15 results about "Exposure fusion" patented technology

The invention discloses a hand-eye-force integration-based catenary cantilever robot assembly method, which comprises the following steps of: synthesizing image sequences of different exposures into a high-quality image based on a self-adaptive multi-exposure fusion technology, identifying a workpiece contour in the image based on a deep learning framework, and calculating a pose of an identified part in a camera coordinate system; the two-dimensional camera and the three-dimensional camera are matched to carry out accurate scanning, an accurate pose deviation matrix of an actual workpiece relative to a theoretical model is obtained through a nearest point cloud registration algorithm, and a corrected moving target pose is calculated; and the robot moves towards the position and posture of the moving target, when the robot is about to make contact with the assembly workpiece, the impedance control mode is switched to conduct cantilever installation, and moment data are continuously monitored in the whole process till installation is completed. According to the method, the robot can intelligently cope with uncertainty in the cantilever assembly process, and the assembly success rate and the assembly efficiency are remarkably improved.

The application provides a deep multi-modal image fusion method and system, and relates to the technical field of image processing; the method comprises the following steps: respectively extracting features of an overexposed image and an underexposed image, respectively obtaining dictionary features and sparse features of the overexposed image and dictionary features and sparse features of the underexposed image, updating the dictionary features and the sparse features of the overexposed image and the underexposed image through a total target function, respectively extracting common features from the updated dictionary features and the sparse features through a nonlinear function, extracting features according to the extracted common features, obtaining an overexposed fusion image and an underexposed fusion image and performing fusion processing, obtaining a reconstructed image and comparing the reconstructed image with a standard image to generate an evaluation index. The total target function is iteratively changed to perform transformation learning, higher-quality sparse features are extracted to capture important internal properties of the image to reconstruct the image, and the fusion of multi-modal images is realized.

The invention discloses a high-reflection surface three-dimensional reconstruction method and device based on virtual exposure fusion. The method comprises the following steps: collecting a plurality of exposure image groups of a to-be-reconstructed target; one exposure image group corresponds to one projection frequency and comprises a plurality of exposure image subgroups; generating a corresponding intermediate exposure image group based on each exposure image subgroup, and then performing weighted fusion to obtain a corresponding virtual exposure image; fusing the virtual exposure image corresponding to each middle exposure image group and the high-exposure image and the low-exposure image in the corresponding exposure image subgroup by adopting a Laplacian pyramid multi-scale fusion mode to obtain a corresponding fused image; based on each fused image, obtaining an absolute phase distribution diagram through a phase shift method and a multi-frequency heterodyne method; and generating a three-dimensional point cloud of the to-be-reconstructed target according to the absolute phase distribution diagram, thereby providing a high-reflection surface three-dimensional reconstruction method which is wide in application range, simpler in process and higher in precision.

An exposure control method includes: calculating a long-exposure brightness mean value of pixels of darker (N−X) kinds of brightness among N kinds of brightness values of a long exposure image, wherein a total number of pixels of brightest X kinds of brightness values among the N kinds of brightness values is a long-exposure bright pixel number; when the long-exposure brightness mean value doesn't approximate to a long-exposure target brightness mean value, adjusting exposure setting for generating / modifying the long exposure image to make the two brightness mean values be similar / equal; determining brightest K pixels of a short exposure image, wherein the K is equal to the long-exposure bright pixel number; calculating a short-exposure brightness mean value; and when the short-exposure brightness mean value doesn't approximate to a short-exposure target brightness mean value, adjusting exposure setting for generating / modifying the short exposure image to make the two brightness mean values be similar / equal.

The application belongs to the technical field of image processing, and particularly relates to a multi-exposure fusion method for separating illumination and motion; low-exposure images, medium-exposure images and high-exposure images are subjected to illumination preprocessing and input into a fusion model; the low-exposure images and the high-exposure images are mapped to the illumination level of the medium-exposure images and normalized according to first gamma values and second gamma values, to obtain first new medium-exposure images and second new medium-exposure images, and the new medium-exposure images are subjected to motion alignment with the medium-exposure images; the first new medium-exposure images and the second new medium-exposure images are subjected to inverse gamma transformation respectively, to obtain new low-exposure images and new high-exposure images, and the new low-exposure images and the new high-exposure images are subjected to illumination fusion with the medium-exposure images to obtain a high dynamic range image, loss is calculated, and model parameters are trained by back propagation; a to-be-processed image is obtained, and a corresponding high dynamic range image of the to-be-processed image is obtained by using the trained fusion model; the application adopts the idea of separating illumination and motion, so that the high dynamic range image retains more information of the input image, and ghosting is reduced.

This invention relates to the field of image enhancement technology and discloses a low-light image enhancement method and system for 5G remote control systems based on deep Retinex decomposition. The method acquires and preprocesses the original low-light image from the front-end device of the 5G remote control system, inputs it into a lightweight multi-scale illumination sensing network to separate the initial illumination and reflection components, corrects the initial illumination component using a dynamic dual-branch exposure fusion module, processes the initial reflection component using a residual noise-detail co-optimization module, and then reconstructs and enhances the image through a halo and color joint correction mechanism. The image is then encoded, compressed, and transmitted to the remote control center via a 5G private network. This invention solves the core problems of underexposure and overexposure, noise interference, detail loss, and wasted bandwidth in low-light images in 5G remote control scenarios, achieving lightweight real-time enhancement at the edge, ensuring image quality and transmission efficiency, and providing reliable support for remote control decisions.

The invention relates to the technical field of image enhancement processing, and particularly provides a camera low-light image enhancement method and system based on dynamic exposure fusion deep learning, and the method comprises the steps: generating a group of control signals with continuous virtual exposure parameters, and driving an image signal processing program to simulate and generate a corresponding short-time image sequence; analyzing a signal reliability measurement diagram of each pixel position in the short-time image sequence under different virtual exposure parameters; performing selective aggregation on features of all corresponding pixel positions in the short-time image sequence in the feature domain to generate an intermediate fusion image; and interacting the features of the intermediate fusion image with a task feature map of an embedded external visual task priori knowledge parallel processing path to generate a group of task-perceived attention masks. The system comprises an image signal processing module, an intermediate fusion image module and a feature interaction module. According to the method, a complete processing link from physical signal simulation to semantic feature maintenance is formed.

The application relates to a low-illumination gray-scale image enhancement and denoising method, which comprises the following steps: constructing an optimal exposure ratio image according to an input low-illumination gray-scale image; decomposing the low-illumination gray-scale image and the optimal exposure ratio image by adopting a LatLRR method to obtain a low-rank part and a significant part; constructing a low-rank part weight and a significant part weight according to the obtained low-rank part and the significant part; performing normalization processing on the obtained low-rank part weight and the significant part weight to obtain a normalized weight; and performing image reconstruction and synthesis according to the low-rank part, the significant part and the normalized weight to obtain a multi-exposure fusion enhanced image. The application can enhance and denoise a single low-illumination image, restore structure information, maintain details, avoid block effects and reduce the calculation complexity.

The invention discloses a self-adaptive multi-exposure fusion three-dimensional measurement method for a high dynamic range scene. The method comprises the following steps: firstly, acquiring high-frequency phase shift fringe patterns at different exposure times, and finding out initial exposure time for preventing effective measurement areas in all phase shift patterns from overexposure through time domain light intensity overexposure detection operation; taking the high-frequency phase shift fringe pattern of the initial exposure time as an initial image of multi-exposure fusion, adaptively reserving a fringe region with high phase quality according to a modulation degree condition through a noise-modulation degree model, and introducing a time domain superposition principle to estimate the next exposure time of the multi-exposure fusion; and finally, calculating an effective measurement area of the current fused fringe image by using a reference plane phase based on depth constraint, and continuing to perform multi-exposure fusion until the effective measurement area meets a modulation degree condition, thereby completing three-dimensional measurement of the whole high dynamic range scene. According to the invention, the high-quality fringe pattern is obtained through adaptive multi-exposure fusion, the total exposure time is significantly reduced by introducing the time domain superposition technology, and high-precision and high-efficiency full-automatic three-dimensional measurement of a high-dynamic-range scene is realized.

This invention provides a multi-exposure image fusion system, method, and electronic device. The system includes: an image sequence alignment and correction module, comprising a selection submodule and an image sequence alignment and correction network. The selection submodule is configured to select a reference exposure level image, and the image sequence alignment and correction network is configured to align and correct other exposure level images based on the reference exposure level image; an image fusion deep network, configured to fuse the aligned and corrected multi-exposure image sequence to generate a multi-exposure fused image; and a visual quality-driven perception optimization module, configured to evaluate the multi-exposure fused image using a fused image visual quality evaluation model and optimize the image fusion deep network based on the evaluation results. This invention, by performing multi-exposure image fusion based on a deep network, can effectively capture image details and better understand the content of multi-exposure images, thereby achieving fast and efficient multi-exposure image fusion.

The application discloses a kind of multi-exposure fusion's angle resolution scattering micro-nano structure measurement method, it is related to integrated circuit measurement technical field.The method includes: obtaining multi-exposure sequence image set, camera response function CRF is modeled;Overexposed pixel value is estimated using linear extrapolation method based on tangent line at response curve end point, and the confidence of extrapolated pixel is calculated;When the confidence of extrapolated pixel is lower than basic confidence, segmented conservative estimation strategy is used to enhance to extrapolated pixel;Corrected image set and corresponding confidence image set are obtained by iterative processing;Weight distribution is carried out to the image in corrected image set, and corresponding normalized weight set is obtained;According to normalized weight set and corrected image set, multi-scale fusion is carried out, and fusion image is obtained.Pixel level correction is carried out to image, and the pixel irradiance of overexposure area is effectively reconstructed, and multi-scale fusion is carried out to image, and high-fidelity fusion of Fourier space intensity is realized.

The invention discloses an intelligent detection method and system for surface defects of a power battery, and belongs to the technical field of computer vision and industrial detection.The method comprises the steps that multiple images under the conditions of forward light, lateral light and diffused light are collected through sequential switching of an annular LED light source array; generating a high dynamic range composite image through multi-exposure fusion; performing multi-light-source feature fusion based on an attention mechanism; performing pixel-level semantic segmentation by adopting a U-Net + + network to output a defect mask and a confidence score; according to the method, the technical problems of image overexposure caused by high light reflection of the metal shell, inconsistent imaging contrast of different defect types, inaccurate defect boundary positioning and the like are solved, high-speed detection of 120 battery cells per minute is realized, and the defect detection rate reaches 99.5% or above.

The present application relates to the technical field of image processing, in particular to a high dynamic range image synthesis and tone mapping method and electronic equipment, the present application obtains multiple RAW images with different exposure under the same scene through a camera; the RAW images with different exposure are fused through a square weighting function to obtain a high dynamic range image synthesized in the RAW domain; the high dynamic range image is subjected to channel tone mapping to obtain a low dynamic range image in the RAW domain. The present application solves the problem of synthesizing and mapping a high dynamic range image on RGB, which occupies a large computer resource and seriously affects the color and brightness information of the image. The present application has fast calculation speed, low resource consumption, good result perception and is suitable for hardware integrated high dynamic range image synthesis, and has strong market application prospect.

This invention discloses a real-time multi-exposure HDR image processing system based on FPGA, comprising: a DDR3 image storage control module, integrated within the FPGA, communicating with an external DDR3 chip via the AXI4 bus protocol, supporting high-speed storage and parallel reading of 8-channel multi-exposure images, and outputting synchronized multi-exposure image data and valid frame, line, and data signals; a multi-exposure HDR fusion module, connected to the output of the DDR3 image storage control module, employing a 6-stage hardware pipeline architecture to achieve pixel-level weighted fusion of 8-channel multi-exposure images, outputting a 24-bit RGB format HDR fusion image; and a Reinhard tone mapping module, connected to the output of the multi-exposure HDR fusion module, implementing dynamic range compression from HDR to LDR images based on an optimized Reinhard algorithm, outputting a 24-bit RGB format LDR image that meets the requirements of display devices. This invention achieves real-time processing of multi-exposure HDR images throughout the entire process through the integrated and synchronized optimization of these three modules.

The invention discloses a signal lamp image generation method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a short-exposure image and a long-exposure image collected by monitoring equipment under the condition that the illumination intensity of an environment where the monitoring equipment is located is determined to be smaller than preset intensity; respectively determining a target short exposure fusion proportion of the short exposure image at the pixel point and a target long exposure fusion proportion of the long exposure image at the pixel point according to the pixel value of each RGB color channel of a plurality of pixel points of the region of interest in the short exposure image and the pixel value of each RGB color channel of the pixel point corresponding to the long exposure image; and fusing the short-exposure image and the long-exposure image according to the target short-exposure fusion proportion and the target long-exposure fusion proportion to generate a traffic signal lamp image. According to the scheme, the abnormal edge area of the signal lamp in the image can be effectively eliminated, the halo of the signal lamp is weakened, and the brightness from the signal lamp body to the halo area in the image can be smoothly and naturally transited.