22 results about "Digital imaging technology" patented technology

The invention relates to a method and a system for identifying particles in insulating oil driven by deep learning, which can realize automatic identification and classification of particles in insulating oil by combining a micro-flow digital imaging technology and a semantic segmentation method of deep learning, constructing a unified training data set and combining a multi-task segmentation model. Images of the particles in the transformer oil are obtained through the micro-flow digital imaging module, and pixel-level classification and particle recognition are carried out on the images through the multi-task segmentation model. The segmentation branches in the model are responsible for extraction of particle boundaries, and the classification branches are used for analyzing particle morphology and outputting particle categories. The model adopts multi-scale feature fusion, an attention mechanism and a deep residual network structure, and the problems of particle morphology diversity, size change, image boundary blur and the like are solved. Through the high-precision particle recognition algorithm and system, the accuracy and efficiency of detection of the particles in the insulating oil are effectively improved, manual intervention is reduced, and the safety and long-term stability of the transformer are improved.

The invention discloses a three-dimensional imaging reconstruction system and method based on X-ray nondestructive testing. Relates to the technical field of power equipment detection. According to traditional electrical equipment detection, a three-dimensional model is constructed mainly according to a two-dimensional picture shot around a target area, complete sampling and shooting cannot be carried out in a scene where the installation position of the electrical equipment is limited and the space is narrow, and consequently, large errors exist in nondestructive detection; the X-ray digital imaging technology is adopted to carry out nondestructive testing on the electrical equipment, the historical database is utilized to carry out fusion reconstruction on the collected images and historical data, the image collection number is effectively reduced, calculation and storage burdens are reduced, the efficiency and precision of three-dimensional reconstruction are improved, and the method is particularly suitable for detection of the electrical equipment with limited space and has wide application prospects. The method has a good market application prospect, can significantly improve the detection efficiency of the power equipment, reduces the detection cost, and improves the accuracy of equipment fault recognition.

The present invention belongs to the field of testing technology, and specifically relates to an intelligent detection method for visual brightness based on digital imaging technology. Aiming at the problems of large volume, high cost, complex operation of traditional visual brightness measurement instruments, as well as poor accuracy and stability of visual brightness measurement, this method measures visual brightness through steps such as selecting a digital imaging device with adjustable parameters, high resolution and wide dynamic range, matching an adapter lens and a filter, constructing a response function of the digital imaging device, and establishing a conversion relationship between gray values and visual brightness. Specifically, it includes setting parameters of the digital imaging device, photographing a standard light source and establishing a relationship with the target, aligning the target area to acquire images, converting to the gray space for correction and calculating the visual brightness. During the process, the measurement accuracy is also improved by setting white balance, image preprocessing and fusing multiple captured images. This method is easy to operate, low in cost and strong in adaptability, and can effectively improve the measurement accuracy and stability.

The invention discloses an intelligent equipment imaging test method, test equipment, intelligent equipment and a medium, and relates to the technical field of digital imaging, the method is applied to the test equipment, and the method comprises the following steps: when communication connection with the intelligent equipment is established, generating a startup instruction, and outputting the startup instruction to the intelligent equipment, so that the intelligent equipment is started in response to the startup instruction; when the intelligent device is normally started and a target module instruction is detected, outputting a target test instruction corresponding to the target module instruction to the intelligent device in response to the target module instruction, so that the intelligent device performs shooting in response to the target test instruction and obtains a test image; storing the test image received from the intelligent device to a preset target storage space; and calling the test image in the target storage space through a preset test tool to test shooting imaging of the intelligent equipment. According to the invention, the imaging test efficiency of the intelligent equipment can be improved.

The invention belongs to the technical field of testing, particularly relates to an intelligent detection method for brightness based on a digital imaging technology, and aims to solve the problems that a traditional brightness measuring instrument is large in size, expensive, complex to operate, poor in brightness measuring accuracy and stability and the like. According to the method, digital imaging equipment with adjustable parameters, high resolution and wide dynamic range is selected, an adaptive lens and an optical filter are matched, a response function of the digital imaging equipment is constructed, a conversion relation between a gray value and the apparent brightness is established, and the apparent brightness is measured. The method specifically comprises the steps of setting parameters of digital imaging equipment, building a relation between a shooting standard light source and a target, collecting an image aiming at a target area, converting gray scale space correction and calculating the apparent brightness. In the process, the measurement precision is improved by setting white balance, image preprocessing, multiple times of image fusion shooting and the like. The method is easy and convenient to operate, low in cost, high in adaptability and capable of effectively improving measurement accuracy and stability.

This invention discloses a method for monitoring shear cracks in reinforced concrete beams based on digital image technology, comprising the following steps: Step 1, acquiring a surface image of a reinforced concrete beam specimen and using the DIC digital image detection method to obtain the principal tensile strain across the entire field in the reinforced concrete beam specimen; Step 2, generating a crack skeleton line corresponding to the crack based on the principal tensile strain across the entire field; Step 3, setting multiple sets of crack measurement reference points on both sides of the crack skeleton line and calculating the motion vector of the cracked area on both sides of each set of crack measurement reference points; Step 4, generating the overall motion of the corresponding crack based on the motion vectors of the multiple sets of crack measurement reference points and outputting the corresponding motion vector result image based on the motion. This invention also provides a device for monitoring shear cracks in reinforced concrete beams. The method provided by this invention can effectively assess the safety and residual life of concrete structures.

The invention relates to a microscope objective, which comprises a first lens group, a second lens group and a third lens group which are sequentially arranged from an object end to an image end along an optical axis direction. A lens combination is formed by a first lens group with positive focal power, a second lens group with positive focal power and a third lens group with negative focal power, and each of the second lens group and the third lens group at least comprises one positive focal power lens with the Abbe number larger than 80. The third lens group adopts negative focal power, so that the light transmitted by the front two groups of lenses can be reasonably corrected, the offset of the edge light under a large field of view is compensated, and the effective imaging field of view of the objective lens is effectively expanded; high-Abbe-number positive-focal-power lenses are introduced into the second lens group and the third lens group, so that the problems of aberration, imaging blurring and the like which are easy to occur under the conditions of large view field and long working distance are solved. Therefore, the microscope objective provided by the invention can improve the imaging quality under the requirement of a large field of view, and meets the requirement of a digital imaging technology on the microscope objective.

The invention relates to the technical field of digital imaging, in particular to a single-photon camera structure. Comprising a lens module, a superconducting detector module, a data processing module, a reading module, a gating module, a storage module, a main control end, an array unit, a time domain multiplexing unit and a reading frame unit. According to the present invention, a plurality of pixels are used to determine which pixel emits a signal, thereby reducing the need for readout lines, while enabling measurement of signals from the whole row or column of pixels at a time, rather than recording of data of each individual pixel, thereby greatly reducing the number of readout lines, and improving imaging quality and data processing efficiency through an algorithm.

A manufacturing flow of apparel such as jeans uses a laser to finish the products. The products are designed using a digital design tool, where photorealistic previews are generated in three dimensions and two dimensions. Imagery of the products are sent to retailers where customers can order the products, such as online orders. Imagery of the products are sent to factories where the products are finished. Based on the imagery, the factories make adjustments to the processes as needed so that the actual products will have an appearance as in the received imagery. As orders are received by the retailers, the factories can manufacture the desired products on demand, and the products can be delivered to customers.

The invention provides a non-stop online inspection method and device for an organic heat carrier pressure pipeline. The method provided by the invention comprises the following steps: determining a first candidate detection position according to the structure of a to-be-detected pressure pipeline; real-time operation information is determined based on the attribute information of the organic heat carrier conveyed by the to-be-tested pressure pipeline and the working condition information of the to-be-tested pressure pipeline; inputting the real-time operation information into a safety performance decay model of the pressure pipeline structure, obtaining a model prediction result based on the attribute information, and screening out an initial detection position from the first candidate detection positions according to the model prediction result; a state image of the initial detection position is obtained through a ray digital imaging technology, the state image is recognized based on a fouling detection standard, and a recognition result of the initial detection position is obtained; and determining the state of the to-be-measured pressure pipeline based on the identification result. The non-stop online inspection method and device for the organic heat carrier pressure pipeline are used for accurately and reliably completing online inspection of the organic heat carrier pressure pipeline.

The application relates to the field of digital imaging technology, in particular to a camera film simulation and digital filter linkage switching method. The method reads a target imaging parameter block according to a film mode dial lever position and a filter knob position, writes the target imaging parameter block into an inactive parameter buffer area, and sets a parameter complete flag after verification is completed; a switching ready flag is generated when the parameter complete flag is valid, wherein the film simulation switching needing entity operation confirmation is also subjected to the condition that an operation confirmation flag is valid; an image frame boundary switching parameter reading address is read, and a current configuration version number is latched when a shooting trigger is triggered. For an old version parameter block still referenced by a shooting task, the old version parameter block is migrated to a version parameter reservation area and a version mapping address is updated before an original buffer area is reused. The application can reduce abnormal frames caused by parameter batch taking effect, and keep the parameters used for shooting images consistent with preview parameters when a shooting trigger is triggered.

The invention discloses a stress path test method and system for a foundation pit excavation process, and the method comprises the steps: building a soil body sample model through an improved triaxial test system, and setting initial consolidation stress states sigma1 and sigma3 (the ratio is 1.0-3.0); calculating the lateral unloading amount; lateral grading unloading is carried out under the drainage condition, a stress-strain curve is obtained, and pore water pressure is recorded; deformation is monitored through a digital image technology, and parameters are updated; introducing a shear test to carry out an undrained shear test; and judging the trend of the shear strength index according to the data, adjusting the confining pressure, completing test analysis and obtaining a final index. The problems that in the prior art, obvious defects exist in the aspects of foundation pit excavation stress path simulation and shear strength parameter measurement, and the requirement of foundation pit engineering design for high-precision parameters is difficult to meet are solved.

The invention provides an X-ray digital ray image optimization method and system based on dual-algorithm collaborative optimization, and relates to the technical field of X-ray digital imaging, and the method comprises the steps: obtaining an original X-ray image; extracting a plurality of key parameters from the preprocessed original X-ray image in real time; constructing a target function by taking maximization of comprehensive image quality as a target, and carrying out two-stage key parameter collaborative optimization by adopting an improved particle swarm optimization algorithm and a grey wolf optimization algorithm under set hardware parameter constraints and exposure dose constraints to obtain optimized parameters; according to the optimization parameters, hardware working parameters of the high-voltage generator and the detector are synchronously adjusted, and a composite image enhancement algorithm is adopted to enhance the image to obtain an enhanced image; and carrying out identification verification on the enhanced image by utilizing AI intelligent identification, synchronously predicting the precision index of the image, and carrying out feedback, updating and optimization to realize the precision optimization of the original X-ray image. According to the invention, the image spatial resolution, the contrast ratio and the fine defect recognition rate are obviously improved.

The invention relates to the technical field of digital imaging, in particular to a digital ray imaging detection prediction model training and process parameter optimization method, which comprises the following steps: constructing a digital ray imaging detection prediction model, determining a non-linear region by a hidden layer of the prediction model based on the output value variation amplitude of the prediction model, setting a central point according to the non-linear region, and activating a function to mix and use a Gaussian kernel function and an inverse radial kernel function to fit the non-linear region; generating a training dataset training prediction model according to an orthogonal test dataset of digital ray imaging, and optimizing nodes of a hidden layer according to a mean square error corresponding to a sample in the training dataset and prediction precision in a training process; and using the random combination parameters to construct a test set to test the prediction model until the prediction performance of the prediction model meets the target requirement. Therefore, the problems of poor reliability, limited fitting capability and the like of the model for optimizing the digital ray imaging detection process parameters in the related technology are solved.

The application discloses a kind of digital direct imaging device exposure pattern position precision compensation method, it is related to digital imaging technical field, after the technical problem that the exposure pattern position precision each area is not consistent in prior art processing is solved;The present application does not need to help complex tool, exposure substrate is the material commonly used to generate laser direct imaging device, calibration condition and process are very simple;The alignment camera of the digital direct imaging device of the present application is a calibrated coordinate system itself, and the accurate position of the mark pattern in the exposed pattern can be identified, and each position of the exposed pattern can be compensated using different compensation parameters;The present application has low compensation cost, and does not need additional cost to improve and optimize hardware system by digital compensation method for CAM pattern;Moreover, compensation is free and flexible, and the CAM pattern is digitally compensated, and similar transformation, affine transformation and perspective transformation can be used flexibly according to specific requirements for each subdivided area.

The invention provides a digital image technology-based color fastness rating method for a single-color sample. The method comprises the following steps of: placing an original sample and a variable / stained sample on a white card which is visually uniform and consistent in parallel; judging whether the color of the variable / stained sample is uniform or not by using an automatic judgment method; if so, the measurement area is selected at the center position of the sample; if the color difference is not uniform, non-uniform parts are processed through digital images to judge whether the color difference is larger than a preset threshold value, and if the color difference is larger than the preset threshold value, the area with the most remarkable color change is adopted as the measurement area; if the color difference is smaller than or equal to the preset threshold value, the measurement area selects all test areas of the sample; and setting the test area of the original sample to be the same as the test area of the variable / stained sample, and evaluating the determined test area based on a digital image technology. According to the method, the non-uniform phenomenon occurring in the actual variable / stained sample is fully considered, the automatic selection of the test area is realized, and the rating accuracy is improved.

The present disclosure provides an image processing method and device, electronic equipment and storage medium, belonging to the field of image processing and digital imaging technology. The method comprises: determining a first image and a saliency map of the first image; performing Gaussian filtering on the first image according to the saliency map to obtain target residual information of pixels in the first image; and performing sharpening processing on the first image according to the target residual information to obtain a target image. Thus, the present scheme can exclude noise enhancement based on the saliency map, determine the target residual information of the first image through Gaussian filtering, and use the target residual information to sharpen the first image, which can improve the sharpening effect of the first image, effectively suppress high-frequency noise, and preserve the overall structural information of the image.

The invention provides an image processing method and device, electronic equipment and a storage medium, and belongs to the technical field of image processing and digital imaging. The method comprises the following steps: determining a first image and a saliency map of the first image; performing Gaussian filtering on the first image according to the saliency map to obtain target residual information of pixels in the first image; and sharpening the first image according to the target residual information to obtain a target image. Therefore, according to the scheme, noise elimination and enhancement based on the saliency map can be realized, the target residual information of the first image is determined through Gaussian filtering, and the first image is sharpened by using the target residual information, so that the sharpening effect of the first image can be improved, high-frequency noise can be effectively suppressed, and the overall structure information of the image is reserved.

This invention discloses a heat exchanger descaling system and method based on digital imaging technology. The method includes: a handheld operating unit; a rod having a proximal end and a distal end, the proximal end being connected to the handheld operating unit; a descaling head rotatably disposed at the distal end of the rod; a driving device for driving the descaling head to rotate; an image acquisition unit disposed at the distal end of the rod, its imaging area covering the area in front of the descaling head; a display device disposed on the handheld operating unit and electrically connected to the image acquisition unit for real-time display of images acquired by the image acquisition unit; and a dosing pipeline arranged along the rod, having a dosing outlet located at the distal end of the rod. This application integrates three core functions—image observation, chemical dosing, and mechanical descaling—into a handheld device, greatly simplifying operation, shortening cleaning time, and reducing labor costs. Furthermore, the real-time feedback from the image acquisition unit and the display device enables visualized operation and precise cleaning.

The present invention relates to the technical field of mine shaft monitoring, and discloses a shaft monitoring method and a shaft monitoring device. The shaft monitoring method comprises: obtaining an original model and original image of the shaft; controlling a three-dimensional laser scanning device and an image acquisition device to move axially along the shaft to obtain point cloud data and monitoring images of the shaft, and determining a monitoring model based on the point cloud data; and comparing the original model with the monitoring model, and comparing the original image with the monitoring image, to determine the deformation data of the shaft. By modeling the point cloud data collected by laser to macroscopically analyze the deformation of the shaft around the entire circumference, and performing microscopic strain and crack analysis of the shaft using digital imaging technology, global monitoring of the shaft is achieved, breaking through the limitations of traditional point sensor monitoring, achieving real-time analysis of deformation distribution across the entire cross-section, expanding the monitoring coverage, reducing monitoring blind spots, and improving the accuracy of monitoring results, thus providing an effective basis for predicting shaft instability and damage.

The invention discloses a method and a system for measuring shear strength parameters of a non-uniform ice-water accumulation soil-rock mixture, the non-uniform ice-water accumulation soil-rock mixture is subjected to soil and stone classification based on the characteristics of the non-uniform ice-water accumulation soil-rock mixture, the stone content ratio is obtained based on a digital imaging technology, and then the shear strength parameters of the non-uniform ice-water accumulation soil-rock mixture are measured based on the Mohr-Coulomb shear strength theory. The method comprises the following steps: constructing a comprehensive internal friction coefficient calculation formula of soil and stone by combining a shear strength equality principle, establishing a shear model of the non-uniform ice-water accumulation soil-rock mixture, and finally performing stress analysis based on the shear model to obtain a shear strength parameter calculation model of the non-uniform ice-water accumulation soil-rock mixture. By utilizing the calculation model, the shear strength parameter, namely the internal friction coefficient, of the non-uniform ice water accumulation soil-rock mixture can be quickly and accurately obtained, and the problem that the shear strength parameter of the special accumulation is difficult to directly test and obtain due to irregularity, non-uniformity and large particle size is effectively solved.

The present application provides a method and device for on-line inspection of an organic heat carrier pressure pipeline without shutting down the machine. The method provided by the present application includes: determining a first candidate detection position according to the structure of the pressure pipeline to be measured; determining real-time operation information based on the attribute information of the organic heat carrier transported by the pressure pipeline to be measured and the working condition information of the pressure pipeline to be measured; inputting the real-time operation information into a pressure pipeline structure safety performance decay model, obtaining a model prediction result based on the attribute information, and screening out an initial detection position from the first candidate detection positions according to the model prediction result; obtaining a state image of the initial detection position through ray digital imaging technology, identifying the state image based on the fouling detection standard, and obtaining an identification result of the initial detection position; determining the state of the pressure pipeline to be measured based on the identification result. The method and device for on-line inspection of an organic heat carrier pressure pipeline provided by the present application are used to accurately and reliably complete the on-line inspection of the organic heat carrier pressure pipeline.