24 results about "Frame grabber" patented technology

The invention relates to a data fusion method based on a multi-channel image acquisition card and related equipment, and the method comprises the following steps: synchronously receiving a multi-view target scene shot by a camera through the multi-channel image acquisition card, and obtaining original multi-channel image data; performing geometric correction on the original multi-channel image data to obtain a geometric correction image group, and performing space-time coordinate conversion based on the geometric correction image group to obtain a space-time registration image group; performing cross-scale feature aggregation on the space-time registration image group to obtain a multi-scale feature pyramid layer, and constructing a multi-scale feature pyramid based on the multi-scale feature pyramid layer; and carrying out adaptive weight convolution fusion on the multi-scale feature pyramid to generate a target fusion image, thereby solving the technical problems that most methods depend on a complex preprocessing process or have relatively strong hypothesis for a specific scene and are difficult to adapt to a dynamically changing real environment.

The invention discloses a data encryption method, which comprises the following steps that: a Web server sends a private key to a display card, then sends the private key to an image acquisition card and then sends the private key to a database server, and the database server encrypts a result of querying a database by using the private key and sends the encrypted result to the display card; according to the technical scheme of the invention, the data output by the Web server is encrypted through the video card / image acquisition card, then the database server sends the encrypted data to the Web server through the video card / image acquisition card, and the Web server sends the encrypted data to the user computer, and the method has the advantages that after the technology is used, the data output by the Web server is encrypted, and the data in the database server is safe, so that the data is very effectively protected.

The application relates to an online monitoring device and method for microelectrodes, and belongs to the technical field of special machining.The online monitoring device is composed of a coaxial holographic imaging module, an LED backlight imaging module, a motion control module, an image acquisition card, a laser power controller and an LED brightness controller.The LED backlight imaging module is used for positioning the microelectrode image; the coaxial holographic imaging module is used for holographic interference imaging of the microelectrode; based on a holographic reconstruction algorithm, electrode profile information is obtained, and the electrode loss degree is judged.The coaxial holographic imaging module and the LED backlight imaging module switch the positions of the reflecting mirrors through the motion control module to realize control of different imaging modes; the collected images are input into a PC through the image acquisition card, image algorithm analysis is carried out, and the microelectrode loss degree is judged.The application realizes online monitoring of the microelectrode loss.

The invention relates to the technical field of image acquisition and transmission, and discloses a high-resolution image acquisition and transmission method and device, equipment and a storage medium. The method comprises the following steps: performing multi-stage downsampling and feature extraction processing on a high-resolution original image acquired by an image acquisition card to obtain global image features and regional image features; performing random delay and data loss characteristic analysis on historical communication data of the image acquisition card to obtain a probability distribution model and a continuous data loss record; performing multi-scene prediction on the future transmission state of the image acquisition card to obtain prediction state information; and generating a self-adaptive transmission control strategy according to the prediction state information, the global image features and the regional image features, and executing a high-resolution image transmission process to obtain a high-resolution image transmission result. According to the method, the optimal distribution of transmission resources is realized on the premise of ensuring the image quality, and the problem of insufficient adaptability of traditional fixed parameter control in a complex network environment is solved.

The utility model relates to the technical field of dimming film production, and discloses a film laminating machine for dimming film production, which comprises a film laminating machine body, a base and a detection mechanism, the base is fixedly arranged at the bottom end of the film laminating machine body, the detection mechanism is fixedly arranged at the top end of the base, and an auxiliary mechanism is fixedly arranged at the upper end of the detection mechanism; the detection mechanism comprises mounting rods, a first gear motor, a conveying belt, a U-shaped plate, an industrial camera, a light supplementing lamp, an image acquisition card, a PC controller and a supporting rod, the mounting rods are fixedly arranged on the two sides of the top end of the base, and the first gear motor is fixedly arranged on one side of each mounting rod; and the output shaft end of the gear motor I penetrates through the mounting rod and is fixedly provided with a conveyor belt. According to the film laminating machine for producing the light adjusting film, by arranging the detection mechanism, quality detection can be conveniently conducted on the produced light adjusting film, defective products with scratches and bubbles can be conveniently removed in time, the product quality is guaranteed, the working efficiency is improved, and the practicability is improved.

The invention discloses a regional slow and small target group tracking method, which mainly solves the problem of low real-time performance of multi-target tracking of a large-size image and improves the visible light target detection and tracking capability of a target range. The implementation scheme is as follows: 1, an image acquisition card acquires a high-resolution visible light grayscale image in real time; 2, each frame of image is divided into a plurality of areas, a plurality of threads are started at the same time, and target detection and tracking are carried out on each area image block through one thread; performing synchronous processing on the main thread and the plurality of sub-threads; 3, using a constrained local adaptive threshold method to detect a target group for the image block; 4, performing target group tracking on a detected target group in a single image block by adopting Kalman filtering and a Hungary algorithm; 5, when the target moves across the seam, unified target tracking ID processing is carried out on the target at the seam; and 6, outputting the miss distance and the gate of each frame of target group. According to the invention, dynamic scene aerial target group detection can be realized, the tracking processing time of a large-size image is reduced, and the detection and tracking capability of a visible light target in a target range is improved.

The application discloses a kind of floating bridge linear automatic control system based on computer vision, including shore-based control end and several floating ship control ends, shore-based control end is set in river bank, shore-based control end includes camera, image acquisition card and industrial computer, floating ship control end is respectively set on each floating ship and is located in same side, floating ship control end includes target on floating ship, environmental data acquisition unit and drive unit for driving floating ship to move, camera is used to monitor and capture target image on several floating ships, and image is converted into digital signal by image acquisition card and transmitted to industrial computer, industrial computer is used to analyze image and judge whether floating bridge linear deviation exceeds preset threshold, and according to the judgment result, environmental data acquisition unit is controlled to collect information, and industrial computer is analyzed to control drive unit to drive floating ship to move adjustment.The application realizes the automatic monitoring and adjustment of floating bridge linear, improves the adjustment efficiency and accuracy, enhances the stability and safety of floating bridge.

The invention discloses a hardness indentation measurement method based on artificial intelligence image segmentation, which comprises the following steps of: 1, acquiring an image of a measured object through a CCD (Charge Coupled Device) camera, and transmitting the acquired image of the measured object to a computer; step 2, in a computer, an image acquisition card is responsible for acquiring and transmitting an image and transmitting the acquired image to an image segmentation module, the image segmentation module segments an original image and segments the image into different areas, and each area represents a potential hardness indentation; step 3; step 4, dynamic automatic measurement is realized; 5, generating a corresponding indentation dynamic measurement report; 6, outputting the dynamic indentation measurement report through a computer, and displaying the dynamic indentation measurement report to a user; according to the method, the image segmentation technology is adopted, the image can be accurately segmented into different areas, potential hardness indentations can be identified and detected, and compared with a traditional manual measurement mode, higher measurement precision can be provided.

1. Name of the product in this design: Video capture card (active cooling). 2. Application of this design: It is used in image acquisition cards, video acquisition cards, and audio acquisition cards, aiming to acquire and compress audio and video signals in real time and display them on one or more devices. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The invention discloses an image sensor testing system, a smudginess testing method and related equipment, the image sensor testing system comprises a closed dome light source and a support, the support is provided with an acquisition inlet used for placing an image sensor, and the acquisition inlet is located in the center of the bottom of the dome light source; the image acquisition card is used for being connected with the image sensor; and the control end is connected with the image acquisition card and is used for performing acquisition control and smudginess test analysis on the image sensor.

The present application relates to a kind of carbon fiber cloth surface defect detection device based on artificial intelligence, it solves how to improve the technical problem of carbon fiber cloth surface defect detection accuracy, speed.It includes CIS line array camera, image acquisition card and controller, CIS line array camera is set in the upper carbon fiber cloth, image acquisition card is electrically connected with controller, CIS line array camera is electrically connected with image acquisition card, carbon fiber cloth surface defect detection device is configured to detect white spot defect, judges white spot according to the gray value of CIS line array camera acquisition image.The present application is widely applied to carbon fiber cloth production process.

1. The name of the design product: anode frame taking device. 2. The use of the design product: the design product is used for taking out anode frame in anode oxidation process. 3. The design points of the design product: in shape. 4. The picture or photo that best shows the design points: perspective view 1.

The utility model relates to the technical field of storage equipment, in particular to a miniature intelligent storage shelf. According to the technical scheme, the goods shelf comprises a goods shelf body, a plurality of storage cells used for storing goods and materials are arranged in the goods shelf body, a PLC used for control and an intelligent terminal used for user interaction are arranged on one side of the goods shelf body, and a mainboard is arranged on the inner wall of the top of each storage cell; an image acquisition card used for converting video signals into digital signals, an embedded processor and a camera are arranged at the bottom of the main board, an image recognition algorithm module is arranged in the embedded processor, and a pushing structure used for pushing materials out is arranged in the storage grid. Through the arrangement of the first motor, the limiting rod, the threaded rod, the connecting sleeve, the push plate, the camera, the temperature sensor, the embedded processor and the PLC, after needed goods and materials are retrieved, the goods and materials can be pushed out through the pushing structure, self-searching is not needed, and the time needed for taking the goods and materials is shortened.

The application relates to an imaging detector chip vibration displacement testing device and method, which comprises an LED plane light source, a homogenizing plate, an imaging lens and an image acquisition card; the LED plane light source illuminates the imaging lens after passing through the homogenizing plate, and the position of the imaging detector chip to be tested is adjusted through a gasket so as to be just located at the focal plane position of the imaging lens; the imaging lens comprises a lens barrel, a diaphragm and a double-sided convex lens which are sequentially arranged in the inner cavity of the lens barrel according to the light path; the lens barrel adopts an integrated forming process to first mill the inner cavity of the lens barrel and finally mill a small hole; the image acquisition card is connected to the imaging detector to be tested, and the image data is read by an upper computer. After the plane light source is homogenized by the homogenizing plate to form diffuse reflection, a point light source is formed through the small hole, small spot imaging is realized by using single-lens imaging, and finally the spot centroid is directly represented by the image plate to represent the chip displacement.

The invention discloses a visual fusion detection device and method for quality grading of picked fruits and vegetables, and relates to the technical field of agricultural automatic detection and sorting, the device comprises a support frame, the front end of the frame is provided with an inclined slideway for feeding, the end face of the frame is provided with a constant-speed conveyor belt, and the rear end of the frame is provided with a grading guide plate and a push rod electromagnet. A detection box body is arranged at the upper end of the frame, a lighting source, an industrial color camera and a background plate are arranged in the box body, a control box is arranged outside the box body, and an image acquisition card and a logic judgment controller are arranged in the control box. The method comprises the steps that the industrial color camera collects images of single fruits and vegetables on the conveying belt, the image collection card converts image signals, the logic judgment controller conducts comprehensive judgment according to preset colors, flaws and size threshold values, the push rod electromagnet is controlled to act, the fruits and vegetables are pushed into the designated grading guide plate, and automatic grading is achieved. According to the invention, rapid, accurate and non-destructive detection and grading of the quality of picked fruits and vegetables are realized.

The embodiment of the invention relates to the technical field of image acquisition, in particular to a scene adaptive acquisition method and system for an image acquisition card, and the method comprises the steps: carrying out the collection and conversion of an optical signal of an optical field of view based on an image acquisition mode, and obtaining original image data; and arranging the original image data at each moment to generate an image information stream, analyzing a visual target and an environment scene for the optical field of view to obtain image acquisition scene characteristics, selecting key frames for the image information stream according to the image acquisition scene characteristics to obtain a reference information set, and sending the reference information set to a cloud server, and carrying out adaptive analysis of image acquisition on the reference information set through an optical acquisition algorithm pre-deployed in a cloud server so as to issue an optimization instruction to optimize an image acquisition mode.

The invention discloses a horizontal adjustment method for a double-light-path laser. The horizontal adjustment method comprises the following steps: S1, installing and debugging a horizontal adjustment device for the double-light-path laser; S2, emitting a left light beam and a right light beam by the laser; s3, detecting image points of the left light beam and the right light beam to acquire image acquisition information, acquiring the image acquisition information of the left and right side image detection components through an image acquisition card, and generating corresponding data; and S4, processing the data through a computer, and controlling and adjusting the position parameters of the laser based on a preset strategy when a processing result does not meet a specified condition until the processing result meets the specified condition, thereby completing the horizontal alignment adjustment of the laser. Precise adjustment is carried out by adopting a digital means, and horizontal alignment adjustment of the double-light-path large-size linear long-strip light beam laser can be realized through a high-precision visual sensor and an image processing technology.

The present application relates to the technical field of strip continuous processing line equipment control in the metallurgical industry, and specifically discloses a disc shear front weld precise positioning system and method based on WPD and visual fusion, which comprises a WPD detection module, a visual detection module, an L1 data fusion module and a tracking execution module; the WPD detection module is installed on the strip running path and outputs a weld on-off signal; the visual detection module is installed downstream of the WPD detection module, and comprises an industrial camera, an image acquisition card and image processing software, and is used for weld contour identification and position output; the L1 data fusion module is arranged in the L1 level control system of the unit, and is used for data receiving, checking and fusion calculation; the tracking execution module receives the corrected data, updates the strip tracking model and controls the disc shear action; the present application realizes the complementary advantages of the two modes, improves the weld detection rate and positioning accuracy under high-speed working conditions, and ensures the stable operation of the disc shear.

The utility model relates to intelligent robot technical field, concretely is a kind of intelligent sorting robot based on visual identification, including mechanical arm and visual identification component;Visual identification component includes support frame, camera, light source and image acquisition card, camera, light source and image acquisition card are located on support frame, the number of camera is three, respectively from three angles to the sorting object to be identified and positioned.The utility model is through three camera cooperative identification system, from top and two sides synchronous acquisition image, realize the three-dimensional space full range identification and positioning of the sorting object to be, effectively solve the feature missing and positioning deviation problem caused by single visual angle.Light source adopts integrated light source and fill light combination to ensure multi-angle uniform illumination, avoid shadow interference, significantly improve the identification precision of special-shaped part and stacked part.Mechanical arm is equipped with multi-degree-of-freedom joint driver and end effector, combined with high-precision positioning data, realize fast and accurate grabbing under complex scene.

The invention provides a device and method for detecting the welding rate of a water cooling plate based on regional division, and the device comprises an X-ray generation device, an X-ray detector, an image collection card, a computer processing unit, and a display unit. The core innovation of the algorithm is that the algorithm executes the following steps: intelligent region division: dividing an X-ray image into N (N is greater than or equal to 2) sub-regions according to a preset regular grid, a runner structure contour or welding feature distribution; welding rate independent calculation: for each sub-region, calculating a ratio of an effective welding area to a theoretical welding area to generate a local welding rate; and visual output is to generate a welding quality spatial distribution diagram on a display unit, and visually present the welding state of each sub-region, so that the problems that local defects are covered and positioning is inaccurate in traditional global analysis are solved, the identification precision and the position positioning capability of micro pseudo soldering / holes are remarkably improved, and the method is suitable for quality management and control of the high-reliability electronic equipment water cooling plate.

The utility model relates to the technical field of acquisition cards, in particular to a robot vision high-speed image acquisition card which comprises an acquisition card body, a fixed block, a round block, an adjusting screw hole, a screw rod, a sliding rod, a bearing, a supporting block, an insulating rubber pad and a rotating ring. When the robot vision high-speed image acquisition card is used, a PCIE socket on one side of the acquisition card body is inserted into a PCIE card slot of a case mainboard, and then a side plate is mounted on a case through mounting screw holes by fixing bolts, so that a first data interface, a second data interface and a third data interface face the outer side of the case; then, according to the heights of the acquisition card body and the bottom of the case, the height of the screw rod can be adjusted by rotating the rotating ring, and finally, the supporting block and the insulating rubber pad at the bottom of the screw rod are in contact with the bottom of the case, so that the acquisition card body can be supported, and the PCIE socket of the acquisition card body is prevented from being stressed for a long time and being bent; and the operation of the acquisition card body is prevented from being influenced.

This utility model relates to the field of medical equipment technology and discloses a medical microscopic image analyzer, including a base. A main body is fixedly installed on one side of the upper surface of the base. An objective lens for microscopic observation of the sample to be tested is installed on the main body. An operating stage for supporting the sample to be tested is installed at the lower end of the objective lens and on the main body. The outer cover of the main body is provided with a protective structure for dustproofing, moistureproofing, and protection against corrosive gas corrosion when the analyzer is not in use. The protective structure is provided with an unfolding component for quickly switching the protective state according to whether the analyzer is in use. A disassembly and assembly component is provided at the connection between the protective structure and the base. By setting up a protective structure, this utility model can provide comprehensive and reliable protection for the analyzer in the idle state, effectively isolating dust, lint, and other particulate matter in the air and preventing them from adhering to the surface of core components such as the objective lens, eyepiece, and image acquisition card.

The utility model discloses an image acquisition card, and belongs to the field of machine vision. The image acquisition card comprises an optical module, the optical module is provided with a first optical fiber interface connected with a camera, and the optical module is used for receiving first image data sent by the camera through the first optical fiber interface; the first image data is serial data; the optical module comprises a plurality of paths of small pluggable optical modules SFP +; a field programmable gate array (FPGA) module, wherein the FPGA module is in communication connection with the optical module; the FPGA module is used for converting the first image data into second image data; the second image data is parallel data, the transmission distance of the image acquisition card is greatly increased (within 300m) by arranging the optical module, the image acquisition card is free of electromagnetic interference, wiring is convenient, and the cost is low; in addition, a plurality of paths of SFP + are arranged, so that the transmission rate is upgraded and can reach 10Gbps, and the transmission rate can be expanded.