Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

531 results about "Observation Object" patented technology

The name of the entity that is being assessed.

Robot skill learning method, system and terminal for text large model assisted reinforcement learning

The invention discloses a robot skill learning method and system for text large model assisted reinforcement learning, and a terminal. The method comprises the following steps: representing an environment by adopting a scene graph; analyzing a task instruction and an environment by utilizing a text large model; taking the large text model as a guide agent, taking a reinforcement learning agent as an exploration agent, combining jump reinforcement learning and conservative Q learning, and training the reinforcement learning agent by using a data set generated by interaction of the guide agent and the exploration agent with the environment to obtain a trained reinforcement learning agent; and selecting a target observation object for the trained reinforcement learning agent by using the text large model, and outputting a target action sequence by the trained reinforcement learning agent. According to the method, language instructions are understood through a large model technology, feasible guide strategies are generated, so that random exploration steps are reduced, parameterized skills are introduced, the training process of reinforcement learning is accelerated, the efficiency is high, and the method does not depend on the data volume of a skill library.
Owner:SHENZHEN UNIV

Radiator micro-channel structure integrity detection method based on acoustic measurement

The invention discloses a radiator micro-channel structure integrity detection method based on acoustic measurement, and relates to the technical field of information, the method couples acoustic propagation measurement with density inversion and particle transport observation, firstly screens a key observation object according to density gradient change, and then constructs a hydrodynamic equilibrium graph by using auxiliary particle flow, and finally obtains the structural integrity of the radiator micro-channel. And channel-by-channel difference is carried out with reflection measurement of standard acquired data, so that defects are indicated by three domains of energy, time and space together. According to the closed-loop link, the sensitivity to tiny blockage, slight deformation and early crosstalk is remarkably improved, the false alarm rate that single measurement is easily influenced by noise and working condition fluctuation is reduced, fine positioning of channel-level abnormal positions and ranges is achieved, and the closed-loop link is suitable for high-resolution detection of dense micro-channel arrays without disassembly or destructive operation.
Owner:DONGGUAN DONGYISI CHUANG ELECTRONICS CO LTD

Three-dimensional model LOD continuous display method and device and electronic equipment

The invention provides a three-dimensional model LOD continuous display method and apparatus, and an electronic device. The method comprises the steps of obtaining viewpoint information of an observation object and model information of each three-dimensional model; screening out a target three-dimensional model from the three-dimensional models based on the viewpoint information and the model information under the condition that the viewpoint information is determined to be changed, and determining an initial LOD model of the target three-dimensional model; determining the visualization quality of the initial LOD model based on the initial LOD model, the viewpoint information and the screen resolution of a screen; determining a target LOD model based on the visualization quality and the minimum number of sensible pixels of the initial LOD model; and the target LOD model is output through the screen, so that the display continuity when the LOD model is switched can be realized, the display effect is improved, and the use experience of a user is further improved.
Owner:SHENZHEN UNIV

Flow cytometer

This flow cytometer includes a flow path through which an observation object flows with a fluid; an optical illumination system including a spatial optical modulation device, and a first optical element; and an optical detection system including a first light detector, wherein the optical illumination system further includes a first spatial filter disposed in a first optical path between a light source and an image position of light imaged in the flow path by the first optical element and having a first region which hinders traveling of light emitted from the light source towards the observation object, the optical detection system further includes a second light detector disposed in a second optical path between the first light detector and the image position and having a second region which directs the light modulated by the observation object towards the first light detector, and the position of the first region and the position of the second region are in a substantially optically conjugate relationship.
Owner:THE UNIV OF TOKYO +1

Observation device and observation method

An observation apparatus includes a light source, a mirror, a condenser lens, an objective lens, a beam splitter, an imaging unit, and an analysis unit. The analysis unit includes an interference intensity image acquisition unit, a first complex amplitude image generation unit, a second complex amplitude image generation unit, a two-dimensional phase image generation unit, a three-dimensional phase image generation unit, a refractive index distribution calculation unit, and a third complex amplitude image generation unit. The analysis unit irradiates an observation object with light along each of a plurality of light irradiation directions by changing an orientation of a reflection surface of the mirror, acquires an interference intensity image for each of the plurality of light irradiation directions from the imaging unit, and performs necessary processing based on the interference intensity images to obtain a three-dimensional refractive index distribution of the observation object.
Owner:HAMAMATSU PHOTONICS KK

Data assimilation method and equipment based on digital twinning and virtual-real verification, and medium

The invention relates to the technical field of data assimilation, and particularly provides a data assimilation method and equipment based on digital twinning and virtual-real verification, and a medium. The data assimilation method based on digital twinning and virtual-real verification comprises the following steps: constructing an agent model of an observation object, and obtaining a prediction result output by the agent model and an actual observation result of the observation object; consistency verification is carried out on the prediction result and the actual observation result, and the prediction result and the actual observation result which pass verification are obtained; performing sequence alignment processing on the predicted result and the actual observation result which pass the verification to obtain a processed predicted result and an actual observation result; and performing data assimilation on the processed prediction result based on the processed actual observation result to obtain a target prediction result of the observation object. According to the method, the technical problems that actual observation data has noise and has sparsity are solved through consistency verification and sequence alignment processing, so that the accuracy and reliability of an agent model prediction result are improved.
Owner:BEIHANG UNIV

Medical image processing apparatus, trocar, medical observation system, image processing method, and computer readable recording medium

A medical image processing apparatus includes a control unit configured to cause, based on a detection result of at least one trocar into which a medical instrument is inserted, the at least one trocar being configured to detect a first state and a second state, the first state and the second state indicating an insertion state of the medical instrument into a subject, a display device to display at least one of a first image generated by capturing an image of an observation object inside the subject and a second image of the observation object inside the subject, the second image being previously acquired.
Owner:SONY OLYMPUS MEDICAL SOLUTIONS

Astronomical data fusion analysis method based on deep learning

The invention relates to the field of data processing, in particular to an astronomical data fusion analysis method and system based on deep learning. The method comprises the following steps: acquiring multi-source astronomical data; the multi-source astronomical data aim at the same observation object or the same observation area; inputting the multi-source astronomical data into an adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data; configurable analysis mode parameters and analysis modes are set in the adaptive exploration space model; and performing multi-branch fusion processing on the multi-source astronomical data by adopting the analysis mode to obtain astronomical fusion data corresponding to the multi-source astronomical data. According to the method, related information of different data sources can be dynamically fused, and deep fusion analysis of multi-source astronomical data is realized, so that more accurate and more comprehensive astronomical fusion data is provided for astronomical research.
Owner:HENAN ACADEMY OF SCIENCES GRAVITY WAVE ASTRONOMY RESEARCH INSTITUTE +1

TLS observation network planning method for large-scale building

InactiveCN119129038ASolve the problem of low efficiency of three-dimensional simulation planningImprove reliabilityGeometric CADDesign optimisation/simulationThree dimensional simulationBuilding simulation
The invention discloses a TLS observation network planning method for a large-scale building, and relates to the technical field of building simulation. Comprising the following steps: acquiring grid three-dimensional information of an observation area; taking all grid points in the screened grid as observation candidate sites, performing observation simulation on each candidate site in a final observation target point union set, and taking a building feature line length value obtained by simulation scanning as a weight value of the candidate site; scanning contents of the selected candidate sites are deleted from the screened simulation observation contents; and performing iterative selection in the remaining candidate sites until the maximum weight value of the current candidate site is lower than a set weight threshold value, obtaining a simulated overlapping degree among the remaining candidate sites, and performing station supplementation operation on the remaining candidate sites with the simulated overlapping degree lower than the set threshold value to obtain the TLS observation network. The method restrains the number of observation objects, solves the problem of low efficiency of three-dimensional simulation planning of a TLS observation network, and has the capability of processing large-scale building groups.
Owner:EAST CHINA UNIV OF TECH

Dual-unmanned aerial vehicle cooperation method and cooperation control system

The invention provides a dual-unmanned aerial vehicle cooperation method and a cooperation control system, and relates to the technical field of unmanned aerial vehicles. The method comprises the steps that a flight task issued by a ground control part is acquired from an unmanned aerial vehicle, first flight data and second flight data are acquired, the first flight data comprise main image data, and the second flight data comprise auxiliary image data; the slave unmanned aerial vehicle determines a space vector between the master unmanned aerial vehicle and the slave unmanned aerial vehicle as a baseline; the slave unmanned aerial vehicle constructs an accompanying flight control model based on the obstacle influence data, the baseline length corresponding to the baseline and the observation sight line included angle, generates an accompanying flight control instruction enabling the accompanying flight control model to reach the flight condition, controls flight according to the accompanying flight control instruction, and the obstacle influence data is used for describing the obstacle avoidance risk of the flight route to the obstacle; the ground control unit fuses the main image data and the auxiliary image data to obtain an observation result of the object to be observed. The flight stability of the multiple unmanned aerial vehicles is improved, and the efficiency of surveying and mapping tasks is improved.
Owner:HUAHANG HI-TECH (BEIJING) TECH CO LTD

Thyroid disease risk prediction method and system based on machine learning

The invention relates to the technical field of machine learning, and discloses a thyroid disease risk prediction method and system based on machine learning. The method comprises the steps of collecting medical record data of a thyroid disease patient, establishing a classification model based on the medical record data, and outputting a thyroid disease type corresponding to the medical record data; establishing a word vector model and a machine learning model, extracting a first feature quantity and a second feature quantity from the medical record data, screening out a first key feature and a second key feature of each thyroid disease from the first feature quantity and the second feature quantity, fusing the first key feature and the second key feature to obtain a comprehensive feature vector, and establishing a risk prediction model; acquiring medical record data of the current observation object, inputting the medical record data into the risk prediction model, and predicting and generating a thyroid disease risk level and a disease type of the current observation object based on the medical record data; if the risk level is a medium risk or a high risk, an optimal adjustment vector is generated, health adjustment suggestions are obtained based on the optimal adjustment vector, and the prediction accuracy of the thyroid disease risk is improved.
Owner:SHENZHEN MINGHAO BIOTECHNOLOGY CO LTD

Motion capture method and device based on multi-view camera and storage medium

The invention relates to a motion capture method and device based on a multi-view camera and a storage medium. Comprising the following steps: simultaneously imaging an observation object by using a multi-view camera to obtain a plurality of sample photos, calibrating the multi-view camera, and calculating a homography matrix of each camera in the multi-view camera; selecting articulation points needing to be captured from the plurality of sample photos for labeling, performing training by applying an action recognition model, and generating two-dimensional coordinates of the articulation points on each of the plurality of sample photos and corresponding confidence coefficients of the two-dimensional coordinates; screening all the two-dimensional coordinates according to a preset threshold value of confidence, and combining every two screened two-dimensional coordinates to obtain a plurality of two-dimensional coordinate pairs; performing three-dimensional reconstruction on the plurality of two-dimensional coordinate pairs based on a homography matrix, and taking a calculation result as a three-dimensional coordinate set of the joint point; and determining a final coordinate of the joint point from the three-dimensional coordinate set according to a preset rule.
Owner:LINGANG LAB

Multi-source data fusion axial flow compressor instability prediction method

The invention discloses a multi-source data fusion axial flow compressor instability prediction method, and belongs to the technical field of aero-engine modeling and simulation. The method comprises the following steps: firstly, preprocessing dynamic pressure sensor data, constructing a multi-source data set and dividing the multi-source data set; secondly, respectively constructing a time domain feature extraction network module, a time-frequency domain image feature extraction network module and an interactive fusion module based on a cross-domain attention mechanism; thirdly, on the basis of the three modules, a multi-source data fusion compressor instability prediction model based on a cross-domain attention mechanism is constructed, and the model is trained to save an optimal model; and finally, performing real-time prediction on test data. According to the method, data of multiple sources are comprehensively processed and analyzed, complementarity and relevance among different data sources are captured, more comprehensive, complete and consistent perception about a target observation object is formed, diagnosis errors caused by a single data source are reduced, and the accuracy and reliability of a prediction result are improved.
Owner:DALIAN UNIV OF TECH

Experimental system and method for research on photodynamic therapy, photothermal therapy and combination of photodynamic therapy and photothermal therapy

The invention relates to an experimental system and method for photodynamic therapy, photothermal therapy and combined research of photodynamic therapy and photothermal therapy. The experiment system comprises an optical irradiation module which comprises a plurality of laser light sources, each laser light source can output collimated light beams, the collimated light beams are combined to form a coaxial light path, and the coaxial light paths are projected to the surface of an observation object through a light beam adjusting assembly; the light path position adjusting module comprises an electric Z-axis displacement mechanism; the temperature monitoring module comprises an active temperature control substrate, an infrared thermal imager and an optical fiber temperature probe interface; the data acquisition and control module is configured to synchronously acquire laser output power, light spot area, electric Z-axis position, temperature of the active temperature control substrate, temperature sequences of a plurality of different areas and optical fiber temperature probe data, and associatively record the data with a unified timestamp; the power density can be calculated based on the real-time output power of the laser light source and the light spot area; and when the data of any temperature monitoring channel exceeds a preset safety threshold value, the laser light source is automatically controlled to close the output.
Owner:XUANWU HOSPITAL OF CAPITAL UNIV OF MEDICAL SCI

Intelligent breeding supervision method and system based on artificial intelligence

The invention discloses an intelligent breeding supervision method and system based on artificial intelligence, and belongs to the technical field of breeding management. The system comprises a data acquisition module, a breeding analysis module, an intelligent management module and an automatic adjustment module. The data acquisition module is used for acquiring equipment information of a farm and a feeding database of bred objects; the breeding analysis module is used for analyzing the feed-meat relationship according to the breeding database and calculating the predicted weight increment of the breeding object; the intelligent management module is used for calculating an abnormal index of a breeding object by predicting weight increment so as to set an observation object and a reference object; and the automatic adjusting module is used for establishing an adjusting instruction according to the reference object and automatically adjusting equipment of the culture area where the observation object is located.
Owner:NANJING AGRICULTURAL UNIVERSITY +1

Evaluation method, evaluation device, and information processing program

A refractive index distribution evaluation method, evaluation device, and information processing program, comprising: a data acquisition step or a data acquisition unit for acquiring refractive index distribution data for an object of observation; a selection step or a selection unit for selecting whether a target included in the refractive index distribution data is an evaluation target; and an evaluation step or an evaluation unit for evaluating the refractive index distribution of the evaluation target.
Owner:HAMAMATSU PHOTONICS KK

Imaging flow cytometer

An imaging flow cytometer includes: a flow channel in which an observation object flows and a length in a width direction is longer than a length in a height direction; an acoustic element configured to apply acoustic waves as standing waves to the flow channel; a light source that irradiates the flow channel with illumination light; an image sensor configured to image at least a line included in a cross section of the observation object crossing a flow line direction which is a direction in which the observation object flows in the flow channel by measuring or imaging the observation object passing through a position irradiated with the illumination light; and circuitry configured to generate an image in which the observation object is scanned in the flow line direction on the basis of a plurality of captured images acquired by the imaging unit imaging the line in a time series.
Owner:THE UNIV OF TOKYO

Method for comprehensively searching hidden defects of operating equipment of transformer substation

The invention discloses a comprehensive searching method for hidden defects of operation equipment of a transformer substation, which comprises the following steps of: firstly, establishing a primary equipment hidden defect library, taking all defective parts of primary equipment as observation objects, and carrying out machine vision and acoustic vibration acquisition; the method comprises the following steps: determining whether primary equipment is deviated or loosened, judging a part where a primary fault occurs according to the sound vibration signal correlation degree, judging whether a secondary signal is abnormal or not through secondary circuit auxiliary contact signal detection, and comprehensively judging an image pairing result, the sound vibration correlation degree and whether the secondary signal is abnormal or not. And determining hidden dangers and defect types of the equipment. The method provided by the invention can be used for distinguishing different hidden dangers and faults of the equipment and improving the detection accuracy.
Owner:DEZHOU POWER SUPPLY COMPANY OF STATE GRID SHANDONG ELECTRIC POWER

Virtual scene display method and device, storage medium and electronic equipment

The embodiment of the invention relates to a virtual scene display method and device, a storage medium and electronic equipment, and relates to the technical field of computers.The method comprises the steps that a first scene picture which is shot at a first scene position through a virtual lens bound in a current controlled object and comprises a current observed object is displayed on a display interface; determining a second scene position needing to be switched by the virtual lens according to the current human eye position coordinate at the current moment, and determining a lens switching track of the virtual lens according to the first scene position and the second scene position; switching the virtual lens from a first scene position to a second scene position based on the lens switching track and an automatic telescopic component bound in the current controlled object; and replacing the first scene picture based on a second scene picture which is shot by the virtual lens at a second scene position and comprises a target observed object. According to the invention, the switching efficiency of the scene picture is improved.
Owner:BOE TECHNOLOGY GROUP CO LTD

Humanoid robot complex terrain balance control method based on state and disturbance observer

The invention provides a humanoid robot complex terrain balance control method based on a state and disturbance observer, and belongs to the technical field of robot application. The problem that the humanoid robot is unstable when walking in a complex environment is solved. According to the technical scheme, the method comprises the following steps that 1, a simplified humanoid robot'spring-damping 'inverted pendulum model is established; 2, designing a state and disturbance observer; step 3, based on the step 2, designing a state feedback controller taking a real-time observation object of the state and disturbance observer as input; 4, selecting an appropriate controller pole and an appropriate controller observation point; and 5, simulation verification of attitude balance control of the humanoid robot under the complex terrain is carried out. The method has the beneficial effects that the robustness of the robot to interference and the task execution capability can be improved particularly in disaster rescue and complex environment operation.
Owner:NANTONG UNIV

Endoscope observation area tracking method and system, electronic equipment and storage medium

The embodiment of the invention provides an endoscope observation area tracking method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring first feature information of a reference observation area in a reference endoscope image; the reference endoscope image comprises a target observation object; obtaining a to-be-detected endoscopic image, wherein the to-be-detected endoscopic image comprises a target observation object; determining at least one candidate observation area from the to-be-detected endoscopic image; for each candidate observation area in the at least one candidate observation area, obtaining second feature information of the candidate observation area; the second feature information is consistent with the type of features contained in the first feature information; calculating the similarity between the candidate observation area and the reference observation area based on the second feature information and the first feature information; and based on the similarity corresponding to the at least one candidate observation area, determining a target observation area containing the same target observation object as the reference observation area. And automatic tracking and identification of the observation area in the endoscopic image can be realized.
Owner:SONOSCAPE MEDICAL CORP

Traffic information processing method, control method, equipment and medium

The invention relates to a traffic information processing method, a control method, equipment and a medium. The traffic information processing method comprises the following steps: determining an observation object belonging to a target lane; wherein the target lane is a lane in a lane group associated with a vehicle driving path; performing motion trail sampling on the observation object to obtain a trail point sequence of the observation object; wherein the track point sequence comprises a first track point sequence obtained by carrying out motion track sampling based on a time change dimension, and a second track point sequence obtained by carrying out motion track sampling based on a position change dimension; each track point in the track point sequence comprises timestamp information, motion information and distance information of the corresponding track point relative to a stop line of the target lane; and obtaining a traffic light prediction state of the target lane according to the track point sequence.
Owner:CORECHENG (BEIJING) TECHNOLOGY CO LTD

Endoscope system, procedure support method, and recording medium

An endoscope system includes: an endoscope including an elongated portion in which an imaging optical system is arranged; an arm supporting the endoscope; and a unit capable of changing a field-of-view direction of the endoscope, wherein each library data stored in a storage includes a parameter related to relative position and attitude between the imaging optical system and an observation object, the parameter includes a first parameter or a second parameter, the first parameter determined by a sum of an inclination of a longitudinal axis of the elongated portion and an amount of curvature of the changing unit on base coordinates, the first parameter related to an orientation of the imaging optical system on the base coordinates, the second parameter indicating an orientation of the imaging optical system as viewed from a coordinate of the observation object, and the unit or the arm based on the library data is controlled.
Owner:OLYMPUS CORPORATION(JP) +1

Observation device and observation method

To provide a device that allows stable observation of an observation object.SOLUTION: An observation device 1A is a device for observing an observation object S, and comprises a light source 11, a beam splitter 12, mirrors 13, 14, a beam splitter 15, a modulation unit 21, lenses 31-34, an imaging unit 41, and a processing unit 42. The modulation unit 21 receives input of first branch light L1 arriving from the mirror 13, and applies spatial amplitude modulation to the input first branch light L1 on the basis of a modulation pattern to obtain first branch light including a plurality of light components different from each other in wavenumber components in an x direction. The modulation pattern of the modulation unit 21 moves in a predetermined direction (x-axis direction) intersecting a propagation direction (z-axis direction) of the first branch light L1. The processing unit 42 creates complex amplitude images when the observation object S is irradiated with the plurality of light components on the basis of detection signals repeatedly output from the imaging unit 41.SELECTED DRAWING: Figure 1
Owner:HAMAMATSU PHOTONICS KK

Medical assistance device, medical assistance system, and program

PCT designated stage expiredWO2024257329A1SurgeryEndoscopesComputer hardwareMedical support
Provided are a medical assistance device, a medical assistance system, and a program that make it possible to leave effective medical information regardless of information regarding the insertion of an endoscope into the body of a subject. The medical assistance device comprises a processor. The processor acquires usage status information regarding a usage status until an endoscope reaches observation of a preset observation site with respect to a subject, determines whether the endoscope has reached the observation site on the basis of the usage status information, generates handover information for a report regarding observation of the observation site on the basis of the determination result of whether the observation site has been reached by the endoscope and the usage status information, and records the handover information.
Owner:OLYMPUS MEDICAL SYST CORP

Digital magnifier

1. The name of the design product: digital magnifying glass. 2. The use of the design product: for magnifying observation objects. 3. The design points of the design product: in shape. 4. The picture or photo that best shows the design points: perspective view 1.
Owner:SHENZHEN TESLONG TECH CO LTD

Method for determining efficiency evaluation index of remote sensing satellite

The invention provides a remote sensing satellite effectiveness evaluation index determination method, and the method comprises the steps: obtaining a test data set of a to-be-evaluated satellite system based on a pre-obtained evaluation index, the evaluation index comprising evaluation demands of the to-be-evaluated satellite system in various aspects, and achieving the comprehensive evaluation of the to-be-evaluated satellite; furthermore, the final target observation object is screened from the at least one target observation object by using a first preset algorithm, and the to-be-evaluated satellite system is evaluated according to the target observation elements of the final target observation object, so that standardized evaluation of the to-be-evaluated satellite system is realized, and the evaluation accuracy of the to-be-evaluated satellite system is improved. And the accuracy and rationality of evaluation are improved.
Owner:周翔

Sensory traits information collecting method and sensory traits information collecting device

A sensory traits information collecting method includes: a first viewed-object presenting step of presenting one or more viewed objects (30) including a predetermined visibility element (31, etc.) to a subject in a white light environment in which white light (L0) is incident on a retina (R) of the subject; a predetermined light environment creating step of creating a predetermined light environment in which predetermined light (L1) different from the white light (L0) in at least one of spectral distribution and luminance is incident on the retina (R) of the subject; a second viewed-object presenting step of presenting the viewed object (30) to the subject again in the predetermined light environment; an information reception step of receiving sensory traits information related to the way of seeing of the viewed object (30) in the first viewed-object presenting step and the second viewed-object presenting step; and a collecting step of collecting the sensory traits information received from the subject.
Owner:KUNKASHA CO LTD

Digital magnifier (V5)

1. The name of the design product: digital magnifying glass (V5). 2. The use of the design product: the design product is used for magnifying observation objects. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.
Owner:深圳市人为数码科技有限公司