651 results about "Visual system" patented technology

The invention belongs to the technical field of artificial intelligence and computer vision, particularly relates to a visual processing edge adaptive decision-making method for resource and task perception, and aims to solve the problem of scheduling mismatch caused by resource dynamic change and task demand diversity in visual task processing in an edge computing environment. The method comprises the following steps: collecting multi-dimensional resource state data of edge nodes in real time to form a resource state vector with high time resolution; analyzing the visual task request, and constructing a quantifiable task feature vector; and establishing a resource-task association mapping model based on a dynamic weight distribution mechanism. The method also supports cross-edge domain collaborative decision, and processes a pipeline dynamic reconstruction and security isolation mechanism. According to the technical scheme, the fluctuation of the resource utilization rate is reduced to 15% or below, the average task processing delay is reduced to 60%, the scheduling satisfaction degree is improved by 40% or above, and the self-adaptability and the service quality guarantee capability of the edge vision system are remarkably enhanced.

The invention relates to the technical field of unmanned aerial vehicle vision, and discloses a vision system of an unmanned aerial vehicle and the unmanned aerial vehicle. The system comprises a visual data acquisition module, a dynamic feature extraction module, an environment modeling module and a decision control module. The visual data acquisition module captures a synchronous frame sequence containing infrared wave bands, visible light wave bands and depth information in a target area through a multispectral sensor array; the dynamic feature extraction module performs cross-modal fusion processing on the original visual data stream to generate a space-time correlation feature tensor containing a target contour geometric invariance descriptor and a motion trail differential topological structure; the environment modeling module constructs a three-dimensional semantic grid map according to the feature tensor, wherein each voxel unit codes the material reflectivity, the dynamic obstacle occurrence frequency and the illumination attenuation coefficient; the decision control module generates a flight path control instruction containing a pitch angle adjustment amount, a yaw angle compensation value and a speed change gradient based on the map, and assists the unmanned aerial vehicle to better cope with a complex environment.

The invention belongs to the technical field of robot positioning and three-dimensional mapping, and discloses a high-precision map reconstruction method and system based on monocular vision, a medium and equipment. Scene image data are acquired through a monocular image acquisition module, after feature extraction and matching are performed on each frame of image, attitude information acquired by an inertial measurement unit is fused, and pose calculation of a robot is completed through a sparse vision SLAM system; meanwhile, an image dense depth map is generated by a monocular depth estimation model based on an attention mechanism, and the image dense depth map is converted into a single-frame color dense point cloud in combination with image RGB color information. According to the invention, a loose coupling fusion strategy is adopted to carry out spatial registration on a single-frame colored dense point cloud and a robot pose at a corresponding moment, multi-frame data fusion is completed through point cloud splicing and optimization, and a globally consistent three-dimensional dense point cloud map is constructed to realize scene modeling. The method has the characteristics of high robustness and high reconstruction precision, and can be effectively applied to three-dimensional map construction in an outdoor complex environment.

A surface evaluation system that includes one or more vision systems that generate target surface data during evaluation of a surface, the one or more vision systems comprising two or more of: at least one light, a camera, a structured light camera, a laser scanner and a 3D scanner.

The invention relates to the technical field of numerical control machining, in particular to a five-axis drilling numerical control machine tool based on visual positioning and a machining method, and the five-axis drilling numerical control machine tool comprises a machine tool body, a numerical control system, a contact type measuring head, a visual system and a calculation control unit. Coordinates of at least three non-collinear reference features on a workpiece in a machine tool coordinate system are automatically collected through a contact type measuring head, the deviation between the workpiece coordinate system and the machine tool coordinate system is automatically calculated through a coordinate system transformation algorithm, and after the workpiece coordinate system is established, a visual system is moved to the position above each programming hole site to shoot actual marks, and the workpiece coordinate system is calculated. According to the method, actual hole center coordinates are extracted through image recognition and compared with theoretical coordinates, and finally, deviation calculation and machining decision are carried out by integrating measuring head data, visual images, numerical control programs and tolerance parameters, so that through the automatic process integrating measurement, recognition, comparison and decision making, the machining precision is improved, and the machining precision is improved. The technical problems of manual errors and lack of verification before processing are effectively solved.

The invention discloses a visual analysis method and equipment for the trafficability of a grain transport vehicle tractor track and a storage medium. According to the method, images are collected through a vehicle-mounted binocular vision system, and multi-dimensional geometric attributes of the terrain and obstacles are automatically extracted through semantic segmentation, three-dimensional reconstruction and voxel modeling. And on the basis of the extracted multi-dimensional attributes, constructing a hierarchical evaluation system containing terrain and obstacle criteria. A local weight of each attribute index is determined by adopting an analytic hierarchy process, and a fuzzy membership degree vector of each index on different passage evaluation grades is constructed according to dynamic judgment parameters adaptively set with the current grain transport vehicle model number and the terrain, so that a membership degree matrix is formed. And finally, through hierarchical fuzzy comprehensive evaluation, calculating to obtain a comprehensive trafficability score. The accuracy, reliability and automation level of tractor track trafficability evaluation are improved.

The invention relates to a digital twinning-based adhesive tape production line full-process collaborative state monitoring method, which comprises the following steps of S1, starting from process monitoring demand carding, deploying an Internet of Things sensor and a visual system, constructing an adhesive tape production line full-process sensing network, collecting data through an industrial gateway, and performing primary processing; s2, equipment modeling is carried out based on the processed multi-dimensional data, a production process twin model is established in combination with a Petri network, and simulation driven by technological parameters and linkage with an MES system are achieved; s3, constructing an AI analysis unit to perform state analysis based on the processed multi-dimensional data, wherein the state analysis comprises equipment health prediction and workshop section risk detection analysis; and S4, fusing the AI analysis result with the twinborn body to generate a multi-angle state risk view. According to the invention, the efficiency and reliability of adhesive tape production line risk collaborative monitoring are effectively improved.

A substrate processing system comprises an edge computing device including processor that executes instructions stored in a memory to process an image or video captured by camera(s) of at least one of a substrate and a component of the substrate processing system. The component is associated with a robot transporting the substrate between processing chambers of the substrate processing system or between the substrate processing system and a second substrate processing system. The cameras are located along a travel path of the substrate. The instructions configure the processor to transmit first data from the image to a remote server via a network and to receive second data from the remote server via the network in response to transmitting the first data to the remote server. The instructions configure the processor to operate the substrate processing system according to the second data in an automated or autonomous manner.

The invention discloses a magnetic sensor angle calibration system and method, relates to the technical field of magnetic navigation, attitude measurement and sensor calibration, accurately controls the position and attitude of a sensor through a six-degree-of-freedom transmission load device, and realizes real-time position feedback and closed-loop control in combination with a binocular vision system. It is ensured that the center position of the sensor on each sampling point is strictly kept unchanged, and multi-angle sampling is completed only through posture rotation. According to the system, a multi-sensor data fusion and optimization algorithm is adopted, the calibration precision and efficiency are remarkably improved, and the system is suitable for the fields of high-precision magnetic navigation, motion capture, virtual reality and the like. Through an automatic calibration process, the problems of low efficiency and poor consistency of a traditional method are solved, and reliable guarantee is provided for high-precision application of the magnetic sensor.

A system includes a vision system camera mounted to a marine vessel with an associated field of view of the vessel's environment. The system receives image data from the camera and identifies waves in the marine vessel's environment based on the image data. When the system determines that a wave's height exceeds a threshold and that the current heading of the marine vessel is misaligned with the wave's heading, the system automatically adjusts the vessel's heading to align more closely with the wave's heading.

A work machine includes an implement that carries an object. A vision system detects the endpoints of the object relative to the implement and provides those endpoints to a damage avoidance control system. The damage avoidance control system generates control signals to avoid a collision between the object and a part of the work machine.

The invention belongs to the technical field of underwater vision measurement, and relates to an underwater binocular vision system refraction parameter self-calibration method, which comprises the following steps of: firstly, constructing a space equation containing a water body refractive index, a refraction interface normal vector, an interface distance and a light path coefficient based on a Snell law; constructing a generalized state vector including an environment parameter, a structure parameter and a path parameter; a system residual equation is established by using different-plane light intersection constraint of binocular vision, and nonlinear iterative least square solution is carried out by constructing a generalized Jacobian matrix so as to realize adaptive calibration of an underwater vision system; according to the method, on the premise that water body parameters do not need to be predicted and high-precision mechanical calibration is not needed, the water body refractive index and the system structure parameters are synchronously solved, self-adaptive calibration of the underwater vision system is achieved, and the three-dimensional measurement precision and robustness in the complex water environment are remarkably improved.

The invention discloses a visual sparse observation and physical model fused flexible body deformation tracking method, which comprises the following steps of: firstly, constructing a flexible body co-rotation finite element model considering geometric nonlinearity, and establishing a low-dimensional flexibility coupling model for describing a mechanical transfer relationship between a virtual actuating source and a characteristic observation point by utilizing a static condensation technology; in the real-time tracking process, a binocular vision system is used for collecting images and resolving three-dimensional coordinates of sparse feature points in a real physical world; constructing and solving a reverse optimization problem based on the low-dimensional flexibility coupling model, and calculating a virtual correction force vector capable of minimizing an observation error; and applying the virtual correction force vector to the finite element model to drive the finite element model to deform, and updating a full-field geometric node position and a tangent stiffness matrix in real time. Through deep fusion of a physical model and sparse visual observation, the problems of visual occlusion and virtual-real model deviation in flexible body assembly are effectively solved, and online real-time full-field high-precision deformation state estimation is realized.

A system for monitoring calibration of a vision system on a marine vessel is provided, comprising: cameras configured to be mounted to the marine vessel with an associated field of view (FOV), and each associated with a 3D camera coordinate system; and a processor configured to: determine 3D location information of a candidate feature in a 3D global coordinate system based on calibration information; determine that the candidate feature is within a FOV of both a first and second camera; determine a distance between a corresponding points calculated by the first and second cameras; add an error metric based on the distance to a data structure; calculate a calibration health metric based on error metrics in the data structure; determine that the calibration health metric is indicative of threshold miscalibration; and generate a calibration alert.

The invention relates to the technical field of acoustic measurement, in particular to a hearth temperature field intelligent visualization system based on an acoustic sensing technology. Comprising an array type sound sensing data acquisition unit; a working condition adaptive inversion unit; a three-dimensional temperature field intelligent visualization unit; and a working condition early warning and interaction unit. The method comprises the following steps: receiving sound wave data, working condition parameters and a corrected temperature field, extracting sound wave frequency-amplitude features, working condition mean values and fluctuation features in a branched manner, and dynamically distributing attention weights according to feature credibility to obtain fusion features; fusion features are input into an inversion model to obtain a current temperature field, the actually measured temperature of the thermocouple is used as a reference to calculate errors, regularization coefficients which are negatively correlated with the errors and the number of iterations are adopted to optimize, the errors are disassembled to adjust related parameters, working condition changes can be adapted without manual intervention, and system automation and long-term operation reliability are improved.

The invention belongs to the technical field of image processing, and particularly relates to a film space position prediction method and system based on machine vision, and the method comprises the steps: collecting a film operation image, extracting a transverse projection value of an edge sub-pixel point, and synchronously obtaining physical field data such as linear speed, mechanical wear and tension; a dynamic drift index is determined by using differential operation, and a steady-state characteristic index is solved by combining fluid dynamics and a physical constant; the spatial displacement of the film in a visual processing hysteresis stage is accurately predicted by calculating the processing time consumption of a visual system based on dynamic drift, steady-state characteristics and a dynamic second-order compensation item, so that a transverse prediction projection value is obtained, and the transverse prediction projection value is further mapped back to a physical spatial position. According to the method, the phase lag problem of visual detection under the high-speed working condition is effectively solved, and the prediction precision and the operation stability of closed-loop control are improved.

The invention relates to the technical field of robots and computer vision, in particular to an anti-dynamic-shielding mechanical arm visual servo method and system, and the method comprises the steps: calibrating an illumination response reference model before servo; in the servo process, the environment monitoring system senses the dynamic obstacle and predicts the movement of the dynamic obstacle; according to the predicted illumination disturbance, the active illumination array performs reverse compensation to maintain the image quality; and the system continuously evaluates the comprehensive stability index, and performs hierarchical response according to the index value, including illumination compensation, path maintenance or obstacle avoidance re-planning. According to the mechanical arm visual servo method and system capable of resisting dynamic shielding, the technical problem that in the prior art, due to the fact that illumination sudden change and physical shielding cannot be effectively processed during dynamic shielding, a visual system fails in advance is solved, and the mechanical arm visual servo method and system capable of resisting dynamic shielding can achieve pre-judgment and actively compensate illumination disturbance; servo task continuity is ensured under a multi-level response mechanism, and stability and robustness of a visual system in a complex dynamic environment are guaranteed.

The invention relates to the field of target feature recognition and unmanned aerial vehicle cluster formation, in particular to an unmanned aerial vehicle cluster using visual recognition beacons, which comprises a plurality of unmanned aerial vehicle sub-clusters. The unmanned aerial vehicle sub-cluster is composed of a central unmanned aerial vehicle and a plurality of auxiliary unmanned aerial vehicles. The auxiliary unmanned aerial vehicles carry visual identification beacons and fly within the visual range of the central unmanned aerial vehicle in a marshalling mode. The central unmanned aerial vehicle uses a visual system to actively detect and identify the visual identification beacons on the auxiliary unmanned aerial vehicles, obtains the position information of the auxiliary unmanned aerial vehicles, completes formation calculation according to task planning, generates a control instruction, and issues the control instruction to the auxiliary unmanned aerial vehicles, thereby achieving the efficient cooperation and agile formation of the cluster. The invention also comprises a method. According to the method, identity recognition, accurate pose calculation and motion state estimation of a large-scale cluster can be realized, rapid and high-agility formation transformation of the cluster is further supported, the method has the advantage of remarkable low detectability, expensive equipment does not need to be additionally arranged, and unification of high performance and low cost is effectively realized.

The present application relates to the technical field of industrial visual inspection, and specifically relates to a visual inspection system and method with differentiable imaging parameters and adaptive computing power, which mathematically differentiates the physical camera imaging process into a differentiable computation graph node, constructs an end-to-end optimization link of "differentiable imaging-inference", combines multi-modal closed-loop control based on a three-dimensional state space of "speed-temperature-confidence", realizes adaptive allocation of computing power, and compensates for light distribution through ROI partition and adaptive light control; the visual inspection system and method with differentiable imaging parameters and adaptive computing power can automatically search for optimal imaging parameters for a detection task, solve the defects of traditional visual system imaging and algorithm fragmentation and rigid computing power allocation, significantly improve the defect detection rate under complex light scenes, reduce the overkill rate and equipment operating temperature, balance the detection real-time performance and accuracy, and adapt to the dynamic working condition requirements of industrial production lines.

The invention provides a seamless steel tube closed-loop processing method based on online in-situ monitoring, which comprises the following steps: when a steel tube reaches a preset online in-situ monitoring station, imaging and identifying the surface of the steel tube through a high-resolution visual system, and planning a plurality of microscopic detection stations; carrying out multi-mode rapid scanning on the surface of the steel pipe by utilizing an atomic force microscope at each microscopic detection site, extracting microscopic characteristic parameters in real time, and forming a microscopic fingerprint data packet of the current steel pipe; inputting the microscopic fingerprint data packet into a pre-trained process inversion model to generate a process adjustment instruction; and the process adjustment instruction is issued to a corresponding execution mechanism in real time through a production line control system, the machining parameters of the current steel pipe or the subsequent steel pipe are adjusted, and microcosmic quality closed-loop control is formed. According to the technical scheme provided by the invention, the crossing from fixed process machining to self-adaptive microstructure regulation and control machining is realized, and the microstructure consistency and the machining precision of the seamless steel tube are improved.

The invention relates to the technical field of agricultural automation equipment, and discloses a UWB navigation-based tomato picking robot, which comprises a crawler-type mobile chassis, a mounting rack, a control cabinet, a picking mechanical arm and an actuator assembly. A UWB positioning tag is installed on the top of the control cabinet, a global navigation and local obstacle avoidance system is constructed in combination with a laser radar, and the problem of large positioning deviation in a greenhouse weak signal environment is solved. The pitch angle of the picking mechanical arm is adjusted through a driving motor, and plane two-dimensional motion is achieved through a cross-shaped sliding table structure. The actuator assembly is based on eye-in-hand design, and an RGB-D depth camera, a multi-layer flexible suction cup and a rotating motor are integrated. During operation, the visual system guides the mechanical arm to accurately position, the pneumatic driver provides negative pressure to adsorb fruits, and the rotating motor drives the suction cup to twist to realize lossless separation of fruit stems. According to the invention, the navigation precision and hand-eye coordination of the picking robot are effectively improved, and automatic, low-loss and efficient picking of tomatoes is realized.

A method or device for determining the distance between an object and a vehicle equipped with a vision system comprising first and second cameras. The distance is determined from depths predicted by a local depth prediction model selected from a plurality of such models. The depths are predicted for pixels of a bounding box associated with the object in an acquired image. The local depth prediction model is learned from training images containing training objects. These objects are detected (32), bounding boxes are determined, and a window size is defined (34) to be larger than the various bounding boxes. Local depth prediction models are then learned (37), each local model being associated with a window covering a portion of an image acquired by a camera. Figure 3 (for the abstract)

The utility model provides a visual system. The visual system can be switched between a first state and a second state; the curvature radius R5 of the first side surface of the third lens, the curvature radius R6 of the second side surface of the third lens and the maximum distance Lb from the first side end surface of the second lens barrel to the second side end surface of the second lens barrel on the optical axis meet the condition that R6 / R5 * Lb is greater than or equal to 0.99 mm and less than or equal to 6.47 mm; the inner diameter dbs of the first side end face of the second lens barrel, the inner diameter dbm of the second side end face of the second lens barrel, and the distance delta L of the second optical element group moving along the optical axis when the visual system is switched between the first state and the second state meet the condition that (dbs-dbm) / delta L is larger than 0.8 and smaller than 2.7. According to the utility model, the problem that structural members such as a lens cone of a visual system in the prior art are easy to generate reflection stray light is solved.

The invention discloses a visual system which comprises a lens cone, a lens group and a spacing element group, wherein the lens group and the spacing element group are assembled in the lens cone; the lens group comprises a first lens with positive focal power, a reflective polarization element, a first quarter-wave plate, a second lens with positive focal power, a third lens with negative focal power, a partial reflection element and a second quarter-wave plate which are sequentially arranged from the first side to the second side along the optical axis. The fourth lens has negative focal power; the spacing element group comprises a first spacing element, a second spacing element, a third spacing element and a fourth spacing element; wherein the number of the lenses with focal power in the lens group is four; the effective focal length f1 of the first lens and the effective focal length f of the visual system satisfy 1.5 lt; f1 / flt; 1.9); the combined focal length FG1 of the first lens, the reflective polarizing element and the first quarter-wave plate and the inner diameter d1s of the first side surface of the first spacing element meet the following conditions: 2.35 lt; fG1 / d1slt, FG1 / d1slt; and 2.75%.

An apparatus and method are provided for manufacturing multiple lasagna pasta strips having rippled edges using an automated extrusion system. An extruder mixes and kneads dough and feeds it into a distribution manifold having multiple chambers, each equipped with an independently actuated valve and corresponding die inserts. The dies form lasagna strips with rippled longitudinal edges as the dough is extruded. Downstream sensors measure extrusion rate and droop distance while a vision system observes the ripple geometry. A control module including may include an AI processor configured to analyze sensor and image data to evaluate ripple amplitude, wavelength, and uniformity and automatically adjusts extrusion rate, chamber pressure, and valve position to maintain consistent shape quality. The AI module may be further configured to record historical production data and adaptively refines baseline operating parameters for subsequent runs, enabling uniform, high-throughput production of rippled-edge lasagna suitable for automated tray assembly lines.

The disclosure provides a visual system, sequentially including a first lens assembly and a second lens assembly from a first side to a second side along an optical axis, the first lens assembly includes a first lens with a positive refractive power, a reflective polarizing element, and a quarter-wave plate; the second lens assembly includes a second lens with a positive refractive power, a partially-reflective element, and a third lens, and the second lens and the third lens are cemented to each other; and the second lens assembly is able to move along the optical axis to cause the visual system to switch between a first state and a second state. A combined focal length fz of the first lens assembly and a focal length fm of the system in the first state satisfy 5.69≤fz / fm≤8.09.

A sorting machine with a dynamic vision system is developed to provide dynamic lighting, imaging, and analysis of industrial materials while moving the conveyor. The sorting machine comprises a washing box, a vision system, a control unit, and a transferring unit. The vision system comprises dynamic imaging unit and dynamic lighting unit. The vision system is configured to provide a dynamic lighting and a dynamic imaging of industrial materials. The imaging unit comprises a camera, a camera movement unit, and a dynamic camera stand. The lighting unit comprises an optical section, a linear motion adjuster section, and a light angle adjuster section.

This application provides a visual control method, system, storage medium, and program product for self-service baggage check-in equipment based on real-time baggage monitoring data, relating to the field of intelligent visual control technology. The method includes: acquiring baggage monitoring data in real time, including trigger signals from multiple photoelectric sensors and weight data output from a weighing platform; determining the speed evolution sequence of baggage based on the trigger signals and performing trend analysis; performing time-series coupling analysis of the trend analysis results and weight data to determine whether the baggage has entered a stabilization transition phase; predicting the target time when the baggage reaches a stationary state during the stabilization transition phase and sending a pre-configured command to the visual system in advance; and confirming that the baggage has reached a stationary state by verifying the fluctuation amplitude of the weight data after the target time arrives, and controlling the visual system to perform image acquisition operations. This solves the technical problem of poor visual recognition reliability of visual systems during the dynamic flow of baggage in related technologies.

The invention provides a distance measurement method in a calibration process of a laser vision system, which belongs to the field of distance measurement, and comprises the following steps: shooting a positioning plate image with a laser point through a camera, and arranging a plurality of positioning identifiers with known world coordinates on the positioning plate; identifying a positioning identifier in the image, and acquiring a pixel coordinate of the positioning identifier; calculating a three-dimensional coordinate of the positioning identifier in a camera coordinate system; fitting a plane equation of the positioning plate in a camera coordinate system; pixel coordinates of laser points in the image are detected and extracted; converting the pixel coordinate of the laser point into a space ray equation in a camera coordinate system, and calculating an intersection point of the space ray and the plane equation to obtain a three-dimensional coordinate of the laser point in the camera coordinate system; calculating the distance from the laser point to the optical center of the camera. According to the method, all calculations are carried out in a unified camera coordinate system, alignment errors caused by non-unified coordinate systems of multiple devices are thoroughly eliminated, and the consistency of distance measurement and the overall calibration precision are improved.

A system for automatically identifying available docking positions using a vision system of a marine vessel is provided, the system comprising: an imaging device, wherein the imaging device is configured to be mounted to the marine vessel with an associated field of view of an environment of the marine vessel; and one or more hardware processors configured to: identify, based on image data captured using the imaging device, a dock instance; determine, based on the image data, whether the dock instance is available for docking; indicate that the dock instance is an available docking position; and cause the marine vessel to maneuver to the available docking position.