27 results about "Visual marker" patented technology

The invention discloses a dexterous grabbing method and system for a robot, and aims to solve the technical problems that an existing robot grabbing system is high in dependence on hand-eye calibration precision (especially translation vectors), and the grabbing capacity of objects without priori knowledge is limited. According to the method, a reference-transformation-correction control framework is provided, the pose of an unknown object is accurately recognized through a multi-stage visual segmentation strategy, and a preliminary grabbing target is generated based on the reference relation of one-time teaching; most importantly, the system starts closed-loop visual servo correction, and iteratively corrects the position by detecting the real-time pose of a tail end visual mark, so that translation errors in hand-eye calibration are eliminated, and high-precision alignment is realized; in addition, the system also integrates the functions of object posture adjustment and rapid rotation calibration. Through cooperative work of open-loop target generation and closed-loop position correction, dependence on hardware accurate calibration is effectively reduced, and the grabbing success rate and robustness are improved.

The invention provides a method and device for relieving carsickness of vehicle passengers, electronic equipment and a medium, and relates to the field of intelligent cabins, and the method comprises the steps: obtaining the driving state data of a vehicle in response to a started vehicle carsickness relieving function; processing the driving state data through a configured animation generation algorithm to obtain a dynamic visual driving process; generating a corresponding visual guidance animation based on the dynamic visual driving process; wherein the visual guidance animation comprises a visual marker dynamically changing according to the driving state of the vehicle, and the visual marker is used for guiding the visual perception of the passenger to be consistent with the vestibular perception. According to the method, the driving state data is collected based on the original hardware of the vehicle, the dynamic visual driving process is constructed through the animation generation algorithm, the visual guidance animation is generated, the visual marker dynamically changes along with the driving state of the vehicle, visual perception of passengers can be accurately guided to be consistent with vestibular perception, and carsickness reaction is effectively relieved.

The invention provides a method for controlling a self-moving device to return to a charging station and the self-moving device, and the method comprises the steps: determining a current region of the self-moving device, and judging whether the current region is a target region or not, the target region being determined by a visual identifier and being communicated with a charging station region; if the current area is the target area, acquiring an included angle between the orientation of the self-moving equipment and a central reference line; and controlling the self-moving equipment to be butted with the charging station according to the included angle. The target area is determined through the visual identifier arranged on the charging station, a guide line is replaced, the dependency degree of the self-moving equipment on positioning or signals is reduced, the environment adaptability is improved, and after the self-moving equipment enters the target area, the self-moving equipment is controlled to return to the charging station according to the included angle, so that the charging efficiency is improved. The efficiency of returning the self-moving equipment to the charging station is improved, and the self-moving equipment can successfully return to the charging station.

A plurality of different visual markers are deployed on a field. The markers include a target marker identifying a portion of the field that has a target of material to be applied to the field and a non-target marker identifying a portion of the field that does not have a target. An on-machine target identification system sense targets as an agricultural machine travels over the visual markers to identify targets in the field. An image processing adjustment controller correlates identified targets with the visual markers to determine an accuracy of the target identification system. An action signal is generated based upon the identified accuracy of the target identification system.

The application discloses a sensitive data operation real-time identification and automatic correction method based on a data development IDE, and belongs to the technical field of big data. Through a plug-in mechanism deeply integrated in the data development IDE, the SQL statements written by developers are monitored and analyzed in real time, and sensitive fields and their levels are automatically identified in combination with an enterprise-level sensitive data knowledge base. The system intelligently matches disposal strategies according to user roles, running environments and sensitive levels, and gives risk prompts in the editing interface in the form of visual markers. Users can trigger automatic correction by one key, replace plaintext sensitive fields with predefined safe function calls, and realize the compliance reconstruction of SQL statements. The whole process is completed in real time in the development stage, forming a closed loop from risk identification, strategy matching, interface prompting to automatic correction and audit tracing, and effectively improving the endogenous safety level and development efficiency of the data development link.

Provided are a method and system for providing information to a user in a scene, wherein one or more sensors and one or more visual markers are deployed in the scene, wherein the sensors can be used to sense or determine the position information of a target in the scene, and the method comprises: receiving information sent by a position acquisition device of the user, wherein the information includes the spatial position information of the position acquisition device, wherein the position acquisition device determines its spatial position information by scanning the visual marker; identifying a user of the position acquisition device within a sensing range of the sensor based on the spatial position information of the position acquisition device; tracking the user through the sensor and updating the spatial position information of the user; and providing information to the user through the user's information receiving device based on the spatial position information of the user.

The invention provides a software interface defect detection method and device based on visual marking and thinking chain prompt, and relates to the field of artificial intelligence. The method comprises the steps of obtaining multi-state UI data of a target application program in different interface display states; preprocessing the component information file set data to filter redundant component data; constructing an adjacency relation graph, and traversing the adjacency relation graph based on a deep optimization algorithm to output a component level view sorted according to the adjacency relation; drawing a visual mark set based on the UI screenshot set data; constructing a structured text description, and inputting the visual mark set and the structured text description into a multi-modal large model; and executing software interface defect detection through the multi-modal large model based on a thinking chain prompt mechanism and outputting a defect detection result. The problem that false detection and missing detection are easily generated in a complex scene due to the fact that a traditional static feature extraction method cannot effectively capture a defect mode caused by dynamic changes of a UI component is solved.

This invention discloses a method for hoisting steel anchor boxes with variable spacing for cable-stayed bridge towers across the sea, belonging to the field of bridge engineering. To address the challenges of short working windows at sea and the low precision, efficiency, and slowness of traditional methods, this invention constructs an integrated intelligent hoisting system. By deploying visual markers and positioning anchor points on the tower columns and steel anchor boxes, and combining differential satellite positioning, inertial measurement units, and other multi-source sensors, the precise pose of the steel anchor boxes is calculated in real time under a unified spatiotemporal reference. Artificial intelligence algorithms are used to predict the dynamic trajectory of sea conditions, the ship's hull, and the hoisting process, and a model predictive controller generates crane linkage compensation commands to dynamically suppress wind and wave disturbances. During the near-field installation phase, the system performs trajectory fine-tuning and anti-collision control based on a segment gap database; finally, a three-way hydraulic jack completes millimeter-level precise alignment and locking. This invention achieves an integrated closed loop of perception, prediction, control, and fine-tuning, significantly improving installation accuracy and efficiency, and shortening the time spent at sea.

This invention provides an underwater immersed tube positioning and monitoring method, a docking monitoring method, and related equipment. By pre-setting a black and white checkerboard pattern on the immersed tube and using an underwater robot equipped with a binocular camera to photograph and identify the checkerboard pattern, reliable calculation of the immersed tube's position and attitude can be achieved in complex underwater environments. Compared to existing assisted positioning methods using active laser targets, this invention utilizes a black and white checkerboard pattern as a passive visual marker, which has the advantages of simple structure, low manufacturing cost, convenient deployment, and no need for retrieval. It can effectively reduce the investment in underwater construction auxiliary equipment and work processes. Combined with underwater robot operations, it can also reduce the risks of manual underwater operations and improve the safety, practicality, and engineering economy of immersed tube positioning and monitoring.

The application relates to the technical field of computer vision, in particular to a three-dimensional positioning method and system of array elements, wherein the method comprises the following steps: acquiring a multi-view high-bit-depth gray image frame sequence of an array element to be measured; completing dynamic range conversion from high-bit-depth to low-bit-depth through adaptive bit-depth mapping enhancement; performing primary detection on the low-bit-depth image to obtain a candidate coded visual marker and a corresponding ROI region; performing local mapping enhancement on each ROI region to obtain an enhanced ROI image; performing secondary precision detection on the enhanced ROI image to output a target coded visual marker containing a target corner point and a single-frame pose; determining a corner point observation covariance according to the ROI dynamic range; constructing an incremental factor graph taking the single-frame pose as a state quantity and taking a re-projection error as an observation constraint, establishing an adaptive noise-weighted multi-frame joint optimization target; and performing optimization solving based on the optimization target to obtain three-dimensional coordinates of the array element in a world coordinate system. Through the application, the precision, consistency and real-time performance of three-dimensional positioning of the array element are improved.

An intelligent Office file comparison method based on structured mapping and hierarchical detection comprises the steps that format recognition and analysis are conducted on a source Office file and a target Office file through a dual-mode self-adaptive analysis engine, worksheet information and cell metadata in the files are extracted, and a file analysis result containing a worksheet set and a cell metadata set is obtained; establishing a mapping relationship for the worksheet set in the file analysis result to obtain a structured mapping relationship; based on the structured mapping relationship, calling a cell metadata set in the file analysis result, and performing difference detection on the worksheet to obtain a difference detection result; for a difference detection result, retaining an original file format by adopting a style cloning model to obtain a cloning style consistent with an original style; superposing the difference mark pattern based on the clone pattern to generate a non-destructive visual mark; and performing fragmentation aggregation and data splicing processing on the marked file data to form a complete comparison result file so as to update a file storage record.

The invention provides a vehicle parking floor estimation method and device, a vehicle and a storage medium. Specifically, through cooperative processing of satellite positioning signal vanishing points and ramp features, a stable reference system for absolute height calculation in the parking lot is established. Specifically, an absolute altitude reference which is not influenced by the environment is provided for a vehicle by utilizing signal vanishing point matching, so that a height accumulative error caused by integral operation of an inertial navigation system is fundamentally eliminated; the height change calculation is strictly limited in the ramp section between the slope entering point and the slope exiting point, so that the error introduction of invalid integration in a flat ground area is avoided, and the measurement precision of the relative altitude height is remarkably improved; finally, it is ensured that the vehicle can reliably determine the absolute altitude and the floor where the vehicle is located independent of the visual marker at any time, and therefore continuous and accurate space position information is provided for the automatic driving function.

The invention relates to an underwater multi-turbidity self-adaptive visual guidance method. An underwater visual marker is composed of a point light source matrix. And the four brightness-adjustable LED light sources are positioned at four vertexes of the point light source matrix. Under low turbidity, the brightness of the LED is increased to cope with the absorption of underwater light, so that the underwater visual guidance range is widened. After the water temperature, the salinity (solute) and the suspended solid concentration are obtained by the sensor, the turbidity is subjected to fusion sensing. By adjusting the brightness of the marker, different enhancement coefficients are adopted for the image to adapt to different underwater turbidities. And finally, the underwater visual guidance is realized through a PnP (Perspective-n-Point) algorithm.

1. Name of the product in this design: Search history interactive area for displaying search history and interactive graphical user interface of electronic device. 2. Purpose of this design: An electronic device. 3. The key design features of this product are: the parts in the graphical user interface, and the parts not marked with dotted lines are the parts for which protection is required. 4. The image or photograph that best illustrates the design's key points: Design 2 main view. 5. Design 2 is designated as the basic design. 6. Purpose of the graphical user interface: The overall appearance design of the interface is used to display intelligent search results with map location markers, visual markers of historical search records, intelligent switching of search record data, and other interactive features. The partial appearance design of the interface is used to display intelligent search results, visual markers of historical search records, intelligent switching of search record data, and other interactive features. 7. Human-computer interaction method of graphical user interface: In the main view of Design 1, the map displays the current search result location marker, the historical search record location marker, and the grayed-out location marker of the previous round of browsing. The scattered dots are the historical search record markers. Users can click on any dot in the historical search record to switch to display the previous round of search records; they can click on the arrow in the floating layer to view more search result sources, and they can also press and hold the control at the bottom of the interface to perform multiple rounds of voice search. In the main view of Design 2 (the top of the interface displays the current search result location marker, multiple rounds of historical search record location markers, and the grayed-out location marker of the previously viewed location, with scattered dots representing historical search record markers), when the user clicks on the dot marker of any historical search record in a certain round, the location marker of the corresponding historical search in that round is switched to be displayed. The locations of other search records remain displayed as dots, and the previously viewed locations are switched to grayed-out locations with a "viewed" label, presenting the interface change from the main view of Design 2 to the interface change state diagram of Design 2. In the main view of Design 3, when the user presses and holds the control at the bottom of the interface, the next round of voice content input is initiated, presenting the interface change from the main view of Design 3 to the interface change state shown in Figure 1. When the user releases their finger after inputting new voice content, an information search request is issued. The search results area at the top of the screen is grayed out, showing the interface changes from Design 3 Interface Change State Figure 1 to Design 3 Interface Change State Figure 2. The bottom of the interface then displays the new search results, while the position of the previous search results at the top of the interface is switched to a dot marker (viewed positions are grayed out and retained), and the position information of the new search results is displayed, presenting the interface changes from Design 3 Interface Change State Figure 2 to Design 3 Interface Change State Figure 3. The human-computer interaction description in Figure 3, which shows the change in state from the main view of Design 4 to the interface of Design 4, is the same as that in Figure 3, which shows the change in state from the main view of Design 3 to the interface of Design 3. In the interface change state diagram 3 of Design 4, when the user presses and holds the control at the bottom of the interface, the next round of voice content input state is entered, presenting the interface change from Design 4 interface change state diagram 3 to Design 4 interface change state diagram 4. When the user releases their finger after inputting new voice content, an information search request is issued. The search results area at the top of the screen is grayed out, and the interface changes from Design 4 Interface Change State Figure 4 to Design 4 Interface Change State Figure 5 are displayed. The bottom of the interface then displays the new search results, while the position of the previous search results at the top of the interface is also switched to a dot marker (the viewed positions are grayed out and retained), and the position information of the new search results is displayed, presenting the interface changes from Design 4 Interface Change State Diagram 5 to Design 4 Interface Change State Diagram 6.

The application discloses a moire-based mechanical vibration detection system and method, which is applied to a computing device connected with a camera in a camera-based non-contact vibration detection scene and comprises the following modules: an image preprocessing module, which is used for selecting a region of interest from an image captured by the camera, performing image enhancement and converting the image into a binary image; a vibration curve calculation module, which is used for solving a three-axis vibration curve of a target object to be detected in the image in an object coordinate system within a time interval; and a vibration parameter estimation module, which is used for estimating a vibration amplitude and a vibration frequency of the target object to be detected in the image. In the application, moire is formed by the projection and superposition of a color filter array (CFA) in the camera and moire visual markers on an imaging plane, and the moire has extremely high sensitivity to the relative pose change between the camera and the target object.

The invention discloses an unmanned aerial vehicle staged autonomous landing method for air-ground cooperation, and belongs to the field of artificial intelligence and robots. The method comprises a first stage of rapid landing based on trajectory tracking and a second stage of accurate landing based on visual servo. In the first stage, an improved environment adaptive weighted ant colony algorithm (EAW-ACO) is adopted to carry out global path search, a Minimum Snap method is combined to generate a smooth and safe flight path, and an unmanned aerial vehicle is guided to rapidly descend to the position near an unmanned vehicle platform. After the unmanned aerial vehicle enters a preset landing area, servo control based on visual marks is adopted in the second stage, and high-precision tail end alignment and landing are achieved. Through the organic combination of two stages of control strategies, the method has the unique advantages of fast landing of the front section and accurate docking of the tail end, provides key technical support for air-ground collaborative operation and cluster continuous operation of the unmanned aerial vehicle-unmanned vehicle, and has wide application prospects in the fields of intelligent storage, autonomous inspection and the like.

The invention discloses a mark generation method and device, electronic equipment and a program product, and relates to the technical field of man-machine interaction, and the method comprises the steps: displaying an interaction sub-interface and a map scene sub-interface; in response to the received interaction content input by the user, displaying the interaction content in the interaction sub-interface; identifying at least one target location from the interaction content in the interaction sub-interface; and adjusting a map display range in the map scene sub-interface, and generating a first location mark corresponding to the at least one target location. Through real-time analysis of the interaction content, the target location in the interaction content is automatically converted into the visual mark in the map scene, and intelligent linkage of the interaction information and the scene map is realized, so that the operation cost of manually positioning the target location by a user is reduced.

The present invention relates to the technical field of electronics. Disclosed are an unmanned aerial vehicle inspection control method and apparatus, a device, and an unmanned aerial vehicle inspection apparatus. In the method provided by the present invention, a controller in the unmanned aerial vehicle inspection apparatus acquires ranging information and / or image information of a visual marker during an inspection process, and generates movement control information on the basis of the ranging information and / or the image information of the visual marker and position information of a plurality of hovering points in a preset inspection route, to control the unmanned aerial vehicle inspection apparatus to sequentially move to the hovering points according to the inspection route, so as to implement inspection. Without relying on GPS positioning information, and without relying on wireless communication during flight, internal positioning of a wind turbine unit and autonomous inspection path planning can be implemented by only relying on the ranging information and / or the image information of the visual marker collected by the apparatus, thereby overcoming the technical problem of autonomous inspection by an unmanned aerial vehicle in a closed space, implementing autonomous inspection of the interior of the wind turbine unit, significantly reducing the workload of manual inspection, and improving the inspection quality and efficiency.

The present application relates to the technical field of robot control, in particular to a visual servo docking method, device, equipment and medium. The infrared visual marker of the present application is not affected by external environmental light, so that even if the external environmental light changes, high-quality images can still be collected, so that the position of the leader robot can be accurately located based on the high-quality images. Moreover, the present application considers disturbance data when calculating the control information required to be applied to the follower robot, so that the follower robot can overcome external interference under the action of the control information, thereby enabling the follower robot to accurately complete docking with the leader robot.

The application discloses a kind of unmanned aerial vehicle phased autonomous landing methods for air-ground cooperation, belong to artificial intelligence and robot field.This method includes the first stage based on trajectory tracking fast landing, and the second stage based on visual servo precision landing.First stage uses an improved environment adaptive weighting ant colony algorithm (EAW-ACO) to carry out global path search, and combined with Minimum Snap method generates smooth, safe flight trajectory, guide unmanned aerial vehicle to quickly drop to unmanned vehicle platform nearby.When unmanned aerial vehicle enters the landing area of pre-set, second stage uses the servo control based on visual marker, realizes high-precision terminal alignment and landing.The application has the unique advantage of fast landing in front and accurate docking in the end by the organic combination of two-stage control strategy, provides key technical support for unmanned aerial vehicle-unmanned vehicle air-ground cooperation and cluster continuous operation, has wide application prospect in intelligent warehousing, autonomous inspection and other fields.

The invention relates to the technical field of artificial intelligence, in particular to a coal mine tunnel vehicle visual positioning method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: presetting and storing a three-dimensional coordinate of a visual marker in a coal mine tunnel; performing target detection on the current video stream data by using a marker detection and recognition algorithm to obtain a detection frame of each marker; tracking the same marker by using a marker smooth tracking algorithm to obtain a camera focal length rate of a region corresponding to the tracking frame; based on the camera focal length rate of the corresponding area of the tracking frame, the relative distance between the vehicle and the marker is obtained through a marker distance calculation algorithm; and fusing the relative distance with the vehicle dead reckoning information to obtain a final vehicle positioning result. A coordinate system is established for markers to construct a quasi-structured visual map, and a specially designed target tracking and distance estimation algorithm is combined, so that sub-meter continuous positioning is realized in a coal mine tunnel, and the vehicle positioning precision is improved.

The present application is suitable for the technical field of pose recognition, and provides a 3D vision-based excavator pose recognition method.The present application can realize automatic pose recognition of the excavator during work, without manual monitoring, thereby reducing labor cost and improving the working efficiency of the excavator.Only one monocular camera is needed to predict the pose of the excavator, without the need to install visual markers, which is convenient to install and has low use and maintenance cost.Meanwhile, by recognizing and optimizing additional points, even in the case that some key points of the excavator are blocked, the problem of accuracy reduction can be effectively alleviated.According to the physical size constraint and kinematic characteristics of the excavator, an optimization pre-processing method and execution logic are designed, and a new target function is designed based on the projection relationship, and a global and local optimization combined method is used to obtain the 3D pose, thereby improving the recognition accuracy and speed.

The invention belongs to the technical field of strabismus inspection equipment, and particularly relates to a child strabismus quantitative inspection system and method based on scene interaction, and the system comprises a display module, a sub-vision module, an input module and a processor. The display module presents a dynamic scene picture containing a static visual mark, a first visual element and a second visual element; the split vision module enables the left eye and the right eye to observe different color elements through the red-green split vision technology. The input module sends a movement control instruction of a child to a target role; the processor calculates eye position parameters according to the deviation between the final coordinate of the target role and the static mark. Through random generation and real-time chasing design of the second visual element, the average concentration time of children is greatly prolonged, the system adopts low-cost hardware, automatic strabismus parameter acquisition is achieved, and the problems that a traditional method depends on professional equipment, the child cooperation degree is low, and static detection sensitivity is insufficient are solved.

The invention provides endoscope bending part gluing equipment and system.The endoscope bending part gluing equipment comprises a workbench, a positioning assembly, a gluing assembly and a visual marker, the workbench is provided with a clamping assembly and a first driver, and the first driver is used for driving the clamping assembly to rotate so as to drive an endoscope tube to rotate; the positioning assembly is arranged on the workbench and comprises a first positioning mechanism and a second positioning mechanism, and the first positioning mechanism and the second positioning mechanism are used for positioning the end of an endoscope tube; the gluing assembly comprises a first sliding frame and a gluing needle, the first sliding frame drives the gluing needle to move along the rotating axis of the clamping assembly, and the gluing needle is provided with a gluing head; the visual marker is arranged on the first sliding frame and used for emitting visible light, and the visible light is used for marking the coating position of the gluing head on the endoscope tube. According to the gluing device, precise control over the gluing process can be achieved, and the gluing precision and the gluing quality can be improved.

The invention relates to the technical field of medical image processing, in particular to a visual positioning method and system for a cervical treatment area, and the method comprises the steps: collecting a current video frame of the treatment area; carrying out multi-dimensional quality detection on the current video frame and carrying out weighted calculation to obtain a quality score; when the quality score is greater than a preset first threshold value, determining that the key frame is a treatment area key frame; boundary position coordinates of the treatment area are obtained through recognition according to the key frame of the treatment area and are converted into visual marks, and the visual marks and video stream frame images corresponding to the timestamps are overlapped to obtain a positioning reference picture; and in the real-time video stream updating process, if the continuous quality score of the treatment area key frame is lower than a preset second threshold value, selecting a new treatment area key frame from the subsequent video frames, and updating the positioning reference picture. According to the invention, by introducing the multi-modal imaging data fusion and dynamic weight distribution strategy, the key frame which can reflect the state of the treatment area most truly is screened out, and the positioning accuracy and the system stability are improved.

The invention provides a marking method and device for SVG construction drawings. The method comprises the steps that a pre-trained large language model is used for analyzing and recognizing construction scheme data to obtain structured information; analyzing the construction drawing in the SVG format, and extracting to obtain element attributes and transformation attributes; identifying construction system nodes, branch equipment and a connection relationship between the branch equipment and the construction system nodes from the element attributes; analyzing translation transformation and affine transformation in the transformation attributes, and calculating element coordinates of nodes of the construction system; generating different types of visual marks based on branch equipment, construction system nodes, a connection relation of the branch equipment and the construction system nodes and the element coordinates; and converting the visual mark and the structured information into a parameter instruction set, and merging the parameter instruction set into the construction drawing in the SVG format to obtain a marked target construction drawing. Therefore, the problems that a traditional method is limited in processing capacity, insufficient in industry adaptability, low in marking precision, difficult in system integration and the like are solved.