73 results about "Super resolution algorithm" patented technology

The invention discloses a visual detection system for an automobile door panel assembly, and relates to the technical field of automatic detection, and the visual detection system comprises the steps: installing a high-precision industrial camera, and carrying out the synchronous collection of the multi-view image data of an automobile door panel; preprocessing the acquired multi-view image data of the automobile door panel; carrying out detail enhancement on the preprocessed multi-view image data of the automobile door panel by adopting a super-resolution algorithm; integrating the enhanced multi-view image data of the automobile door panel into an automobile door panel panorama through binocular stereoscopic vision matching, and constructing an automobile door panel three-dimensional model; the automobile door panel three-dimensional model is compared with a standard automobile door panel three-dimensional model, and the buckle defect in the automobile door panel is recognized; and carrying out position marking and defect type analysis on the identified defect points, and generating an automobile door panel detection report according to the defect type analysis. According to the invention, details are enhanced by using a super-resolution algorithm, defects are accurately positioned by using a three-dimensional model, and the detection efficiency and accuracy are improved.

A communication system may include an electronic device, one or more external devices, and one or more reconfigurable intelligent surfaces (RIS's). Wireless signals may be incident upon the RIS(s) from the external device(s). The RIS(s) may have antenna elements that reflect the signals towards the electronic device while being swept over a set of reflected angles. The device may include one or more antennas that receive the reflected wireless signals. The device may perform measurements of the received wireless signals and may generate a steering vector using the measurements. The device may input the steering vector to a super-resolution algorithm that outputs angles-of-arrival of the wireless signals at the RIS(s), which can be used to detect the position of the external device(s). The device may receive the wireless signals using a single antenna to minimize resource and space consumption or using multiple antennas to maximize location accuracy.

The invention discloses a lithium metal battery in-situ time space thermal monitoring system and method based on a distributed optical fiber, and the system employs a distributed optical fiber sensing technology (OFDR) to combine with a spiral arrangement structure of a single mode fiber (SMF), converts one-dimensional temperature data into two-dimensional plane distribution, and achieves the precise monitoring of an internal temperature field of a battery. Besides, by introducing a super-resolution algorithm based on an SRGAN model, a low-resolution temperature image is converted into a high-resolution image, details are reconstructed, and the spatial resolution and the time resolution are improved. The method integrating physical sensing and the super-resolution algorithm can reduce the thermal runaway risk, prolong the service life of the battery, realize more uniform lithium deposition and prolong the cycle life of the battery, thereby providing powerful technical support for safe operation and performance optimization of the lithium metal battery. In addition, a hot spot generation mechanism can be explored, and the effectiveness of a battery protection strategy is verified. According to the invention, real-time, lossless and high-precision large-measurement-area super-resolution monitoring can be provided for the lithium metal battery.

The invention discloses a building design drawing generation method and system based on a stable diffusion model, and the method comprises the steps: obtaining image materials of different building facades, and carrying out the screening and marking of the image materials, and obtaining a data set; a stable diffusion model based on Control-Net guidance is adopted to train and finely adjust the data set, and a building image generation model is obtained; inputting the sketch and the cue word into a building image generation model, and outputting a building design drawing; and rendering and enhancing the architectural design drawing by adopting an image super-resolution algorithm based on the generative adversarial network. According to the method, building facade image materials are acquired, a data set is constructed, stable diffusion model training guided by Control-Net is combined, so that rapid generation from a sketch to a building design drawing is realized, meanwhile, a generative adversarial network is introduced to render and enhance the generated building design drawing, the definition and detail performance of the image are remarkably improved, and the image quality is improved. And a high-fidelity visual effect picture is quickly output, and the design efficiency and quality are improved.

The invention discloses a geomagnetic anomaly data stable downward continuation method based on an SRGAN deep learning network, and belongs to the field of geophysical magnetic field data continuation. According to the invention, in combination with the continuation characteristic of geomagnetic anomaly data, a CBAM space attention mechanism module is added to improve the spatial perception capability of a network model to the magnetic anomaly data, and in combination with the characteristic that the downward continuation of potential field data can amplify the noise generated by a high-frequency signal; and the deep learning model is combined with adaptive threshold multiple wavelet transform to suppress noise data so as to further improve the continuation precision. In order to enable a model to fully learn detailed information of geomagnetic anomaly data, a training data set construction method combining a Kriging super-resolution algorithm with a sliding subarea mode is provided. By designing and synthesizing a simulation model experiment and comparing actual measurement data with other three algorithms, the model is highest in calculation precision and best in magnetic anomaly detail information recovery.

A video processing method and apparatus, an electronic device, and a storage medium. The video processing method includes: in a first zoom mode or a second zoom mode, obtaining a video shot through a camera lens; in the first zoom mode, processing a video image of a first exposure frame by using a super-resolution algorithm; in the first zoom mode, fusing a video image of a first exposure frame processed by using the super-resolution algorithm and a video image of a second exposure frame not processed by using the super-resolution algorithm, to obtain a fused video; and in the second zoom mode, fusing the video image of a first exposure frame and the video image of a second exposure frame, to obtain a fused video.

An image edge smoothing processing method based on an ink droplet diffusion principle can be divided into three parts: a first part, performing various image preprocessing on a mask part of a specified image, including graying, binaryzation, opening operation, median filtering and connected domain analysis, so as to corrode and eliminate small noise points and convex regions; the second part is that local closed operation is performed on the preprocessed image to fill up the concave area, the local closed operation may cause significant distortion of the image, and only the part which is small in filling area and does not cause significant deformation of the image is reserved through image subtraction and connected domain analysis; and a third part, performing bilinear interpolation and Gaussian blur on the image to resist aliasing, and then applying a super-resolution algorithm to obtain a high-definition image with smooth edges. According to the method provided by the invention, the problem that the image edge is uneven in the color separation treatment process of template manufacturing in the textile field is solved, so that the working efficiency of factory template manufacturing is improved.

The invention provides a multi-mode high-precision terrain interaction system based on tactile feedback and fuzzy logic, when a user touches the surface of a sensor by fingers, a piezoresistive sensor records pressure position and intensity information in real time, and an upper computer adopts a super-resolution algorithm to filter and compensate original data. And after two-dimensional funnel effect and fuzzy logic calculation, the platform adjusts feedback amplitudes and frequencies of the LRA at four corners in real time, and accurately simulates topographic features at a touch position. A two-dimensional interface on the upper computer displays touch points and corresponding tactile feedback parameters in real time, a user can adjust touch actions in real time according to feedback, and the accurate and efficient multi-mode terrain interaction effect is experienced.

The present invention discloses a method for detecting pedestrians on highways based on super-resolution. A bicubic downsampling operation is performed on a data set to obtain a corresponding high-resolution image, and blur kernels and noise are extracted from the data set to construct a low-resolution image. The obtained high-resolution image and low-resolution image are used to train a super-resolution generative adversarial network to obtain a super-resolution generator. The low-resolution image to be identified is input into the trained super-resolution generator, and then a feature point detection network is used to extract feature points, and the total weight is calculated. If the calculated total weight is greater than the set weight threshold, it is judged to be a pedestrian. The present invention uses a super-resolution algorithm to supplement detailed information for small-sized pedestrians, and uses human feature point information for further screening, thereby improving detection accuracy, reducing false alarm rate, and adapting to different application scenarios.

A computational pupillometry system comprises an imaging device configured to capture video frames of a subject's eye and processors executing instructions to perform advanced pupillary assessment. The system employs multi-frame integration techniques, including super-resolution algorithms that utilize sub-pixel shifts between frames, temporal averaging for noise reduction, and parallax-based artifact mitigation to enhance measurement accuracy. Artificial intelligence models, including temporal neural networks, analyze the enhanced pupillary data to determine pupillary parameters and calculate a light-invariant Pupil Reactivity (PuRe) score. The system processes ambient lighting conditions through computational models that analyze video frames before and after controlled stimulation, enabling consistent scoring across varying environmental conditions. Quality assurance mechanisms provide pre-recording and post-recording validation with real-time feedback. The system integrates with electronic medical records through standardized healthcare protocols and supports synchronized, multi-device deployment across healthcare networks.

The present invention discloses a single-image super-resolution algorithm based on a feedback mechanism, which includes the following steps: (1) Obtain the DIV2K dataset as the training set for training the neural network, and use bicubic downsampling to obtain image pairs; (2) Utilize the feedback mechanism to construct a single-image super-resolution generation network model; (3) Input the image pairs into the single-image super-resolution generation network model, use the Charbonnier loss as the loss function, and optimize the model parameters through the Adam backpropagation algorithm to obtain a trained super-resolution network model. The present invention fully obtains the features of the front and back layers by adopting the feedback mechanism, continuously strengthens the shallow features by using the features of the back layer, and further reduces the number of network parameters and memory occupancy; optimizes the features of the front and back layers by using coordinate attention to allocate attention to the features of the front and back layers; in addition, by using a dense connection receptive field module, the receptive field size of the features is increased.

This disclosure describes systems, methods, and devices related to video post-processing using a single local directional pattern (LDP) for multiple post-processing steps. A method may include identifying video received by a first device from a second device and decoded by the first device; generating a LDP of a video frame of the decoded video; detecting, based on the LDP and the video frame input to a blurred region detection algorithm, a blurred region and a non-blurred region of the video frame; applying, based on the LDP and the video frame input to a super resolution algorithm, super resolution on the non-blurred region of the video frame without applying the super resolution to the blurred region; and generating, based on the LDP and the video frame input to a blended image algorithm, a blended image of a low-resolution image of the video frame and a high-resolution image of the video frame.

The invention relates to the field of image display, in particular to an infrared image display method, which comprises the following steps of: S1, performing respe operation on an input temperature array; s2, converting the temperature array into a temperature matrix; s3, performing smoothing operation by using a Laplacian algorithm; s4, normalizing the temperature matrix into a gray value; s5, colors are distributed according to the color map of each pixel; s6, processing the low-resolution image by using a super-resolution algorithm; according to the invention, the readability of the image can be improved, and the visualization of information is enhanced.

The invention discloses a near-field millimeter wave super-resolution imaging method based on nuclear adaptive filtering, and relates to the field of super-resolution imaging. The method is based on a kernel adaptive filtering operator, through a lightweight learning method, it is ensured that estimation characteristics conforming to original data to the maximum extent are met, and a high-resolution image is efficiently predicted and reconstructed. Aiming at a subsequent image processing process of a two-dimensional near-field millimeter wave imaging system, under the condition of shortening data sampling time, a high-resolution image is reconstructed from low-resolution sampling data, and redundant hardware, a large number of image data sets and a dictionary learning process are not needed. Based on the method provided by the invention, the optimal visual effect is achieved in data sets with different shape features, and detail information in an amplified view is clearest. And compared with a typical super-resolution algorithm, the effect is better. Compared with a typical super-resolution algorithm, the method provided by the invention has the highest numerical value similarity and higher structural similarity.

The invention provides a VCSEL (Vertical Cavity Surface Emitting Laser) multi-modal defect image enhancement method and a VCSEL multi-modal defect image enhancement system. The method comprises the following steps: acquiring multi-modal defect image data of a VCSEL; constructing and training an SRCNN image enhancement model; the SRCNN image enhancement model is used for recovering high-resolution details from a low-resolution multi-modal defect image by combining an electroluminescent imaging technology and utilizing an improved SRCNN image super-resolution algorithm; and inputting the multi-modal defect image data into a trained SRCNN image enhancement model to perform image enhancement on the multi-modal defect image data, and outputting high-resolution defect image data. According to the method, the EL imaging technology is combined, the improved SRCNN image super-resolution algorithm is utilized, high-resolution details are recovered from the low-resolution multi-mode defect image, the image quality is remarkably improved, and therefore the yield of VCSEL products is improved.

The present invention relates to the technical field of tunnel engineering and structural engineering, and in particular to a method for identifying risk blocks of tunnel lining falling and evaluating stability, comprising the following steps: S100, inducing tunnel lining vibration by a vibration device; S200, detecting the vibration echo signal of the tunnel lining by a vibration meter; S300, calculating the lining falling block index TSI according to the vibration echo signal of each measuring point i , the vibration energy I of the vibration echo signal under the excitation of the sound wave of frequency i 6i and the power I of the vibration echo signal under the excitation of the sound wave of frequency i 7i ; S400, the index TSI of each point of lining block falling under the i-frequency acoustic wave excitation i Normalization processing, using pixel matrix imaging and learning-based super-resolution algorithm to draw a two-dimensional cloud map Cloud i , calculate the correlation between each two-dimensional cloud map, and the TSI of each cloud map point with a correlation coefficient higher than the threshold α i The average value is taken to finally form a two-dimensional cloud map Cloud of the tunnel lining vibration characteristics.

The invention discloses a hyperspectral image super-resolution method based on a double-domain gating convolution attention mechanism, which can improve the attention of high-frequency information of a hyperspectral image and improve the super-resolution effect after feature fusion. The method comprises a depth feed-forward convolution module, a non-bureau gate control convolution module, a dual-domain gate control attention module and a reconstruction module. According to the method, firstly, a spatial high-frequency information region in an image is filtered by adopting non-local department controlled convolution (NGC), and meanwhile, attention to a global context is kept through a self-adaptive high-frequency component attention mechanism; under the guidance of spatial domain-spectral domain correlation, a hyperspectral image is reconstructed without influencing details, and then spatial high frequency and texture information of the hyperspectral image is reserved through depth feed-forward convolution (DFC) and double-domain convolution attention. Experimental results prove that the algorithm is superior to other common remote sensing image super-resolution algorithms in subjective visual effects and objective evaluation indexes.

The method for stable downward extension of geomagnetic anomaly data based on the SRGAN deep learning network belongs to the field of geophysical magnetic field data extension. The present invention combines the characteristics of geomagnetic anomaly data extension and adds a CBAM spatial attention mechanism module to improve the network model's spatial perception of magnetic anomaly data. In combination with the characteristics that the downward extension of potential field data will amplify high-frequency signals and generate noise, the deep learning model is combined with adaptive threshold multiple wavelet transform to suppress noise data and further improve the extension accuracy. In order to enable the model to fully learn the detailed information of geomagnetic anomaly data, a training data set construction method combining a Kriging super-resolution algorithm with a sliding sub-area mode is proposed. By designing a synthetic simulation model experiment and comparing the measured data with the other three algorithms, the model of the present invention has the highest calculation accuracy and the best recovery of magnetic anomaly details.

The present invention discloses a facial image super-resolution method and device based on a dual discriminant generative adversarial network, which belongs to the field of facial image super-resolution. The method comprises: first, the generative adversarial network combines residual learning with dense connection learning to construct a dense-residual block, thereby enhancing the feature extraction capability without increasing the network depth and parameters; second, the discriminant network is improved, and a local discriminator is added to make the texture details of the reconstructed image more realistic and rich; finally, a new joint loss function is proposed. The network proposed by the present invention is superior to other latest facial image super-resolution algorithms, can generate higher quality facial images, and experiments on low-resolution facial datasets have proved the effectiveness of the algorithm.

The invention discloses a rendering method and device, and belongs to the field of data processing. The method comprises the following steps: loading texture resource data of a first scene; processing the texture resource data based on a super-resolution algorithm to obtain super-resolution texture resource data; and rendering the first scene through the super-divided texture resource data.

The invention discloses a visual sensing information preprocessing method, system and device applied to a nuclear emergency robot and a medium, relates to the technical field of image processing, and solves the technical problem that the image quality of the nuclear emergency robot is poor. The image detail reduction capability in an extreme environment is effectively improved, the structural similarity of a dark area reaches 90% or above, and meanwhile, the irradiation resistance of a visual module is improved to a certain extent on the algorithm level. The framework can be applied to a nuclear emergency robot vision system and can be popularized to other emergency low-illumination radiation field scenes at the same time, and the problem that a traditional vision system is low in returned imaging quality is solved.

The invention provides an image enhancement method and device for an X-ray security inspection machine. The method comprises the following steps: acquiring a security inspection display video output by the X-ray security inspection machine; extracting a region-of-interest map from a security check X-ray image frame sequence corresponding to the security check display video; striping the region-of-interest image with the foreground object into a plurality of striped images, and performing super-resolution processing on the plurality of striped images to obtain a plurality of super-resolution sub-images; and splicing the plurality of super-resolution sub-images to obtain a target enhanced image. According to the method, the region of interest in the security check X-ray image is extracted and striped, so that a key information region can be focused, and the calculation load of a super-resolution algorithm is reduced; according to the X-ray pseudo-color image super-resolution enhancement method and device, super-resolution processing is carried out on the striped images, accurate enhancement of the region of interest in the X-ray pseudo-color image output by the old X-ray security inspection machine is achieved, the image quality can be remarkably improved without replacing core hardware of the X-ray security inspection machine, and the networking expansion capacity is achieved.

This invention discloses a near-field millimeter-wave super-resolution imaging method based on kernel adaptive filtering, belonging to the field of super-resolution imaging. This method, based on a kernel adaptive filtering operator, uses a lightweight learning method to ensure maximum accuracy in predicting and reconstructing high-resolution images by accurately matching the estimated features of the original data. This invention addresses the subsequent image processing of two-dimensional near-field millimeter-wave imaging systems, reconstructing high-resolution images from low-resolution sampled data while shortening data sampling time, without requiring additional hardware, large image datasets, or dictionary learning processes. The proposed method exhibits optimal visual effects across datasets with varying shape features, providing the clearest detail in magnified views. It outperforms typical super-resolution algorithms. The proposed method demonstrates the highest numerical similarity and high structural similarity compared to typical super-resolution algorithms.

The invention relates to the technical field of signal analysis, and discloses a high-speed signal integrity analysis method, system and device and a medium, and the method comprises the steps: configuring a measuring instrument and a probe; amplitude-phase errors are eliminated through de-embedding calibration; acquiring original time domain or frequency domain signal data, and preprocessing to obtain a signal sequence with a high signal-to-noise ratio; constructing a channel model based on a transmission line theory, including performing noise suppression processing on the de-embedded frequency domain response and improving the time delay resolution capability of a reflection point through a super-resolution algorithm; utilizing a sparse reflection model to position impedance discontinuous points; aiming at a plurality of parallel lines, a multi-conductor transmission line model is adopted to separate crosstalk signals; carrying out jitter and phase noise modeling; the reflection time delay and the crosstalk propagation time delay estimated in the channel model are converted into physical distances, and positioning of a reflection point or a crosstalk source is achieved. According to the invention, the problem of step / pulse response distortion caused by limited bandwidth, discontinuous impedance and weak reflection of an instrument in a traditional high-speed signal integrity test is solved.

The invention discloses a crop organ phenotype analysis method for unmanned aerial vehicle RGB image super-resolution reconstruction based on semantic perception, and the method comprises the steps: collecting images at different flight heights, and constructing a semantic guidance data set and a degradation data set; constructing a degradation model for simulating a low-resolution unmanned aerial vehicle image at a high flight height and training the degradation model; performing super-resolution reconstruction on the RGB image acquired by the unmanned aerial vehicle according to a semantic perception super-resolution algorithm; organ phenotype extraction is carried out based on the super-resolution reconstruction image; compared with a traditional method, the method can effectively solve the problems of low reconstruction efficiency and unreal texture caused by the scale change of the same ground feature in different flight height images, difficulty in acquiring paired images through the unmanned aerial vehicle in the field and lack of semantic guidance, improves the spatial resolution of the RGB image of the high flight height unmanned aerial vehicle, and improves the image quality. Time and space resolutions are considered, so that the extraction precision of the organ phenotype is improved.

The present application relates to the technical field of image processing and computer vision, and discloses an infrared image super-resolution system and device based on ZYNQ, which comprises an infrared image acquisition module, a ZYNQ infrared image processing module comprising an ARM processor and a FPGA hardware acceleration module, a high-resolution infrared image output module and a high-resolution infrared image display module; the infrared image acquisition module acquires low-resolution infrared images through an infrared camera, the image data collected by the infrared camera is transmitted to the ZYNQ infrared image processing module through a digital interface, the image processing algorithm in the ZYNQ infrared image processing module starts to perform super-resolution processing on the image data, the processed high-resolution image data is sent to the high-resolution infrared image output module through a digital interface, and is converted into HDMI through a VGA interface and output to the high-resolution infrared image display module. Through the optimized super-resolution algorithm, the image details are effectively restored, and the image resolution is improved.

A computational pupillometry system comprises an imaging device configured to capture video frames of a subject's eye and processors executing instructions to perform advanced pupillary assessment. The system employs multi-frame integration techniques, including super-resolution algorithms that utilize sub-pixel shifts between frames, temporal averaging for noise reduction, and parallax-based artifact mitigation to enhance measurement accuracy. Artificial intelligence models, including temporal neural networks, analyze the enhanced pupillary data to determine pupillary parameters and calculate a light-invariant Pupil Reactivity (PuRe) score. The system processes ambient lighting conditions through computational models that analyze video frames before and after controlled stimulation, enabling consistent scoring across varying environmental conditions. Quality assurance mechanisms provide pre-recording and post-recording validation with real-time feedback. The system integrates with electronic medical records through standardized healthcare protocols and supports synchronized, multi-device deployment across healthcare networks.

This invention provides an image enhancement method and apparatus for X-ray security inspection machines. The method includes: acquiring a security inspection display video output by the X-ray security inspection machine; extracting a region of interest (ROI) map from the X-ray image frame sequence corresponding to the security inspection display video; striping the ROI map containing foreground items into multiple striped images, and performing super-resolution processing on the multiple striped images to obtain multiple super-resolution sub-images; and stitching the multiple super-resolution sub-images to obtain a target enhanced image. This method, by extracting the ROI from the security X-ray image and performing striping processing, can focus on key information areas and reduce the computational load of the super-resolution algorithm. By performing super-resolution processing on multiple striped images separately, it achieves precise enhancement of the ROI in the pseudo-color X-ray images output by older X-ray security inspection machines. It significantly improves image quality without replacing the core hardware of the X-ray security inspection machine and has network expansion capabilities.

The present invention relates to the technical field of seismic damage identification of concrete structures, and particularly to a method, device, electronic device and storage medium for seismic damage identification and segmentation of RC structures. The method includes: acquiring images of damaged RC structures and components, and constructing a target detection data set and a semantic segmentation data set; constructing a damage location model and a semantic segmentation model and training them, and fine-tuning the image super-resolution algorithm using the target detection data set and the semantic segmentation data set; fusing the trained damage location model and the trained semantic segmentation model based on the fine-tuned image super-resolution algorithm to obtain a final damage identification and segmentation model. It breaks through the limitation of the traditional damage segmentation model on the shooting distance of the input image, helps to promote the practical application of advanced computer vision algorithms in actual projects, realizes the long-distance identification and segmentation of seismic damage of RC structures, and improves the efficiency of post-earthquake assessment work.

The invention relates to the technical field of computer image processing, and discloses a screen capture method and device.The method comprises the following steps that interface elements on a screen are intelligently recognized through a capture instruction input by a user, a preset capture area is automatically recommended, and meanwhile the user can manually adjust the capture area; the method comprises the following steps: after dynamic content capture is carried out on a scrolling page or a video, generating a long screenshot or recording a GIF or a video clip with a specified time length by splicing a plurality of pictures; applying a super-resolution algorithm to long screenshots, GIF or video clips to optimize image quality and remove moire and noisy visual flaws; through a real-time editing function and gesture operation, a storage path or a sharing platform is automatically recommended according to historical operation or content characteristics of a user. By integrating a multi-mode trigger recognition mechanism, including voice, gesture, shortcut key and floating button operation, the screen capture instruction accurate response of a user in different use scenes is realized, and the effects of uniform operation inlets and flexible trigger modes are obtained.