Search

Seismic signal denoising and feature extraction play crucial roles in geophysics, particularly in applications like earthquake monitoring, subsurface imaging, and reservoir characterization. However, the inherent noise in seismic data poses significant challenges for accurately identifying seismic arrival times. Traditional methods such as STA/LTA and P-phase picker have proven effective in simple scenarios but struggle in complex and noisy environments. This study adapts and extends the Convex Non-Convex Fused Lasso Signal Approximation (CNC-FLSA) framework, originally proposed for biomedical signal processing, to seismic data analysis. By optimizing key parameters and leveraging non-convex regularization, the CNC-FLSA method achieves superior denoising and precise seismic event detection. Comprehensive evaluations on synthetic and real datasets demonstrate its robustness in diverse noise conditions and its advantages over traditional methods and state-of-the-art techniques. The proposed method not only improves accuracy but also offers computational efficiency, making it a viable tool for seismic signal processing applications. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Diabetes Mellitus combined with Mild Cognitive Impairment (DM-MCI) is a high incidence disease among the elderly. Patients with DM-MCI have considerably higher risk of dementia, whose daily self-care and life management (i.e. self-management) have a significant impact on the development of their condition. Thus, the inclusion and discrimination of subsequent interventions according to their self-management is an urgent issue. A Sparse-representation-based Discriminative Classification model (SDC) is proposed in this paper to correctly classify MCI-DM patients based on their self-management ability. Specifically, an L1-minimization sparse representation model, an efficient machine learning model, is used to obtain the sparse histogram that encodes the identity of the test sample. Then, the coefficient of determination is adopted to determine the category based on the sparse histogram of the test sample. Extensive experiments on the self-management data of DM-MCI are conducted to verify the effectiveness of SDC. The experimental results show that the accuracy , precision , recall , and F1-score are 94.3%, 95.0%, 94.3%, and 94.5%, respectively, demonstrating the excellent performance of SDC. The model used in this study has high accuracy and can be used for subgroup discrimination. The use of the sparse representation model in this study has supportive implications for the inclusion of research subjects in clinical intervention strategies. [ABSTRACT FROM AUTHOR]

Summary: Fraud keeps increasing in our society and security applications become crucial and needed in our daily life. Biometric technology attempts to stop fraud and falsification in different opportunities such as bank services, access to controlled areas or crossing frontiers, by recognizing the identity of a person using his physiological (fingerprint, iris, face) or behavioral modalities (gait, signature). In this article, we focus on an emerging biometric modality called the finger knuckle print (FKP). In fact, this modality has several advantages such as the easy distinction between different persons, stability over time and user acceptance. So, an FKP identification approach is proposed using scale invariant feature transform descriptors based sparse representation method. The classification step, between training and testing FKP samples, is made using the support vector machines method. Experiments applied on two public FKP databases: The Hong Kong Polytechnic University (PolyU) Contactless Finger Knuckle Images Database and the Indian Institute of Technology Delhi (IITD) Finger Knuckle Database, containing respectively 2500 and 790 images, demonstrate high correct identification rates by reaching 98.58% and 99.15% for these two databases. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification aims to classify pixels in hyperspectral image into different land-cover classes. Considering multi-view data can improve the classification performance as it contains more abundant information than single view, a multi-view based method is proposed for hyperspectral image classification in this paper. In the proposed method, spatial neighboring pixels are adaptively determined by the mean and deviation of samples in the fixed-size spatial window. Then, the sparse representation algorithm is realized to obtain the sparse coefficients for the multi-view matrix set of the spatial neighboring pixels. Moreover, the renyi-entropy is calculated to determine the weight of each view in the classification task since the performance of different views is different. Finally, the obtained sparse coefficients and weights are jointly used to determine the class label of each test pixel. Experimental results on the Indian Pines dataset and University of Pavia dataset demonstrate the superior performance of the proposed method compared to several state-of-art methods. [ABSTRACT FROM AUTHOR]

The accuracy analysis of dictionary sparse representation for channels in massive MIMO systems is a relatively unexplored field. Existing research has primarily focused on investigating the accuracy of dictionary sparse representation using simulation in massive MIMO systems, but has not provided quantitative accuracy analysis. To address this gap, the correlation numerical proportional factor is proposed to represent the accuracy performance of non‐zero elements in the coefficient matrix. Additionally, a qualitative analytical formula for dictionary sparse representation accuracy is provided and an optimal upper bound for the correlation numerical proportional factor is established. Furthermore, the innovation indicates that the accuracy of dictionary sparse representation is mainly influenced by the cross‐correlation between the pilots matrix and the dictionary matrix, as well as sparsity. The author has also developed a method for minimizing the correlation numerical proportional factor. In order to obtain an optimal sparse representation coefficient matrix, a cross‐correlation matrix is constructed and an analytical expression is derived for it as well as its use as an optimal hard decision threshold is determined. Finally, a sparse representation coefficient optimization algorithm is proposed using this optimal threshold. Simulation results demonstrate that this algorithm can significantly improve channel sparse dictionary representation accuracy. [ABSTRACT FROM AUTHOR]

As a non-invasive imaging method, electrical impedance tomography (EIT) technology has become a research focus for grounding grid corrosion diagnosis. However, the existing algorithms have not produced ideal image reconstruction results. This article proposes an electrical impedance imaging method based on sparse representation, which can improve the accuracy of reconstructed images obviously. First, the basic principles of EIT are outlined, and the limitations of existing reconstruction methods are analyzed. Then, an EIT reconstruction algorithm based on sparse representation is proposed to address these limitations. It constructs constraints using the sparsity of conductivity distribution under a certain sparse basis and utilizes the accelerated Fast Iterative Shrinkage Threshold Algorithm (FISTA) for iterative solutions, aiming to improve the imaging quality and reconstruction accuracy. Finally, the grounding grid model is established by COMSOL simulation software to obtain voltage data, and the reconstruction effects of the Tikhonov regularization algorithm, the total variation regularization algorithm (TV), the one-step Newton algorithm (NOSER), and the sparse reconstruction algorithm proposed in this article are compared in MATLAB. The voltage relative error is introduced to evaluate the reconstructed image. The results show that the reconstruction algorithm based on sparse representation is superior to other methods in terms of reconstruction error and image quality. The relative error of the grounding grid reconstructed image is reduced by an average of 12.54%. [ABSTRACT FROM AUTHOR]

This paper introduces a robust bi-orthogonal projection (RBOP) learning method for dimensionality reduction (DR). The proposed RBOP enhances the flexibility, robustness, and sparsity of the embedding framework, extending beyond traditional DR methods such as principal component analysis (PCA), neighborhood preserving embedding (NPE), and locality preserving projection (LPP). Unlike conventional approaches that rely on a single type of projection, RBOP innovates by employing two types of projections: the "true" projection and the "counterfeit" projection. These projections are crafted to be orthogonal, offering enhanced flexibility for the "true" projection and facilitating more precise data transformation in the process of subspace learning. By utilizing sparse reconstruction, the acquired true projection has the capability to map the data into a low-dimensional subspace while efficiently maintaining sparsity. Observing that the two projections share many similar data structures, the method aims to maintain the similarity structure of the data through distinct reconstruction processes. Additionally, the incorporation of a sparse component allows the method to address noise-corrupted data, compensating for noise during the DR process. Within this framework, a number of new unsupervised DR techniques have been developed, such as RBOP_PCA, RBOP_NPE, and RBO_LPP. Experimental results from both natural and synthetic datasets indicate that these proposed methods surpass existing, well-established DR techniques. [ABSTRACT FROM AUTHOR]

Subspace clustering typically clusters data by performing spectral clustering to an affinity matrix constructed in some deterministic ways of self-representation coefficient matrix. Therefore, the quality of the affinity matrix is vital to their performance. However, traditional deterministic ways only provide a feasible affinity matrix but not the most suitable one for showing data structures. Besides, post-processing commonly on the coefficient matrix also affects the affinity matrix's quality. Furthermore, constructing the affinity matrix is separate from optimizing the coefficient matrix and performing spectral clustering, which can not guarantee the optimal overall result. To this end, we propose a new method, affinity adaptive sparse subspace clustering (AASSC), by adding Laplacian rank constraint into a subspace sparse-representation model to adaptively learn a high-quality affinity matrix having accurate p-connected components from a sparse coefficient matrix without post-processing, where p represents categories. In addition, by relaxing the Laplacian rank constraint into a trace minimization, AASSC naturally combines the operations of the coefficient matrix, affinity matrix, and spectral clustering into a unified optimization, guaranteeing the overall optimal result. Extensive experimental results verify the proposed method to be effective and superior. [ABSTRACT FROM AUTHOR]

This paper introduces two novel self-induced basis strategies, interior cevian initialization for orthogonal matching pursuit (ICe) and its l 2 -sense optimized version, optimized interior cevian initialization (OICe). These methods address the complexity and convergence issues of the previously proposed self-inspired bases (SIBS) approach. Both algorithms enhance sparse image representation by generating adaptive auxiliary atoms tailored to the image, thereby improving reconstruction quality and computational efficiency. Experimental results show that ICe achieves up to a 35.6% improvement in Normalized Mean Squared Error (NMSE) and a 16.4% increase in Structural Similarity Index (SSIM) compared to conventional OMP. OICe, as the l 2 -sense optimized version of ICe, delivers even greater performance, with improvements of up to 40% in NMSE and 18.5% in SSIM. Additionally, both ICe and OICe significantly reduce bits per pixel (BPP) for image encoding, outperforming SIBS when paired with state-of-the-art dictionaries such as KSVD, MOD, RBDL, and ODL. These results highlight the effectiveness of ICe and OICe in addressing key challenges in sparse representation, offering enhanced accuracy and efficiency across a variety of applications. [ABSTRACT FROM AUTHOR]

Copyright of Journal of East China University of Science & Technology is the property of Journal of East China University of Science & Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In clinical environments, the quality of low-dose computerized tomography (LDCT) images is inevitably degraded by artifacts and noise. Accurate and clinically relevant image quality assessment (IQA) for LDCT images is crucial to provide appropriate medical care. However, due to the absence of reference images and inadequate understanding of the human visual system (HVS), there is currently a lack of effective IQA methods. To address this problem, this paper proposes a no-reference IQA method that emulates the perceptual characteristics of the HVS. The method is based on the use of sparse representation in conjunction with a just noticeable distortion (JND) model. Specifically, for each tested image, a patch-level JND map is first calculated to indicate the noticeable level of distortion in different regions. Subsequently, noticeable patches of the image are encoded via sparse representation, followed by max pooling to obtain sparse features. Finally, these sparse features, along with the sorted JND values, are combined as overall features into a regression model to predict an objective quality score. By combining two types of features, our method can measure the quality from the perspectives of both local spatial structures and visual distortion sensitivity. Our method is evaluated on the LDCTIQAC2023 database, and the experimental results demonstrate the effectiveness of our method, which correlates reasonably well with the radiologists’ subjective scores.

Abstract This paper introduces two novel self-induced basis strategies, interior cevian initialization for orthogonal matching pursuit (ICe) and its $$l_2$$ l 2 -sense optimized version, optimized interior cevian initialization (OICe). These methods address the complexity and convergence issues of the previously proposed self-inspired bases (SIBS) approach. Both algorithms enhance sparse image representation by generating adaptive auxiliary atoms tailored to the image, thereby improving reconstruction quality and computational efficiency. Experimental results show that ICe achieves up to a 35.6% improvement in Normalized Mean Squared Error (NMSE) and a 16.4% increase in Structural Similarity Index (SSIM) compared to conventional OMP. OICe, as the $$l_2$$ l 2 -sense optimized version of ICe, delivers even greater performance, with improvements of up to 40% in NMSE and 18.5% in SSIM. Additionally, both ICe and OICe significantly reduce bits per pixel (BPP) for image encoding, outperforming SIBS when paired with state-of-the-art dictionaries such as KSVD, MOD, RBDL, and ODL. These results highlight the effectiveness of ICe and OICe in addressing key challenges in sparse representation, offering enhanced accuracy and efficiency across a variety of applications.

Terahertz (THz) single-pixel imaging has received major research attention because of the lack of a suitable high-resolution array detector for THz imaging applications. Improving both imaging speed and quality has become a research hotspot for this field in recent years. In this study, a terahertz single-pixel imaging system with Hadamard spatial encoding was constructed by using optically induced semiconductor materials to perform THz wave modulation. Sparse coding was added to the system's reconstruction algorithm to enhance imaging quality. Numerous image patches were then collected from a natural image set to train an overcomplete dictionary and each patch in the measured image was reconstructed through sparse representation. To validate the effectiveness of the proposed algorithm, the reconstruction performances of different algorithms were compared under various conditions (i.e., with sampling rates varying from 5 to 100% and with noise levels within a signal-to-noise ratio range of 10–50 dB). The proposed algorithm, in combination with sparse representation of an overcomplete dictionary, showed a higher peak signal-to-noise ratio and a lower mean square error than both the inverse Hadamard transform (IHT) and TVAL3 algorithms. Finally, THz imaging experiments were performed to validate the algorithm's reconstruction performance at sub-Nyquist sampling rates. The experimental and simulation results coincided closely, thus indicating that the use of the proposed algorithm enhances the signal-to-noise ratio of the reconstructed image, reduces its mean square error, and retains greater image detail. The proposed algorithm was demonstrated to be the preferred choice for THz single-pixel imaging applications. [ABSTRACT FROM AUTHOR]

Conformal coatings are used to protect microelectronic circuitry and increasingly optoelectronics and photonics from detrimental effects of the environment, such as moisture, dust, gasses, and mechanical abrasion. The conventional approach to determine the mean time to failure of conformally coated microelectronic components is usually labor-intensive and time-consuming. We recently showed (Shi et al., 2024) that the quasi-optical approach terahertz (THz) time-of-flight tomography (TOFT) could in principle be used to map conformal-coating thickness over a sample of dimensions on the scale of square centimeters. In this study, we employ THz TOFT to characterize several conformal-coating types on microelectronic test samples in a nondestructive and noncontact manner. This study extends previous work on acrylic conformal coatings. THz TOFT is shown to be effective in the thickness characterization of silicone and acrylic conformal coatings, but not nanometric atomic-layer-deposition metal-oxide coating, which is too thin for the technique. [ABSTRACT FROM AUTHOR]

Current super-resolution algorithms exhibit limitations when processing noisy remote sensing images rich in surface information, as they tend to amplify noise during the recovery of high-frequency signals. To mitigate this issue, this paper presents a novel approach that incorporates the concept of compressed sensing and explores the super-resolution problem of remote sensing images for space cameras, particularly for high-speed imaging systems. The proposed algorithm employs K-singular value decomposition (K-SVD) to jointly train high- and low-resolution image blocks, updating them column by column to obtain overcomplete dictionary pairs. This approach compensates for the deficiency of fixed dictionaries in the original algorithm. In the process of dictionary updating, we innovatively integrate the circle chaotic mapping into the solution process of the dictionary sequence, replacing pseudorandom numbers. This integration facilitates balanced traversal and simplifies the search for global optimal solutions. For the optimization problem of sparse coefficients, we utilize the orthogonal matching pursuit method (OMP) instead of the L1 norm convex optimization method used in most reconstruction techniques, thereby complementing the K-SVD dictionary update algorithm. After upscaling and denoising the image using the dictionary pair mapping relationship, we further emphasize image edge details with local gradients as constraints. When compared with various representative super-resolution algorithms, our algorithm effectively filters out noise and stains in low-resolution images. It not only performs well visually but also stands out in objective evaluation indicators such as the peak signal-to-noise ratio and information entropy. The experimental results validate the effectiveness of the proposed method in super-resolution remote sensing images, yielding high-quality remote sensing image data. [ABSTRACT FROM AUTHOR]

The fusion of infrared and visible images together can fully leverage the respective advantages of each, providing a more comprehensive and richer set of information. This is applicable in various fields such as military surveillance, night navigation, environmental monitoring, etc. In this paper, a novel infrared and visible image fusion method based on sparse representation and guided filtering in Laplacian pyramid (LP) domain is introduced. The source images are decomposed into low- and high-frequency bands by the LP, respectively. Sparse representation has achieved significant effectiveness in image fusion, and it is used to process the low-frequency band; the guided filtering has excellent edge-preserving effects and can effectively maintain the spatial continuity of the high-frequency band. Therefore, guided filtering combined with the weighted sum of eight-neighborhood-based modified Laplacian (WSEML) is used to process high-frequency bands. Finally, the inverse LP transform is used to reconstruct the fused image. We conducted simulation experiments on the publicly available TNO dataset to validate the superiority of our proposed algorithm in fusing infrared and visible images. Our algorithm preserves both the thermal radiation characteristics of the infrared image and the detailed features of the visible image. [ABSTRACT FROM AUTHOR]

Techniques that exploit spectral-spatial information have proven to be very effective in hyperspectral image classification. Joint sparse representation classification (JSRC) is one such technique which has been extensively used for this purpose. However, the use of a single fixed-sized window has limited its ability to incorporate spatial information. Several techniques such as multiscale superpixels based sparse representation classification (MSSRC), multiscale adaptive sparse representation classification (MASRC) and Discriminant Subdictionary Learning (DSDL) have tried to overcome this drawback by fusing information from different scales. However, their inability to simultaneously consider the correlated information at different scales and appropriate spatial neighbourhoods limits their performance. In order to better model contextual information, in this paper, we propose a modified max-tree and modified min-tree to represent the connected components of the image. Then, by exploiting these connected components, adaptive multiscale windows are defined. The potentiality of the proposed technique is validated by performing a comparative analysis with four state-of-the-art sparse representation methods using three real hyperspectral datasets. For a fixed training and test sets of University of Pavia and Indian Pines dataset, our proposed technique provides at least 3% and 2%, respectively higher classification results than the best state-of-the-art method. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) is a pivotal diagnostic tool for epilepsy. EEG signals have complex sources, significant individual differences, and data distribution varies across different domains are also easily influenced by noise. This study develops a low-rank sparse representation-based transition subspace learning (LRSRTS) algorithm. Based on low-rank reconstruction transfer subspace learning, the LRSRTS algorithm uses subspace projection and low-rank constraints to ensure that multiple domains are aligned in the subspace and uses sparse constraints to ensure reconstruction from the source domain to the target domain. Separating the noise information in the subspace, the LRSRTS algorithm uses the source domain samples to establish a discriminative classifier. Since the label information is non-negative, the LRSRTS imposes non-negative constraints on the transition subspace. With the more flexible subspace and classifier, the LRSRTS algorithm demonstrates satisfactory recognition performance on the CHB-MIT dataset. [ABSTRACT FROM AUTHOR]

Generally, bearing early failure-induced impulses is weak and easily submerged by strong background noise. How to extract weak impulses is a big challenge. In this paper, based on the K Singular Value Decomposition (KSVD) algorithm, an improved dictionary learning model (WID-MSKW-KSVD) is proposed, which integrates a special denoising method and a multi-scale transformation into a typical dictionary learning model and it successfully overcomes two major shortcomings of traditional KSVD model including the lack of multi-scale learning process and the ability of dictionary atoms to resist strong noise interference. Furthermore, the kurtosis of the envelope spectrum is weighted into the proposed model as a fault matrix to enhance the fault feature. Finally, the feasibility of the proposed model is demonstrated by numerical simulation and practical experiments, and the superiority and reliability of this model in suppressing noise interference and extracting fault features are verified by comparison with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This study focused on improving the clustering performance of hyperspectral imaging (HSI) by employing the Generalized Orthogonal Matching Pursuit (GOMP) algorithm for feature extraction. Hyperspectral remote sensing imaging technology, which is crucial in various fields like environmental monitoring and agriculture, faces challenges due to its high dimensionality and complexity. Supervised learning methods require extensive data and computational resources, while clustering, an unsupervised method, offers a more efficient alternative. This research presents a novel approach using GOMP to enhance clustering performance in HSI. The GOMP algorithm iteratively selects multiple dictionary elements for sparse representation, which makes it well-suited for handling complex HSI data. The proposed method was tested on two publicly available HSI datasets and evaluated in comparison with other methods to demonstrate its effectiveness in enhancing clustering performance. [ABSTRACT FROM AUTHOR]

Battery swapping is an emerging energy supply method for Electric Heavy Trucks (EHTs), and Rack and Pinion Drives (RPDs) in widely used in Battery Swapping System (BSS). Fault diagnosis for RPDs improves the safety and efficiency of battery swapping, however, unique operation conditions of driving gear in RPDs, including low rotational speed, reciprocating motion, and speed fluctuation pose steep challenges for the fault diagnosis. To address these issues, in this study, a novel signal representation method, Planar Dot Pattern (PDP) is proposed: first, spatial relative features of adjacent teeth is employed in PDP, which is suitable for representation of weak fault feature caused by low rotational speed; then, tooth-by-tooth representation method is proposed in PDP to maximizing utilization of the short samples caused by reciprocating motion; finally, an adaptive delay factor is defined in PDP to reduce the impact of speed fluctuation. Additionally, exclusive feature extraction method for PDP based on dot distribution analysis is proposed, which enhances the accuracy and efficiency of fault diagnosis. The recognition of fault patterns is achieved based on sparse representation, with the proposed dot distribution features. The fault diagnosis accuracy based on the vibration data of BSS experimental platform was 98.21%, which is more accurate than conventional fault diagnosis methods. [ABSTRACT FROM AUTHOR]

Recent advances in spatial transcriptomics (ST) enable measurements of transcriptome within intact biological tissues by preserving spatial information, offering biologists unprecedented opportunities to comprehensively understand tissue micro-environment, where spatial domains are basic units of tissues. Although great efforts are devoted to this issue, they still have many shortcomings, such as ignoring local information and relations of spatial domains, requiring alternatives to solve these problems. Here, a novel algorithm for spatial domain identification in S patial T ranscriptomics data with S tructure C orrelation and S elf- R epresentation (ST-SCSR), which integrates local information, global information, and similarity of spatial domains. Specifically, ST-SCSR utilzes matrix tri-factorization to simultaneously decompose expression profiles and spatial network of spots, where expressional and spatial features of spots are fused via the shared factor matrix that interpreted as similarity of spatial domains. Furthermore, ST-SCSR learns affinity graph of spots by manipulating expressional and spatial features, where local preservation and sparse constraints are employed, thereby enhancing the quality of graph. The experimental results demonstrate that ST-SCSR not only outperforms state-of-the-art algorithms in terms of accuracy, but also identifies many potential interesting patterns. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Brain tumor detection using MRI imaging has the potential to be greatly improved through the integration of medical knowledge. Solving the problem of brain tumor classification is highly important in the field of medicine as it can greatly impact the effectiveness of treatment options. However, the classification of tumors into Benign or Malignant categories remains a challenging task due to the need for detailed texture analysis and the possibility of errors. Image processing techniques such as dictionary learning-based classifiers can play a critical role in this field. This paper proposes a method that combines textural-statistical features to categorize brain tumors based on employing sparse non-negative matrix factorization (SNMF) and a dictionary learning-based model using a sparse representation technique. In the next step, the extracted features from the sparse coefficient matrix were fed into a ResNet10 model for the classification of the input image. The experimental results emphasize that the proposed method, which trains the dictionary atom based on the combinational features vector, can accurately distinguish different types of brain tumors with high precision. This is a significant method as it can improve the effectiveness of brain tumor classification, leading to more accurate treatment decisions for patients. [ABSTRACT FROM AUTHOR]

Focusing on the issue that millimeter-wave radar was difficult to accurately estimate the vital signs of multiple moving targets in complex indoor scenes, a multi-target vital sign estimation method based on sparse representation under complex scenes was proposed. Firstly, the echo data was preprocessed to acquire the point clouds of target and background. After that, a dynamic clutter suppression model was constructed to filter out the dynamic interference. In what follows, the echo data was assigned to the corresponding target, and multi-target tracking could be achieved by exploiting the extended Kalman filter to extract the phase information of the chests of the multi-moving targets. Subsequently, with the sparsity of respiratory and heartbeat signals in the frequency domain, a data-driven adaptive dictionary construction method was proposed to effectively separate respiratory and heartbeat signals. Finally, high precision multi-target vital signs estimation could be achieved by using the sparse reconstruction method. Amount of experimental results in the actual scenes show that the proposed method can effectively perceive the vital signs of multi-target in complex dynamic clutter scenes as compared to the state-of-the-art vital sign estimation methods.