Timothée Maison , Fabrice Silva , Nathalie Henrich Bernardoni , Philippe Guillemain

引用次数: 0

QP-adaptive compressed video super-resolution with coding priors

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-06 DOI: 10.1016/j.sigpro.2024.109878

Tingrong Zhang, Zhengxin Chen, Xiaohai He, Chao Ren, Qizhi Teng

{"title":"QP-adaptive compressed video super-resolution with coding priors","authors":"Tingrong Zhang, Zhengxin Chen, Xiaohai He, Chao Ren, Qizhi Teng","doi":"10.1016/j.sigpro.2024.109878","DOIUrl":"10.1016/j.sigpro.2024.109878","url":null,"abstract":"<div><div>Video super-resolution algorithms have found widespread applications as post-processing techniques in down-sampling based coding methods. With the advancements in deep learning techniques, video super-resolution has achieved remarkable success. However, applying existing video super-resolution methods to compressed videos requires training specific models for various quantization parameters (QPs), significantly increasing the resource consumption for model training and compromising their practical utility. To address this issue, we propose a QP-adaptive network for compressed video super-resolution based on coding priors (QPAN). Firstly, we design a QP modulation module (QPMM), which can utilize the frame-wise QP to recalibrate feature maps. Then, on the basis of QPMM, an adaptive multi-scale prior fusion module (Ada-MSPFM) and an adaptive enhancement modulation module (Ada-EMM) are constructed. The former effectively integrates multi-scale features from spatial coding priors in the bitstream and multi-scale features from the decoded video frames. And the latter improves the expressive ability of the network by leveraging QP modulation and reinforcing feature flow adaptively. Extensive experiments demonstrate the highly flexible and adaptive of our proposed method, which exhibits superior reconstruction performance compared to state-of-the-art video super-resolution algorithms.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"230 ","pages":"Article 109878"},"PeriodicalIF":3.4,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143131789","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}

引用次数: 0

Adaptive order synchrosqueezing transform

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-06 DOI: 10.1016/j.sigpro.2024.109881

Marcelo A. Colominas , Sylvain Meignen

引用次数: 0

Hurst exponent estimation using natural visibility graph embedding in Fisher–Shannon plane

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-04 DOI: 10.1016/j.sigpro.2024.109884

T. Averty, A.O. Boudraa, D. Daré-Emzivat

{"title":"Hurst exponent estimation using natural visibility graph embedding in Fisher–Shannon plane","authors":"T. Averty, A.O. Boudraa, D. Daré-Emzivat","doi":"10.1016/j.sigpro.2024.109884","DOIUrl":"10.1016/j.sigpro.2024.109884","url":null,"abstract":"<div><div>In this article, two important stochastic processes, namely fractional Brownian motions (fBm) and fractional Gaussian noises (fGn) are analyzed, within a Fisher–Shannon framework. These processes are well suited for the realistic modeling of phenomena occurring across various domains in science and engineering. An unique feature that characterizes both fBm and fGn, is the Hurst parameter <span><math><mi>H</mi></math></span>, that measures the long/short range dependence of such stochastic processes. In this paper, we show that these processes, from which we extract the degree distribution of the associated natural visibility graph (NVG), can be located in an informational plane, defined by normalized Shannon entropy <span><math><mi>S</mi></math></span> and Fisher information measure <span><math><mi>F</mi></math></span>, in order to estimate their Hurst exponents. The aim of this work is to map signals onto this informational plane, in which a reference backbone is built using generated fBm and fGn processes with known Hurst exponents. To show the effectiveness of the developed graphical estimator, some real-world data are analyzed, and it found that the <span><math><mi>H</mi></math></span> estimated by our method are quite comparable to those obtained from four well-known estimators of the literature. Besides, estimation of <span><math><mi>H</mi></math></span> parameter is very fast and requires a reduced number of samples of the input signal. Using the constructed reference backbone in the Fisher–Shannon plane, the associated <span><math><mi>H</mi></math></span> exponent can be easily estimated by a simple orthogonal projection of the point <span><math><mrow><mo>(</mo><mi>S</mi><mo>,</mo><mi>F</mi><mo>)</mo></mrow></math></span> extracted from the truncated degree distribution of the considered signal NVG representation.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"230 ","pages":"Article 109884"},"PeriodicalIF":3.4,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132727","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}

引用次数: 0

Supervised online multi-modal discrete hashing

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-04 DOI: 10.1016/j.sigpro.2024.109872

Yun Liu , Qiang Fu , Shujuan Ji , Xianwen Fang

{"title":"Supervised online multi-modal discrete hashing","authors":"Yun Liu , Qiang Fu , Shujuan Ji , Xianwen Fang","doi":"10.1016/j.sigpro.2024.109872","DOIUrl":"10.1016/j.sigpro.2024.109872","url":null,"abstract":"<div><div>Multi-modal hashing has been proposed due to its flexibility and effectiveness in multimedia retrieval tasks. Nevertheless, the majority of multi-modal hashing methods now in use acquire hash codes and hash functions through batch-based learning, which is unsuitable to handle streaming data. Online learning can be used for multi-modal hashing, but still exists in some issues that need to be addressed, such as how to properly employ the modal semantic information and reduce hash learning loss. To address these issues mentioned above, we propose a multi-modal hashing method, called Supervised Online Multi-modal Discrete Hashing (SOMDH). SOMDH first imposes a multi-modal weight to obtain the integrated multi-modal feature representation and then leverages matrix factorization to directly obtain hash codes. In addition, the correlations between the new data and existing data are established with a similarity matrix. Finally, SOMDH can learn the hash codes by discrete optimization strategy. Experimental results on two benchmark datasets demonstrate that SOMDH outperforms state-of-the-art offline and online multi-modal hashing methods in terms of retrieval accuracy.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"231 ","pages":"Article 109872"},"PeriodicalIF":3.4,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143138408","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}

引用次数: 0

When non-local similarity meets tensor factorization: A patch-wise method for hyperspectral anomaly detection

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-04 DOI: 10.1016/j.sigpro.2024.109875

Lixiang Meng , Yanhui Xu , Qiangqiang Shen , Yongyong Chen

{"title":"When non-local similarity meets tensor factorization: A patch-wise method for hyperspectral anomaly detection","authors":"Lixiang Meng , Yanhui Xu , Qiangqiang Shen , Yongyong Chen","doi":"10.1016/j.sigpro.2024.109875","DOIUrl":"10.1016/j.sigpro.2024.109875","url":null,"abstract":"<div><div>Hyperspectral anomaly detection (HAD) entails identifying anomaly pixels in hyperspectral images (HSI) that significantly diverge from the background spectral signatures. However, the conventional tensor-based HAD methods typically leverage tensor nuclear norm (TNN) and its variants to exploit the low-rank characteristic on the image-level HSI. Specifically, the omission of non-local similarity features in HAD reduces the potential to leverage pertinent information, leading to the loss of crucial HSI structures and details. In addition, the tensor singular value decomposition (t-SVD) involved in solving the TNN minimization tends to augment the computational time as the data size expands. To address these issues, a novel patch-wise model for HAD that integrates non-local similarity with tensor factorization (NSTF) is proposed. Specifically, instead of using the entire image, we employ aggregated non-local similarity patches to characterize the low-rank structure of HSI, accounting for both spectral correlation and non-local similarity simultaneously and equivalently. Moreover, we introduce tensor factorization to factorize the large-scale tensor generated by grouping non-local similarity patches into two small-scale tensors, which more efficiently exploits its low-rank property of background. Finally, comprehensive experimental results validated on HSI datasets unequivocally establish the superiority of our proposed method over cutting-edge methods.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"230 ","pages":"Article 109875"},"PeriodicalIF":3.4,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132719","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}

引用次数: 0

Efficient homography estimation using a recursive algorithm with a mixture of weighted Gaussian kernels

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-04 DOI: 10.1016/j.sigpro.2024.109882

F. Hashemzadeh , T. Kumbasar

{"title":"Efficient homography estimation using a recursive algorithm with a mixture of weighted Gaussian kernels","authors":"F. Hashemzadeh , T. Kumbasar","doi":"10.1016/j.sigpro.2024.109882","DOIUrl":"10.1016/j.sigpro.2024.109882","url":null,"abstract":"<div><div>In this study, we propose an efficient recursive algorithm, named GK-RLS, defined with a mixture of weighted Gaussian kernels for efficient homography estimation. By defining the homography estimation problem as a least square problem and optimizing the estimation parameters based on minimizing expected estimation errors, GK-RLS offers efficient incremental processing of feature points, rather than processing them as a batch like RANSAC, resulting in reduced computation time (CT) when handling a large number of paired features. To address real-world challenges such as noise and outliers commonly encountered in feature extraction and pairing, GK-RLS incorporates a small-pass filter defined with Gaussian kernels to effectively attenuate their resulting large prediction errors, thus reducing outlier drawbacks. The algorithm's effective stopping criteria are established based on a concept akin to RANSAC, with termination occurring when the estimated homography matrix yields low geometric error for a predefined portion of paired feature points. The CT of the algorithm is crucial for online applications or scenarios requiring the sharing of feature data points within communication networks, such as between multiple drones or between drones and a ground station. Therefore, leveraging the iterative structure and effective stopping criteria of GK-RLS, it estimates the homography matrix using only a limited number of feature points, resulting in a smaller CT compared to RANSAC while having a similar estimation performance. Extensive evaluations, including sensitivity analysis, a drone simulation, and experimental implementation, demonstrate the superiority of GK-RLS over RANSAC, especially concerning the required CT. Overall, GK-RLS presents a promising solution for robust and efficient homography matrix estimation in various real-world scenarios that require process data in high sampling frequencies.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"231 ","pages":"Article 109882"},"PeriodicalIF":3.4,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143138410","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}

引用次数: 0

Multi-source DOA tracking with an adaptive superposition model for sparse array

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-03 DOI: 10.1016/j.sigpro.2024.109877

Jinke Cao , Mingyi You , Dawei Li , Xiaofei Zhang , Fuhui Zhou

{"title":"Multi-source DOA tracking with an adaptive superposition model for sparse array","authors":"Jinke Cao , Mingyi You , Dawei Li , Xiaofei Zhang , Fuhui Zhou","doi":"10.1016/j.sigpro.2024.109877","DOIUrl":"10.1016/j.sigpro.2024.109877","url":null,"abstract":"<div><div>Tracking the direction of arrival (DOA) with a passive sensor array is a well-known problem in signal processing. Traditional methods, such as subspace tracking and super-resolution techniques, struggle with data association and trajectory crossing. Although Kalman filter-based methods are excellent for tracking, they are difficult to apply to DOA tracking due to complex nonlinear transformations and unknown source signals in the array-received signals. To overcome these limitations, we propose two adaptive tracking methods using a sparse array (SA): one based on the extended Kalman filter (SA-AEKF) and the other on the unscented Kalman filter (SA-AUKF). Tracking is implemented using an adaptive superposition model that adapts to changes in signal and noise intensity. Moreover, it avoids the presence of multiple measurements at the same tracking time by superimposing multiple snapshot measurements into a single measurement. Finally, we analyze the Cramér–Rao bound (CRB) and posterior Cramér–Rao bound (PCRB) for the proposed algorithms. Simulation results show that our methods outperform conventional techniques in challenging scenarios with low signal-to-noise ratios, limited snapshots, trajectory crossovers, and fewer array elements than signal sources.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"230 ","pages":"Article 109877"},"PeriodicalIF":3.4,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132722","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}

引用次数: 0

Correction of underwater images via fast centroid method and Wasserstein regularization

IF 3.4 2区工程技术

Signal Processing Pub Date : 2025-01-03 DOI: 10.1016/j.sigpro.2024.109879

Bian Gao, Xiangchu Feng, Weiwei Wang, Kun Wang

{"title":"Correction of underwater images via fast centroid method and Wasserstein regularization","authors":"Bian Gao, Xiangchu Feng, Weiwei Wang, Kun Wang","doi":"10.1016/j.sigpro.2024.109879","DOIUrl":"10.1016/j.sigpro.2024.109879","url":null,"abstract":"<div><div>Removing geometric distortion in images captured through turbulent media, like air and water, presents a substantial challenge. Previous studies have proposed a variational model that integrates optical flow with total variation (TV) regularization to address distortion. However, total variation regularization introduces an inherent bias-while it can recover the structure of the signal, it also leads to a reduction in the signal’s amplitude. In this paper, we extensively utilize histogram information, employing the Wasserstein distance as a constraint to reduce bias introduced by total variation regularization, thereby enhancing the quality of the restored images. The core concept involves minimizing the discrepancy between the histograms of the restored and distorted images using the Wasserstein distance. Moreover, for severely distorted underwater images, a fast centroid method is employed as a preprocessing step for the frames with distortion. Ultimately, experimental results demonstrate that the proposed model can mitigate the bias introduced by TV regularization and obtain high-quality restored images.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"230 ","pages":"Article 109879"},"PeriodicalIF":3.4,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132720","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}

引用次数: 0