43 results about "Exposure data" patented technology

The invention discloses a combined denoising and demosaicing method for a low-exposure original image under low light, and the method is divided into two stages: in the first stage, introducing a high and low frequency fusion module based on wavelet transform, and generating relatively clean pseudo long exposure data to reduce noise; and in the second stage, through a color space attention subnet, image reconstruction is carried out by using the pseudo long exposure data generated in the first stage, the color is recovered, and texture details are enhanced. In addition, the invention also provides a wavelet loss function to balance detail recovery and noise suppression, and discusses the influence of three different training strategies on the performance of the model. Experimental results show that the method provided by the invention is superior to most advanced algorithms in the aspects of quantitative indexes, color accuracy, detail retention and the like.

The invention discloses a direct writing type photoetching machine exposure control method and device, a medium and a direct writing type photoetching machine, and the direct writing type photoetching machine exposure control method comprises the following steps: obtaining exposure data; digital micromirror control information is obtained according to the exposure data and a uniformity compensation template, and the uniformity compensation template is determined according to the influence value of the DMD digital micromirror on the photoresist thickness in the effective area of the DMD digital micromirror array and the corresponding photoresist thickness difference value; and controlling the DMD digital micromirror array according to the digital micromirror control information. According to the method disclosed by the invention, the exposure uniformity can be more finely controlled, the non-uniform glue thickness caused by factors such as equipment error and non-uniform light source is reduced, the precision of the photoetching process and the line width size consistency are improved, meanwhile, the high cost of replacing hardware and repeatedly exposing is avoided, the production efficiency and the yield are improved, and the production cost is reduced.

The invention discloses a method and terminal for detecting glass defect characteristics, and the method comprises the steps: carrying out the line-by-line scanning of glass through employing a line-scan digital camera, and switching a preset type of light source condition for each line of image during the scanning; respectively acquiring exposure data of each row of images under a corresponding light source condition; splitting the collected exposure data into a plurality of sub-images according to light source conditions, and splicing image lines under each light source condition to generate corresponding independent light source images; based on each independent light source image, extracting an image with clearest defect features as an optimal image; and performing defect detection on the optimal image by using a deep learning model, and outputting defect positions and types.

The invention relates to a method, a device and equipment for reconstructing a space target image in a dynamic observation scene, and the method comprises the steps: sequentially dividing sequence images in a dynamic sequence multi-exposure data set into a plurality of groups of low-dynamic-range sub-image sequences in a manner that three images form one group; wherein the low dynamic range sub-image sequences comprise three sequence images with exposure degrees from low to high and different space target postures, generating corresponding static sub-image sequences, and training the space target image reconstruction network by using multiple groups of low dynamic range sub-image sequences and the corresponding static sub-image sequences to obtain a trained space target image reconstruction network. The space target image reconstruction network comprises a feature extraction unit, a feature deformable alignment unit and a feature fusion reconstruction unit, and an observation sequence image of a space target in a dynamic observation scene can generate a high dynamic range image of the space target by using the trained space target image reconstruction network. By adopting the method, efficient HDR image reconstruction in a dynamic scene can be realized.

The invention discloses a method for determining the optimal exposure focal length difference, which comprises the following steps: obtaining exposure data sets of various types of semiconductor products, the exposure data sets comprising the optimal exposure focal length difference and pattern spacing of the corresponding type of products, the optimal exposure focal length difference is the difference value of the maximum exposure focal length of the exposure process window in the two exposure processes; fitting according to the exposure data set to obtain a mapping relationship, wherein the mapping relationship is a relationship between the optimal exposure focal length and the pattern spacing; and determining the optimal exposure focal length of the target type product according to the mapping relation and the pattern spacing of the target product. According to the method, the exposure data sets of the semiconductor products of various types are obtained, the mapping relation between the optimal exposure focal length difference and the pattern spacing is obtained through fitting according to the exposure data sets, and then the optimal exposure focal length difference of the product in two exposure processes is determined according to the mapping relation and the pattern spacing of the product of the target type.

The invention provides an exposure apparatus, an exposure method, and an alignment method. In an exposure device provided with a stage or the like, proper alignment is performed in consideration of a linear error generated along with movement of the stage. An exposure device (10) is provided with a pair of calibration scales (62, 64) on which reference marks (CM) facing each other in an X direction (main scanning direction) are disposed, and the reference marks (CM) facing each other are imaged by an alignment camera (80) while a stage (50) moves. The amount of linear error in the amount of movement of the stage (50) is detected on the basis of the amount of misalignment of the reference mark (CM) in the captured image. Then, scale correction processing is performed on the exposure data in accordance with the calculated linear error amount.

The invention relates to the field of image processing, and relates to a high-dynamic image processing method, a chip, equipment, a medium and a program product. The method comprises the following steps: acquiring an original image set comprising an abnormal exposure frame and a plurality of normal exposure frames, and selecting an alignment reference frame from the plurality of normal exposure frames; performing alignment processing on the normal exposure frames which are not selected and the alignment reference frame to generate a ghosting region positioning mask; performing ghosting detection according to the plurality of normal exposure frames and the abnormal exposure frames to obtain an initial ghosting region; determining a target ghosting region according to the ghosting region positioning mask and the initial ghosting region, and selecting a compensation reference frame according to exposure data of the abnormal exposure frame and the normal exposure frame in the target ghosting region; and determining a fusion weight corresponding to each frame in the original image set according to the compensation reference frame, and processing the original image set according to the fusion weight to obtain a target high-dynamic image. By adopting the method, the high-dynamic image generation quality can be improved.

The invention discloses a photoetching process optimization method of a flat-panel display. The photoetching process optimization method comprises the following steps: completing first photomask manufacturing by using test patterns with different specifications and dimensions along with a current product; collecting exposure data of the first photomask under a plurality of different exposure energy conditions, and establishing a process window model; by using the process window model, giving the optimal exposure energy of the next product and a revised photomask layout under the condition that the optimal exposure energy is increased by 10-50%, and finishing the manufacturing of a second photomask along with the product; performing an exposure test on the second photomask according to each exposure energy condition, collecting and sorting each exposure energy and a critical dimension value of the wafer after the exposure energy is changed by a preset proportion, and obtaining a plurality of linear relational expressions about the change of the critical dimension along with the exposure energy; and according to the critical dimension value and the slope value of each linear relation, obtaining a relation curve graph of the slope of the linear relation along with the change of the exposure energy for selecting the final exposure energy.

The embodiment of the invention discloses a multi-lens shooting system. The multi-lens shooting system comprises a control assembly, a double-rate synchronous dynamic random access memory DDR, a first processing assembly comprising n image front-end processing units IFPU, a second processing assembly comprising m high dynamic range imaging HDR sensors, and an HDR pipeline arranged on any IFPU, and n and m are integers greater than 0; and the control assembly is used for performing opening and closing control on a connection circuit between the IFPU and the corresponding HDR sensor, controlling the IFPU to output corresponding exposure data to at least one of the DDR pipeline and the HDR pipeline, and controlling the HDR pipeline to perform hardware HDR processing on at least one path of exposure data. According to the invention, the purpose of HDR multi-camera video recording is realized by designing and multiplexing a set of HDR hardware based on time division, and on the premise of ensuring a certain rate, the chip area is effectively reduced, and the construction cost is reduced.

The invention relates to the field of expressway electromechanical equipment, in particular to an expressway electromechanical equipment multi-parameter cooperative adjustment system, which realizes fine monitoring and display control of different road sections of an expressway through cooperative work of a video acquisition module, a video divider, a cooperative adjustment module, an adjustment module and an LED dimming control module. According to the system, the adaptive capacity to a complex environment is improved by utilizing a region segmentation type dynamic sensing technology, the data acquisition module is responsible for collecting exposure data of the video acquisition module and related information of the LED controller, the control module coordinates operation of all the modules, the video switching module outputs an exposure adjustment video image according to an instruction of the control module, and the control module controls the control module to operate. The cooperative adjustment module processes the brightness information, calculates the brightness variation and the specific value of the exposure adjustment video image, and feeds the information back to the video acquisition module to adjust the exposure, so that the intelligence and the response speed of the system are remarkably improved, and the operation safety and efficiency of the expressway are enhanced.

The invention relates to the technical field of printed circuit board manufacturing, and discloses a manufacturing method of a printed circuit board and the printed circuit board, and the manufacturing method of the printed circuit board comprises the steps: providing a core board which comprises an insulating dielectric layer and a first metal layer; arranging a first photosensitive anti-corrosion film on the first metal layer; performing exposure treatment on the first photosensitive anti-corrosion film by using first exposure data, the first exposure data comprising a circuit pattern and a process pattern, the process pattern comprising a detection pattern, and the detection pattern comprising an isolation pattern and an identification pattern; and if the orthographic projection of the exposure detection part on the surface, deviating from the insulating dielectric layer, of the first metal layer is incomplete relative to the identification pattern, determining that the exposure offset of the first photosensitive anti-corrosion film is out of tolerance. The manufacturing method of the printed circuit board and the printed circuit board provided by the invention are used for solving the problems that a lot of time needs to be consumed for manually detecting the pattern exposure offset and a wet film / dry film of a board surface is easily damaged in the detection process in the related technology.

The application provides an exposure data determination method, device and equipment and a storage medium. The method comprises the following steps: obtaining historical bidding data, historical exposure data, a plurality of expected bidding data and historical exposure index data of a to-be-launched object corresponding to the historical bidding data of a target object; determining expected exposure index data of the to-be-launched object corresponding to each of the plurality of expected bidding data; determining fitting parameters according to the expected exposure index data and the plurality of expected bidding data; fitting the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bidding data; and determining exposure data of the target object under different bidding data within a preset time period based on the historical exposure index data, the exposure index fitting data and the historical exposure data. The application can cover exposure estimation of different bidding data, improve the accuracy of exposure data estimation, and facilitate accurate recommendation of objects based on high-accuracy exposure estimation.

The application discloses a wafer surface type detection and compensation method, system, device, medium and program, and the method comprises the following steps: scanning a wafer to obtain a plurality of groups of original data; filtering all the original data to obtain scanning strip data; exposing the wafer and dynamically compensating the scanning strip data of the exposure position by a preset compensation value to obtain exposure strip data; equally spacing sampling the exposure strip data; assigning the exposure data obtained by the equally spacing sampling to the preset compensation value to compensate the height of the wafer in the wafer exposure step, and detecting the wafer surface type by using the equally spacing sampled exposure strip data. The technical scheme provided by the application can solve the technical problem that the wafer surface type detection in the prior art has a large error.

The invention discloses a shooting method and device, electronic equipment and a readable storage medium, and belongs to the technical field of image processing. The shooting method comprises the steps that in the zooming process of the electronic equipment, first exposure data are obtained, and the first exposure data are exposure data determined according to image data collected by at least one of a first camera module and a second camera module; carrying out convergence processing on the first exposure data through an exposure algorithm parameter of the first camera module to obtain second exposure data; calculating a first exposure parameter and a second exposure parameter according to the second exposure data; and controlling the first camera module to perform exposure according to the first exposure parameter, and controlling the second camera module to perform exposure according to the second exposure parameter.

The invention relates to the technical field of internet information, can be applied to the fields of financial advertisement putting, user behavior analysis and the like, and provides a page component exposure information automatic capturing method and device, a medium and equipment. When rolling stops or the rolling speed is lower than a threshold value, the current position of each assembly in the window is calculated according to the rolling distance and direction; for the component element, marking the component element as an exposure state when the component element enters the visible range for the first time, and recording an entry timestamp; if the video is marked and is still in the visible range, updating the staying duration; if the user leaves the visual range, recording a leaving timestamp and calculating a single-time stay duration; the staying duration is accumulated as the total staying duration during multiple times of entering and exiting, and when the total duration exceeds the preset minimum effective duration, the data are marked as effective exposure data, and the effective exposure data are encrypted in batches through a buffer queue and then reported to a server. By automatically capturing and analyzing the component exposure information, manual statistical errors can be reduced, and the data accuracy is improved.

An embodiment of the present invention provides a method, device, electronic device, and medium for processing a rendered image. The method includes: obtaining automatic exposure data pre-baked based on preset sampling points in a virtual scene; determining target exposure data for the current frame of the rendered image from the automatic exposure data of each preset sampling point according to the virtual camera position and current observation direction of the current frame of the rendered image; and performing exposure control on the rendered virtual scene according to the target exposure data to obtain a final rendered image. By utilizing a method of exchanging space for time, the exposure data for exposure control is calculated based on the direct reading of pre-baked data using the virtual camera position and observation direction. This reduces video memory consumption and computational complexity, making the final rendered image on the device more realistic and clear, and enabling the display of human-eye-adaptive images on high-energy-consuming mobile devices.

The present invention relates to the field of electromechanical equipment for highways, and specifically to a multi-parameter coordinated adjustment system for electromechanical equipment for highways. The system achieves refined monitoring and display control of different sections of highways through the coordinated work of a video acquisition module, a video splitter, a coordinated adjustment module, an adjustment module, and an LED dimming control module. The system utilizes regional segmentation dynamic perception technology to improve its adaptability to complex environments. The data acquisition module is responsible for collecting exposure data from the video acquisition module and related information from an LED controller, while the control module coordinates the operations of the various modules. The video switching module outputs an exposure-adjusted video image according to instructions from the control module. The coordinated adjustment module not only processes brightness information but also calculates the brightness change and ratio of the exposure-adjusted video image and feeds this information back to the video acquisition module to adjust the exposure. This significantly improves the intelligence and response speed of the system and enhances the operational safety and efficiency of highways.

Embodiments of the present application provide a sample data generation method and device, for the received user behavior data, real-time pre-processing of user behavior data into user behavior objects, and the user behavior object is stored in association with the unique identifier corresponding to the user behavior data; for the received exposure data including the display content and its feature data, the display content in the exposure data is pre-processed into exposure data objects, and the exposure data objects are stored in association with the unique identifier corresponding to the exposure data; and, the feature data of the display content in the exposure data is stored in association with the unique identifier corresponding to the exposure data; at the end of each unique identifier corresponding time window, all user behavior objects, exposure data objects and feature data associated with the unique identifier in the time window are obtained, and all user behavior objects, exposure data objects and feature data obtained are spliced into sample data corresponding to the unique identifier associated with the time window.

This application relates to an exposure data adjustment method, apparatus, and computer device. The method includes: determining histogram data and image quality data of a current image; determining first exposure data of the current image based on the histogram data; and determining second exposure data of the current image based on the image quality data; fusing the first exposure data and the second exposure data to obtain desired exposure data; and adjusting the first exposure data based on the difference between the first exposure data and the desired exposure data. By employing the above technical solution, the accuracy of the first exposure data adjustment result is improved.

The invention discloses a three-dimensional visual high-precision real-time positioning method and system for a single agent, and belongs to the technical field of visual localization, and the method comprises the steps: obtaining visual camera exposure real-time data of the single agent, analyzing a visual camera exposure characterization factor, and judging a visual camera exposure execution scheme of the single agent; performing single-agent visual camera exposure adjustment, judging a single-agent visual camera feature compression execution scheme, judging a single-agent visual camera fuzzy execution scheme, analyzing a visual camera high-frequency loss characterization factor to obtain a single-agent visual camera feature execution scheme, performing image partitioning, and performing image segmentation; and performing visual camera feature point adjustment of the single agent. According to the method, the exposure of the visual camera is analyzed and adjusted, so that the quality of a three-dimensional reconstructed image is guaranteed, the environmental adaptability is enhanced, and high-precision real-time positioning is guaranteed. And feature adjustment is carried out to improve the image feature quality so as to optimize the three-dimensional visual positioning precision and meet the real-time performance of positioning.

The invention discloses a wafer surface type detection and compensation method, system and device, a medium and a program, and the method comprises the steps: scanning a wafer, and obtaining a plurality of groups of original data; performing filtering processing on all the original data to obtain scanning strip data; exposing the wafer, and performing dynamic compensation of a preset compensation value on the scanning strip data of the exposure position to obtain exposure strip data; carrying out equal-interval sampling on the exposure strip data; and endowing a preset compensation value to the exposure data sampled at equal intervals so as to compensate the height of the wafer in the step of exposing the wafer, and carrying out surface type detection on the wafer by utilizing the exposure stripe data sampled at equal intervals. According to the technical scheme provided by the invention, the technical problem that the detection of the surface type of the wafer in the prior art has a relatively large error can be solved.

Method (and apparatus) for producing a 3D target structure in lithographic material. Focus region of a laser writing beam travels through a scanning manifold through the lithographic material. In the focus region of the laser writing beam, an exposure dose is irradiated into the lithographic material, and a structure region is locally defined. At least one exposure data set which represents a local exposure dose for the scan manifold as a function of location is determined. A structure which approximates the target structure is defined based on at least one exposure data set. This structure is analyzed and at least one analysis data set which represents the analyzed structure is determined. Deviation data set which represents deviations of the already defined structure from the target structure is determined. At least one correction exposure data set is determined. Correction structure based on the at least one correction exposure data set is defined.

The utility model belongs to the technical field of PCBs (printed circuit boards), and discloses an optical communication board with a segmented golden finger process. The optical communication board comprises P golden finger arrangement unit structures, each golden finger arrangement unit structure is spaced by N-1 columns of golden fingers through N photosensitive oil exposure data areas; m first photosensitive oil strips transversely penetrate through the (N-1) columns of golden fingers; the N photosensitive oil exposure data areas are exposed through photosensitive oil in the longitudinal direction, 3M second photosensitive oil strips are developed through the photosensitive oil, and the second photosensitive oil strips are communicated with the first photosensitive oil strips. And the 3M second photosensitive oil strips are subjected to golden finger electrical connection, selective dry film exposure, selective dry film development and alkaline etching, and then the optical communication board containing the segmented golden finger process is prepared. According to the utility model, the adhesive force of the photosensitive oil is enhanced, and the reject ratio that the photosensitive oil is easy to fall off is reduced to 0%.

To provide an imaging system capable of performing remote image display with high quality.SOLUTION: An imaging system 200 comprises: a display device 100 with a display panel P; and an imaging apparatus 300 which is disposed with the display panel P sandwiched between itself and a subject PA and captures an image of the subject PA transmitted through the display panel P. The imaging apparatus 300 acquires exposure data of a color different from a display color of the display device 100 and generates imaging data of the subject PA.SELECTED DRAWING: Figure 1

The invention provides a method for optimizing the exposure effect of an endoscope based on color features, and the method comprises the steps: embedding a multi-scale color feature pyramid in an encoder-decoder structure to distinguish and represent different exposure regions, and applying different convolution kernels to the color features of different scales, according to the method, the region recognition capability of an encoder-decoder structure is improved, efficient multi-scale attention is introduced, and the calculation overhead is reduced while the feature extraction quality is improved. In order to adaptively restore the exposure level of the image, the method adopts a Retinex algorithm to perform double-branch enhancement on the image. According to the method, on a laparoscope overexposure data set, the PNSR index reaches 21.06; the NIQE index on a real laryngoscope data set reaches 41.79, which is superior to that of other existing methods. The method provides a new thought for the development of a low-quality endoscope image enhancement method.

The embodiment of the invention discloses an image generation method and a related device, and the method is applied to a processor of a vehicle electronic rearview mirror system, and comprises the steps: obtaining a first long-frame image and a first short-frame image collected by an image collection device; fusing the first long-frame image and the first short-frame image according to a preset exposure ratio to obtain a first composite image; determining first brightness distribution histogram data of the first short frame image and second brightness distribution histogram data of the first composite image; determining a target exposure ratio according to the first brightness distribution histogram data, the second brightness distribution histogram data, the first exposure duration of the first long frame image, the second exposure duration of the first short frame image and historical exposure data; and fusing the first long-frame image and the first short-frame image according to the target exposure ratio to generate a target composite image. According to the method, the exposure ratio of the image frame can be adaptively regulated and controlled in different dynamic range scenes, and the imaging quality of the streaming media rearview mirror is improved.

The invention belongs to the technical field of image fusion, and particularly relates to a multi-modal image fusion method based on Swi n-MOE, and the method comprises the following steps: 1, preparing training data; a multi-focus data set, a multi-exposure data set, an infrared image data set and a visible light image data set are selected, the data sets are divided into a training set, a verification set and a test set, and original images in the multi-focus data set and the multi-exposure data set and corresponding labels of the original images are preprocessed. According to the invention, a dual-channel adaptive attention fusion architecture and a decoder integrated with a hybrid expert system are innovatively designed, the limitation that an existing fusion model only aims at a single task is broken through, the information collaboration advantage in multi-task fusion is fully excavated, joint optimization of multiple fusion tasks is realized, and the fusion efficiency is improved. And knowledge migration and complementation among different fusion data sets are promoted.

According to an aspect, an imaging system includes: a display device that includes a display panel on which a plurality of pixels are arranged in a first direction and a second direction intersecting the first direction and a light source configured to emit light to a side surface of the display panel; and an imaging device that is provided with the display panel interposed between the imaging device and a subject and is configured to capture an image of the subject transmitted through the display panel. The display device is configured to have: a first period in which pixel data is written to the pixels; and a second period in which the light source emits the light after the first period. The imaging device is configured to generate imaged data of the subject using exposure data acquired during the first period.

The invention relates to a photographing method and device, electronic equipment and a storage medium, and the photographing method comprises the steps: responding to a preset photographing operation of a user, executing global exposure, and obtaining a plurality of target exposure data under different exposure durations in the global exposure process; based on each target exposure data, generating an exposure image corresponding to each target exposure data; and generating a target image based on each exposure image, the target image having a high dynamic range effect. The exposure images corresponding to the multiple target exposure data are generated by acquiring the multiple target exposure data under different exposure durations in the global exposure process, so that the inter-frame difference among the multiple exposure images is reduced, the problems of ghosting, ghosting and the like of the target image with a high dynamic range effect are avoided, and the user experience is improved.