ABSTRACT Deep learning methods for image forgery detection often struggle with compression attack robustness. This paper proposes a novel multi‐class forgery detection framework combining spatial‐frequency fusion with Swin‐Transformer, outperforming existing methods in compression attack scenarios. Our approach integrates a frequency domain perception module with quantization tables, a spatial domain perception module through multi‐strategy convolutions, and a dual‐attention mechanism combining spatial and channel attention for feature fusion. Experimental results demonstrate superior performance with an F 1 score of 87% under JPEG compression ( q = 75), significantly surpassing current state‐of‐the‐art methods by an average of 15% in compression resistance while maintaining high detection accuracy.

Traditional sound source localization methods encounter significant challenges in simultaneously locating rotating and static sources. These challenges arise from the different motion patterns of these two types of sound sources, and they are typically not situated on the same plane. To address this issue, a method based on Modal Composition Beamforming (MCB) and the equivalent source method is proposed for separating rotating and static sound sources, which fully utilizes the prior knowledge of the spatiotemporal properties of these sources. The proposed approach involves establishing a Rotating-Static Sources Power Propagation (R-S2P) model, utilizing the relationship between the equivalent source strength and the actual beamforming output. By employing this forward model and applying an appropriate inversion method, it is possible to separate the components of rotating and static sources. Simulations for three cases with different source strengths are presented, and the R-S2P inversion problem is resolved using the Least Absolute Shrinkage and Selection Operator (LASSO) method. We showed that this method enables accurate separation and localization of rotating and static sources on different planes with varying relative intensities, even if the background noise is strong.

Rotating source beamforming techniques have been effective means of noise localization on rotary machines. In this letter, we derive an alternative expression for modal composition beamforming (MCB) and subsequently consider the equivalent source assumption and cyclostationarity of the constant angular-speed rotating sound source so that a rotating sound source power (RSP) propagation model is derived. By estimating a suitable solution for the RSP model using the subspace variational Bayesian (SVB) technique with sparsity and total variation (TV) priors, the validity of the RSP model was established. According to the simulation results, the proposed RSP-SVB method leads to a significantly higher resolution than the MCB method. It can localize multiple fast-rotating sound sources accurately, rapidly, and effectively in environments with strong background noise interference. Therefore, our proposed RSP-SVB can offer a reliable solution for identifying fast-rotating blade noise.

The non-synchronous measurement (NSM) technology has been significantly developed. NSM at the coprime position (CP-NSM) is a measurement principle in two-dimensional (2D) acoustic imaging, wherein a planar array is moved to a coprime position for measurements. However, there are certain drawbacks to the measurement principles of spherical arrays in three-dimensional (3D) acoustic imaging. A measurement principle of 3D acoustic imaging has been investigated using 3D Non-Synchronous Measurements with a Central Reference based on Revolution and Autorotation (CR-NSM). The primary contributions of this CR-NSM are as follows: (1) A measurement principle for 3D non-synchronous measurements with a central reference based on revolution and autorotation is proposed. (2) The spatial resolution is primarily determined by the revolution in CR-NSM, and the side lobe is reduced by autorotation in CR-NSM. In the simulation results, the spatial resolution is obtained using CR-NSM for good imaging at low signal-to-noise ratios (SNR). Moreover, the cross-spectral matrix (CSM) completion error is enhanced by adding the phase relations between consecutive positions. The CR-NSM algorithm was developed according to the measurement principles of 3D acoustic imaging.

In this letter, an acoustic imaging method is proposed to improve conventional non-synchronous measurements (NSM) by carrying out the NSM at coprime positions (CP-NSM). The pattern of the NSM movement is guided by a set of coprime positions. A virtual domain signal is then constructed by vectorizing the covariance matrix of the NSM. Similarly, a virtual array is constructed using the Kronecker product of the Green's function of the CP-NSM. Therefore, the synthetic aperture of the proposed CP-NSM is first expanded by the NSM, and further enlarged by the virtual array. The simulation results demonstrate that the proposed CP-NSM achieves higher spatial resolution at lower frequencies and a lower signal-to-noise ratio than the conventional NSM.

This letter is devoted to the layout reconstruction via the ultra-wideband (UWB) through-wall imaging radar under one single observation and simultaneously takes account of the real-time human indication. In the proposed framework, layout reconstruction is taken as the preprocessing, where a coherent processing interval consisting of several successive received echoes in the initial stage is first employed to construct a range-Doppler (RD) spectrum. Then, in the RD spectrum, a series of selected discrete Doppler frequency signals is used to form Doppler back projection (BP) images. Finally, in the Doppler BP image stack, we design a 3-D constant false alarm rate detector to extract the building layout. Once completed, the achieved layout as auxiliary information is fused with the simultaneous human indication. Through-wall experiments show that the proposed method can effectively extract the covered layout of multiple walls under one single view and accordingly provide strong support for the concealed human sensing.

Recently the improved deconvolution methods using sparse regularization achieve high spatial resolution in aeroacoustic imaging in the low Signal-to-Noise Ratio (SNR), but sparse prior and model parameters should be optimized to obtain super resolution and be robust to sparsity constraint. In this paper, we propose a Bayesian Sparse Inference Approach in Aeroacoustic Imaging (BSIAAI) to reconstruct both source powers and positions in poor SNR cases, and simultaneously estimate background noise and model parameters. Double Exponential prior model is selected for source spatial distribution and hyper-parameters are estimated by Joint Maximized A Posterior criterion and Bayesian Expectation and Minimization algorithm. On simulated and real data, proposed approach is well applied for near-field wideband monopole and extended source imaging. Comparing to several classical methods, proposed approach is robust to noise, super resolution, wide dynamic range, but parameters like source number or SNR are not needed.