44 results about "High speed vision" patented technology

A high-speed vision sensor includes: an analog-to-digital converter array 13, in which one analog-to-digital converter 210 is provided in correspondence with all the photodetector elements 120 that are located on each row in a photodetector array 11; a parallel processing system 14 that includes processor elements 400 and shift registers 410, both of which form a one-to-one correspondence with the photodetector elements 120; and data buses 17, 18 and data buffers 19 and 20 for data transfer to processing elements 400. The processing elements 400 perform high-speed image processing between adjacent pixels by parallel processings. By using the data buses 17, 18, it is possible to attain, at a high rate of speed, such calculation processing that requires data supplied from outside.

A high-speed vision sensor includes: an analog-to-digital converter array 13, in which one analog-to-digital converter 210 is provided in correspondence with all the photodetector elements 120 that are located on each row in a photodetector array 11; a parallel processing system 14 that includes processor elements 400 and shift registers 410, both of which form a one-to-one correspondence with the photodetector elements 120; and data buses 17, 18 and data buffers 19 and 20 for data transfer to processing elements 400. The processing elements 400 perform high-speed image processing between adjacent pixels by parallel processings. By using the data buses 17, 18, it is possible to attain, at a high rate of speed, such calculation processing that requires data supplied from outside.

A high-speed vision capture apparatus of a moving object characteristic belongs to the image processing field and the machine vision image measurement field. In the high-speed vision measurement, a real-time processing speed is not fast, a data volume is large and a transmission speed is low. By using the apparatus of the invention, the above problems can be solved. The apparatus comprises: a field-programmable gate array (FPGA), a digital signal processor (DSP), an advanced RISC machines (ARM) microprocessor, a network chip, an original image video graphics array (VGA) interface module, a processing image VGA interface module, a digital camera interface module, a first and a second first in first out (FIFO) data buffers. A digital camera collects an original image to the FPGA. The FPGA is connected with the original image VGA interface module and the processing image VGA interface module. A cached output terminal of the FPGA is connected with input terminals of the first and a secondFIFO data buffers respectively and is connected with the DSP. The DSP is connected with the ARM microprocessor. The ARM microprocessor is connected with a control signal input terminal of the FPGA. The ARM microprocessor is connected with a computer through the network chip.

The invention relates to the technical field of measuring instruments, in particular to a high-precision tunnel cross section detection method and a high-precision tunnel cross section detection device based on double laser bands. The device is used for measuring the tunnel cross section dimension and the limit detection, and is mainly applicable to the high-precision and high-density cross section detection of railway tunnels. A plurality of linear lasers are utilized for taking photos on the surface of the tunnels, two complete tunnel cross section outline light bands are formed, a high-speed visual system is used for collecting light band images, the images are subjected to high-speed parallel processing for extracting light band positions, the actual tunnel cross section coordinates are calculated through a system calibration technology, and the high-speed real-time tunnel cross section detection function is realized. The method and the device provided by the invention have the advantages that a camera collection region is reasonably utilized, so the cross section detection precision and the density are exponentially improved, the structure is compact, the integrality is high, and the method and the device can also be used in high-speed detection of tunnel local sensitive regions.

The invention discloses a wind tunnel separation simulation experiment system, belongs to the technical field of wind tunnel experiments, and relates to a simulation experiment system suitable for measuring the separation process of an external carried object model in the wind tunnel environment. According to the simulation experiment system, an explosive bolt is matched with a mechanical concentric sliding rail device, acting force is exerted through a feeding assistant device to complete separation between an external carried object and a master, and the separation process is measured through a high-speed visual device. By means of the wind tunnel separation simulation experiment system, the explosive bolt is matched with the mechanical concentric sliding rail device, it is guaranteed that a wind tunnel separation body model separation system is safe and reliable, the high bearing capacity and the rapid triggering capacity are achieved, the feeding assistant device is introduced to exert the adjustable feeding force to the model, the separation initial angle, the separation angle, the separation speed and the separation angular speed of the wind tunnel separation model are controlled, high consistency of the separation model separation process and the true machine separation process is guaranteed, and the whole separation process parameter measurement requirement is met due to the fact that the binocular high-speed visual device has the advantages of being high in accuracy, high in frequency response and the like.

The invention discloses high-speed visual on-line detection equipment for surface defects of steel rails, which comprises an imaging system, a low-speed parallel steel-rail moving device, a high-speed rotating device, a high / low-speed switching device, a bracket, a steel rail and a control system, wherein the high-speed rotating device and the steel rail are arranged on the high / low-speed switching device, and driven by the high / low-speed switching device, any one of the high-speed rotating device and the steel rail can move to a position below a camera in the imaging system; the high-speed rotating device comprises a high-speed rotary disc, and the upper surface of the high-speed rotating disc and the rail surface of the steel rail are arranged on the same horizontal plane; and the imaging system is arranged on the low-speed parallel steel-rail moving device, and can move along the arrangement direction of the steel rail when driven by the low-speed parallel steel-rail moving device.The equipment disclosed by the invention has the advantages of simple and compact structure, low cost, easy operation, high degree of automation, high precision, rapid detection speed, and the like.

The invention relates to a high-speed visual positioning and correction system of a solar cell piece and a method of the high-speed visual positioning and correction system. The system comprises an image acquisition module, an image processing module, a motion control module and an action execution module which are sequentially connected, wherein the image acquisition module is used for automatically acquiring an image of the solar cell piece on an automatic production line of the solar cell piece, the image processing module is used for analyzing the acquired image of the solar cell piece and positioning the image of the solar cell piece, and the motion control module is used for controlling the action execution module to perform position correction on the solar cell piece. The method comprises the steps of 1) acquiring a standard position and a standard angle of the solar cell piece by the system in an initialization way; 2) acquiring a current position and a current angle of the solar cell piece by the system during subsequent running; and 3) correcting the position and the angle of the solar cell piece. The system has the advantages of high positioning and angle accuracy, fast positioning speed, high automation and the like, and labor is saved.

The invention discloses a high-speed visual positioning and double-station flexible mounting device, and mounting method thereof. The high-speed visual positioning and double-station flexible mountingdevice comprises a base, an X-axis motion module, a Y-axis motion module, a vacuum adsorption platform, a first material conveying device, a second material conveying device, a left mounting module,a right mounting module and a CCD visual positioning module; the X-axis motion module and the Y-axis motion module are arranged on the base, and the X-axis motion module can move left and right on thebase, the Y-axis motion module can move front and back on the base, the X-axis motion module and the Y-axis motion module are arranged vertically, and the Y-axis motion module is located below the X-axis motion module, the vacuum adsorption platform is fixed on the Y-axis motion module, and the left mounting module, the right mounting module and the CCD visual positioning module are arranged on the X-axis motion module. According to the device and the mounting method thereof, can effectively save the movement distance and the device space, and greatly improve the mounting speed and precisionrequirements.

The invention belongs to the field of material counting packaging, and particularly relates to a high-speed vision counting machine based on a CCD. The high-speed vision counting machine comprises a feeding unit, a recognition unit, a discharging processing unit and a data processing and control unit. The feeding unit comprises a feeding hopper, a vibration conveying device and a material guidinggroove. The vibration conveying device is located at the outlet position of the feeding hopper and is used for conveying materials in the feeding hopper into the material guiding groove. The discharging processing unit is located below the material guiding groove and used for receiving materials falling down from the interior of the material guiding groove. The recognition unit comprises a light source and a CCD image sensor matched with the light source. The light source is located above the material guiding groove. The CCD image sensor is located below the material guiding groove, so that the materials fall into the discharging processing unit from the material guiding groove to be recognized by the CCD image sensor. The data processing and control unit is connected with the recognitionunit through a circuit and collects and processes recognition data of the recognition unit, and material counting is finished.

The invention discloses a fast corner detection method for signal processing of a time domain vision sensor, Different from 'frame sampling' imaging method, vision sensor is sensitive to light intensity change in shooting scene, and its output visual information has the characteristics of real-time, very low redundancy and small amount of data. Compared with the traditional frame sampling imagingmethod, the processing and storage requirements are greatly reduced, so it is more suitable for high-speed vision applications. The invention adopts an event-driven mode, and judges whether each inputevent is generated by a corner point according to the temporal-spatial correlation between the events. In the calculation process, the 'local closest event distribution map' centered on the input event is first constructed, and then the 'local closest event distribution map' is partitioned and statistically and binarized. According to the obtained partition binary representation, the table-lookupmethod is used to determine whether the input event is generated by the corner point or not. In addition to corner detection, this method can simultaneously judge the direction and type of corner points, and provide more abundant feature information for further target recognition.

The invention relates to a method and a system for estimating the relative position of a vehicle based on high-speed visual characteristic point matching, which includes: utilizing a high-speed camerato capture a video image to the ground under the vehicle and extracting video frame characteristic points; calculating a moving amount of the current frame relative to the previous frame according tothe video frame characteristic points of the previous two frames; calculating the position of the vehicle in the current frame according to the heading angle, longitude and latitude of the vehicle atthe previous time, and the amount of movement between the two images. The invention adopts a downward-arranged high-speed camera, takes a road surface image as a reference, adopts an ORB feature matching algorithm, and performs self-position estimation, thereby improving position estimation accuracy.

The invention discloses a cooperative-target-based real-time global search method for high-speed vision measurement and relates to a marking-point search method. By using the real-time global search method, the problems that in the high-speed vision measurement, the global search process is overlong in time consumption and is sensitive to the resolution of a camera, and the updating rate of a system is limited by the moving speed of the target are solved. In a data preprocessing module, parallelized data are outputted to a data buffering control module and a marking-point real-time detection module simultaneously. After the marking-point real-time detection module detects a marking-point pixel, subsequent related data of marking points are sent to an operating module which is in a multi-production-line structure; and after the transmission of a frame image is ended, coordinates of all the marking points can be outputted, and mass-center data of the marking points are obtained by calculation and is stored into a corresponding cache. The real-time global search method disclosed by the invention has the advantages that the global search process is short in time consumption, good in robustness and insensitive to the resolution to the camera and the moving speed of the target. The real-time global search method is applicable to the image processing field and the vision-measuring field.

The invention discloses high speed visual detection and recognition equipment. The high speed visual detection and recognition equipment comprises a main body support, a bearing platform, a first moving mechanism, a first shooting device and a control device, wherein the bearing platform is arranged in the main body support and used for placing and conveying to-be-detected and recognized finishedcircular boards; the first moving mechanism is arranged at the top of the main body support and can move in the Y-axis direction; the first shooting device is arranged on the first moving mechanism and used for shooting the finished circuit boards; the control device is arranged in the main body support, is connected with the first moving mechanism and the first shooting device and is used for controlling. The high speed visual detection and recognition equipment disclosed by the invention has the advantages of low quantity of required shooting devices, high degree of automation and high shooting efficiency.

The invention provides an anti-collision system of a high-speed motion mechanical arm. The anti-collision system comprises a high-speed vision capturing hardware system, a rapid identifying, trackingand positioning system, an initialization reference list module, a wafer reference list comparison module, a mechanical arm mark detection module and a pre-warning module; a work beat video in the normal working process is acquired, and a relation table of the position, the speed and the accelerated speed of the wafer carrying mechanical arm and the time; the circle center position coordinate, thespeed and the accelerated speed information of the wafer are acquired through the vision capturing hardware system and the identifying, tracking and positioning system to be compared with the data stored in the initialization reference list module; marks are made at the fixed positions on the two sides of the edge of the wafer, and the relative position relation between the wafer and the mechanical arm holding structure is determined by acquiring whether the information of the marking points on the mechanical arm exist or not; and the differential value of the motion state is calculated according to the calculated wafer position motion state and the built reference table, and the collision pre-warning device is started once the differential value surpasses the set threshold value. The anti-collision system achieves collision vision detection of high-speed motion objects in a low-cost and high-precision mode, and has the universality.

The invention provides a high-nitrogen steel arc additive system based on high-speed vision and electrical parameter cooperative sensing control and a control method thereof. The system comprises an additive robot, a CMT power supply, a CMT welding gun, a laser, a high-speed camera, an electrical signal acquisition unit and an upper computer controller; and the high-speed camera and the laser arefocused at the tail end of a welding wire and used for collecting a molten drop transition image, and the upper computer controller is used for receiving the molten drop image collected by the high-speed camera and current and voltage waveforms collected by the electric signal collecting unit and extracting the molten drop size in the image. The arc additive method comprises the steps that moltendrops formed in the pulse stage are made to complete transition in the CMT stage, then the diameter of the molten drops formed in the pulse stage serves as feedback quantity through the upper computercontroller, and pulse peak current time and pulse peak current magnitude serve as control quantity; and on the basis that good forming of each deposited metal is guaranteed, splashing caused by explosion due to too large molten drops is reduced, the high-nitrogen steel welding wire arc additive stability is improved, and the splashing clearing workload is reduced.

The invention discloses a high-speed visual detection device for soft magnetic cores, which includes a device table, on which a feed turntable, a servo drive unit, a workpiece position adjustment module, a photoelectric switch, a front station CCD and a light source module are arranged. , rear station CCD and light source module, left station CCD and light source module, right station CCD and light source module, upper station CCD and light source module, lower station CCD and light source module and industrial computer, the feeding carousel passes through The rotation fixing mechanism is arranged on the device table, and the kicking module station is provided on the feeding turntable, and the kicking module station is fixed on the feeding turntable by a buckle mechanism, and the cross section of the kicking block body is The fan-shaped structure and the angle formed after the opposite two sides are extended are 60°. The invention has the advantages of simple structure and strong practicability.

The invention relates to the technical field of motion detection, in particular to a motion detection method based on a pulse array. The method comprises the following steps: collecting space-time signals of a monitoring area to generate a space-time pulse array; inputting the space-time pulse array into a pulse neural network, wherein pulse neurons in the pulse neural network process a space-time pulse sequence with motion characteristics and generate corresponding pulses; and obtaining motion information of different spatial positions according to the pulses generated by the pulse neural network. According to the method, the time-space characteristics of the pulse array obtained by the high-frequency retina camera are utilized, the visual pulse sequence is directly used as input, various motion states existing in the monitoring area are obtained, parameter information corresponding to the motion states is obtained, the output motion information can be used for object tracking, motion compensation and the like, and the accuracy of motion compensation is improved. Therefore, subsequent high-level visual tasks such as detection, recognition and tracking of high-speed visual objects based on pulse signals are facilitated.

The invention discloses a method and a device for measuring the rotating speed of a table tennis ball. The method comprises the following steps of: constructing a coordinate system, setting an image acquisition range and acquiring an image; identifying a mark of a table tennis ball and acquiring a main direction of the mark; calculating an included angle alpha between the main direction and the xaxis of the coordinate system; obtaining an included angle beta between the main direction of the mark of the table tennis ball in the image and the x axis of the coordinate system after a time interval T; obtaining the rotating direction of the table tennis ball according to the angle difference between the included angle alpha and the included angle beta; and calculating the rotating speed omegaof the table tennis ball according to the angle difference and the time interval T. According to the invention, the characteristics of the table tennis ball in the small-range image are analyzed by setting the image acquisition range, so that the defects of large transmission data volume and low speed in the traditional high-speed vision field are overcome, and the rotating speed of the table tennis ball can be calculated in an extremely short time.

The invention discloses a classified screening assembly line which comprises a modularized rack, a classified output device, a high-speed visual detection device, a modularized putting device, an overturning conveying device, a third material arranging device, a second material arranging device, a first material arranging device, a feeding device, a vibrator, a belt conveyor, a support, a roller and an air cylinder. According to the classified screening assembly line provided by the invention, an independently researched and developed high-speed visual detection system is adopted, and a product rotates on a conveying rotating wheel of the overturning conveying device on the overturning conveying device, so that 360-degree high-definition detection of materials can be completed in the rotating process of the materials, the problems that the detection is unreliable and the accuracy is low due to single detection at several angles are solved, the original sorting efficiency is improved by 6 to 8 times, and the accuracy can be greatly improved through a deep learning system.

The invention belongs to the field of EAST plasma optical edge reconstruction, and particularly relates to a reconstruction method and system based on high-speed visual diagnosis and a BP neural network, and the method comprises the steps: collecting the corner coordinates of a plasma discharge image, and obtaining a corresponding matrix from the pixel coordinates of the image to the physical coordinates during plasma discharge; introducing non-linear variables to add variables and variable characteristics to the data; constructing a BP neural network, setting a learning rate and an allowableminimum error of the BP neural network, and performing training by utilizing data; packaging the trained BP neural network, taking real-time data as the input of the neural network, and predicting theplasma optical edge in the real physical world. According to the method, the problem that the plasma optical edge is reconstructed in the process of predicting the coordinates of the corner points inthe next unknown time period on the EAST device is solved.

The invention discloses a method for measuring the latency of multiple pesticide fog drops impacting a leaf surface based on high-speed visual coupling contour feature extraction. Comprising the following steps: building a high-speed visual capture system, calibrating a high-speed camera system, collecting fog drop impact leaf surface images, preprocessing video images, selecting an ROI (Region of Interest) region, identifying pesticide fog drops, extracting pesticide fog drop contours, extracting pesticide fog drop centroids, and tracking and timing pesticide fog drops, so as to obtain the delay of multiple pesticide fog drops to impact the leaf surfaces. According to the invention, a quantitative analysis means is provided for optimizing pesticide spraying parameters, especially for controlling the pesticide application amount, optimizing the droplet spectrum distribution and blending the pesticide liquid content; the obtained measurement result has theoretical significance and application value for developing a precise pesticide application technology and improving the deposition efficiency of tea tree pesticide spray.

The invention provides an FPGA-based high-speed visual positioning system. The FPGA-based high-speed visual positioning system comprises an upper computer, a linear CCD camera and an FPGA control board card; the FPGA control board card is provided with an upper computer interface and a linear CCD camera interface and is further provided with an image acquisition signal generator, an image processing module and a position calculation unit; the image processing module synthesizes a plane image according to sampling frequency; and the position calculation unit calculates the current position of paper and transmits the current position to the upper computer through the upper computer interface. The FPGA-based high-speed visual positioning system performs image acquisition by the linear CCD camera and performs intelligent image processing, and can adapt to more quantity and types of paper, thereby improving the diversity of printing products and the adaptability of the positioning system.

The invention discloses high-speed visual on-line detection equipment for surface defects of steel rails, which comprises an imaging system, a low-speed parallel steel-rail moving device, a high-speed rotating device, a high / low-speed switching device, a bracket, a steel rail and a control system, wherein the high-speed rotating device and the steel rail are arranged on the high / low-speed switching device, and driven by the high / low-speed switching device, any one of the high-speed rotating device and the steel rail can move to a position below a camera in the imaging system; the high-speed rotating device comprises a high-speed rotary disc, and the upper surface of the high-speed rotating disc and the rail surface of the steel rail are arranged on the same horizontal plane; and the imaging system is arranged on the low-speed parallel steel-rail moving device, and can move along the arrangement direction of the steel rail when driven by the low-speed parallel steel-rail moving device. The equipment disclosed by the invention has the advantages of simple and compact structure, low cost, easy operation, high degree of automation, high precision, rapid detection speed, and the like.

The invention discloses a high-speed visual flexible circuit board placement machine, which structurally comprises support legs, a placement machine, a longitudinal guide rail bracket, a transverse guide rail bracket, a transverse chain, a placement head, a longitudinal chain and a servo motor. In order to achieve working of a plurality of suction nozzles of the high-speed visual flexible circuitboard placement machine, to reduce the overall occupied space of equipment and to improve the product placement speed, the placement machine is provided with the placement head and the placement headsucks products by adopting a first suction nozzle and a second suction nozzle, so that the production efficiency is improved, the placement accuracy is ensured and the suction time of each product isshortened; a tray bouncing and clamping-type lifting mechanism is arranged in the placement machine and the overall occupied space of the equipment is reduced by using the tray bouncing and clamping-type lifting mechanism, so that the equipment can adapt to a placement position in a workshop; and the products are quickly pushed through a tray push mechanism, so that the product placement efficiency is improved, and the high-speed visual flexible circuit board placement machine is reasonable in design and practical.

The invention relates to a power transmission line insulator string windage yaw motion attitude measurement device and measurement method. The measurement device comprises a video online monitoring device and an image processing and identification unit. The video on-line monitoring device is arranged at the bottom of the tower, the direction of a camera of the video on-line monitoring device is anobliquely upward direction, and video images of the insulator string during on-line operation are acquired and sent to the image processing and identification unit; the image processing and identification unit calculates the displacement of the insulator string in space and corresponding time information based on high-speed visual dynamic measurement. Video images of an insulator string during online operation are collected through a visible light camera; a non-contact visible light image processing technology is adopted to automatically monitor insulator string swing, the swing frequency, direction and amplitude of the insulator string and the stress condition are analyzed, processed, calculated and judged through an image processing algorithm, hidden dangers are warned in advance, the online monitoring level of a line is improved, and safe and stable operation of a power grid is guaranteed.

The invention discloses a method and system for continuously exciting crystallization. The method comprises the following steps of controlling a laser generator to emit laser, and refracting and focusing the laser at a specified position of a test tube, averaging the radius of the bubbles of the plurality of image frames acquired at the same moment in two directions to obtain the average radius of the bubbles at the moment, calculating the average radius of each frame of image from bubble generation to disappearance, obtaining an array of the average radius of the bubbles corresponding to time, and fitting to obtain a function r=f(t) of the average radius of the bubbles and the time, controlling a plurality of laser generators to emit at intervals or circularly emit at intervals for continuous excitation, the continuous excitation being that when the moment tx meets f(tx-tx-1)=R, the laser generators are controlled to emit, and R is smaller than the maximum radius of bubble diffusion and is greater than the product of the system interval excitation duration and the bubble diffusion speed. According to the method and the system, a plurality of lasers are fed back and controlled to continuously excite in sequence after high-speed visual capture and fitting, and a gradually increased supersaturation gradient is locally formed in the solution, so that the discovery of a new crystal form is facilitated.

The invention discloses a high-speed visual positioning device and method applied to a substrate. The high-speed visual positioning device applied to the substrate comprises a frame, a temporary storage area, a positioning area, a transport positioning device, at least two visual devices arranged on the frame and a carrier plate, wherein the transport positioning device is movably arranged on theframe and is used for absorbing and transporting a plurality of substrates; the transport positioning device comprises an I-shaped absorbing head which is used for absorbing the plurality of substrates sequentially; the at least two visual devices correspond to the I-shaped absorbing head and are used for capturing an image of each substrate absorbed by the transport positioning device so as to position the plurality of substrates; and the carrier plate is arranged on the frame.