35 results about "Image reduction" patented technology

The application provides a differential-based white light lensless single-frame weakly conjugate reconstruction method, which can realize weakly conjugate image reduction and improve single-frame imaging resolution in a white light lensless imaging system without using additional elements and complex algorithms. The method comprises the following steps: step one, obtaining spectral distribution information of a system light source by using a spectrometer and performing differential processing to obtain a reconstruction wavelength; step two, performing preprocessing on a collected single-frame image by using a hologram average value reduction method; step three, generating light intensity diagrams of different defocusing surfaces by using an angular spectrum propagation formula, and determining a defocusing distance range based on a definition discrimination factor; and step four, calculating differential distribution on different focal planes in the distance range obtained in step three based on numerical differentiation, and obtaining a final result by selection. The application can reduce the requirement of spectral width of a traditional lensless microscope, effectively reduce the cost of the system, improve the imaging resolution of the white light lensless microscope, and reduce the weakly conjugate image in the case of single-frame image collection.

This invention provides an automatic 3D coronary artery segmentation method based on a graph attention neural network, belonging to the field of medical image segmentation technology. It solves the technical problems of traditional methods not fully considering the high noise and uneven grayscale in medical images. The technical solution includes the following steps: Step 1, processing the image by adjusting the window width and window level; Step 2, reducing the image size to 128×128×64; Step 3, performing dilation on the image obtained in Step 2; Step 4, establishing a graph structure based on the image obtained in Step 2; Step 5, segmenting the block image using a Vnet3D network; Step 6, fusing the coronary artery images obtained in Steps 4 and 5 to obtain the final segmented coronary artery image. The beneficial effects of this invention are: ensuring high segmentation accuracy and robustness for coronary arteries.

The application discloses a kind of based on visual device transmission line external damage hidden danger early warning method, and the method steps are as follows: S1 obtains the transmission line image containing large construction machinery and pre-processes;S2 is to the pre-processed image Shadow synthesis obtains enhanced image, reduces enhanced image, and obtains fusion feature image by fusing the features of three;S3 is constructed and is trained target recognition model with fusion feature image, and the optimal model is obtained by optimizing parameters using optimization algorithm;S4 visual device obtains real-time image, and optimal model identification, if mechanical is identified, then progress S5;S5 millimeter wave radar scans three-dimensional point cloud data, projection two-dimensional is compared with identification result, and if it coincides, then progress S6;S6 preset safety distance, calculate the height of machinery in combination with point cloud data and projection area, and if it exceeds safety distance, then alarm.The application can realize all-weather unattended, accurately identify machinery, filter invalid early warning, reduce missed detection, reduce the risk of early warning failure, avoid line trip-out and other accidents, and protect the safety of transmission line.

The application relates to a medical instrument operating device and a surgical robot, wherein the medical instrument operating device realizes swinging in each direction around an RCM point and linear motion of a medical instrument through swinging and rotating of first and second support arms and passive joints, meets the requirements of different visual fields and image zooming in or out during surgery, and facilitates linear extraction of an endoscope from a patient's body without additional linear motion mechanisms. Therefore, active joints and linear motion mechanisms are not needed between the passive joints and the medical instrument, so that the medical instrument does not have a tendency to move into the abdominal cavity. Even if the first to fourth active joints fail and lose support for the passive joints, the passive joints will be dragged to move away from the puncture device, so that the medical instrument has a tendency to exit the abdominal cavity, damage to intracavity tissues is avoided, and safety is improved.

Embodiments of the present application disclose a gesture recognition method and device, and a storage medium, including: in a case where a to-be-processed image is acquired, processing the to-be-processed image according to a plurality of preset image reduction rules to obtain a plurality of reduced to-be-processed images; performing hand detection on the plurality of reduced to-be-processed images to obtain a hand detection frame; acquiring an image in the hand detection frame from the to-be-processed image to obtain a hand region image; and determining a target gesture in the to-be-processed image according to the hand region image.

This object detection device detects an object from each of a prescribed number of surfaces for each frame from a divided image obtained by dividing an image of individual frames included in a video into a plurality of images and a surface corresponding to individual reduced images obtained by reducing the entire image, synthesizes object detection results for each of the prescribed number of surfaces, and determines a prescribed number on the basis of an index related to the difference between the input frame rate of the video and the frame rate of the object detection process.

The application provides a large-view-field compact reflective projection objective lens, and belongs to the technical field of semiconductor manufacturing lithography. The projection objective lens system comprises six aspheric mirrors. After a light source irradiates a mask, the light source sequentially passes through a first mirror M1, a second mirror M2, an aperture, a third mirror M3, a fourth mirror M4, a fifth mirror M5 and a sixth mirror M6. The aperture is located between the second mirror M2 and the third mirror M3. Finally, the light source is imaged on a wafer surface, and the projection objective lens system realizes an image reduction ratio of 0.2. In the embodiment of the application, the light path does not have a light blocking phenomenon and the structure is compact. The main optical parameters are as follows: the numerical aperture on the image side is 0.2, the object field on the object side is 10mm, and the total length of the system is 1280mm.

The present application relates to remote sensing image processing technical field, especially to a kind of high bit depth remote sensing image reduction and enhancement method based on three levels optimization, comprising: cutting to remote sensing image, and screening out representative local sample block;Representative local sample block is decoupled and image enhancement in Lab space;With enhancement parameter as optimization variable, construct hierarchical objective function, and obtain optimal parameter by optimization algorithm optimization, and generate enhanced image by optimal parameter full-width processing original image;The whole scene enhanced image obtained is corrected.The present application is cooperated between representative local sample block construction, Lab decoupled enhancement and optimization learning, whole scene correction, realizes three levels closed loop operation of sample layer, parameter layer, whole scene layer, so that the last obtained high bit depth optical remote sensing image has good brightness level, detail distinguishability, display balance and color naturalness whole scene enhanced result.

The present application relates to the technical field of image processing, in particular to a grid-based image matching positioning method, system, device and medium; the method divides the input image into grids, performs template matching of the image according to the grid position, and reduces the input image matched to the smallest range, greatly reducing the number of matching comparisons, improving the running efficiency of the RPA process and the accuracy of image positioning; by setting a priority quadrant, the efficiency of positioning matching is improved, the input image is reduced to the smallest range, the number of matching is reduced under different resolutions, and the running efficiency and positioning accuracy are improved.

A solution for analyzing images of a scene captured under different visibility conditions includes obtaining images of a scene captured by one or more cameras and, for each image, obtaining an indication of an actual or assumed visibility (distance) at the scene when the image was captured; selecting, based on the visibility, an artificial neural network (ANN) architecture from a plurality of ANN architectures, wherein the ANN architectures are each trained for image analysis but configured for different input image resolutions, and analyzing the image using the selected ANN architecture. If the selected ANN architecture has a lower input image resolution than the image, the image may be downscaled to match the input image resolution of the selected ANN architecture.

The invention discloses a power transmission line external damage hidden danger early warning method based on a visual device. The method comprises the following steps: S1, obtaining and preprocessing a power transmission line image containing a large construction machine; s2, performing shadow synthesis on the preprocessed image to obtain an enhanced image, reducing the enhanced image, and fusing the features of the three to obtain a fused feature map; s3, constructing and training a target recognition model by using the fused feature map, and optimizing parameters by using an optimization algorithm to obtain an optimal model; s4, the visualization device obtains a real-time image, optimal model recognition is carried out, and if a machine is recognized, S5 is carried out; s5, scanning the three-dimensional point cloud data by the millimeter wave radar, comparing the projected two-dimensional point cloud data with an identification result, and if the projected two-dimensional point cloud data are And S6, presetting a safe distance, combining the point cloud data and the projection area to calculate the mechanical height, and giving an alarm if the safe distance is exceeded. According to the invention, all-weather unattended operation can be realized, machinery can be accurately identified, invalid early warning can be filtered, leak detection can be reduced, early warning failure risks can be reduced, accidents such as line tripping can be avoided, and the safety of power transmission lines can be guaranteed.

The application discloses a method and device for acquiring a fluorescent region image in a biological section, and low-power fluorescent objective lenses and high-power fluorescent objective lenses are integrally arranged on an electric objective converter. The two kinds of fluorescent objective lenses can be flexibly switched in the same light path through the electric objective converter. The low-power fluorescent objective lenses can be used to scan (image acquisition) and splice a complete tissue region image of the biological section under illumination of a fluorescent excitation light source, and X and Y coordinate values of the image boundary of the tissue region generating fluorescence in the biological section are calculated. After the region needing to be scanned is determined, the high-power fluorescent objective lenses are used to accurately scan the tissue region generating fluorescence in the biological section and splice the image, so that a complete fluorescent region image in the biological section is obtained, the scanning region is reduced, and the work efficiency is improved.

The present invention makes it possible to further reduce a bit rate while suppressing and compensating an information loss due to quality degradation in video data and image data.　A conversion processing device 20 disposed on the transmission side comprises: an object detection unit 21 that detects an object from an image captured by an imaging device 10 and generates object information; a resizing unit 23 that compares the object information with a predetermined threshold to determine whether or not the degree of an adverse effect due to an information loss when the image is reduced exceeds a standard, if the degree of the adverse effect due to the information loss is determined to exceed the standard, does not reduce the image, and if not, reduces the image; and an encoding unit 24 that encodes the image processed by the resizing unit 23.

The application provides a fire anti-interference detection method and device based on flame jitter characteristics, and the method comprises the following steps: acquiring a video to be detected; reading two adjacent frames of images of the video to be detected in sequence, and reducing the two adjacent frames of images to obtain a matrix array of the reduced two adjacent frames of images; segmenting the matrix array of the reduced two adjacent frames of images to obtain a matrix array of the segmented images; performing HSV color detection on the matrix array of the segmented images to obtain a matrix array containing suspected flame images; performing boundary extraction on the matrix array containing suspected flame images to obtain a matrix array of a boundary binary image; calculating a matrix array of a flame edge change image according to the matrix array of the boundary binary image; calculating an edge change rate of the matrix array of the flame edge change image; and judging whether to send a fire warning signal according to the edge change rate. The application can quickly detect fire flames, is simple in operation, has strong anti-interference performance, and has high accuracy.

The embodiment of the invention discloses an image processing method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of image processing. The method comprises the following steps: acquiring an original image, and shrinking the original image into a shrunk image; segmenting the original image into a plurality of block images; determining the size of a convolution kernel, and determining a plurality of edge pixel points in the plurality of block images according to the size of the convolution kernel; according to the coordinates of the edge pixel points and the size of the convolution kernel, determining a first local neighborhood of the edge pixel points in the block image and a second local neighborhood of the edge pixel points in the reduced image; performing convolution processing on the edge pixel points according to the first local neighborhood and the second local neighborhood, and performing lookup table LUT adjustment processing on the edge pixel points according to the reduced image to obtain target edge pixel points; and determining the target edge pixel points as the pixel points in the enhanced block image corresponding to the block image. According to the scheme, the problem of inconsistent boundary effects during image enhancement can be efficiently solved.

According to implementations of the present disclosure, a scheme for image scaling is proposed. According to the scheme, an input image having a first resolution is obtained. An output image having a second resolution and high-frequency information subject to a predetermined distribution are generated based on the input image by using a trained invertible neural network, where the first resolution is higher than the second resolution, and the input image and the output image have the same semantics. Furthermore, another input image having the second resolution is obtained. Another output image having the first resolution is generated based on the other input image and the high-frequency information subject to the predetermined distribution by using an inverse network of the invertible neural network, where the other input image and the other output image have the same semantics. The scheme is capable of scaling down original images into low-resolution images with the same semantics and visually pleasing, and is capable of reconstructing high-quality high-resolution images from the low-resolution images.

An object detection device that detects an object from an image included in a moving image includes: an acquisition unit configured to acquire the image from the moving image; a number-of-faces setting unit configured to set a number of faces for dividing the image into a plurality of partial faces using a difference between consecutive images; an allocation control unit configured to allocate a frequency of detecting the object for each of the divided partial faces; a division processing unit configured to divide the image into a plurality of partial faces depending on the set number of faces and to detect an object from the partial faces in accordance with the allocated frequency; an overall processing unit configured to reduce the image to an entire face indicating the entire image and to detect an object from the entire face; and a combination processing unit configured to combine respective detection results detected from the partial faces and the entire face to detect an object from the image.

A device operating with a beam of charged particles, comprising the following: an optical system designed to irradiate a sample with multiple beams of primary charged particles, an optical parameter setting unit (160) designed to set a parameter of the optical system, a detector (101) designed to individually detect several beams of secondary charged particles emitted by the sample, several storage units (112), each designed to store a signal captured by the detector (101) and converted into a digital pixel in the form of a captured image, an assessment value derivation unit (113) designed to derive an assessment value for the beam of primary charged particles from the acquired image, a GUI (130) designed to display an image and receive input from a user, an image reduction unit (114) designed to reduce the size of the captured image, a display image memory (150) designed to store the image reduced by the image reduction unit (114), and a display control unit (140) designed to simultaneously display several reduced-size images stored in the display image memory (150) and assessment results based on the assessment values ​​side by side on a screen (200) of the GUI (130).

The invention relates to a large-numerical-aperture high-resolution reflective imaging system. The imaging system comprises two aspheric reflectors. After the light source irradiates the mask surface, the light source sequentially passes through the first reflector M1 (diaphragm) and the second reflector M2 and is finally imaged on the wafer surface, so that the objective image reduction magnification of the imaging system 0.2 is realized. The imaging system is a coaxial reflection system and has the advantages of being high in aberration correction capability, easy to machine, install and adjust and the like. The main optical parameters are as follows: the numerical aperture is 0.4, the object space field of view is 3mm * 1mm, and the total length of the system is 572.4 mm.

The invention discloses a display optimization method and system for data fusion of a multi-modal sensor, relates to the technical field of display optimization, and aims to solve the problems that the image reduction degree is reduced and the visual distortion risk is increased. And evaluating the proportion deviation by combining the reference proportion obtained by the painting database, dividing the scanned copy into different areas, detecting the brightness of each area, calculating the brightness deviation rate, and judging whether to carry out distortion repair or not by combining the proportion and the brightness deviation. In the repairing process, the surface glossiness and the stroke height of an original corresponding to each area are collected, the concave-convex fluctuation characteristics are calculated, the glossiness and the concave-convex fluctuation characteristics are synthesized to calculate a distortion risk coefficient, and a repairing sequence is generated according to risk sorting. And performing distortion restoration on the scanned copy according to the restoration sequence to realize accurate restoration and optimized display of the scanned copy of the artistic painting, so that accurate restoration and display optimization of the scanned copy are realized, and the image restoration authenticity and the visual effect are improved.

To realize a new technology for performing multiple image processing operations using a support program in an information processing device that incorporates a general-purpose printing program. [Solution] When a print command is output from the editing application 43, the general-purpose printing program 41 generates intermediate data based on the image to be printed, and the auxiliary program 42 obtains the intermediate data and the print settings corresponding to the print command from the general-purpose printing program 41. The auxiliary program 42 performs a synthesis process to synthesize composite information such as watermarks into the intermediate data according to the print settings obtained from the general-purpose printing program 41, and after the synthesis process, it performs a layout process to reduce the size of images from multiple pages and place them on a single sheet of paper, or to divide an image from one page so that it is printed on multiple sheets of paper. Furthermore, the auxiliary program 42 controls the printer 2 to perform printing based on the edited image.

A method and device (1600, 1700) for image reduction. The method for image reduction comprises: obtaining a phase coefficient corresponding to a position of a first pixel point in an image comprising N*N pixel points, and performing demosaicing on the pixel points in the image to obtain N*N first pixel points, and then performing reduction processing on the N*N first pixel points according to the phase coefficient. Through the demosaicing processing, a plurality of pixel points can be converted into the same pixel point, so that the first pixel points in a region of the image are increased, which helps to maintain more high-frequency performance when performing the reduction operation, thereby improving the definition of the reduced image.

The present disclosure relates to adaptive neural network selection methods and systems, the method comprising: obtaining one or more images from a camera; obtaining a zoom factor of the camera, the zoom factor representing a measure of a current zoom level applied by the camera when capturing the one or more images; selecting a neural network from a plurality of neural networks configured to segment the one or more images and / or detect one or more objects in the one or more images based on the zoom factor, the plurality of neural networks being configured to operate at different image resolutions, a higher zoom factor corresponding to selecting a neural network configured to operate at a lower image resolution, and a lower zoom factor corresponding to selecting a neural network configured to operate at a higher image resolution; downscaling the one or more images to an image resolution required by the selected neural network; applying the selected neural network to segment the downscaled one or more images and / or detect the one or more objects in the down scaled one or more images.

The application discloses an image reduction processing method and device, the method comprising: acquiring image information of an input image and a reduction multiple, wherein the input image information comprises an image width and an image height; dividing the image into a plurality of image blocks with equal areas according to the image information of the input image; unifying values of all pixel points in each image block into a pixel point value to obtain a unified image; obtaining a multiple for bilinear interpolation reduction according to the size of the image block and the reduction multiple; and performing bilinear interpolation reduction processing on the unified image according to the multiple for bilinear interpolation reduction to obtain a target image. The application solves the problem of large occupation of computing resources in the prior art bilinear interpolation, thereby reducing the occupation of computing resources and improving the image reduction speed.

The application discloses an unmanned aerial vehicle horizon real-time detection method and system based on improved YOLO segmentation, and relates to the technical field of horizon detection, and comprises the following steps: S1, acquiring a front view image or a video frame sequence of an unmanned aerial vehicle; S2, performing sky region segmentation by using a lightweight sky segmentation network; S3, extracting a low sky boundary point set from a sky mask; S4, fitting a current frame horizon parameter based on the low sky boundary point set; S5, performing adaptive time sequence smoothing processing based on boundary integrity; and S6, outputting the horizon parameter after time sequence smoothing. The application adopts the unmanned aerial vehicle horizon real-time detection method and system based on improved YOLO segmentation, extracts a sky region by using a lightweight sky segmentation network, reduces the horizon search range from a complex original image to a real demarcation region between the sky and the non-sky, and effectively reduces the interference of buildings, ground textures, cloud changes and complex background edges on the detection result.

The invention discloses a multi-picture video matrix previewing method and system and a medium. The method comprises the steps that an MCU chip obtains the screen resolution, the number of windows in a screen previewing window matrix and the number of multiple paths of video input sources; the MCU chip is configured with a multi-path picture resolution parameter and a reduction scale parameter; the MCU chip sends a multi-path picture resolution parameter and a reduction scale parameter to the image reduction module, controls the video matrix switching chip to switch input and output signals, and sequentially inputs pictures of a multi-path video input source to the image reduction module; the image reduction module is used for carrying out scaling processing on the images of the multi-channel video input source input by the video matrix switching chip by adopting a local mean reduction algorithm, and caching the scaled images in a DDR (Double Data Rate) chip; and the video output module is used for splicing the zoomed pictures and then displaying the pictures in a screen preview window. According to the invention, the previewing function of multi-channel video input pictures is realized, and the problem that the picture quality becomes blurred after the image is reduced is solved.

To provide a method, a camera and a program for analyzing an image of a scene under different visibility conditions.SOLUTION: The device 200 includes one or more cameras 210 that obtain a plurality of images 212 of a captured scene, a visibility estimation block 220 that obtains, for each image, an indication of an actual or assumed visibility distance in the scene when the image was captured, a demultiplexer / ANN architecture selector 230 that selects an ANN architecture from a plurality of artificial neural network (ANN) architectures 240 based on visibility, and a plurality of different ANN architectures 240 that analyze the image using the selected demultiplexer / ANN architecture. If the selected ANN architecture has a lower input image resolution than the image, the image can be downscaled to match the input image resolution of the selected ANN architecture.SELECTED DRAWING: Figure 2

The invention provides a large-view-field compact reflective projection objective, and belongs to the technical field of semiconductor manufacturing lithography, the projection objective system comprises six aspheric reflectors, after a light source irradiates a mask, the light source passes through a first reflector M1, a second reflector M2, a diaphragm, a third reflector M3, a fourth reflector M4, a fifth reflector M5 and a sixth reflector M6 in sequence, and the six aspheric reflectors are connected with the first reflector M1, the second reflector M2, the diaphragm, the third reflector M3, the fourth reflector M4, the fifth reflector M5 and the sixth reflector M6. And the diaphragm is positioned between the second reflector M2 and the third reflector M3, and is finally imaged on a wafer surface, so that the objective image reduction magnification of the projection objective lens system 0.2 is realized. In the embodiment of the invention, the light path has no light blocking phenomenon, and the structure is compact. The main optical parameters are as follows: the image space numerical aperture is 0.2, the object space field of view is 10mm, and the total length of the system is 1280mm.

The invention provides an image data processing method and device, and belongs to the technical field of image data processing, and the method comprises the steps: obtaining a bit width reduced image of an original image, and original image data of the original image in a first preset region; the bit width reduction image is an image generated by performing bit width reduction processing on the original image; performing blurring processing and bit width recovery processing on the bit width reduced image in sequence to generate an intermediate image with the same bit width as the original image; and replacing the image data corresponding to the first preset area in the intermediate image with the original image data to generate a target image. The finally generated target image is the image data of the original image in the first preset area, all features of the original image are reserved, the data transmission amount is reduced compared with the original image for the part outside the first preset area, the immersion of a user is improved during display through fuzzy processing, and the user experience is improved. And the use experience of the user is improved.