21 results about "Machine vision system" patented technology

FIELD: underwater equipment.SUBSTANCE: invention is intended for precise automatic docking and fixation of autonomous unmanned underwater vehicles (AUVs) using bottom mooring devices (BMDs). For automatic docking and fixation of an autonomous unmanned underwater vehicle on bottom mooring devices, an underwater vehicle is used with the ability to detect bottom mooring devices using a hydroacoustic navigation system installed on it. Using the onboard control system, the underwater vehicle stabilizes its position in the working area of the manipulator with a given orientation to its grip; simultaneously with the last command, a signal is sent using the hydroacoustic navigation system of the underwater vehicle about its arrival in the area of the bottom mooring device. After receiving this hydroacoustic signal from the hydroacoustic navigation system, a machine vision system installed near the manipulator's grip is turned on, and with its help, the spatial location of the clamp of the gripping device located in the bow part of the underwater vehicle’s hull is detected, and then, with the help of the technical vision system and the manipulator control system, its open grip is smoothly moved towards the clamp until the contact sensor, located inside the gripper jaws, is triggered; upon the signal from the contact sensor, the gripper jaws are closed, fixing the underwater vehicle in the water space. Using the manipulator control system, the corresponding control signals are sent to the manipulator drives, smoothly moving the underwater vehicle to the bottom mooring device platform; during this movement, the underwater vehicle’s thrusters maintain its horizontal position; said movement of the underwater vehicle by the manipulator is completed after the activation of the locking devices located, respectively, on the underwater vehicle and the bottom mooring device. After said fixation, using contactless devices located inside the fixing devices, the underwater vehicle's batteries are recharged via a cable-rope, information is exchanged between this underwater vehicle and the accompanying vessel, or the underwater vehicle is quickly lifted onto this vessel using a winch.EFFECT: precise and rapid docking of the AUV with the charging device or with the device for its rapid ascent to the surface, as well as rigid fixation of the AUV at a given point in the water space when the onboard equipment of this apparatus performs arbitrary working operations.1 cl, 1 dwg

The application discloses a kind of tea rolling degree classification methods based on machine vision system, comprising the following steps: step 1: based on machine vision system acquisition different rolling time under tea rolling leaf sample image;Step 2: extract and analyze the color feature information of tea rolling leaf sample image;Step 3: based on portable color difference instrument acquisition different rolling time under tea rolling leaf sample color appearance index;Step 4: based on the color appearance index under different rolling time, obtain the variation law of color appearance index with rolling time;Step 5: based on color feature information and the variation law of color appearance index with rolling time, the classification model of tea rolling degree is established by CNN-SVM algorithm, the application based on machine vision system establishes objective quantization tea rolling degree classification method, realizes the quality quality of product and the quality quality of product of precision control tea processing process.

An apparatus for adjusting a display of a graphical user interface (GUI) based on image data. The apparatus includes a machine vision system configured to capture images of real-world objects within an environment, at least a processor; and a memory coupled to the processor. The memory contains instructions configuring the processor to receive input data objects, comprising image data and location data, using the machine vision system, process the image data using the machine vision system to extract and classify components of the visual inputs, generate structured environmental data based on the processed image data, and modify the GUI based on the input data objects and the structured environmental data. The image data is cross-referenced with applicable regulatory mandates by performing real-time safety assessments and compliance checks based on visual inputs of the image data.

The application provides a vegetable precise root cutting device based on intelligent row-omnidirectional profiling, comprising: a rack; a portal frame type track walking mechanism connected with the front end of the rack; a profiling mechanism installed at the frontmost of the rack; a cutting mechanism installed at the rear of the profiling mechanism and connected with the rack and the profiling mechanism; a machine vision sensing system and a control system, the control system being respectively communicatively connected with the portal frame type track walking mechanism, the machine vision system and the cutting mechanism; wherein a displacement sensor detects the vertical displacement generated when the profiling plate touches the ground in real time and converts it into an electrical signal to feed back to the control system, the control system receives the topographic displacement signal fed back by the displacement sensor and cooperatively drives the cutting height adjusting electric push rod and the cutting angle adjusting electric push rod to dynamically adjust the ground clearance and working inclination angle of the disc cutter; and the application effectively improves the precision of the root cutting position, the integrity of the cut, and the adaptability of the machine to different vegetable varieties and complex field environments.

This application relates to a path tracking control method, apparatus, device, and storage medium for a transportation equipment cluster. The path tracking control method for the transportation equipment cluster includes: calculating an initial path deviation based on road images collected by a lead transportation equipment in the cluster; optimizing the initial path deviation to obtain visual navigation parameters; determining the steering angle of the lead transportation equipment based on the visual navigation parameters, and mapping the steering angle of the lead transportation equipment to the steering angles of the other transportation equipment in the cluster; and controlling each transportation equipment in the cluster to perform a steering action according to the corresponding steering angle. This application eliminates the need to install visual sensors on other transportation equipment besides the lead transportation equipment, reducing hardware deployment costs. Furthermore, by using the steering angle of the lead transportation equipment to map the steering angles of other transportation equipment, it fundamentally avoids angle command conflicts caused by sensor error accumulation and differences in lighting conditions in multi-machine vision systems.

Method and arrangements for providing one or more annotated training images (336) for use in training of a trainable image content recognition algorithm of a machine vision system (205) that is operative, by means of the trainable image content recognition algorithm, to recognize content in images captured by the machine vision system (205). Annotation information (337) is obtained (301) for one or more intermediate images (338) to be captured by the machine vision system (205) and indicates properties of content in said intermediate images (338). The machine vision system (205) is operated (302) so that said one or more intermediate images (338) are captured by the machine vision system (205) in accordance with the obtained annotation information. It is provided (303) one or more annotated intermediate images (339) that correspond to said one or more intermediate images (338) captured by the machine vision system (205) with annotation in accordance with the obtained annotation information (337). Said one or more annotated training images (336) are then provided (306) based on at least one of said annotated intermediate images (339).

This invention belongs to the field of agricultural product storage management technology, and specifically to a blockchain-based intelligent agricultural product storage management method and system. The method includes the following steps: Data acquisition and preprocessing: Before agricultural products enter the warehouse, image processors, semiconductor lasers, and machine vision systems deployed on the inspection conveyor belt are used to detect surface defects, dimensions, and physical characteristics of the agricultural products in real time, generating inspection data containing unique identifiers for each product. Semiconductor lasers and other equipment are used to accurately detect surface defects, dimensions, and physical characteristics of the agricultural products, eliminating substandard products and ensuring the quality of products entering the warehouse from the source. Simultaneously, with the help of blockchain technology, the entire lifecycle data of agricultural products, from field inspection to logistics trajectory, is accurately recorded and cannot be tampered with. Users can clearly retrieve this information through the traceability terminal module, achieving full-process traceability of agricultural products, providing strong support for agricultural product quality supervision, and ensuring consumer food safety.

This application discloses an adaptive adjustment method for the closure of a side span of a long-span cable-stayed bridge, relating to the field of bridge construction technology. The closure construction method includes: deploying a multi-point machine vision system at the side span, main span, and closure joint to achieve real-time monitoring of three-degree-of-freedom micro-displacement and cantilever deformation, with calibration synchronized with a clock; performing displacement trajectory prediction and risk assessment based on an artificial intelligence algorithm adapted through transfer learning and pre-training using multiple construction data; implementing closed-loop adjustments for cable tensioning, vertical jack height adjustment, and lateral alignment of sliding supports based on model predictive control; and establishing electronic fences for elevation, axis, and angle within the monitoring field of view to achieve proactive safety protection and pre-correction. Compared with existing technologies, this invention features a highly integrated system with advantages in proactive pre-correction, comprehensive environmental perception, and intelligent prediction and control, improving the accuracy and efficiency of closure construction, reducing cantilever section waiting time, shortening the construction period, and lowering construction costs.

1. Name of the product in this design: Telecentric Lens (0.7X). 2. Purpose of this design: For precision inspection in machine vision systems. 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 present disclosure generally relates to machine vision systems, illumination sources for use in machine vision systems, and components for use in the illumination sources. More specifically, the present disclosure relates to machine vision systems incorporating multi-function illumination sources, multi-function illumination sources, components for use in multi-function illumination sources, machine vision systems incorporating hidden strobe technology, and light emitting diode strobe power management.

This invention relates to the field of monocrystalline silicon production technology, specifically to a visual shoulder-forming method for monocrystalline silicon, comprising the following steps: S1: configuring and calibrating a machine vision system outside the observation window of the monocrystalline furnace, establishing a mapping relationship between the image pixel coordinate system and the actual physical dimensions; S2: acquiring liquid surface reflection images in real time during the shoulder-forming stage and performing preprocessing to extract crystal diameter, crystal alignment, aperture features, and solid-liquid interface contour; S3: performing Kalman filtering on the real-time calculated diameter, alignment, and shoulder angle for time-series smoothing, suppressing measurement noise and improving parameter stability. This invention achieves fully automated operation of the entire shoulder-forming process, completely replacing manual monitoring and operation, significantly improving production efficiency and batch-to-batch process consistency; the crystal head diameter fluctuates less, the shoulder contour is smooth, and the diameter is excellent, effectively reducing defects such as edge lines, distortion, eccentricity, and dislocations, and significantly improving the crystal rod head forming quality.

The application discloses a method for generating a safe control file based on a picture recognition model training technology, a machine vision system is built, a picture recognition model suitable for a power scene is selected through a multi-stage verification process; an intelligent agent is developed, three collaborative intelligent agents are constructed based on a power industry special large model, a picture recognition model and an optical character recognition technology, picture information extraction, text recognition, information completion, document generation and compliance audit are realized; picture collection and model training; intelligent service interface empowerment; display and output. The application has the beneficial effects that the problems of low efficiency and repeated input of manual input are solved, the labor cost is saved by about 50%, the staff is relieved from tedious information input and checking work, focuses on core business and improves the smoothness of management process; with the help of factory station name standardization completion, intelligent audit and other functions, the standard of filling is unified, and the phenomenon that the standardization of work tickets is uneven due to the operation habits and understanding differences of personnel is reduced.

Three-dimensional machine vision system with subpixel precision are provided herein. A system configured to generate a three-dimensional (3D) image of a physical environment. The system comprises a photonic module configured to project a laser line onto a surface in the physical environment, and an imaging device configured to capture a two-dimensional (2D) image of the projected laser line. The photonic module and the surface are in relative motion in a physical y-direction. The 2D image comprising pixel columns extending in an image Y direction, which corresponds to a physical z-direction, and aligned in an image X direction, which corresponds to a physical x-direction. The system comprises a processor configured to identify an edge of the captured laser line with a subpixel precision in the image X direction.

The application relates to the technical field of brake component detection, and discloses a machine vision-based intelligent detection system and method for flatness of brake spring sheets. The method comprises the following steps: acquiring historical brake spring sheet image data, and generating a standard flatness curve according to the historical brake spring sheet image data; collecting real-time brake spring sheet image data through a machine vision system, and generating a real-time flatness curve; then calculating a flatness deviation curve according to the real-time flatness curve and the standard flatness curve; then analyzing the matching degree of the deviation curve and a reference defect model, and determining the flatness state of the brake spring sheet; finally, dynamically adjusting detection parameters based on the flatness state, and generating an optimized detection scheme. The method takes historical data as a benchmark, realizes non-contact detection by relying on machine vision, can accurately present the flatness deviation and clearly show the defect properties corresponding to the deviation, can dynamically optimize the detection scheme, improves the detection consistency, efficiency and adaptability, reduces the dependence on manual operation and the wear of components, and is suitable for batch detection of brake spring sheets.

The utility model belongs to cigarette making machine equipment technical field, concretely relates to a cigarette making machine filter tip bending detection device, including machine vision system and alarm system, machine vision system includes the camera and camera of setting in the hopper part of cigarette making machine, image processor sets up in the back side of camera and camera, alarm system includes sound generator and light generator, and alarm system and image processor electric signal connection. This technical scheme can monitor the hopper part in real time, and identify the filter tip in the hopper, judge whether there is bending filter tip, if there is bending filter tip, then send out the alarm, remind the operator to remove, to reduce the number of shutdown caused by filter tip bending, reduce the consumption of raw and auxiliary materials, improve the operation efficiency of equipment.

This application relates to the field of machine vision technology and proposes an optical imaging system, including: a first lens group with negative optical power; an aperture stop; the aperture stop being disposed on one side of the first lens group; a second lens group with positive optical power; and a third lens group with positive optical power. The first lens group, aperture stop, second lens group, and third lens group are arranged sequentially from the object side to the image side along the optical axis. The second lens group can move between the aperture stop and the third lens group along the incident direction of the light. This application also proposes a machine vision system, including an optical imaging system. The optical imaging system provided by this application has the characteristics of high resolution, low distortion, uniform image quality, wide working object distance range, good color reproduction, and high contrast, and is highly practical.

Systems and methods for learning software assisted, fixtureless object pickup and placement include a controller which derives measured target points from image(s) of a part in a work area received from a machine vision system, performs an iterative analysis to determine a best fit solution for moving the part adjacent to another part for forming the assembly such that each of the measured target points is within a predetermined range of an associated one of desired target points for said part, where the other part is located at support object(s). The controller converts the measured target points to a common reference frame and command movement of the part, by way of the robot, according to said best fit solution as converted such that the part is moved and secured adjacent to the other part in a fixtureless manner.

The application discloses a bonding encapsulation equipment health state evaluation method based on twin data, classifies and combs three major functional components of an ultrasonic welding head system, a motion control system and a machine vision system of the bonding encapsulation equipment, establishes a hierarchical structure model and a fault tree, constructs a three-level health evaluation model including a component layer, a functional component layer and a whole machine layer, divides equipment health states into four qualitative grades of excellent, good, general and observation, introduces a health degree into quantitative characterization in combination with a fuzzy mathematics theory, adopts a multi-channel neural network model based on an attention mechanism to recognize the health state of a vibration signal, adopts a grey clustering model for health indexes which are not vibration type and are difficult to directly quantitatively evaluate, calculates clustering coefficients of the health indexes belonging to various health states based on a whitening weight function, and determines the health state; and adopts an entropy weight method based on twin data driving to determine the weight of each health index, carries out grey class weighted fusion, and outputs the real-time health degree and the health state grade of the equipment. The application improves the reliability, accuracy and equipment operation efficiency of the equipment health state evaluation, shortens the maintenance time, and reduces the production cost.

An apparatus including a graphical user interface (GUI) for adjusting its display based on image data, the apparatus includes a processor and a memory, wherein the memory contains instructions configuring the processor to receive input data objects including image data of an environment using a machine vision system, and modify a GUI based on the input data objects and the assessment score, wherein modifying the GUI includes automatically generating context-sensitive command inputs that trigger analysis routines within the GUI based on at least a geographic location received from the input data objects, and reconfiguring the GUI to adjust a display hierarchy of interactive elements based on the assessment score.

This application relates to the field of PCB technology and provides a positioning method, calibration device, and drilling and measuring integrated machine for a machine vision system. The positioning method includes: controlling a detection device to contact at least three calibration elements on a calibration device to acquire height information; determining a first tilt posture of the calibration device based on the height information of the at least three calibration elements; acquiring a second tilt posture of the machine vision system relative to the calibration device; and determining the relative spatial posture of the machine vision system relative to the detection device based on the first and second tilt postures. Embodiments of this application can eliminate the influence of the spatial posture error of the calibration device itself on the calibration results of the machine vision system, improving drilling positioning accuracy and PCB quality.