58 results about "Compressive imaging" patented technology

The invention discloses a hyperspectral fusion imaging method and device based on deep nonlinear transformation tensor low-rank representation, and the method comprises the following steps: collecting a priori multispectral image while collecting hyperspectral compression measurement in an observation scene, and taking the two data as input at the same time; based on tensor representation and deep learning theories, novel deep nonlinear transformation tensor low-rank regularization for the hyperspectral image is established, and global high-dimensional low-rank correlation of the hyperspectral image in a deep nonlinear transformation domain is fully described; taking the regularization item as a target function, modeling compression imaging and a spectrum degradation process into two data fidelity items, and constructing a fusion imaging model and a loss function; and minimizing a loss function through a learning algorithm to optimize the model, and fusing and reconstructing a complete hyperspectral image. According to the novel method and the novel device provided by the invention, high-precision fusion imaging of the observation scene can be realized without manual intervention and explicit intermediate steps.

One embodiment provides a compressive hyperspectral imaging system. The compressive hyperspectral imaging system can include a coded aperture configured to spatially encode an optical signal associated with a scene, an integrated photonic device configured to disperse the spatially encoded optical signal, and an array of photo detectors configured to detect the dispersed and spatially encoded optical signal. The output of the array of photo detectors is used for reconstruction of a hyperspectral image corresponding to the scene.

The invention discloses a hyperspectral image reconstruction method based on Transform, and the method comprises the steps: carrying out the snapshot compression imaging operation of a hyperspectral image, and obtaining two-dimensional compression observation data; and on the basis of a Transform architecture, reconstructing the compressed observation data by adopting a focusing hybrid rearrangement rectangle (FHSRT) module. The FHSRT module comprises a focusing hybrid rearrangement rectangular multi-head self-attention FHSR-MSA module, and the FHSR-MSA module is composed of a focusing linear attention FLA module and a hybrid rearrangement rectangular self-attention HSRT module. The FLA module optimizes attention weight distribution through a mapping function, and enhances feature diversity by using a rank recovery module; the HSRT module effectively captures local and non-local features in a spatial domain through rectangular self-attention in the horizontal and vertical directions. And the two-dimensional compressed observation data processed by the FHSRT module is finally output as a reconstruction result of the hyperspectral image. The method has the advantages that spectrum consistency and space details can be effectively reserved in the hyperspectral image reconstruction process, the reconstruction precision is improved, and high calculation efficiency is achieved.

The invention relates to the technical field of image processing, in particular to a compression imaging method and system based on a Swin Transform network, and the method comprises the steps: carrying out the sampling processing of training data through employing a CC Hadamard matrix, obtaining a coding image, training a neural network based on the Swin Transform through employing the coding image, and obtaining an optimal compression reconstruction model; in the system, the optimal compression reconstruction model is loaded into a processing center, multiple low-resolution images collected by a detector are preprocessed to obtain coded images, and then the optimal compression reconstruction model is utilized to obtain reconstructed images. Compared with a common sampling matrix, the system and the method provided by the invention have the advantages that the reconstruction effect after sampling of the CC Hadamard matrix is better, and the reconstruction quality of the image is effectively improved.

The invention relates to a hyperspectral snapshot compression imaging reconstruction method fusing conditional diffusion, and belongs to the technical field of deep learning. The method comprises the following steps: S1, obtaining a two-dimensional compressed image of a target scene; s2, preprocessing the hyperspectral image training set to generate sample data for training; s3, inputting the preprocessed training sample into a hierarchical condition diffusion image reconstruction network for training; s4, after network training is completed, a test sample is input into the network for hyperspectral image reconstruction, and a result is obtained; according to the method, the detail structure of the hyperspectral image is reconstructed, meanwhile, the denoising capability is higher, and compared with other methods, the method has obvious advantages in the aspect of suppressing artifacts.

The invention discloses a differential compression structured light illumination super-resolution imaging device based on time sequence multiplexing. The differential compression structured light illumination super-resolution imaging device is composed of a light source and beam expanding system, a structured light illumination imaging system, a coding aperture time domain compression imaging system, a time sequence control system and a data processing reconstruction system. According to the invention, the two digital micromirror devices are controlled through a time sequence, and wide-field and structured light compression imaging is realized respectively. In the wide-field mode, the two digital micromirror devices are switched to the total transmission mode, and fluorescence signals of the excitation sample are directly collected by the camera; in a structured light mode, the first digital micro-mirror device generates six time-varying stripe coding patterns, and dynamic space coding of the second digital micro-mirror device is combined, so that a camera obtains a compressed image through single exposure. Through differential processing of a wide field and a compressed image, background noise is suppressed, high-frequency information weight is enhanced, the bottleneck of high-frequency signal offset in traditional compressed imaging is broken through, image reconstruction quality is remarkably improved, and high-fidelity imaging of a high-speed dynamic scene is realized.

The invention discloses a spatial-spectral domain joint compressed sensing method for an infrared spectral image, and belongs to the field of high-resolution spectral imaging and compressed imaging. The implementation method comprises the following steps: generating a spatial-spectral domain joint compression imaging coding matrix, loading the matrix as a coding template onto a DMD (Digital Micromirror Device), carrying out spatial modulation on target light information, carrying out spectral modulation on a spectral image subjected to spatial modulation by using a diffraction grating, and carrying out spectral imaging on the spectral image subjected to spatial modulation. And carrying out space down-sampling and spectrum down-sampling on the modulated image by using a low-resolution infrared camera to obtain a low-resolution two-dimensional aliasing image. The limitation of the spatial resolution and the spectral resolution of an infrared camera is broken through through spatial domain compression imaging and spectral domain compression imaging, and an original high-space and high-spectral-resolution infrared image can be recovered from a collected low-space and low-spectral-resolution infrared image by using a reconstruction algorithm. According to the invention, the spatial and spectral correlation of the spectral image is utilized, data compression is carried out before data acquisition through a compression imaging method, and the data volume of acquisition, storage and transmission is significantly reduced.

According to the multi-mode single-pixel compression imaging system based on the spatial light modulator provided by the embodiment of the invention, a light source supply module in the system can provide a broadband light source, and light emitted by the broadband light source can irradiate a target object and is reflected to a light field modulation module; the light field modulation module performs spectrum separation on the received light signal, and after multiple beams of monochromatic light after separation are incident to the spatial light modulator, the spatial light modulator performs light splitting and parallel modulation; the single-pixel detection module feeds back the collected light intensity data to the data processing module when detecting the modulated light signal; the data processing module issues a mode switching instruction to the spatial light modulator to perform mode switching when determining that the light signal reaches an ideal modulation state, and performs joint optimization modeling and iterative solution calculation based on multi-mode imaging light intensity data to realize synchronous reconstruction of a target object image. The system can realize joint acquisition and fusion reconstruction of multi-modal information.

The present invention provides a self-adaptive and saliency-aware snapshot compressive imaging (SCI) system. In comparison with the existing SCI systems, the self-adaptive and saliency-aware SCI system of the present invention integrates saliency detection, which feedbacks to the coding masks with a calculated sampling efficiency for updating the coding masks. As such, self-adaptation of the system is achieved, and high-level information such as saliency is also obtained and given consideration, thereby producing reconstruction results with better quality, lower power cost and higher efficiency.

The invention discloses a point spread function and dislocation superposition-based compression imaging method and system, and relates to the technical field of compression imaging, and the method comprises the specific steps: carrying out the PSF imaging of a collected image based on a point spread function, and obtaining a blurred image; encoding the blurred image based on an encoding matrix to obtain an encoded image; carrying out frame-by-frame dislocation superposition on the coded image to obtain an original image; and constructing a measurement matrix based on the original image, and decoding and reconstructing the original image by using a reconstruction algorithm according to the measurement matrix to obtain a reconstructed image. According to the method, a high-speed compression imaging model based on PSF diffusion, frosted glass coding and frame-by-frame staggered superposition is constructed on the basis of a compressed sensing theory, and multiple frames of images are superposed on a photosensitive chip of a camera in a staggered manner by the model between two electronic reading times of the camera. Therefore, the electronic reading speed of the camera is improved in a disguised manner.

A system for detecting an object from an image includes: a computing apparatus having a processing unit, a memory unit and a user interface, the processing unit operatively coupled to the memory unit, the computing apparatus configured to: compress optical signals (i.e., visual signals) from a real world scene using a Snapshot Compressive Imaging (SCI) system to obtain compressed signals, receive the compressed signals, store the compressed signals as compressed images, apply one or more knowledge distillation techniques in conjunction with a pre trained object detection model to detect one or more objects directly from each compressed image, utilize motion information encoded within the compressed data to optimize the object detection process, and present on the user interface the one or more detected objects on an image.

The invention discloses a double-path spatial-spectral domain joint compressed sensing imaging method and device, and belongs to the field of high-resolution spectral imaging and compressed imaging. Target light is divided into two paths through the beam splitter prism, and one path is imaged to the high-spatial-resolution detector through the imaging lens. And the other path enters a spatial spectrum compression measurement light path. A spatial-spectral joint coding matrix is generated for a spatial-spectral compression measurement light path, a DMD is introduced into the light path to serve as a spatial light modulator to load the joint coding matrix to carry out high-resolution spatial-spectral joint coding on a target scene, and then a prism is used as a dispersion element to carry out dispersion on the coding scene. And finally, carrying out space and spectrum down-sampling measurement on the coded information of dispersion through an imaging lens by using a low-spatial-resolution detector to obtain a low-spatial-resolution two-dimensional spectrum aliasing measurement value. An original high-space and high-spectral-resolution image can be reconstructed through a back-end reconstruction algorithm on the collected high-spatial-resolution gray-scale image and the low-spatial-resolution spectral aliasing image.

This invention proposes a wavenumber spectrum reconstruction and rapid fusion imaging method and system for arbitrary bistatic SAR. It proposes a method to consistently center the wavenumber spectrum of the spatial domain signal of the imaging scene, introduces a two-dimensional wavenumber spectrum position correction filter to compress the wavenumber spectrum width of the imaging scene, reduces the Nyquist sampling requirement in the spatial domain, and achieves accurate SAR imaging of the imaging scene with less computation, thus improving the imaging efficiency of the imaging method. Furthermore, while achieving accurate and consistent centering of the wavenumber spectrum of the imaging scene, this invention proposes a new method for calculating the minimum Nyquist sampling requirement of the spatial domain signal of the imaging scene. Based on the framework of the time-domain FFBP imaging method, this invention enables the imaging method to have good parallelism, utilizing parallel processing mechanisms on hardware platforms such as GPUs and FPGAs, which will further significantly improve the imaging efficiency of the time-domain FFBP imaging method in bistatic SAR systems in practical applications.

The present application relates to the technical field of sonar imaging, and particularly relates to a multi-beam sonar compressed imaging method and system based on depth unfolding, which comprises the following steps: a multi-beam sonar system is used to emit sound waves to the seabed, and a receiving device is used to receive reflected echo signals to obtain multi-channel digital time sequence echo signals; an observation matrix is constructed to compress and sample the multi-channel digital time sequence echo signals to obtain a low-dimensional measurement matrix; the low-dimensional measurement matrix is input into a trained depth unfolding beamforming network to output a reconstructed beamforming spectrum, and a sonar sounding image is generated according to the beamforming spectrum. The present application can greatly improve the imaging speed and support real-time applications such as underwater obstacle avoidance and online monitoring.

The application relates to the technical field of spectral imaging, and discloses a multi-snapshot hyperspectral compression imaging system. The multi-snapshot hyperspectral compression imaging system disclosed by the application comprises an optical lens, a pixel filter, a surface array camera and a displacement actuator. The displacement actuator moves the pixel filter according to a preset movement mode so that a detector collects multiple image data with the filter being at different positions and having different filtering effects. An upper computer carries out spatial combination through a spectral domain reconstruction neural network model to reconstruct the multiple image data into spatial-spectral data cube reconstruction data. At this time, image processing is carried out through a set original image acquisition device, so that the spatial-spectral data cube reconstruction data reconstructed through the above scheme has high accuracy, thereby solving the technical problem of low image reconstruction accuracy of the existing hyperspectral compression imaging system.

The application relates to the technical field of image processing, and discloses a light-weight single-pixel imaging method based on frequency domain-space domain modulation attention, which comprises a single-pixel image data generator and a calculation reconstruction generator; an initial inversion estimation is obtained through inverse mapping of a measurement matrix; then, the initial inversion estimation is input into a dual-domain collaborative attention deep reconstruction network; the network is composed of a plurality of dual-domain collaborative attention module cascades connected in series, a multi-head spectrum calibration module in the module realizes long-distance information reconstruction through dual-domain feature information fusion interaction; a multi-scale-depth dynamic convolution fusion module extracts features in a space domain, accurately processes high-frequency edges, and significantly enhances the reconstruction capability of texture details; and the features are corrected in combination with a residual error guiding update module. Through the dual-domain collaborative mechanism, the reconstruction precision and the detail recovery capability of single-pixel imaging are effectively improved while the network parameter quantity and the calculation complexity are greatly reduced, and the application is suitable for edge deployment.

The invention discloses a compression ultrafast imaging device based on instantaneous image reference. The compression ultrafast imaging device is composed of a dynamic scene acquisition system, an instantaneous imaging system, a coding compression imaging system and a control and processing system. According to the method, dynamic scenes including coding compression imaging and instantaneous imaging are recorded simultaneously through two different imaging models, and collected bimodal data are processed and reconstructed by using a bimodal information fusion image reconstruction algorithm based on a non-training neural network, so that a high-fidelity dynamic scene is recovered. According to the method, the image quality of compression ultrafast imaging can be effectively improved, the defect of a traditional compression ultrafast imaging technology in the aspect of image fidelity is overcome, the temporal-spatial resolution of an imaging system is remarkably improved, and the method is suitable for fine observation of ultrafast dynamic phenomena and particularly has important application value in the fields of scientific research, industrial application and military affairs.

The invention discloses a hyperspectral compression imaging method and system, a terminal and a storage medium in the technical field of hyperspectral image processing, and aims to solve the problem of low reconstruction precision caused by loss of high-frequency details, weak spectral correlation and poor anti-noise capability in a compression imaging process in the prior art. The method comprises the following steps: acquiring compression measurement and a sensing mask of a coded aperture snapshot spectral imaging system, and acquiring an initial feature map according to the compression measurement and the sensing mask; inputting the initial feature map into a pre-constructed U-Net model to obtain a decoded feature map; performing convolutional mapping on the decoded feature map, and obtaining a reconstructed hyperspectral image in combination with the initial feature map; according to the method, long-sequence data are efficiently processed through the spectrum-space state synchronizer, local and global features of the image can be effectively captured through multi-scale decomposition of the wavelet variance modulation block, and the problem that reconstruction precision is not high due to loss of high-frequency details, weak spectrum correlation and poor anti-noise capacity in the traditional compression imaging process is solved.

The invention relates to the technical field of high-resolution imaging, discloses a hyperspectral high-resolution imaging method based on compressed sensing Fourier laminated imaging, and provides a hyperspectral high-resolution rapid imaging technology based on Fourier laminated imaging. Through combination of a single-exposure hyperspectral compression imaging technology and a Fourier lamination imaging technology, hyperspectral high-resolution rapid imaging is realized. According to the method, a two-dimensional image is acquired by using a single-exposure hyperspectral compression imaging acquisition module, hyperspectral images of multiple wavebands are calculated through a deep learning algorithm, then a high-resolution image is synthesized by using a Fourier lamination imaging algorithm, and finally the high-resolution hyperspectral images of the multiple wavebands are obtained. The image reconstructed by the method provided by the invention can simultaneously meet the requirements of high resolution and high spectrum, and the method provided by the invention has the advantages of improving the imaging speed, reducing the hardware requirement standard and cost and improving the acquisition efficiency.

The present invention proposes a single-photon hyperspectral imaging method and system based on spectral compression sampling. In order to address the problem that hyperspectral compression imaging methods are difficult to apply to beam scanning detection systems, a spatial light modulator is used to efficiently and flexibly modulate the spectrum of the dispersed light source, and spatial information is acquired through point-by-point scanning, which makes the imaging method applicable to beam scanning detection systems. Then, the sparsity of spectral information is fully utilized to construct a hyperspectral reconstruction model, and finally the alternating direction multiplier method is used to iteratively solve the hyperspectral reconstruction model, thereby reconstructing the hyperspectral data of the target using the compressed sampling image. This method can reconstruct hyperspectral data using a small amount of compressed sampling observation data, greatly reducing the imaging time and the amount of imaging data, and providing convenience for hyperspectral imaging of beam scanning detection systems.

The invention relates to a high-sensitivity streak camera ultrafast scanning image enhancement and noise reduction method, and belongs to the technical field of ultrafast imaging and signal processing. The method mainly comprises the following steps of: performing spatial modulation on three-dimensional image data coded by a spatial coding element through a periodic grating; carrying out compression imaging on the modulated three-dimensional image data by the streak camera to form a two-dimensional observation image; an ADMM-TV algorithm is adopted to carry out image decoding, and a three-dimensional image containing a periodic modulation structure is recovered; after the three-dimensional image is reconstructed, effective fringe information in the modulated image is further extracted, high-frequency modulation residues are removed, and denoising of the interference fringe image is achieved. Physical separation of signals and noise is achieved through periodic grating modulation, high-frequency interference such as space charge noise can be restrained, the signal-to-noise ratio and contrast ratio of images are improved, and accuracy and stability of diagnosis of an ultrafast imaging system of a VISAR speed interferometer are improved.

This invention discloses an underwater target detection device and operating method based on forward-looking sonar partitioning, relating to the field of underwater acoustic signal processing technology. This invention, by displaying the measurement range, divides the beam domain into grids from two dimensions: beam and range, forming multiple local detection grids. It compresses and images the corresponding beam domain data to form image domain data, and determines the detection threshold for each local detection grid based on the signal-to-noise ratio of the corresponding image domain data to identify underwater targets. By dividing the beam domain data of the detection area into grids according to beam and range, this invention can reasonably divide the beam domain data generated by underwater targets, underwater reverberation, and acoustic ray changes in the beam domain data corresponding to the signal domain. It compresses and images the beam domain data of each local detection grid, and accurately identifies the parameters corresponding to underwater targets, underwater reverberation, and acoustic ray changes from the perspective of obtaining the detection threshold from the signal-to-noise ratio of the image domain data, thus accurately identifying underwater targets.

The invention relates to the technical field of image processing, and discloses a lightweight single-pixel imaging method based on frequency domain-space domain modulation attention, which comprises the following steps: constructing a single-pixel image data generator and calculating a reconstruction generator; initial inversion estimation is obtained through reverse mapping of the measurement matrix; sending the data to a double-domain collaborative attention depth reconstruction network; the network is formed by cascading a plurality of stages of double-domain collaborative attention modules which are connected in series, and multi-head spectrum calibration modules in the modules realize remote information reconstruction through double-domain feature information fusion interaction; the multi-scale-depth dynamic convolution fusion module performs feature extraction in a spatial domain, accurately processes a high-frequency edge and remarkably enhances the reconstruction capability of texture details; and a residual error is combined to guide the updating module to correct the features. Through a double-domain cooperation mechanism, the reconstruction precision and the detail recovery capability of single-pixel imaging are effectively improved while the network parameter quantity and the calculation complexity are greatly reduced, and the method is suitable for edge deployment.

The present invention relates to a method and an imaging system for obtaining single-exposure four-dimensional compressive imaging; the method includes an object optical signal, performing one-dimensional Fourier transform on the object optical signal to obtain an object dynamic spectral signal, then applying random modulation to obtain an object spectral signal modulation signal, and finally obtaining a two-dimensional compressed image; the system part includes a spectral signal conversion module, a spectral signal modulation module, and a spectral signal compression module. Through the present invention, four-dimensional compressive imaging images can be obtained while considering the time variable.

This invention discloses a hyperspectral fusion imaging method and apparatus based on low-rank representation of deep nonlinear transform tensors. The method includes the following steps: simultaneously acquiring a prior multispectral image while performing hyperspectral compression measurements in the observation scene, using both data points as inputs; establishing a novel low-rank regularization of deep nonlinear transform tensors for hyperspectral images based on tensor representation and deep learning theory to fully characterize the global high-dimensional low-rank correlation of hyperspectral images in the deep nonlinear transform domain; using this regularization term as the objective function, and modeling the compression imaging and spectral degradation processes as two data fidelity terms respectively, constructing a fusion imaging model and a loss function; minimizing the loss function through a learning algorithm to optimize the model, and fusing and reconstructing a complete hyperspectral image. The novel method and apparatus proposed in this invention can achieve high-precision fusion imaging of the observation scene without manual intervention or explicit intermediate steps.

The invention discloses an underwater double-pulse laser compression imaging method and system, and the method comprises the steps: transmitting a double-pulse laser waveform containing different pulse widths through a double-pulse laser source, and irradiating a target region after the double-pulse laser waveform is collimated and expanded; focusing, modulating and collecting laser echoes of the target area; according to the collected laser echo waveform, distance and intensity information of the target area is obtained through cross-correlation calculation, and high-precision three-dimensional imaging of the underwater target area is carried out. According to the method and the system, non-scanning underwater laser imaging is realized by combining a double-pulse distance measurement method and a compression imaging method, and meanwhile, the intensity of an image and the distance reconstruction precision are remarkably improved by introducing cross-correlation calculation.

The present invention discloses a three-channel compression imaging system and an image reconstruction method. The three-channel compression imaging system includes a dual-channel recording component. By adding a diffraction optical element and a streak camera without a lens, the parameters of the diffraction optical element and the lens are set so that two light paths are imaged at different positions of the streak camera sensor, and the photosensitive areas of the pixel points are staggered relative to the image, thereby doubling the sampling rate. Then, an integral channel recording component is added, and the integral image is recorded using a CMOS camera. The combination of the dual-channel recording component and the integral channel recording component achieves a three-fold increase in the sampling rate, overcoming the problem of spatial information loss and insufficient dynamic range of the streak camera in traditional single-channel ultrafast compression imaging system technology. The image reconstruction method can reconstruct extremely high-quality two-dimensional images to avoid distortion in the depiction of shock wave characteristics and improve the accuracy of velocity field analysis.

This invention specifically relates to a single-exposure compressed imaging reconstruction method and system that integrates pre-trained language models, solving the problem that existing technologies can only decode a single imaging modality. It employs a model framework of "physical constraints-semantic guidance-sparse controlled diffusion," uniformly mapping cross-modal compressed data to align the data stream. On one hand, it utilizes a lightweight mask-gated constraint feature extraction module to extract high-fidelity underlying physical features; on the other hand, it cascades a pre-trained multimodal large language model to generate a global semantic representation. In the controlled diffusion large model denoising and reconstruction stage, an asymmetric sparse controlled DiT architecture is used to solve the problem of easily losing high-frequency details, and computational redundancy is significantly reduced by decreasing the number of controllable modules and layers. Through this hardware-software co-design, 3D positional encoding mechanism, and text prompt word design, a single model can adaptively reconstruct high-precision images with multiple imaging modalities and compression rates.

The invention relates to the technical field of laser micro-nano processing, and discloses a real-time in-situ monitoring imaging method for pulse laser processing, which comprises the following steps of: a, monitoring femtosecond laser processing in real time by using a high-speed holographic single-exposure compression imaging system and a high-speed video single-exposure compression imaging system; b, the laser is subjected to beam splitting through a beam splitter prism, and the laser is guided to the surface of the sample for three-dimensional shape micro-nano machining; and c, quickly coding the image information of the surface of the sample by using a digital micromirror device (DMD). According to the real-time in-situ monitoring imaging method for pulse laser processing, the high-speed two-dimensional image and the high-speed three-dimensional shape information of the processed material can be obtained at the same time, ultra-fast imaging is achieved in a low-cost mode, real-time imaging can be conducted on femtosecond laser processing, the sample is monitored in situ, and the real-time monitoring and imaging effect is achieved. The imaging system is independent and can reconstruct a low-frame-rate image into a high-frame-rate dynamic video, and the storage space is saved.

The application discloses a hyperspectral compression imaging method, system, terminal and storage medium in the technical field of hyperspectral image processing, and aims to solve the problem of low reconstruction accuracy caused by high-frequency detail loss, weak spectral correlation and poor noise resistance in the compression imaging process in the prior art. It comprises obtaining the compression measurement and the perception mask of the coded aperture snapshot spectral imaging system, obtaining the initial feature map according to the compression measurement and the perception mask; inputting the initial feature map into the pre-constructed U-Net model to obtain the decoding feature map; and performing convolution mapping on the decoding feature map to obtain the reconstructed hyperspectral image in combination with the initial feature map; the spectral-space state synchronizer efficiently processes long sequence data, and the wavelet variance modulation block can effectively capture the local and global features of the image through multi-scale decomposition, thereby solving the problem of low reconstruction accuracy caused by high-frequency detail loss, weak spectral correlation and poor noise resistance in the traditional compression imaging process.