35 results about "Vision control" patented technology

A system and method to generate a target image from a reference image are provided. The system may receive, via a LDM, a reference image and a text prompt. The system may extract, via a trained vision encoder in the LDM, a vision control signal from an object in the reference image. The vision control signal indicates an identity of the object. The system may extract, via trained text encoders in the LDM, text control signals associated with the text prompt. The system may generate, via cross attention summation of an output of a vision cross attention unit(s) associated with the vision control signal and an output of text cross attention units associated with the text control signals, spatial features indicative of the reference image and the text prompt. The system may output, via a decoder in communication with the LDM, a target image based on the generated spatial features.

The present disclosure relates to a contact lens that is easily rotated when worn, comprising: a vision correction zone having a first refractive power based on an eyeball prescription and located in the central region of the contact lens; and a vision control zone that surrounds the first correction zone and is annular in shape, wherein the equivalent refractive power of the vision control zone is positive compared to the first refractive power, the vision control zone including a first control zone adjacent to the first correction zone, the boundary between the first control zone and the first correction zone being a first inner edge defined by a first inner circle and a first outer circle that oscillates around the circumference of the contact lens, the diameter d1 of the first inner circle satisfying the following conditions: 2.4 mm ≤ d1 ≤ 3.6 mm, and the diameter d2 of the first outer circle satisfying the following conditions: d1 + 0.2 mm ≤ d2. The contact lens can provide different defocus stimuli over time, thereby achieving a long-term myopia control effect.

1. Name of the product in this design: Graphical User Interface for the Operation and Management of Medical Consumables for Electronic Devices. 2. Intended use of this design: for electronic devices; Intended use of the graphical user interface: for the operation and management of medical consumables for electronic devices. 3. The key design feature of this product is its graphical user interface. 4. The image or photograph that best illustrates the design's key features: the front view. 5. Human-computer interaction method of graphical user interface: The graphical user interface of this product is the user interface for running the vision control system software. The main change in the main view and various state change diagrams is that the corresponding interface state change diagram is presented according to the user's current control position. The main view is the main interface view of the software; enter your account and password, click the [Login] button to enter the changed state diagram 1; click the [Medical Consumables Operation Management] button in changed state diagram 1 to enter the changed state diagram 2; click the [Date Range] button in changed state diagram 2 to enter the changed state diagram 3.

The invention relates to the technical field of industrial automation and machine vision, in particular to an intelligent factory voice and vision cooperative control method and system. According to the intelligent factory voice and vision cooperative control method and system, a multi-target recognition model is combined with an object feature point extraction algorithm to determine the grabbing difficulty tendency type of a target object; according to the grabbing difficulty tendency type of the target object and the shape complexity degree of the target object, the calculation sub-parameters for the grabbing posture of the target object are determined, then the grabbing posture of the mechanical arm is determined according to the calculation sub-parameters, and non-contact control is achieved through the preset wake-up word. Operators can quickly start the grabbing process through natural language processing instructions, time delay of traditional button or touch screen operation is remarkably reduced, voice instructions and visual collection are seamlessly connected, the manual confirmation link is avoided, the system response speed is increased, and the system reliability is improved. And for a target object with relatively high grabbing difficulty, the grabbing success rate is improved through a multi-angle coordinate calculation mode.

The present application relates to the technical field of deep learning machine vision control convex letter steel rolling, and relates to a convex letter steel rolling plate shape control method and system based on deep learning, which comprises the following steps: heating and descaling a blank, setting a first visual detection unit at the outlet of a heating furnace, triggering hydraulic correction when the centering deviation is greater than a first threshold value; setting a second visual detection unit at a rough rolling mill, extracting the residual area of the rolling piece surface oxide scale through an image segmentation algorithm, and detecting whether to trigger secondary descaling; setting a third visual detection unit at a medium rolling mill, adjusting the flow distribution of the cooling water of a finishing mill if the temperature distribution is uneven, and correcting the side pressure of the finishing mill vertical roll if the corner radius error exceeds a fourth threshold value; setting a fourth visual detection unit at the finishing mill, calculating the roll gap compensation amount and correcting the finishing mill reduction amount in real time when the filling rate is less than a fifth threshold value. The present application combines convex letter steel with deep learning and machine vision, and can make the quality of the manufactured convex letter steel better and the shape more accurate.

This application relates to the field of vision control technology, and in particular to a method and system for compensation and control of CNC machine tools based on industrial vision. The method includes: acquiring real-time images and the position coordinates of the CNC machine tool during the machining process; parsing the current machining instructions to reconstruct the theoretical trajectory, and then constructing an initial contour of an active contour model; performing multiple iterative evolutions on the initial contour using the active contour model until a target contour is obtained; calculating spatial compensation components based on the image deviation of the target contour relative to the initial contour; and adjusting the workpiece zero-point offset of the CNC machine tool using the spatial compensation components. The technical solution of this application can effectively improve the machining accuracy and stability of CNC machine tools in complex machining environments.

The application relates to a mechanical vision-based automatic insulation resistance detection device, characterized by being composed of a device fixing assembly, a mechanical vision control assembly and an insulation resistance test assembly; the device fixing assembly comprises guide rails, connecting rods, pulleys, two-side fixers and clamping groove fixers; the guide rails are divided into left and right parts, the guide rail end parts are telescopically inserted into the holes of the connecting rods to adapt to secondary wiring terminal rows with different lengths, and the device is fixed on the two sides of the secondary wiring terminal row through the two-side fixers; the pulleys are slidingly connected in the guide sliding channels of the connecting rods, the pulleys are connected with controllers, and five groups of clamping groove fixers are arranged on the outer sides of the connecting rods; the mechanical vision-based automatic insulation resistance detection device is rationally designed and is favorable for solving the problem of low efficiency of the traditional manual insulation resistance detection method.

The invention provides a bionic eyeball vision device, a vision system, a vision control method and a robot. The bionic eyeball vision device comprises a bionic eyeball shell, a bionic crystalline lens is arranged in the bionic eyeball shell, and the bionic crystalline lens is made of an electro-deformation material; the bionic eyeball shell is provided with a bionic pupil, and the bionic pupil is made of an electrochromic material; the bionic pupil is located in front of the bionic crystalline lens; the bionic eyeball further comprises a photosensitive element, and the bionic pupil, the bionic crystalline lens and the photosensitive element are sequentially arranged in the bionic eyeball shell. According to the bionic eyeball vision device provided by the invention, the anthropomorphic degree of eyeballs can be improved, the vision integration level is improved, and the compactness of the structure is improved; according to the bionic eyeball vision device, the electrochromic material is adopted to simulate the pupil, the electrodeformation material is adopted to simulate the crystalline lens, the device approaches the physiological structure of human eyes from the aspects of materials and principles, and unification of structural bionics and functional bionics is achieved.

The invention relates to the technical field of mechanical arm visual control, in particular to a mechanical arm obstacle avoidance grabbing method and device which comprises an obtaining module, a processing module, a control module, a mechanical arm with mechanical arm joints and connecting rods connected with each other and a clamping jaw installed at the tail end of the mechanical arm. The acquisition module comprises a depth camera used for acquiring target object and obstacle information under a camera coordinate system, and the depth camera is installed beside a clamping jaw at the tail end of the mechanical arm and is orthogonal to the clamping jaw coordinate system; the method has the beneficial effects that the target object and obstacle information is obtained through the depth camera, then the obstacle information is converted to the base coordinate system in consideration of the possibility that the joint connecting rod of the mechanical arm collides with the obstacle in the operation process, and the models of the obstacle and the joint connecting rod of the mechanical arm are established respectively; collision detection is carried out on each planned path point, so that the operation safety is improved; and finally, the position over the target object serves as the middle point of the path, and the tail end grabbing posture of the mechanical arm is determined.

The application discloses an automatic patching machine and a working method thereof, and relates to the technical field of patching machines, which comprises a workbench, a film feeding device, a patch feeding device, a taking device, a vision system and a control system are arranged on the workbench, the film feeding device comprises a glue applying mechanism and a glue stripping mechanism, the patch feeding device comprises a feeding mechanism, a feeding mechanism and a material moving mechanism, the taking device comprises an X-axis moving module, a glue applying mechanism and a taking mechanism, the vision system comprises a camera structure, a light supplementing structure and a vision control device, and the control system comprises a control panel; the working method of the application mainly comprises the following steps: the film feeding device automatically strips glue, the patch feeding device automatically feeds, the vision system determines the position of the film, the taking device completes the work of taking glue and applying glue, the vision system detects the finished product, and the taking device places the finished product into a finished product box; the application is automatically worked by a machine, and can effectively improve the work efficiency and the yield.

This invention discloses an anesthesia injection device, its automatic control method, and a hair transplant robot, relating to the field of medical surgical equipment technology. The device includes: a fixing mechanism for mounting on a robotic arm and being driven by the robotic arm; a first feeding mechanism disposed on the fixing mechanism; an injection mechanism disposed on the first feeding mechanism, the first feeding mechanism driving the injection mechanism to move; and a vision control unit disposed on the fixing mechanism for acquiring images and controlling the movement of the first feeding mechanism and / or the robotic arm based on the acquired images, so that the injection mechanism reaches a target position. The anesthesia injection device, its automatic control method, and the hair transplant robot of this invention can automatically inject anesthetic into the scalp of a target person with low pain during injection, and the injection process is fast and efficient.

A state-observed and updated model predictive control strategy is proposed for image-based visual servoing (IBVS) of micro air vehicles (MAVs). The proposed strategy can accurately adjust the pose of MAVs without global positioning system (GPS). Specifically, image features are defined on a virtual image plane to decouple the translational motion of MAVs. Then, a linear velocity observer is developed to provide high-quality linear velocity information for MAVs in real time. The image dynamics on the virtual image plane are linearized by first-order Taylor expansion, and a controller is constructed based on model predictive control to efficiently solve the optimal control input. Furthermore, the state input of the controller is updated at each control period to eliminate the cumulative error of the rolling optimization on the linear approximation dynamics, ensuring the accuracy of IBVS. Experimental results demonstrate the performance of the proposed observer and control strategy.

The application relates to a robot vision control method and system based on spatiotemporal context perception and belongs to the field of vision control. The method comprises the following steps: acquiring an original image sequence, performing spatiotemporal context feature coding, and outputting a spatiotemporal context feature map; mapping the spatiotemporal context feature map into an initial attention map through a lightweight convolution network, introducing an attention diffusion process to output an attention potential field; obtaining a resource allocation matrix based on the attention potential field and performing calculation power allocation; obtaining a historical attention potential field based on the attention potential field, performing attention dynamics prediction according to the historical attention potential field, and obtaining a predicted attention potential field; and realizing prospective vision control based on the attention potential field and the predicted attention potential field. Through the introduction of spatiotemporal context perception coding, gated fusion, attention diffusion, nonlinear resource allocation and the like, the intelligent level of robot vision control is comprehensively improved.

The invention discloses a camera remote real-time control system and a control method based on video monitoring, and relates to the technical field of camera control, in an image communication link, video and holder control cooperation is realized, a control symbol is embedded into a video code stream, and synchronous correction is carried out based on control and video double-link time delay estimation. The cloud platform motion and control intention is mapped into a coding structure and ROI bit distribution through visual control isomorphism, so that low-delay and high-definition transmission is still carried out in a key target area under network fluctuation, target loss and misoperation are reduced, and the monitoring disposal and evidence obtaining continuity of a chemical industrial park and an oil and gas storage tank area is improved.

An apparatus of a wearable robot may comprise a transceiver configured to communicate with at least one controller of the wearable robot, at least one processor, and memory. The memory may store instructions that, when executed by the at least one processor, are configured to cause the vision control apparatus to receive, from the at least one controller of the wearable robot via a receiver of the transceiver, an indicator of a current robot foot position, detect, via a depth camera of the wearable robot, a characteristic of terrain around the wearable robot, generate, based on the detected characteristic of terrain, point cloud-based geometric information associated with the terrain, determine, based on the current robot foot position and the point cloud-based geometric information, a subsequent robot foot position, and transmit, to the at least one controller of the wearable robot via a transmitter of the transceiver, the determined subsequent robot foot position.

The invention discloses a global self-adaptive parallel mechanical arm apple picking and follow-up collecting device and method.The device comprises a central controller, a longitudinal multi-speed lifting module, a transverse telescopic module, a parallel mechanical arm and a visual control system, and the longitudinal multi-speed lifting module, the transverse telescopic module and the parallel mechanical arm are electrically connected with the central controller; the visual control system is used for obtaining three-dimensional coordinates and depth information of fruits, and the central controller controls the longitudinal speed-multiplying lifting module to drive the picking operation platform to move to a plurality of height stations in sequence. Meanwhile, after the transverse telescopic module is controlled to transversely move the picking operation platform according to three-dimensional coordinates and depth information obtained by the visual control system at each height station, the central controller controls the parallel mechanical arm to pick the fruits, and the picked fruits are collected in a follow-up mode through the follow-up fruit collecting module. According to the device, full-area covering picking of fruits at different heights and different depth positions of tree crowns is achieved, and the environmental suitability of the device is greatly improved.

Computer vision control of spray nozzles and related systems, circuitry, and methods are disclosed. A circuitry of a computer vision sprayer control system receives an image signal captured by a computer vision system disposed at a distal end of a boom arm of a boom carried by a crop sprayer. The circuitry provides a spray nozzle control signal to a spray nozzle controller configured to control operation of a spray nozzle at the distal end of the boom arm. The spray nozzle is electrically controllable with at least one degree of freedom. The circuitry includes a processor to determine adjustments to make to the spray nozzle based, at least in part, on the image signal and generate the spray nozzle control signal responsive to the determined adjustments. A method includes retrieving a spray maneuver and determining adjustments to make to the spray nozzle to execute the spray maneuver.

This invention provides a flexible positioning and nailing device, including a support platform, a moving assembly, a drive component, a nail gun mechanism, and a vision control system. The flexible positioning and nailing device of this invention features a support platform with an mounting plane for supporting other equipment; a moving assembly that slidably connects to the support platform; a drive component connected to the moving assembly, which moves the moving assembly in a circular trajectory to perform ring nailing; a nail gun mechanism connected to the bottom of the moving assembly, which moves horizontally on the support platform with the moving assembly to perform ring nailing; and a vision control system electrically connected to the moving assembly and drive component, which controls the drive component to move the moving assembly and nail gun mechanism to the corresponding positions for nailing. The device is simple to operate, highly efficient and precise, adaptable, and practical.

The invention relates to a visual control device and method of a wearable robot. A visual control device of a wearable robot may include a transceiver configured to communicate with at least one controller of the wearable robot; at least one processor; and a memory. The memory may store instructions that, when executed by the at least one processor, are configured to cause the visual control device to: receive, via the receiver of the transceiver, an indication of a current robot foot position from the at least one controller of the wearable robot; detecting, via a depth camera of the wearable robot, features of terrain around the wearable robot; generating point cloud-based geometric information associated with the terrain based on the detected features of the terrain; based on the current robot foot position and the geometric information based on the point cloud, determining a subsequent robot foot position; and transmit, via a transmitter of the transceiver, the determined subsequent robot foot position to at least one controller of the wearable robot.

The invention relates to the technical field of deep learning machine vision control embossed steel rolling, in particular to a deep learning-based embossed steel rolling plate shape control method and system.The method comprises the steps that a blank is heated and descaled, a first vision detection unit is arranged at an outlet of a heating furnace, and when the centering deviation is larger than a first threshold value, hydraulic deviation correction is triggered; a second visual detection unit is arranged on the roughing mill, a rolled piece surface oxide skin residual area is extracted through an image segmentation algorithm, and whether secondary descaling is triggered or not is detected; a third visual detection unit is arranged in the intermediate rolling mill, temperature distribution is uneven, flow distribution of cooling water of the finishing mill is adjusted, and if the fillet radius error exceeds a fourth threshold value, the side pressure amount of the vertical roller of the finishing mill is corrected; and a fourth visual detection unit is arranged on the finishing mill, when the filling rate is smaller than a fifth threshold value, the roll gap compensation amount is calculated, and the rolling reduction of the finishing mill is corrected in real time. The embossed steel is combined with deep learning and machine vision, so that the manufactured embossed steel is better in quality and more accurate in shape.

The present invention belongs to the field of robotic vision control and discloses a method and system for collaboratively controlling the motion of a robotic arm based on visual servoing and force sensing. The method comprises: the robotic arm moves to the assembly target position, and an image acquisition device acquires an image of a target point at the assembly target position as a desired image; the end of the robotic arm grips the workpiece to be assembled and moves to the assembly target position. During the movement of the end of the robotic arm, the image acquisition device acquires an image of the target point in real time, and compares the real-time acquired image with the desired image to calculate the motion speed v of the end of the robotic arm. c When the workpiece to be assembled contacts the pin at the assembly target position, the force sensor measures the force and torque at the contact, and uses the force and torque to calculate the movement speed v of the end of the robotic arm f ; Using the robot arm movement speed v c and v f The present invention solves the problem in the prior art that vision control and force control cannot coordinate control.

The invention relates to a mountain mobile intelligent vegetable sorting and fresh-keeping system based on AI vision, and belongs to the technical field of agricultural machinery and agricultural product postharvest treatment. The system aims at solving the problems that the sorting efficiency of vegetables in mountainous areas is low and the sorting standard adaptability is poor. According to the technical scheme, the system is characterized by comprising a pre-cooling unit for quickly cooling harvested vegetables, a sorting unit for performing automatic quality grading and flaw detection, a packaging unit for performing sealed packaging, a temporary storage unit for providing a temporary fresh-keeping storage environment, a moving platform for supporting and moving the units and an AI visual control system. According to the system, field immediate processing is achieved through mobile integrated design, images are collected through a visual detection channel integrating a high-definition camera and a spectral imager, the image processing process is executed through an embedded processor, a sorting model is updated regularly in combination with a continuous learning module, and therefore the sorting precision and the localized adaptive capacity are improved, and the sorting efficiency is improved. The device is mainly used for on-site sorting and fresh-keeping operation in mountain vegetable producing areas.

The utility model discloses a visual control structure of tentering setting machine equipment, and relates to the technical field of control structures. The visual control structure of the tentering setting machine equipment comprises a camera and a support used for supporting the camera, and the camera is installed on the upper portion of the tentering setting machine equipment through the support so that visual monitoring can be conducted on the tentering setting machine equipment in the operation process through the camera. According to the device, the rail and the supporting base sliding in the rail are arranged on the top face of the tentering setting machine, the visual control structure is connected with the supporting base through the support, so that the position, needing to be monitored, of visual control equipment relative to the tentering setting machine can be conveniently adjusted, meanwhile, the support does not occupy the surrounding space of the tentering setting machine, and the stability of the tentering setting machine is improved. And in combination with a supporting plate, a limiting block, a fixing screw rod and other components, the setting height of the visual control structure relative to the tentering setting machine equipment can be correspondingly adjusted, and the visual control structure is prevented from colliding with the outer wall of the tentering setting machine equipment.

The present application relates to the technical field of pipeline code reading and conveying, and particularly relates to a pipeline code reading and conveying device based on multi-vision sensing cooperation, which comprises a pipeline conveying assembly, a control cabinet and a suspension support, the pipeline conveying assembly is installed on one side of the control cabinet, four groups of optical code scanning vision control assemblies are installed on one end of the upper side of the pipeline conveying assembly, a horizontal moving assembly is installed on the side of the pipeline conveying assembly away from the control cabinet, a material clamping assembly capable of clamping materials is arranged on the upper side of the pipeline conveying assembly, and a telescopic assembly capable of telescoping is arranged on the side of the material clamping assembly close to the horizontal moving assembly. The present application can control the material to rotate half a circle through the turnover assembly, so that the clamped material is turned over half a circle, the barcode of the material faces upward, the turned-over material is placed on the upper side of the pipeline conveying assembly again, and the pipeline conveying assembly re-conveys the turned-over material to the lower side of the optical code scanning vision control assembly for code scanning.

This disclosure relates to object detection in a vehicle's surrounding environment under low-light conditions. Specifically, it relates to a method executed by a vision control system for supporting object detection in a low-light environment surrounding a moving vehicle, using at least one vehicle-mounted rearward and / or lateral image acquisition device. The vision control system acquires images of the surrounding environment located behind and / or to the sides of the moving vehicle, supported by at least one first image acquisition device. The vision control system further determines the lighting conditions in the surrounding environment. Furthermore, when the lighting conditions meet an insufficient lighting criterion, the vision control system provides light output illuminating a ground area of ​​the surrounding environment, supported by at least one first light source, to facilitate object detection via the at least one first image acquisition device. This disclosure also relates to a vision control system according to the foregoing, a vehicle including such a vision control system, and a corresponding computer program product and a non-volatile computer-readable storage medium.

This invention discloses a multi-axis clamping harvester for multi-terrain intercropping and relay cropping of underground root and tuber crops, relating to the field of agricultural machinery technology. A main harvesting mechanism is located in the center of the walking platform, with auxiliary harvesting mechanisms symmetrically arranged on both sides. A row adjustment module is fixed to the walking platform, and its output end is connected to two first frames, which are connected by a first hydraulic rod. A first clamping conveyor belt is located on the side of each of the two first frames that are close to each other. A cherry-gathering and soil-loosening module is located at the lower end of each first frame, and a cherry-cutting module is located at the higher end. The walking platform also includes a collection module, a sowing mechanism, and a vision control module. The multi-axis clamping harvester for multi-terrain intercropping and relay cropping of underground root and tuber crops proposed in this invention has multi-degree-of-freedom adjustment capabilities, adaptive clamping force control capabilities, and can adapt to crops of different shapes and arrangements, achieving precise, low-loss, and efficient harvesting of crops.

The invention relates to the technical field of industrial vision control, and provides a quantitative discharging control method and system based on industrial vision, and the method comprises the steps: obtaining a first image of a conveying belt collected by an industrial camera lens at a first moment and a second image of the conveying belt collected by the industrial camera lens at a second moment; the first moment is the moment when the conveying belt is in the recent no-load state, and the conveying belt loads materials fed in the current batch at the second moment; adjusting a parameter value of a target parameter in a material identification algorithm according to the first image to obtain an adjusted parameter value of the target parameter; based on the adjusted parameter value of the target parameter and a material identification algorithm, determining a target putting amount of the material in the second image; and determining the calculated putting amount of the next batch of materials according to the target putting amount. And the accuracy of quantitative discharging control can be improved.

1. Name of the product in this design: Vision control camera for swimming pool robot. 2. Purpose of this product design: To be installed above a swimming pool (home outdoor camera installation method) to provide a full view of the pool environment and the operation of the robot in the pool. With a built-in artificial intelligence chip, it can identify the pool environment and robot status in real time, send control commands to the pool robot, and connect to the network in real time to interact with the server with the acquired information. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

Embodiments of the application disclose a vision control method and device based on an agricultural robot and an electronic device, and relate to the technical field of agricultural robots. The method applies the agricultural robot to an agricultural work area, positions a fruit area based on a vision image, and determines a fruit variety in the fruit area, so as to trigger replacement of a gripper of the agricultural robot according to the fruit variety, detect the adaptation of the gripper of the agricultural robot to the fruit, and determine a gripping plan based on the multiple fruits in the vision image and the positioning of the fruits. The gripping plan is used to regulate a moving track of the gripper of the agricultural robot, and the gripper is synchronously regulated to avoid obstacles, thereby improving the safety of gripping the fruits by the agricultural robot. In addition, when the gripper grips the fruits, the positions of other fruits in the current environment are synchronously monitored, a falling state is determined based on the offset track of the other fruits, the safety of gripping the fruits by the agricultural robot is further ensured, and the other fruits in the falling state can be timely controlled to realize preferential gripping.

The application discloses a kind of uncalibrated visual servo method, system, equipment and medium for six degrees of freedom mechanical arm, belong to visual servo technical field, including: the image frame before and after the movement of mechanical arm is acquired, feature point coordinates are extracted based on the image frame before and after movement;Determine initial image Jacobian matrix according to feature point coordinates;The initial image Jacobian matrix is updated, and current image Jacobian matrix is obtained;By comparing target image desired position with current observation position, image feature error is obtained, image feature error and current image Jacobian matrix are combined to calculate, and control increment is obtained;Control increment is converted into six degrees of freedom motion command, and position adjustment is carried out based on six degrees of freedom motion command control mechanical arm;Image frame of the current position of mechanical arm is acquired, feature point is extracted based on the image frame of current position and image feature error is updated.The application realizes high-precision, fast response, dynamic vision control of calibration-free.