279 results about "Automatic focus" patented technology

The invention discloses a high-precision automatic focusing system and focusing method for a continuous zooming television camera, and solves the technical problem of insufficient focusing precision caused by image delay and system rotation errors in the prior art. According to the method, the definition evaluation value of the current frame image is associated with the exposure time of the current frame image in the CMOS imaging stage, the definition evaluation value of the image and the corresponding exposure time of the current frame image are obtained at the same time in the automatic focusing process, and the clear position deviation of the focusing motor caused by image delay is accurately compensated; by means of trajectory planning in the search process of the image sharpness evaluation value extremum of automatic focusing, it is guaranteed that the direction of reaching the most image sharpness evaluation value extremum finally is consistent with the direction of searching the extremum, the method completely eliminates the influence of system rotation errors, and the adaptability is higher; and all units are integrated on the same FPGA platform, so that more product space is saved, the communication transmission delay of the definition evaluation value is eliminated, and the focusing precision is higher.

The invention provides a dynamic interference focusing method and system based on a Michelson interferometer, and the method comprises the steps: obtaining interference fringes under different defocusing amounts through employing the dynamic interference focusing system based on the Michelson interferometer, carrying out the analysis of the received interference fringes through an upper computer, and obtaining phase information, based on the phase information of the interference fringes corresponding to different defocusing amounts, a mapping relation between the defocusing amounts and the phase information is constructed; in the application, the current interference fringes are obtained through the dynamic interference focus fixing system of the Michelson interferometer, the current interference fringes are analyzed through the upper computer to obtain the current phase information, and the current defocusing amount is obtained by adopting the mapping relation based on the current phase information. And moving the sample to a calibrated focal plane position by controlling a dynamic interference focus fixing system of a Michelson interferometer based on the current defocusing amount to complete automatic focus fixing. The method can achieve the nanoscale focusing sensitivity.

The invention relates to the technical field of optical detection and automatic control, and discloses a computer vision-assisted nano-particle recognition and micro-spectrum automatic measurement system, which comprises a sample positioning module, an imaging module, an optical measurement module and a processing control module, automatic focusing is realized on the basis of a definition evaluation value calculated by performing Fourier transform on the microscopic image; graying, binaryzation and morphological operation are carried out on the focused image so as to identify effective nano-particles and calculate centroid coordinates of the effective nano-particles; according to the coordinates of the center of mass, the X axis and the Y axis of the electric three-axis displacement table are controlled through closed-loop iteration movement, and the measured particles are accurately positioned to the center of the view field. According to the invention, the problems of low manual measurement efficiency, poor repeatability and complex operation in the prior art are solved, and high-flux, full-automatic and high-precision measurement of the spectral characteristics of the nanoparticles is realized.

An automatic focusing method, a laser processing apparatus and system, and a non-transitory computer-readable storage medium are provided. The automatic focusing method for a laser processing apparatus includes: controlling the first light output module to emit a first light spot onto a workpiece, and controlling the second light output module to emit a second light spot onto the workpiece; controlling the first light output module to move downward, and acquiring a plurality of images of the workpiece at different distances; and determining, based on the plurality of images, a distance between a processing surface of the workpiece and the first light output module or a thickness of the workpiece.

The invention discloses an on-orbit automatic focusing method for a spaceborne space target observation camera, relates to the technical field of space application of spaceborne cameras, and solves the problems of poor real-time performance and insufficient unattended operation adaptability of a manual focusing technology in the existing focusing technology. And meanwhile, in the automatic focusing technology, the hardware structure is complex, the space environment adaptability is weak, satellite-borne platform resources are limited and difficult to deploy, and focusing is difficult in a severe out-of-focus scene. According to the invention, the realization of automatic focusing is divided into a coarse adjustment stage and a fine adjustment stage. A large step pitch is adopted in the coarse tuning stage, rapid crossing is achieved, and an area adjacent to a positive focus position is rapidly positioned; in the fine adjustment stage, small step pitch is adopted, fine adjustment is achieved, and the peak position is accurately locked. The contradiction between the search speed and the positioning precision is balanced. When far away from the positive focus, a large-step-pitch fast approximation peak region is used, so that the number of iterations and the number of image acquisition frames are greatly reduced; when the focus is approached, small step pitch is switched for fine tuning, and the final precision is ensured.

The invention discloses a plano-convex lens curvature radius intelligent measuring and calculating system and method based on Newton ring interference, and relates to the technical field of optical measurement, and the system comprises a light path calibration unit which is used for enabling target light to enter a Newton ring device at a preset angle based on a calibration device; the automatic focusing unit is used for acquiring Newton ring images at different positions of the lens cone 8 based on the Newton ring device, screening the Newton ring images based on a pre-trained focusing scoring model to obtain a first image, obtaining a target position based on the first image, and adjusting the position of the lens cone 8 of the Newton ring device to the target position; the image acquisition unit is used for acquiring a second image based on the Newton ring device; the data measuring and calculating unit is used for classifying the second image based on a pre-trained image screening model to obtain an effective image with a central spot, and obtaining the curvature radius of a plano-convex lens based on the effective image, the problems that a traditional Newton ring measurement system is poor in adjustment precision, poor in reading accuracy, lack of automation degree and weak in external interference resistance are solved.

The invention relates to the technical field of projection, and discloses a projector asynchronous focusing method and device, equipment and a medium. The method comprises the following steps: controlling a projection lens of a projector to move at a constant speed along an optical axis; in the constant-speed displacement process of the projection lens, an image sampling device is controlled to carry out continuous image sampling on a projection picture of the projection lens, and multiple groups of first sampling images are obtained; performing definition evaluation on each first sampling image to obtain a first definition evaluation value; based on the displacement speed of the projection lens and the first definition evaluation value, predicting the position of the projection lens when the definition of the projection picture reaches a peak value, and obtaining a target focusing position; and controlling the projection lens to move to the target focusing position. According to the embodiment of the invention, the automatic focusing speed can be improved on the basis of keeping the focusing precision.

A method and a system for optimizing auto-focus functionality for capturing a multimedia content are provided. The method includes detecting, by an object detection module, one or more objects in a preview frame of the multimedia content, performing, by a feature extraction module, a plurality of functions for extracting attributes of the detected one or more objects, computing, by a priority assignment module, occupancy factor and popularity factor of each detected object are computed to determine priority score, identifying, by a focus identification module, a suitable focus mode and a focus area mode for each selected object are identified based on extracted attributes. In one embodiment, the selected object includes all the detected objects that have a priority score greater than or equal to a predefined threshold value, and applying, by a frame capture and combining module, the identified focus mode and the focus area mode are applied on each selected object for providing the multimedia content.

The application discloses an automatic focusing device, method and equipment for single-pixel microscopic imaging. The device comprises a projection module, a focusing module and a detection module. The projection module is used for generating a first image and projecting the first image to a target surface to obtain a second image. The focusing module is used for zooming the projection module to adjust the definition of the second image. The detection module is used for detecting the light intensity of the second image and outputting a photoelectric response value sequence. The calculation and control module is used for controlling the working states of the projection module, the focusing module and the detection module. The in-focus focal length is calculated according to the photoelectric response value sequence. The application can be used for quickly and conveniently focusing the image projected on a microscopic sample and can be widely applied in the field of single-pixel microscopic imaging.

The utility model provides a dual-linkage focusing mode lens and camera shooting equipment, and relates to the technical field of optical imaging, the dual-linkage focusing mode lens comprises a manual focusing lens group, an automatic focusing lens group, a manual driving assembly, an automatic driving assembly and a position sensing trigger unit, the manual focusing lens group comprises at least one manual lens group, and the automatic focusing lens group comprises at least one automatic lens group. The automatic focusing lens group comprises at least one automatic lens group, and the manual driving assembly is connected with and manually drives the manual focusing lens group; a motor of the automatic driving assembly is in driving connection with the automatic focusing lens group; when the manual focusing lens group moves to a preset position along the optical axis, the position induction triggering unit is triggered to start the motor to drive the automatic focusing lens group to execute automatic focusing, the manual focusing lens group and the automatic focusing lens group are sequentially arranged along the optical axis, relay type optical path design is achieved, the size of the lens can be reduced, and redundant motion of the focusing lens groups can be avoided; the position sensing trigger unit is triggered to quickly switch the focusing mode, the movement of a single focusing lens group can be accurately controlled, and the focusing precision and speed are improved.

The application provides a focusing motor and a camera module. The focusing motor comprises a fixed part, a moving part, a focusing assembly, a magnetic attraction sensing part, a guide part and a position sensor. The fixed part comprises a first support arm and a second support arm connected with each other, and a light passage hole formed between the first support arm and the second support arm. The moving part is arranged in the light passage hole and can move in a preset direction. The magnetic attraction sensing part is arranged in the moving part. The angle between the magnetization direction of the magnetic attraction sensing part and the first direction and the second direction perpendicular to the preset direction is an acute angle. The guide part is arranged on the first support arm and corresponds to the magnetic attraction sensing part. The position sensor is arranged on the second support arm and corresponds to the magnetic attraction sensing part. The position sensor can generate an induction force with the magnetic attraction sensing part, so that the position sensor can sense the moving position of the moving part. The focusing motor can significantly reduce the size of the focusing motor, and can guarantee the guiding stability and the position detection precision required by the automatic focusing function while realizing the miniaturization of the camera module.

The invention relates to the technical field of forensic examination, and discloses a forensic diatom automatic scanning and interpretation system based on optical microscopic imaging and AI, which comprises an automatic scanning imaging optical platform, an embedded high-performance all-in-one computer and an artificial intelligence recognition algorithm module. The all-in-one computer is configured to control the optical platform to execute XY-axis automatic scanning and Z-axis automatic focusing, and the automatic focusing is realized based on a definition evaluation function and a search algorithm to obtain a clear field-of-view image; and the artificial intelligence recognition algorithm module is configured to call a diatom target detection model and a diatom form classification model to carry out automatic detection and morphological classification on diatom targets in the clear view field image, and can also comprise an online learning and image library expansion mechanism. The problems that forensic diatom inspection depends on manpower, efficiency is low, interpretation is subjective, and an automatic system lacks accurate focusing and self-adaptive capacity are solved.

The invention provides a total station automatic focusing and reflector plate identification method and system based on intelligent image.The method relates to the technical field of engineering surveying, and comprises the steps that a stepping motor is controlled to drive a focusing lens barrel to move step by step in the direction of an optical axis, a coaxial camera collects images at all positions and calculates definition evaluation values to complete coarse adjustment and fine adjustment focusing, and the focusing precision is improved; and automatic focus locking is realized. The center coordinates of the reflector plate are determined through image preprocessing and reflector plate area recognition, the horizontal and vertical angle deviation can be calculated, sighting is achieved by driving a horizontal servo motor and a vertical servo motor to rotate automatically, and closed-loop control can be completed through iterative correction. The system is composed of a coaxial camera, a focusing execution mechanism, a master control module, an image processing module, an angle calculation module and a servo driving module, a coaxial optical path structure is adopted to eliminate parallax errors, the system has the high-precision automatic focusing, intelligent recognition and rapid automatic sighting capabilities, and the automation level and the measurement precision of the total station can be remarkably improved.

The utility model discloses an automatic imaging device for detection, which comprises an imaging connecting structure and an imaging camera, the imaging connecting structure comprises a bottom plate, a first mounting seat and a second mounting seat which are sequentially connected from bottom to top, the first mounting seat and the second mounting seat are internally provided with vertically through cavities, the bottom plate is provided with an imaging hole, and the imaging hole is communicated with the first mounting seat and the second mounting seat. A cavity of the first mounting seat is internally provided with a first dichroic mirror and a spectroscope, one side edge of the imaging connecting structure is connected with an imaging light source structure, the other side edge of the imaging connecting structure is connected with an automatic focusing system, and the second mounting seat is internally provided with a first optical filter, a first lens group and a plane mirror which are sequentially arranged from bottom to top. The automatic imaging device has the beneficial effects that the two light sources can be conveniently and quickly switched, different detection requirements can be met, and the application range and the flexibility of the automatic imaging device are improved; each part adopts a modular design, the connection and communication logic is simple and clear, the complexity and the maintenance cost of the imaging device are reduced, and the stability and the reliability are improved.

A focus detection apparatus hierarchically detects one or more specific region from an object in a captured image, sets focus detection regions divided into a plurality of regions with respect to the specific region, detects focus detection information for each focus detection region, decides a target region for performing an automatic focus operation, obtains a distribution of defocus amount of the specific region, and decides, based on a distribution of defocus amount of a lower level region including an upper level region of the specific region, the target region included in the upper level region.

This invention relates to the field of automatic shooting technology, and in particular to an automatic focusing method, system, intelligent storage medium, and shooting device. The automatic focusing method includes: acquiring the original image of the current frame; acquiring the average brightness of the original image; performing exposure processing on the original image based on the average brightness to acquire an exposed image; acquiring an initial focus evaluation value, brightness value, and gain value of the exposed image; acquiring an interference value based on the initial focus evaluation value, brightness value, and gain value; filtering the initial focus evaluation value based on the interference value to acquire an optimized focus evaluation value; using a climbing algorithm to acquire the peak value of the optimized focus evaluation value; taking the focus position corresponding to the peak value as the optimal focus; and focusing based on the optimal focus. This invention enables accurate automatic focusing under complex lighting conditions.

The invention provides a novel graph and image processing system which comprises an image acquisition module which adopts a high-resolution image sensor, has automatic focusing and exposure adjusting functions and is used for quickly and accurately acquiring static image and dynamic video image data. According to the novel graph and image processing system provided by the invention, through a parallel computing technology and an efficient algorithm, the image processing time is greatly shortened, and an application scene with a relatively high real-time requirement is met; through application of a deep learning algorithm and multi-modal fusion processing, the accuracy of image recognition, classification and analysis is improved, and image features can be extracted and a target object can be recognized more accurately. The system integrates various image processing functions and can process multi-modal data, so that diversified requirements of different fields and different users are met; meanwhile, due to the real-time feedback and interaction functions, the user can operate and control the image processing process more visually and conveniently, and the satisfaction degree of the user is improved.

The invention discloses a coaxial automatic focus detection system based on FPGA acceleration, which comprises a computer, an integrated optical module and an FPGA processing module, and is characterized in that the computer is used for issuing instructions to the integrated optical module and the FPGA processing module and controlling image data to be transmitted between the integrated optical module and the FPGA processing module; the integrated optical module is used for projecting a pattern to a to-be-measured object and collecting an optical signal reflected by the to-be-measured object; and the FPGA processing module is used for directly performing phase shift modulation degree calculation on the acquired sequence image flow through internal parallel hardware logic, and constructing a modulation degree-axial position curve of each pixel point in parallel to determine an optimal focal plane. According to the method, the coding pattern is actively projected, stable and reliable characteristics are established for the focus detection process, a general optical principle and special hardware acceleration are deeply fused, a traditional software processing mode is replaced, the order of magnitude of the focus detection speed is improved, the system has high adaptability, the application range is expanded, and the method is suitable for high-speed online precision detection.

We provide a system and method for autofocus and automated cell counting. [Solution] A system and method for autofocus using artificial intelligence includes (i) capturing multiple monochrome images over a nominal focal range, (ii) identifying one or more connected components within each monochrome image, (iii) sorting the identified connected components based on the number of pixels associated with each connected component, (iv) generating focus quality estimates for at least some of the sorted connected components using a machine learning module, and (iv) calculating a target focal position based on the focus quality estimates of the evaluated connected components. The target focal position can be used to perform cell counting using artificial intelligence, for example, by (i) generating seed likelihood images and whole cell likelihood images based on the output of a convolutional neural network, and (ii) generating a mask indicating the quantity and / or pixel location of objects based on the seed likelihood image.

This application provides a focusing method and electronic device based on human eye gaze recognition. The focusing method based on human eye gaze recognition is applied to electronic devices with shooting capabilities, such as mobile phones and cameras. By implementing this method, during the shooting process, the electronic device can identify the user's eye gaze point, determine the subject corresponding to the gaze point as the focus, and perform automatic focusing, thereby providing the user with a more user-friendly autofocus service and improving the user experience.

The invention provides eye adjusting equipment integrating eyelid opening, fundus photography and a data port, and belongs to the technical field of intelligent medical wearable equipment. The equipment comprises a glasses frame main body, a non-invasive eyelid opening mechanism, a high-resolution fundus photographing module, diopter-adjustable lenses, a data processing unit and a wired and wireless data port. The eyelid opening mechanism adopts a medical silica gel flexible opening sheet and a push rod, so that safe and automatic eyelid separation is realized; the fundus photographing module supports clear imaging at a field angle of 30-50 degrees based on infrared illumination and a CMOS sensor, and has pupil tracking and automatic focusing functions; the built-in electric control zoom lens can dynamically adjust the diopter from 6.0 D to + 4.0 D. The problems that existing fundus examination equipment is large in size, complex to operate, serious in eyelid shielding, unable to use and the like are solved, and the fundus examination equipment has remarkable clinical application value and industrialization prospects.

The invention relates to a parameter calibration method and device of image acquisition equipment and computer equipment. The method comprises at least one of the following two steps: a) determining a gain matrix corresponding to a first target calibration mode and / or a first target object distance based on a first gain matrix and a trained gain mapping relation; and b) determining an out-of-focus conversion coefficient corresponding to the second target calibration mode and / or the second target object distance based on the first out-of-focus conversion coefficient, the second out-of-focus conversion coefficient and the trained out-of-focus mapping relation. And writing the obtained gain matrix and / or defocus conversion coefficient into a memory in the image acquisition equipment for optical shadow correction and phase detection automatic focusing in an image signal processing stage. Through the trained gain mapping relation and the trained defocus mapping relation, corresponding gain matrixes and defocus conversion coefficients under various calibration modes and various object distance conditions can be generated, and the calibration cost and the calibration time consumption are reduced.

The present application relates to the technical field of image measuring instrument, and discloses an automatic focusing method and device of image measuring instrument.The present application is invented from two angles of the special design of the projection pattern and the judgment of whether the pattern is clear, and is placed in the form of pattern piece on the mounting position of the object to be measured so as to be the same as the position of the measured object.In the judgment of the focusing result, when the distribution of the gray value corresponds to the stripe on the pattern piece, it is indicated that the focal length is appropriate, the focusing is completed, the stripe on the pattern piece is known in advance, in the focusing process, the light splitting device blocks or reflects one color in the stripe, and the light of another color is projected onto the sensor, so that the absolute gray value difference can be caused, and the subsequent recognition of the gray value distribution is more favorable.Because the stripe on the pattern piece is known in advance, the distribution of the gray value is also fixed, and only when the distribution of the gray value corresponds to the stripe, the focusing is determined to be successful.

Systems and methods for autofocus using artificial intelligence include (i) capturing a plurality of monochrome images over a nominal focus range, (ii) identifying one or more connected components within each monochrome image, (iii) sorting the identified connected components based on a number of pixels associated with each connected component, (iv) generating a focus quality estimate of at least a portion of the sorted connected components using a machine learning module, and (iv) calculating a target focus position based on the focus quality estimate of the evaluated connected components. The calculated target focus position can be used to perform cell counting using artificial intelligence, such as by (i) generating a seed likelihood image and a whole cell likelihood image based on output—a convolutional neural network and (ii) generating a mask indicative quantity and / or pixel locations of objects based on the seed likelihood image.

The invention relates to the technical field of steel structure appearance detection, and discloses a steel structure building appearance intelligent detection method and system, and the method comprises the steps: collecting multi-scene existing steel structure appearance defect images, marking the images, dividing a data set, training an AI model to preset precision based on a deep learning algorithm, and storing the AI model to a cloud; setting inspection parameters according to the building characteristics, and generating an unmanned aerial vehicle flight path; the unmanned aerial vehicle carries an automatic focusing device to collect images according to a path, synchronously record shooting time and GPS parameters and upload the parameters to the cloud in real time; the cloud calls an AI model to identify image defects, outputs defect data and synchronizes the defect data to the management platform; the platform automatically generates a report based on an industry template, archives an image, a result and the report and establishes a'building-detection batch-defect 'association; and constructing a digital twinborn model and importing defect data to realize marking and cross-batch change comparison. The method has the advantages of low safety risk, high efficiency, high precision and traceability.

The invention relates to an automatic focusing method based on double-frame image and focus fusion depth coding. The automatic focusing method comprises the following steps: acquiring a first original image, a second original image, a first focus position scalar and a second focus position scalar; based on a focus perception and feature alignment module, obtaining a first cross-frame fusion feature according to the first grayscale image, the first focus position scalar, the second grayscale image and the second focus position scalar, and obtaining a second cross-frame fusion feature with a reduced size and a regular channel according to the first cross-frame fusion feature; performing focus feature extraction processing on the second cross-frame fusion feature through T focus feature extraction modules in sequence, and finally outputting a Tth focus prediction feature; and performing focus regression by using the Tth focus prediction feature to determine a final focus position. According to the automatic focusing method provided by the invention, the focus position information is coded and deeply fused with the visual features of the image, so that the optimal focus position can be quickly, accurately and flexibly predicted.

The utility model relates to a high -speed double light source automatic focusing laser engraving machine, include: cabin, the cabin has the installation cavity in, red blue light integral laser ware, the configuration in the cabin, high accuracy diffuse reflection module, the configuration in the cabin and detect work piece height downward, galvanometer, the configuration in the cabin, and with red blue light integral laser ware butt joint, field mirror, connect in the below of galvanometer, and emit laser beam downward, red dot laser ware, the configuration in the cabin, and emit focusing light beam downward, automatic focusing lifting assembly is connected with the cabin, drives the cabin and carries out the lift to carry out focusing, engraving platform, the configuration below the cabin.

This application provides an automated testing method and apparatus for the mechanical properties of single-particle lithium battery materials, relating to the field of automatic control technology. The method includes: starting with user-inputted particle testing requirements, an automated global particle screening process is completed using a visual recognition module. After confirming that the number of qualified particles meets preset requirements, the physical coordinates of all particles to be tested are accurately located, forming a set of particle coordinates. Based on this coordinate set, the system plans the optimal path for the indenter to move, driving the indenter of the pressure testing module to precisely align itself above each target particle sequentially. Subsequently, an automatic focusing module determines the height of the particle's apex, and the indenter presses vertically downwards until the particle breaks, simultaneously recording core mechanical data such as the crushing force, crushing displacement, and load-displacement curve. This method achieves full automation from particle screening and positioning to testing, significantly improving testing efficiency and data accuracy, and meeting the rapid testing needs of massive samples.

The invention discloses an efficient automatic focusing method and system, and relates to the field of automatic focusing. The method is applied to an off-axis automatic focusing device comprising a distance measuring module and an imaging module, and comprises the following steps: detecting height values of a plurality of measuring points by using the distance measuring module, and screening out focusing points at fixed intervals; based on the first height difference between the adjacent focusing points, the height of an objective lens focus in the imaging module is adjusted at a constant speed, so that the objective lens focus and the focusing points are consistent in height when the horizontal plane positions coincide; when the objective lens focus coincides with the horizontal plane position of any correction point, determining a corresponding fuzzy kernel matrix according to a second height difference between the objective lens focus and the correction point; and performing deblurring processing on an image generated by the image sensor based on the blurring kernel matrix to obtain an image of the measured object. Based on the above processing, the problem of image blurring caused by poor real-time focus following performance is improved, and the detection rate of the automatic focusing device is improved.

The invention relates to a focusing method and device, computer equipment, a chip and a chip module. The method comprises the following steps: carrying out image acquisition on a target scene at each lens position to obtain a first image of each lens position; for each first image, performing color space conversion on the first image to obtain a second image, and performing coding compression on the second image to obtain a coded image; the data volume of the coded image is used as a focusing value; and determining a target focusing numerical value meeting the focusing condition, and taking the lens position corresponding to the target focusing numerical value as the focusing position of the target scene. As the coding compression process is more sensitive to the compactness of global information included in the second image, and rich details included in the clearer second image can cause the coded image to have a higher data volume, the focusing value can more stably and accurately reflect the overall definition change trend of the second image, and the image quality is improved. Therefore, the stability and the success rate of automatic focusing in scenes of point light sources, high contrast and the like are remarkably improved.