1695 results about "Image extraction" patented technology

The invention relates to the technical field of image processing, in particular to an image acquisition and analysis method and system, and provides the following scheme: obtaining a visible light and near-infrared multispectral image, generating a spectral difference image, and performing weighted fusion to obtain a first image; segmenting a target region based on the fused saliency map, and calculating a pixel reflectance ratio; solving a color mapping matrix according to the reflectance ratio, and carrying out color correction on the target region to obtain a standardized feature image; and extracting characteristic parameters such as spectrums, colors and textures, inputting the characteristic parameters to a multi-branch convolutional neural network, fusing the characteristic parameters through an attention mechanism, and outputting a state classification result and a quantitative index. The cross-spectral imaging difference can be adaptively compensated, and the fusion precision and the analysis stability are improved.

The invention provides a science and technology information deep analysis method and system based on cross-modal semantic enhancement, and relates to the technical field of science and technology information analys.The method comprises the steps that firstly, a cross-modal semantic anchor point set is constructed, and the cross-modal semantic anchor point set comprises text theme anchor points extracted from science and technology information texts, visual object anchor points extracted from images and the association mapping relation of the text theme anchor points and the visual object anchor points; constructing a semantic conduction path between anchor points based on the cross-modal semantic anchor point set, realizing bidirectional information transmission, generating a cross-modal semantic enhanced representation, performing hierarchical semantic analysis on the enhanced representation to obtain a topic association rule, a technical element dependency relationship and a concept evolution sequence, and integrating the topic association rule, the technical element dependency relationship and the concept evolution sequence into an analysis conclusion; the analysis conclusion is reversely mapped to adjust the association mapping relation strength, an updated set is obtained, finally, a structured science and technology information analysis report is generated based on the updated set, logic connection of all modules is achieved, and comprehensive and accurate science and technology information analysis is provided for users.

The invention discloses a zero sample anomaly detection method and system based on a triple perception learning enhanced visual language model, and relates to the field of computer vision, and the method comprises the steps: extracting global and local visual features from an input image; in the visual coding process, local features in a deep network are corrected through a spatial perception attention enhancement module, and fine-grained attribute text description is generated for abnormal visual features; performing deep semantic alignment on the attribute text description and the general text prompt through an attribute perception guide module; calculating the similarity between the enhanced visual features and the optimized text features, and generating a pixel-level abnormal segmentation map; in the inference stage, the segmented image is converted into a space attention weight through an anomaly perception reconstruction module, the space attention weight is fed back to a visual encoder to generate final global feature representation, and an anomaly score is calculated. According to the method, under the condition that a target domain training sample is not needed, the anomaly detection and positioning accuracy and generalization ability of the model under the scenes of industrial defect detection and the like are remarkably improved.

The invention discloses a safety real-time detection method in a complex scene based on multi-scale feature fusion, and relates to the technical field of safety detection, and the method comprises the steps: S1, obtaining a to-be-detected complex scene image; s2, extracting multi-scale initial feature maps with different semantic information and spatial details; s3, inputting the initial feature maps of the plurality of scales into an adaptive feature fusion network; s4, inputting the enhanced feature pyramid into a lightweight decoupling detection head, and executing target classification and bounding box regression in parallel; and S5, based on the category and position information, generating and outputting a final security detection result. The method has the advantages that semantic and detail features of different levels are effectively integrated through a self-adaptive gating fusion mechanism and multi-scale context aggregation, and the detection precision and robustness of the model on a multi-scale target in a complex scene are remarkably improved.

The invention discloses a method for estimating plant biomass based on map multi-modal feature extraction and fusion. The method comprises the following steps: acquiring a plant RGB image and a multi-spectral image; inputting the preprocessed RGB image and NIR wave band image into a double-model cooperation segmentation framework to realize image segmentation; binary image features, color features, texture features, reflectivity and the like are calculated, feature splicing is carried out, and high-dimensional features are constructed; carrying out dimension reduction on the high-dimensional features; and training a deep neural network through the effective features and the biomass to realize biomass estimation. According to the method, a zero sample learning-based double-model cooperation segmentation framework is utilized to realize accurate segmentation of a single plant on the premise that a large number of training sets are not needed; multi-modal feature information is extracted based on the segmented single plant image, an improved SHAP model is introduced to reduce the feature space dimension, and the inversion precision and the operation efficiency are improved while the information effectiveness is ensured; through a high-precision deep neural network model, rapid, lossless and accurate biomass acquisition is realized.

The invention provides an image region-of-interest extraction method and system based on a Mama architecture, and relates to the technical field of image processing, and the method comprises the steps: obtaining a to-be-extracted image; performing multi-scale feature extraction on the to-be-extracted image through a local enhancement module; multi-scale semantic enhancement features are generated through a cross-scale self-attention module, and dimension reduction processing is performed through a feature conversion module; local detail features are generated through an adaptive detail enhancement module; performing global context enhancement processing on the local detail features through a pyramid pooling module to generate context enhancement features; performing up-sampling processing on the context enhancement features; the context enhancement features after up-sampling processing are fused through a self-adaptive global-local fusion gating module; and carrying out image extraction based on the decoded fusion features. The image segmentation precision is improved, the model is light in weight, reasoning is fast, and the problems of image boundary blurring and scale variability are effectively solved.

The invention relates to an acquisition equipment parameter determination method and equipment for improving welding seam image quality, and the method comprises the steps: determining the current parameters of acquisition equipment, and obtaining a welding seam region image under the current parameter condition; high-brightness pixel points and low-brightness pixel points in the welding seam area image are extracted to determine the high-brightness pixel proportion, the low-brightness pixel proportion and the high-brightness pixel distribution divergence; according to the high-brightness pixel proportion, the low-brightness pixel proportion and the high-brightness pixel distribution divergence, whether the welding seam area image is qualified or not is judged; if yes, taking the current parameter as a determined parameter of the acquisition equipment; and if not, correcting the current parameter to obtain the updated current parameter, and returning to determine the current parameter until the determined parameter of the acquisition equipment is obtained. The problems that in the prior art, under the complex illumination working condition, proper collection equipment parameters cannot be determined to ensure clear presentation and stable extraction of a welding seam feature area, then the robustness and positioning precision of a welding seam tracking system are affected, and the technical adaptability is reduced are solved.

The invention relates to the technical field of image recognition, and discloses a crop lodging image data detection method and system, and the method comprises the steps: carrying out the self-adaptive illumination correction processing of the original image data of crop lodging, and obtaining an illumination compensation image of the original image data; performing multi-scale super-pixel segmentation on the illumination compensation image to obtain a crop area image of the illumination compensation image; extracting texture features and shape features in the crop region image, and performing feature fusion on the texture features and the shape features to obtain a multi-modal fusion feature set of the crop region image; performing multi-dimensional feature collaborative analysis on the multi-modal fusion feature set to obtain an initial discrimination result of the multi-modal fusion feature set; performing confidence coefficient optimization on the initial judgment result in combination with a spatial context relationship to obtain a target lodging detection result of the crop region image; according to the invention, the efficiency of crop lodging image data detection can be improved.

The invention discloses a defect multi-angle detection and fusion method based on a vector graph and affine transformation, and relates to the technical field of image processing, and the method comprises the steps: collecting a plurality of sub-images with overlapping regions at a single angle; constructing a collision map at the angle, wherein the view field of each grid corresponds to a sub-image; extracting defect contours from the sub-images and converting the defect contours into defect vector graphs; according to the defect vector set of all the sub-images at the angle, collision detection and cross-sub-image defect fusion are carried out based on the collision map at the angle, and a defect set at the angle is obtained; one angle is selected as a reference angle, other angles are selected as target angles, a defect set of the target angles is transformed to a reference angle coordinate system based on affine transformation, collision detection and cross-angle fusion are carried out on the transformed defect set and the defect set of the reference angles, and a final optical assembly defect set is obtained. And integrated detection of large-area coverage, high-precision alignment and high-efficiency fusion is realized.

The invention discloses a target guiding navigation method which comprises the following steps: S1, coding an environment image by adopting a multi-teacher distillation pre-trained RADIO framework, extracting an initial visual feature, and splicing the initial visual feature with a target embedded vector to obtain a cross-modal fusion initial input feature; s2, generating causal alignment fusion features through global hybrid factor estimation, residual elimination and anti-fact co-occurrence matrix intervention; and S3, inputting the features into the LSTM, and generating a navigation action strategy through double-commentator conservative value estimation, Gaussian perturbation and semantic post-view playback training in combination with a cross attention fusion semantic graph relationship and time sequence features. According to the method, multi-source prior knowledge is fused to improve visual feature generalization, hybrid interference is separated through a causal de-confusion mechanism, semantic enhancement is combined to reinforce learning training, the problems of category dependence, false correlation, insufficient exploration efficiency and the like of an existing method are solved, and the stability, causal rationality and training effect of a navigation strategy are improved.

The embodiment of the invention discloses a building engineering crack detection method and system based on image recognition, and the method comprises the steps: obtaining a building surface image, carrying out the preprocessing of the image, obtaining a standardized image, and carrying out the multi-scale decomposition extraction and integration of various features, and forming a multi-dimensional feature descriptor set; after feature importance is evaluated, a compact feature vector is generated through dimension reduction, quantization coding and compression, and then a multi-level feature index mechanism for optimized compression is constructed. A query feature vector is extracted from a newly collected image, searching and screening are completed by means of an index mechanism and a tolerance threshold, and a crack matching result is obtained; and based on the result, positioning cracks, classifying types, measuring parameters and evaluating severity, and generating a crack state report. The crack trend is analyzed in combination with the historical data time sequence, a multi-stage early warning mechanism is designed, maintenance suggestions are provided, and a real-time monitoring and early warning system is formed. According to the embodiment of the invention, the technical problems of high storage pressure and low real-time detection efficiency in the prior art can be effectively solved.

The invention discloses an SAR image despeckle method and device, and relates to the technical field of image processing. The method comprises the following steps: constructing an SAR image despeckle model based on an encoder-decoder structure; acquiring an SAR observation image polluted by noise; extracting shallow layer features of the SAR observation image; separating the shallow features into high-frequency features and low-frequency features; aggregating the spatial context information of the high-frequency features and encoding the spatial context information into a query matrix, a key matrix and a value matrix; calculating high-frequency output characteristics according to cross covariance attention among the matrixes; extracting noise distribution features in the low-frequency features and splicing the noise distribution features with the low-frequency features to obtain low-frequency output features; learning complementarity weight coefficients of the high-frequency output features and the low-frequency output features, and fusing the high-frequency output features and the low-frequency output features to obtain deep features; reconstructing the deep features output by the last layer of the decoder, and outputting a residual image; and connecting the residual image with the SAR observation image residual to obtain an SAR freckle-removed image.

The application discloses a kind of based on triple perception learning enhanced visual language model's zero sample exception detection method and system, it is related to computer vision field, method includes: extracting global and local visual features from input image;Visual coding process is corrected local feature in deep network by spatial perception attention enhancement module, and fine-grained attribute text description is generated for abnormal visual feature;Through attribute perception guide module, attribute text description and general text prompt are deeply semantically aligned;The similarity of enhanced visual feature and optimized text feature is calculated, and pixel-level exception segmentation map is generated;Inference stage converts segmentation map into spatial attention weight by exception perception reconstruction module, and feedback is generated to visual encoder final global feature representation and calculates exception score.The method of the application significantly improves the accuracy and generalization ability of model in industrial defect detection and other scenarios without target domain training samples.

The invention relates to a document image restoration method and system, and the method comprises the steps: obtaining a to-be-restored document image, carrying out the preliminary reconstruction through a pre-trained preliminary restoration network, and obtaining a preliminary restoration image; document structured information of the to-be-repaired document graph is extracted, and text features are obtained based on the document structured information; performing text content coding, position information coding and confidence coefficient coding on each text feature, and performing fusion through a feature fusion module to generate a text control feature; inputting the text control feature and the preliminary restoration image into a ControlNet together to generate a control signal; and inputting the control signal into a pre-trained potential diffusion model to de-noise the potential spatial features step by step, and decoding the de-noised potential spatial features by using a pre-trained potential decoder to generate a repaired document image. The method and the device have the effect of improving the document image restoration efficiency and the restoration effect.

The invention discloses a bill recognition method and system based on artificial intelligence image enhancement, and relates to the field of image recognition. The method comprises the following steps: S1, extracting multi-dimensional quality features based on an original image of a bill and calculating a scene consistency factor; s2, adjusting a global enhancement weight according to a scene consistency factor, adjusting a local gain in combination with a detail fidelity factor, and performing adaptive enhancement on the original image to generate an enhanced image; s3, establishing an optical flow field model to analyze geometric deformation of the enhanced image, and performing adaptive correction in combination with local deformation rigidity to generate a corrected image; and S4, analyzing gradient features and character confidence of the corrected image, extracting a candidate character region, and performing context recognition by adopting a sequence model to obtain a text field set. Scene complexity is quantified through multi-dimensional quality features, and detail fidelity self-adaptive enhancement and optical flow deformation correction of high-frequency character distinguishing are combined, so that bill character definition and recognition accuracy are remarkably improved.

The invention discloses a multi-modal data fusion and fault diagnosis method, and belongs to the field of transformer partial discharge fault diagnosis. According to the method, for the problems of false alarm and missing alarm caused by data isolation and lack of effective integration in partial discharge diagnosis of the transformer, acoustic, infrared and visible light multi-mode data are synchronously collected, pixel-level space alignment is carried out based on feature point matching, time sequence synchronization is achieved through hardware trigger signals, and the fault diagnosis accuracy is improved. Multi-level fusion diagnosis of a data layer, a feature layer and a decision-making layer is adopted, including channel superposition to form a fusion diagnosis image, voiceprint features, temperature rise features and arc light or corona features are extracted and input into a feature fusion model to obtain an associated feature vector, decision fusion is performed through a support vector machine classifier and a D-S evidence theory, and a decision-making result is obtained. And outputting a final diagnosis conclusion, thereby realizing accurate and reliable diagnosis of the partial discharge fault of the transformer.

The invention relates to the technical field of flexible OLED screen manufacturing, in particular to a laser cutting equipment control method and system for a flexible OLED screen, and the method comprises the steps: obtaining an original image of the flexible OLED screen, removing reflection and noise to obtain an enhanced image, and extracting the edge contour and geometric parameters of a functional area of the flexible OLED screen; and when the parameters exceed the limit, adjusting the optical parameters, re-extracting the edge feature point sequence of the functional area, generating an initial cutting path curve, detecting the matching degree and smoothness of the path curve, correcting the offset area, if the update state of the offset area of the adjusted cutting path curve meets the standard, obtaining a qualified cutting path curve, and then executing the cutting operation. And obtaining a flexible OLED screen finished product. And evaluating the edge quality of the finished screen, carrying out electrical and optical performance tests on the finished screen, and carrying out adjustment and feedback to obtain a stable and matched final path. According to the method, the technical problem that the cutting precision of the flexible OLED screen is insufficient is solved.

The invention relates to a photovoltaic sand and dust identification method based on color space fusion and lightweight learning, and the method comprises the following steps: S1, obtaining image data of a photovoltaic module, detecting a module region in an image, and obtaining a mask image of the module region; s2, extracting an ROI image of the photovoltaic module, and performing geometric correction processing; s3, converting the ROI image from an RGB color space to an HSV color space; s4, respectively carrying out threshold setting on the H, S and V three-channel images based on the HSV color space; s5, fusing threshold setting results of the H, S and V channels, generating a final sand and dust pollution mask pattern, and completing sand and dust region identification; and S6, calculating the sand-dust covering proportion of the polluted area on the surface of the component, and dividing pollution grades according to the sand-dust covering proportion. According to the invention, the dust area on the surface of the photovoltaic module can be accurately extracted under different illumination conditions, standardized quantitative evaluation of the pollution degree is realized, and the method is suitable for intelligent cleaning management and remote operation and maintenance scheduling scenes of a photovoltaic system.

The invention relates to the technical field of AI vision, in particular to a sesame seed candy forming defect real-time detection method and device based on AI vision. The method comprises the following steps: respectively collecting multimode images of qualified sesame seed candies, generating a qualified characteristic fingerprint set, and calculating sugar body light transmission uniformity and sesame adhesion density as a domain parameter set; constructing a probability distribution model, and setting an anomaly judgment threshold value and a domain parameter early warning threshold value; collecting a multi-mode image of the to-be-detected sesame seed candy in real time, extracting a to-be-detected feature fingerprint, and calculating the light-transmitting uniformity of a to-be-detected candy body and the sesame adhesion density; calculating a comprehensive abnormal score, and judging a defect; and capturing a low-confidence sample based on the comprehensive anomaly score, obtaining an artificial correction feedback sample, and updating a probability distribution model, an anomaly judgment threshold value and a domain parameter early warning threshold value by utilizing the feedback sample through online incremental learning. According to the invention, the detection cost of a high-yield production line can be reduced, and the model deployment period is shortened.

Provided is a pattern inspection system, including a scanning electron microscope (SEM) including an electron gun configured to generate a first electron beam and emit the generated first electron beam toward a first wafer, a detector configured to detect electrons emitted from the first wafer based on the first electron beam emitted toward the first wafer, and at least one processor configured to generate a first SEM image including a plurality of pixels based on the detected electrons, and determine, based on a period of a pattern extracted from the first SEM image, a pixel size of a second SEM image to be generated by the SEM with respect to a second wafer.

The invention provides an information transmission method and electronic equipment. The method comprises the steps that N frames of first images are obtained, each frame of first image in the N frames of first images comprises particle points coded with target information, the particle points comprise positioning points used for positioning a display area and information points used for indicating data, in the same frame of first image, the positioning points are circularly displayed according to a first preset color sequence, and the information points are displayed according to a second preset color sequence; the information points are circularly displayed according to a second preset color sequence; determining a target area containing particle points in the first image; extracting particle points from the first image according to the target area; and determining coded target information in the particle points according to the distribution condition of the particle points. In the technical scheme, the first electronic equipment can scan the image displayed by the second electronic equipment to obtain the coded information in the image, so that information transmission between the first electronic equipment and the second electronic equipment is realized, for example, when equipment connection is carried out, an equipment interaction path can be shortened, and the sense of science and technology can be improved.

The invention discloses an aviation transient electromagnetic pod coil attitude correction method and system, and belongs to the field of aviation geophysical exploration, and the system comprises a surface scanning industrial camera module which is used for obtaining the image information of a suspension coil in real time; the industrial-grade integrated navigation module is used for outputting inertial navigation data; the time synchronization and data acquisition module is used for establishing a time unification mechanism; the visual processing module is used for extracting the image processed by the time unification mechanism to obtain visual features; the inertial navigation resolving module is used for obtaining an inertial navigation state of a coil attitude angle through angular velocity integration; the data fusion and attitude estimation module is used for performing fusion calculation by combining the visual features and the inertial navigation state to obtain a fusion result; and the projection area and magnetic moment calculation module is used for calculating the ground projection area and the effective emission magnetic moment component of the coil according to the fusion result. According to the method, the system complexity and the electromagnetic interference risk caused by multi-inertial navigation layout are reduced, and the detection precision and stability of the aviation transient electromagnetic data are improved.

The invention discloses a coarse and fine particle inclusion photoelastic sample preparation and contact force chain network analysis method, and relates to the field of particle material mechanical tests, and the method comprises the following steps: calculating target void ratios under different coarse particle contents through a discrete element method; generating a corresponding numerical calculation sample according to the target void ratio and the preset coarse grain content, and exporting related parameters to prepare a coarse and fine grain inclusion photoelastic sample with the same initial compactness; in combination with non-polarization and polarized photoelastic images of the photoelastic sample, extracting intergranular contact force and constructing a contact force network; based on the contact force network, a strong contact force network is extracted and microscomic analysis is carried out, and force transmission characteristic comparison results under different coarse grain content conditions are obtained. According to the method, preparation efficiency of samples with different coarse grain contents and controllability of an initial state are realized, an influence rule of the coarse grain contents on a force chain structure and force transmission characteristics thereof is disclosed based on analysis of a contact force chain network, and the method is of great significance in researching a force transmission mechanism of a coarse and fine grain inclusion system and microstructure characteristics thereof.

The invention provides an oil monitoring control method, device and equipment fused with machine learning and a medium. According to the method, a polarized light scattering image of oil is collected through a sensor, and an original data set with time aligned with voiceprint signals is generated; optical features are extracted for the polarized light image, and acoustic features are extracted for the voiceprint signal; optical and acoustic features are associated and fused, and a spatial-temporal feature vector is constructed; based on the fusion feature vector, the double-branch neural network outputs a bubble interference probability and a metal particle existence probability; outputting a real particle count based on the bubble interference probability and the metal particle existence probability; and verifying the real particle count through physical sorting and spectral analysis to obtain a verification result, and optimizing the double-branch neural network according to the verification result. The invention further discloses a corresponding device, equipment and medium. According to the invention, the industrial problem that bubbles are misreported as dangerous particles in oil circulation is solved, and the identification specificity and alarm reliability of wear particles under complex working conditions are improved.

The invention provides an optical correction camera lens module and an imaging method thereof. The method comprises the following steps: extracting a radial distortion parameter and a tangential distortion parameter from an original imaging image; performing target identification on the original imaging image to obtain a plurality of identification targets, performing regularized screening to obtain a regularized identification target, extracting a pixel reduction matrix of the regularized identification target based on a regularized target library, performing region reconstruction on a corresponding region of the original imaging image according to the pixel reduction matrix, and performing region reconstruction on a corresponding region of the original imaging image; extracting a radial distortion correction parameter and a tangential distortion correction parameter according to the reconstructed image area; and constructing an optical correction model based on the radial distortion correction parameter and the tangential distortion correction parameter, performing distortion correction on the original imaging image through the optical correction model to obtain a target imaging image, extracting a regularized identification target according to the original imaging image, and extracting a dynamic distortion correction parameter through the regularized identification target to obtain the target imaging image. And the real-time performance of imaging distortion correction is improved.

The application is suitable for the field of visual measurement, and provides a target, an information detection method and device, a terminal and a storage medium, wherein the method comprises: controlling a camera to take a picture of the target to obtain a first imaging image; based on the first imaging image, extracting a first pixel point pair with the farthest relative distance on the inner circumference of a circular ring, a second pixel point pair with the farthest relative distance on the outer circumference of the circular ring, a center pixel point of three circles and a vertex pixel point of a first triangle; based on the first pixel point pair and the second pixel point pair, determining a first straight line where the long diameter of the circular ring in the first imaging image is located; based on the center pixel point and the vertex pixel point, determining a second straight line where the bottom side of the first triangle in the first imaging image is located; and determining the intersection of the first straight line and the second straight line as the imaging center point of the target in the first imaging image. The scheme can improve the image data processing efficiency and the practicability of the target.

The invention discloses a story-driven role and scene image generation method. The method comprises the steps that a natural language story text input by a user is received and preprocessed; through predefined role description structure constraints, enabling the language understanding and generation model to output a structured role description information structure under template constraints; generating a role image according to the structured role description information text, and extracting image features for consistency control; establishing a mapping table of structured role description information and image feature representation, and realizing the consistency of the appearance of roles in multiple scenes; automatically disassembling the complete story text into a plurality of scene nodes, and generating structured scene description information for each scene; and generating a complete story picture in combination with the scene description information and the role reference diagram. The invention provides a story-driven role and scene image generation method, which is used for automatically generating a story text to a role image and a scene image through semantic understanding, information description structured generation and image consistency management.

The invention provides a vehicle-mounted instrument driving record panoramic image fusion three-dimensional projection method and system, and relates to the technical field of vehicle-mounted display, and the method comprises the steps: obtaining original panoramic image data collected by cameras around a vehicle and real-time driving state information of the vehicle; distortion correction and multi-view splicing processing are carried out on the original image to generate a spliced panoramic image; determining the type of a driving scene according to the real-time driving state information, setting corresponding three-dimensional viewpoint parameters including viewpoint height, viewpoint distance and pitch angle, performing three-dimensional space coordinate transformation on the spliced panoramic image based on the parameters, and generating a three-dimensional aerial view image adaptive to the current driving scene; an obstacle target is extracted, the boundary of an image area of the obstacle target is recognized, height stretching rendering is carried out at the corresponding position of the three-dimensional aerial view image, and a three-dimensional panoramic projection image containing an obstacle three-dimensional identifier is generated; and finally adaptively outputting to a vehicle-mounted instrument panel display screen for real-time display. The visual angle can be dynamically adjusted according to different driving scenes, the stereoscopic perception of the obstacle is enhanced, and the driving safety is improved.

The invention relates to the technical field of water meters, in particular to a character wheel-pointer type intelligent camera shooting water meter high-precision reading method and system. Comprising the following steps: positioning a character wheel area in a water meter image by adopting a rotating target detection model, and automatically correcting dial plate deflection by analyzing a deflection angle and geometrical characteristics of the character wheel area; and extracting a pointer and a pointer end region based on the corrected image, and calculating and obtaining a pointer reading by utilizing a long side slope of a pointer end bounding box. And finally, based on the pointer reading and the character wheel region, constructing a convolutional neural network classification model containing a carry state, and realizing digital reading by combining a dual-threshold carry correction algorithm, thereby realizing composite water meter reading. According to the method provided by the invention, high-precision reading can be realized under the influence of any deflection angle, indication error and mechanical carry precision difference, the processing speed reaches 74 milliseconds / frame, and the average pointer angle identification error is lt; and the method is particularly suitable for water meter automatic reading scenes in complex environments.

The invention discloses a multi-object arrangement method and system for a mobile operation robot, and the method comprises the steps: obtaining an object image of the robot at a current visual angle, and extracting the attribute information of an object; constructing a bearing relation matrix and a semantic scene graph; the bearing relation matrix is converted into a directed acyclic graph, an edge set serves as a state space in reinforcement learning, an action space is defined to select one of unselected edges, the depth of the edge set serves as the basis of current grouping, and objects are grouped based on a high-level reinforcement learning model; obtaining a stacking execution sequence of the objects in the group based on the semantic scene graph; and the grabbing posture of the current to-be-operated object is obtained through prediction of the grabbing network, the object is grabbed according to the grabbing posture, and the grabbed object is stacked according to the planned stacking sequence. According to the robot, efficient action decision making is achieved in the grabbing, stacking and placing processes, and the robot has the capacity of carrying multiple objects in different places and orderly placing the multiple objects in a complex environment.