25results about How to "High image resolution" patented technology

The invention discloses a segmentation method for rail defect detection based on improved YOLOv10 and SETR, and the method comprises the steps: S1, collecting image data, carrying out the enhancement processing of the image data, carrying out the segmentation processing, and making a data set; s2, an improved YOLOV10 algorithm model is built and trained; s3, using the improved YOLOV10 model weight to detect image data to be detected, judging whether defects exist or not, if the defects are detected, storing detection frame information of the defects, and outputting a target detection frame and confidence; and S4, transmitting the detection frame information as prompt information into the SETR model, segmenting the target by adopting the SETR model to obtain a segmentation result, and outputting a mask pattern. The improved YOLOv10 algorithm and the SETR algorithm are adopted to detect the rail defects, the calculation complexity and the efficient detection speed are kept, the detection precision is improved, and the robustness of the model is improved.

The invention discloses a self-adaptive endoscope system and method based on photoacoustic image structure feature recognition, and relates to the technical field of photoacoustic endoscopic imaging, the system comprises a control system, a light source system, an endoscope probe, a feedback system, a signal processing system and a computing terminal; the control system synchronously triggers the light source system and the signal processing system, the light source system comprises a white light source and a laser, laser exciting light enters the endoscope probe through a single-mode optical fiber, scanning is controlled by a micro-electro-mechanical system (micro-electro-mechanical system scanning micro-mirror) scanning micro-mirror in the probe, scanning light enters the focusing lens group through the relay lens, and the focusing lens group is connected with the signal processing system through the relay lens. A to-be-imaged tissue surface is irradiated by the liquid lens, echo signals are acquired and processed by the signal processing system, photoacoustic image reconstruction is completed, the feedback system is connected with the liquid lens in the probe, and optical signals of optical images are acquired and reconstructed by an eyepiece at the top of the endoscope and a matched CMOS (complementary metal oxide semiconductor).

The invention relates to the technical field of anti-drowning early warning, in particular to an anti-drowning early warning method for lakes and reservoirs, which identifies and analyzes human body behaviors in a lake and reservoir area in real time through video monitoring and deep learning technologies, provides accurate drowning early warning and danger level judgment, enhances safety protection measures, reduces the occurrence rate of drowning accidents, and improves the early warning effect of the lakes and reservoirs. And public safety is guaranteed.

The invention discloses detection equipment for a battery device, and relates to the technical field of battery manufacturing. The detection equipment for the battery device comprises a detection device and a ray device, the detection device is used for bearing a to-be-detected battery cell, and the detection device is further used for receiving rays penetrating through at least two corner areas of the to-be-detected battery cell; the ray device is used for being arranged on the side, back on to the detection device, of the to-be-detected battery cell and is spaced from the to-be-detected battery cell, and rays emitted by the ray device are used for covering at least two corner areas of the to-be-detected battery cell. When the detection equipment of the battery device is used, the to-be-detected battery cell can be borne through the detection device, and the ray device is arranged on one side, back to the detection device, of the to-be-detected battery cell and is spaced from the to-be-detected battery cell, so that the detection device is closer to a cathode piece and an anode piece of the to-be-detected battery cell; therefore, the degree of boundary blurring caused by the focus size of the ray device is reduced, and the imaging definition of the cathode and anode pieces with a large number of layers and small thicknesses can be improved.

The invention discloses an unmanned aerial vehicle remote sensing surveying and mapping image processing method, and relates to the technical field of image processing, and the method specifically comprises the steps: S1, carrying out the image data collection of a target region, and obtaining a to-be-processed surveying and mapping image set; s2, obtaining an initial gray level image set from the to-be-processed surveying and mapping image set, and denoising the initial gray level image set through median filtering introducing a window weight factor to process a denoised gray level image; s3, performing calculation processing on the de-noised grayscale image through inverse grayscale transformation and a color channel reduction algorithm to obtain a color enhanced surveying and mapping image; s4, performing deblurring processing on the color-enhanced surveying and mapping image, calculating a Dew gray scale main value region representative, a fixed segmentation threshold value and an ambient light interference amount based on the de-noised gray scale image and the color-enhanced surveying and mapping image, and performing calculation through a dynamic segmentation threshold value to obtain a deblurred surveying and mapping image; and S5, performing registration and splicing processing based on the deblurred remote sensing surveying and mapping image to obtain a panoramic registration image.

This invention discloses a remotely replaceable radiation-resistant pan-tilt camera, comprising: a fixed bracket with a wiring compartment fixedly mounted at its end; a pitch-rotation pan-tilt compartment mounted on the top surface of the wiring compartment; and a periscope lens compartment detachably mounted on the pitch-rotation pan-tilt compartment. The periscope lens compartment includes a fixing block, a fixing latch, a lens housing, and a lens module. Fixing latches are fixedly positioned at the center of both the left and right side walls of the lens housing. To improve the radiation resistance of the high-definition image sensor, this invention employs a three-layer shielding structure and a periscope reflective lens module to prevent direct damage to the camera sensor from radiation. The three-layer shielding structure also allows adjustment of the lens housing's center of gravity, ensuring the stability of the lens housing's pitch movement.

The application relates to a method and system for realizing 90-degree integer multiple rotation of an image, wherein the method comprises the following steps: an FPGA receives original image data output by an image sensor and image processing parameters issued by an ARM, the image processing parameters at least including width, height and a rotation angle, wherein the rotation angle is an integer multiple of 90 degrees; the original image data is preprocessed and demosaiced to obtain a full-color image in RGB or YUV format; according to the width, height and rotation angle of the image, a coordinate transformation formula for 90-degree integer multiple rotation is used to determine the position mapping relationship between each source pixel in the full-color image and a target pixel after rotation; the full-color image is written into a BRAM cache in a ping-pong mode, and each pixel is read according to the order of the position mapping relationship and written into a target address in a DDR, wherein the target address in the DDR is calculated according to the position relationship.

The present invention relates to the field of computer medical image processing, and proposes a pancreatic tumor image segmentation processing method based on a local linear embedded interpolation neural network. The method comprises the following steps: inputting a local interpolation network to interpolate the input 3D tumor slice and the corresponding tumor label slice; inputting a multi-scale cascade segmentation network to perform tumor segmentation, and visualizing the result. The present invention is easy to implement, improves the image quality and the number of tumor slices, reduces the tumor differences between adjacent slices, and avoids missed detection as much as possible. The present invention can effectively alleviate the fuzzy labeling problem of tumor boundaries, and process different tumor image features under limited computing conditions, significantly improving image resolution.

The invention discloses a terahertz time-domain spectral imaging method based on a femtosecond laser pumping-detection principle. The terahertz time-domain spectral imaging method comprises the following steps: acquiring a terahertz wave beam signal of a to-be-detected sample through a terahertz time-domain spectral system; gaussian fitting is carried out on the terahertz wave beam signal by using the terahertz wave beam model; and performing imaging reconstruction on the Gaussian fitting result of the terahertz wave beam signal by adopting a maximum likelihood and maximum expected value strategy to obtain an imaging reconstruction result. According to the terahertz time-domain spectral imaging method based on the femtosecond laser pumping-detection principle, the reconstruction technology combining the Gaussian beam model and the MLEM algorithm is introduced, the wave path calculation error is effectively reduced, the scanning imaging quality is improved, and high-resolution two-dimensional terahertz imaging is achieved; according to the method, the structural characteristics of fiber distribution, agglomeration, interruption and the like in the cigarette can be clearly presented, the defects of image blurring and multiple artifacts of a traditional back projection algorithm are overcome, and an efficient and reliable solution is provided for nondestructive testing and quality evaluation of the internal structure of a cigarette product.

The embodiment of the invention provides a medical imaging method and device and medical imaging equipment. The method comprises the following steps: acquiring a region of interest on a reconnaissance image of an examination object by using a deep learning method; determining a geometric center of an organ of interest of the examination object according to the region of interest; and driving the patient table to move according to the geometric center of the organ of interest and the geometric rotation center of medical imaging equipment. According to the embodiment of the invention, the automatic movement of the patient table is realized, so that the geometric center of the organ of interest is close to the geometric rotation center of the medical imaging equipment, the diagnostic image has higher image quality, including higher image resolution, meanwhile, rays penetrating through the geometric rotation center of the medical imaging equipment are fully utilized, and correspondingly, the image quality is improved. And the dose efficiency of the rays is higher.

The present application relates to a kind of big field of view big aperture negative focal length visual optical system and near-eye display device, visual optical system includes: the first lens group close to human eye side and the second lens group close to micro display screen side;Light is emitted from micro display screen, after converging once by the second lens group, then enter human eye by the first lens group, form image;System total focal length is negative, the first lens group and the second lens group both have positive refractive power;The first lens group is sequentially arranged by a piece of positive lens, a piece of negative lens and a piece of negative lens, and the second lens group is arranged by a piece of positive lens, a piece of negative lens, a piece of positive lens and a piece of negative lens.The present application uses big field of view big aperture negative focal length visual optical system, greatly increases the optimization degree of freedom of optical system, greatly improves the imaging quality of entire optical system, realizes the big field angle of visual optical system, high image resolution, low distortion, small field curvature and other indexes, greatly improves the competitiveness of product.

The present application discloses a method, device and equipment for detecting motherboard defects based on an improved abnormal detection model, and relates to the field of defect detection technology. The method includes: obtaining the original image of the motherboard to be detected, and extracting the key area to be detected from the original image of the motherboard to be detected; based on the improved Anomalib model, detecting the key area to be detected, and obtaining the abnormal probability distribution data of the key area to be detected; based on the abnormal probability distribution data of the key area to be detected, determining the defect position in the key area to be detected; marking the key area to be detected and the defect position in the key area to be detected respectively, and generating a result heat map of the motherboard to be detected. Through the above method, the model structure is optimized, the amount of calculation is reduced, and the reasoning efficiency of the model is improved. At the same time, the key areas of the image are used for training and reasoning, the model's pertinence is improved, the accuracy and reasoning efficiency of the model are improved, and the accuracy and efficiency of defect detection are improved.

The utility model provides a lens structure and a monitoring camera, and the lens structure comprises a lens group. The lens frame is of a hollow through structure and is located in the middle of the lens structure; the inner ring surface of the adjusting ring is in threaded fit with the outer peripheral surface of the mirror frame; the inner ring surface of the adjusting ring and the outer peripheral surface of the mirror frame are provided with threads which are matched with each other; the lens focusing process is more convenient / more stable, when the lens focusing is not in place, the optimal focusing effect can be achieved by adjusting the position of the adjusting ring to move up and down, the adjusting ring is made of a plastic transparent material, dispensing and curing of the lens support are more convenient, and after UV glue is dispensed between the adjusting ring and the lens support, the lens support can be fixed conveniently. The ultraviolet light source irradiates and can penetrate through the adjusting ring in all directions to cure the glue, so that the glue curing time is shorter, the curing effect is better, the strength of the joint is guaranteed, and the production cost / production time is saved.

The invention provides a magnetic resonance imaging and radio frequency heating integrated guide wire and a use method thereof, and can be applied to the technical field of medical instruments. The magnetic resonance imaging and radio frequency heating integrated guide wire comprises a signal processing circuit, the signal processing circuit comprises a first filtering sub-circuit and a second filtering sub-circuit, and a first filtering range of the first filtering sub-circuit and a second filtering range of the second filtering sub-circuit are different from each other, the first end of the first filtering sub-circuit is used for being connected with a magnetic resonance imaging system, the first end of the second filtering sub-circuit is used for being connected with a radio frequency generator, and the radio frequency generator is used for providing radio frequency heating signals for the second filtering sub-circuit; the first end of the guide wire main body is connected to the second end of the first filtering sub-circuit and the second end of the second filtering sub-circuit, and the second end of the guide wire main body is used for collecting a magnetic resonance imaging signal of an organ tissue; wherein the radio frequency heating signal and the magnetic resonance imaging signal are synchronously transmitted in the guide wire main body.

The present invention discloses graphical fiducial marker recognition suitable for augmented reality, virtual reality, and robotics. In various examples, image data representing an image is received. Corner detection can be used to identify pixels that may be candidate corner points. The image data can be converted from a higher dimensional color space to a converted image in a lower dimensional color space, and boundaries within the converted image can be identified. A set of candidate corner points within a threshold distance to one of the boundaries is determined, and the set of candidate corner points can be analyzed to determine a subset of candidate corner points representing corners of a polygon. Using the subset of candidate corner points, one or more polygons can be identified, and a filter can be applied to the polygons to identify polygons corresponding to the fiducial marker boundaries of a fiducial marker.

The utility model discloses a passive coil, which comprises a coil base material, a coil, a conductor material and at least one group of series combination A formed by an inductor La and two PIN diodes Va which are reversely connected in parallel, and the series combination A is connected in parallel with a decoupling capacitor Ca and then is connected in series with a bridging capacitor C through the conductor material to form an annular ring or a rectangular ring; by optimizing the layout through the passive coil, the higher signal-to-noise ratio and image resolution of the local region of interest are improved, and by means of the mode, the device can improve the accuracy and reliability of magnetic resonance imaging and has important practical significance and clinical application value.

The embodiment of the utility model provides a light guide device, an optical display system and display equipment. The light guide device comprises a substrate, an optical coupling-in area and an optical coupling-out area, wherein the optical coupling-in area and the optical coupling-out area are arranged on the substrate. The light coupling-in area is set to be in a target shape, or a diaphragm is arranged on one side of the light coupling-in area, and the diaphragm is provided with a light transmitting area in the target shape, so that the light coupling-in area can adjust the light spot shape of light before the light enters the substrate; therefore, uniform light spots can be formed when light passes through the substrate and reaches the optical coupling-out area.

The utility model discloses a machine vision reverse side detection device which comprises a working table, a conveying belt is arranged in the working table, a portal frame is fixedly connected to the top of the working table, a detection mechanism is installed on the top of the working table, an adjusting mechanism is arranged on the outer side of the detection mechanism, and the detection mechanism comprises a computer. A connecting wire is fixedly connected to the outer side of the computer, a CCD camera is fixedly connected to the outer side of the connecting wire, a light source body is arranged on the outer side of the CCD camera, the adjusting mechanism comprises an operation box, connecting plates are fixedly connected to the outer side of the operation box, a rotating rod is rotationally connected between the connecting plates, and the rotating rod is fixedly connected to the outer side of the operation box. According to the machine vision reverse side detection device, the reverse side of an object can be efficiently and accurately detected, and the light source angle and the detection position can be flexibly adjusted according to actual requirements.

The application belongs to the technical field of semiconductor packaging, and particularly relates to a glass-based high-integration packaging COB module, which comprises a glass substrate, LED chip die bonding, a frosted epoxy adhesive layer and a driving PCB board; one side of the glass substrate is a lamp surface wiring pad, and a steel mesh printing tin paste layer is arranged on the surface; the other side is a wiring array pad; TGV glass through holes and multilayer metal wiring are arranged in the glass substrate, and vertical connection of the lamp surface wiring pad and the other side wiring array pad is realized through mutual connection; the glass-based direct display COB module has small pixel spacing and many pixel points in a unit area, can bring higher image resolution and better visual quality; the lamp surface is directly molded and formed by using high-transmittance, anti-dazzle black matte frosted epoxy glue, so that the process is simplified, and the cost is reduced; the product batch ink color is controllable, the consistency is high, and the color difference is small; the COB overall light emitting module can be freely assembled and applied to the scene of curved surface and other special-shaped displays, and the indoor decoration and brightening display effect is enriched.

One or more embodiments of the invention provide a personalized customized drawing method and system. The method comprises the following steps: determining a face description text specified by a user, and calling a generative algorithm to generate a face image based on the face description text; obtaining a first dressing effect image of a target garment, wherein the first dressing effect image is used for presenting a wearing effect of the target garment on the digital model; and performing fusion processing on the face image and the first dressing effect image to generate a second dressing effect image of the target garment, the second dressing effect image being used for presenting a wearing effect of the target garment on the fused digital model. According to the scheme, the garment picture can be quickly output with high quality, the fused image can keep feature consistency, and the display effect of the image can also meet the personalized requirements of users.

This invention provides a pixel structure and its display driving method, comprising, from bottom to top: a first metal layer, a first transparent conductive dielectric layer, a first phase change material layer, a second transparent conductive dielectric layer, a second phase change material layer, a third transparent conductive dielectric layer, a second metal layer, and a fourth transparent conductive dielectric layer; the thickness of the first metal layer is within a first preset thickness range, constituting a total reflection layer; the thickness of the second metal layer is within a second preset thickness range, constituting a semi-transparent reflective layer; the other layers serve as dielectric materials, forming a Fabry-Perot resonant cavity with the first and second metal layers; when the physical thickness of the resonant cavity is within a third preset thickness, the pixel structure can selectively reflect different colors of light when the crystal state of either the first or second phase change material layer changes. This invention achieves in-situ switching of multiple reflected colors on a single display pixel, featuring high pixel density and effectively improving the image resolution of reflective display devices.

The present invention relates to different frame rate settings. A technique for setting the frame rate of a camera is provided. The camera includes a plurality of image sensors arranged to capture images to be stitched into a panoramic image of a scene. Information is obtained about a corresponding angle between an optical axis of each of the plurality of image sensors and a direction along which a straight path structure to be monitored by the camera extends through the scene. Based on the angle, the plurality of image sensors are divided into at least two groups. All angles of the image sensors within each of the at least two groups are part of its own continuous angle interval. A frame rate is set for each of the at least two groups. The frame rate decreases from the group with the highest continuous angle interval to the group with the lowest continuous angle interval.

An underwater imaging method based on suppressing forward scattered light. It belongs to the technical field of underwater polarization imaging, and specifically relates to the technical field of underwater polarization image restoration. The method comprises the following steps: S1, defining a global coordinate system and a local coordinate system of a water body; S2, constructing a forward scattering Mueller transmission matrix of water body particles; S3, converting the forward scattering Mueller matrix into an equivalent Jones matrix to obtain a forward scattering wavefront phase; S4, performing an inverse Fourier transform according to the obtained forward scattering wavefront phase, and constructing a forward scattering point spread function model of a water body; S5, suppressing underwater forward scattering according to the forward scattering point spread function model of a water body, and restoring the degraded image using an image restoration algorithm. The method of the present invention can be applied to the technical field of underwater target polarization imaging detection.

The invention relates to a color three-dimensional image acquisition method, device and system, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: controlling a binocular structured light camera to collect structured light three-dimensional image original data of a target object; controlling the binocular stereo camera to collect binocular stereo three-dimensional image original data of the target object, and controlling the color camera to collect color image original data of the target object; obtaining a structured light three-dimensional image of the target object according to the structured light three-dimensional image original data, obtaining a binocular three-dimensional image of the target object according to the binocular three-dimensional image original data, and obtaining a color image of the target object according to the color image original data; and carrying out fusion processing on the structured light three-dimensional image, the binocular stereo three-dimensional image and the color image to obtain a color three-dimensional image of the target object. By adopting the method, the image resolution of the acquired color three-dimensional image can be improved.

This invention relates to the field of intelligent manufacturing, specifically to an automatic planning method, system, device, and storage medium for aircraft aperture projection positions. The method includes the following steps: determining the placement area of ​​the projector; setting optimization target parameters; initializing optimization units; evaluating the aperture coverage, aperture quality, precision, projection utilization, and comprehensive planning results for each optimization unit; determining whether the optimization target is met; if not, optimizing each unit based on the comprehensive evaluation score using an optimization strategy, and resubmitting the optimized results, iterating until the algorithm's stopping condition is met. This invention provides an automatic projection position planning method by evaluating indicators such as aperture coverage, global aperture projection quality, image precision, and projector utilization, combined with an optimization algorithm, ensuring full aperture coverage, high-quality projected images, and a minimum number of projectors after planning.