1316 results about "Image pre processing" patented technology

The invention relates to the technical field of tunnel crack detection and artificial intelligence edge calculation, and provides a tunnel apparent disease detection method based on deep learning and knowledge distillation, which comprises the following steps: step 1, introducing spectral domain information enhancement to an original tunnel image, the edge texture features of the disease area in the image are enhanced through methods such as multi-scale wavelet transform and small-scale enhancement. Step 2, constructing a high-performance teacher model, introducing a flexible up-sampling structure to adapt to feature recovery requirements of different levels of semantic information, introducing an efficient visual coding module to enhance feature fusion capability of different scale channels, and designing a scale adaptive weighted loss function at the same time; by introducing a frequency spectrum enhancement mechanism, structural features of disease areas with low contrast, fuzzy edges and the like are remarkably enhanced in an image preprocessing stage, clearer information input is provided for a model, and the stable recognition capability of a system in environments of uneven illumination, complex background and the like is enhanced.

The present application provides a cardiac fibrosis diagnosis model based on multi-task attentional feature fusion. The cardiac fibrosis diagnosis model is established by the following steps: S01: image collection and labeling: obtaining cardiac magnetic resonance (MR) images as sample data, and performing manual labeling to obtain heart labels corresponding to the MR images; S02: image preprocessing, including normalization processing, data enhancement, and data clipping; S03: model establishment, including establishment of an image recovery network and establishment of an image segmentation and classification network, and executing an image recovery task; S04: model pre-training: training the image recovery network such that the encoder of the image recovery network fully learns the feature of the cardiac fibrosis image; and S05: model training. An objective of the present application is to improve the segmentation precision and diagnosis accuracy of a network model for a cardiac fibrosis image.

The invention relates to the technical field of deep learning and computer vision, and discloses a histogram interactive attention-based pavement crack segmentation network processing method and system, so as to enhance the edge detail fidelity and improve the crack segmentation precision. The method comprises the steps of image preprocessing, up-sampling, down-sampling, feature fusion and image reconstruction processing. Wherein global feature modeling in the intensity sub-boxes and among the sub-boxes is realized by constructing a histogram interactive attention module (HIA); a double-branch detail enhancement feedforward module (DDEF) is introduced to enhance spatial detail and high-frequency edge information expression; meanwhile, a Fourier jump enhancement module (FFSM) is adopted to jointly refine jump connection features in a spatial domain and a frequency domain. Through the synergistic effect of the modules, the network can realize continuous recovery and structural consistency modeling of a crack boundary in a complex pavement environment, so that the accuracy and the stability of a segmentation result are remarkably improved.

The invention relates to the technical field of image processing, and provides an indoor three-dimensional image intelligent rendering method based on image processing. Comprising the following steps of indoor multi-view image acquisition, image preprocessing, intelligent analysis of indoor scene elements, construction of an indoor three-dimensional initial model with attributes, intelligent generation of rendering parameters, adaptive LOD real-time rendering and intelligent interaction optimization. According to the intelligent interaction optimization system, through deep fusion of natural language processing, user preference learning and real-time rendering technologies, a set of efficient, visual and personalized virtual scene rendering interaction process is constructed. According to the method, the problems that traditional graphic software is complex in operation, high in learning cost and low in debugging efficiency are solved, and the user satisfaction and creation efficiency are remarkably improved through an intelligent recommendation and rapid iteration mechanism.

The invention relates to a gesture recognition and projection fusion non-contact interaction method and device, equipment and a medium. The method comprises the steps of obtaining multi-user gesture original image data, extracting geometric features and boundary features of a hand contour after image preprocessing and noise removal, and generating recognition result data; secondly, on the basis of three-dimensional coordinate information in the recognition result, a tracking trajectory is analyzed through trajectory continuity, a user identity identifier is matched in combination with a user identity feature library, and user space positioning information is generated; then, a three-dimensional track point sequence is extracted from the user space positioning information, an initial projection area is divided by adopting a dynamic area segmentation algorithm, and an operation area mapping relation is formed; and finally, analyzing the operation area mapping relation to extract gesture action features, generating a control instruction set in combination with a preset rule, and scheduling a conflict instruction to generate an instruction execution sequence. By adopting the method, the scene limitation of traditional contact type interaction can be broken through, and the stability and practicability of non-contact interaction in a multi-user environment are improved.

The invention discloses an autoclaved aerated concrete member surface defect intelligent identification system based on image processing, and particularly relates to the field of defect identification, comprising an image acquisition module, an image preprocessing module, a defect candidate region extraction module, a defect identification and classification module, and a result output and alarm module; according to the method, a high-definition industrial camera is used for collecting a component surface image, and adaptive median filtering and a Retinex algorithm are adopted for image denoising and enhancement, so that the influence of noise and uneven illumination is eliminated; utilizing an improved multi-threshold segmentation and Canny edge detection algorithm to accurately extract a defect candidate region; the method comprises the following steps: extracting three types of feature parameters of shape, texture and gray scale, and inputting the three types of feature parameters into a deep learning model taking ResNet50 as a basic network to realize automatic identification and classification of four types of typical defects of cracks, holes, unfilled corners and surface peeling; and finally, the system divides severity levels according to the defect size, and triggers differentiated visual alarm and linkage control.

The invention discloses a photovoltaic module construction quality identification method based on computer vision and three-dimensional modeling. The method comprises the following steps: S1, collecting an original image sequence of a photovoltaic construction site and carrying out image preprocessing; s2, outputting a semantic tag graph and a two-dimensional space boundary graph through an improved BiSeNet network; s3, using a mask constraint SIFT algorithm to extract cross-view key point features, generating a dense three-dimensional point cloud according to multi-view stereo reconstruction, and outputting a structure three-dimensional geometric model; s4, mapping the semantic tag graph and the two-dimensional space boundary to the structure three-dimensional geometric model to obtain a semantic three-dimensional model; s5, performing spatial registration on the semantic three-dimensional model and the reference model, and calculating spatial error parameters of the photovoltaic module; s6, performing compliance discrimination on the spatial error parameters, and outputting a quality discrimination result; and S7, generating a construction quality evaluation report. According to the invention, automatic identification and accurate evaluation of the photovoltaic construction quality are realized, and the detection efficiency and the discrimination accuracy are improved.

The invention discloses a Mars transverse wind ridging few-sample remote sensing interpretation method and system based on an SAM model. According to the method, contrast stretching preprocessing is carried out on an original Mars image, a dual-branch feature fusion framework based on VIT and CNN is constructed to extract and fuse image features, a position coding generator is introduced to support input of any size, a fine-tuning SAM strategy of a selective freezing encoder and a trainable mask decoder is adopted, and LoRA low-rank adaptation optimization calculation is combined, so that the Mars image is obtained. And a double-branch prompt generation module is used for fusing labeled and unlabeled data to generate a high-precision prompt, and finally, an interpretation result is output through a mask decoder and connected component analysis is carried out, so that instance-level labeling is realized. The system comprises an image preprocessing module, a double-branch feature extraction and fusion module, an image embedding generation module, a model fine tuning module, a prompt embedding generation module and an interpretation module. According to the method, the recognition precision and robustness of the mars transverse wind ridge formation under the condition of few samples are effectively improved.

The embodiment of the invention provides an edge detection method and device based on gradient weighted fusion and an adaptive threshold, and is applied to the field of computer vision and digital image processing. The method comprises the steps of firstly preprocessing an input image, then extracting two groups of gradient magnitude diagrams and directional diagrams through an adaptive morphological operator and a traditional difference operator, and constructing a weighted fusion function according to the gradient direction consistency of each pixel point to obtain a fused gradient magnitude diagram; and adaptively determining a high threshold and a low threshold based on an information entropy maximization principle, executing an improved Canny process by combining the fused gradient magnitude diagram and the second gradient directional diagram to obtain an initial edge diagram, and outputting a final edge detection result after dynamic structure element optimization. In this way, the defects that in a traditional edge detection method, gradient information extraction is not precise, threshold selection lacks adaptability, and an edge result is fractured can be overcome, more robust and more accurate image edge detection is achieved, and the reliability of an edge detection algorithm in a complex image scene is improved.

The invention relates to an animal wound multi-modal intelligent identification method based on artificial intelligence, and the method comprises the steps: carrying out the feature extraction and semantic constraint through multi-modal sample collection and metadata extraction, employing an image preprocessing and text natural language processing technology, and combining a mixed visual model of a convolutional neural network and a visual Transform, and a large language model. A cross-modal attention mechanism and a semantic trigger are utilized to realize feature reweighting, clinical standard soft boundary constraints are introduced, and fuzzy semantic rules are converted into learnable constraints in a feature space, so that the accuracy and consistency of model judgment are improved. The method has adaptive optimization and incremental learning capabilities, and is beneficial to improving generalization and clinical applicability of exposure level intelligent judgment under different animals and complex wound types.

The invention relates to the technical field of ancient music score intelligent processing, and discloses an ancient music score intelligent identification and visual playing system, which comprises an image preprocessing module, a stroke enhancement module, a symbol segmentation module, a symbol identification module, a semantic analysis module, a visualization module, an acoustic synthesis module and the like. Through a specially designed image processing and symbol analysis method, the aging problem of the ancient music score can be accurately repaired, adhered symbols are separated, a complex structure is identified, music semantics are inferred in combination with a knowledge graph, and a multi-modal visualization effect and a high-sampling ancient charm tone are generated. The system supports feedback optimization and automatic workflow, significantly improves the efficiency and accuracy of ancient music score recognition, translation and presentation, and provides technical support for ancient music research and propagation.

The invention discloses a multi-target license plate recognition method based on a visual attention mechanism, and belongs to the technical field of image processing and mode recognition, and the method comprises the steps: obtaining an input image, carrying out the multi-scale feature extraction, and generating a multi-scale feature map; performing spatial saliency calculation and normalization processing on the multi-scale feature map to generate an attention map; carrying out region division on the input image, and adopting differentiated image preprocessing strategies for different regions to generate a preprocessed image; based on the preprocessed image and the attention map, multi-target detection is carried out through a target detection network, candidate area screening is carried out, and a candidate license plate area is generated; and performing binarization processing, character segmentation and feature recognition on the candidate license plate region, and performing verification in combination with context information to generate a license plate recognition result. The attention map is generated by adopting a visual attention mechanism, differentiated image preprocessing and multi-target detection are guided according to the attention map, and multi-target license plate recognition can be completed in a complex scene.

The invention discloses a few-sample inductance core surface defect detection method based on model interaction, and belongs to the technical field of machine vision and industrial defect detection. The method comprises the following steps: S1, data acquisition and image preprocessing are carried out, and normal samples, labeled samples and unlabeled samples are constructed; s2, constructing an unsupervised statistical model based on statistical learning; s3, constructing a supervised semantic segmentation model; s4, inputting an inductance core image to be detected into the unsupervised statistical model and the supervised semantic segmentation model at the same time for processing, and generating a segmentation result; s5, detecting result differences are quantified; s6, performing parameter updating on the unsupervised statistical model; s7, generating a pseudo label based on an unsupervised statistical model; s8, carrying out weight updating on the supervised semantic segmentation model; and S9, inputting the processed to-be-detected images into the updated unsupervised statistical model and supervised semantic segmentation model in batches for detection to obtain a detection result, and analyzing and calculating system performance indexes.

The invention discloses an emotion rehabilitation intervention method based on face recognition. The method comprises the steps that S1, a user face image sequence is collected through a front camera; s2, performing image preprocessing to generate a standardized image tensor set; s3, facial dynamic features are extracted through an improved BiFormer network, emotional states are recognized, and a multi-dimensional emotional state sequence and a facial expression coding sequence are generated; s4, jointly analyzing the emotion change trend and the expression behavior mode of the user through a multi-mode RETNet network, and outputting a psychological state grade and a future emotion fluctuation score sequence of the user; s5, matching an emotion rehabilitation intervention strategy through a preset rule engine; s6, executing the emotion rehabilitation intervention strategy, collecting user data in real time, and generating a user response scoring sequence; and S7, performing incremental updating on the multi-modal RETNet network and a preset rule engine based on the user response score sequence. According to the invention, the accuracy of emotional state recognition and the intelligent level of intervention strategy pushing are improved.

The invention relates to the technical field of wave-absorbing material quality detection, and discloses a pyramid wave-absorbing material coating quality online detection system based on machine vision, which comprises a conveying unit, a vision acquisition unit, an image preprocessing unit, a coating quality analysis unit, a result output unit and a feedback control unit. The coating quality analysis unit is internally provided with a pyramid surface image geometric correction core model, a coating thickness quantitative calculation core model and a coating uniformity and defect judgment core model, cooperation is achieved through a feedforward correction and feedback optimization linkage mechanism, and the visual collection unit achieves full-view coverage through three sets of industrial cameras. The image preprocessing unit reduces distortion correction errors through conical surface constraint iterative correction; the thickness calculation model is combined with quadratic polynomial fitting and temperature compensation; the defect discrimination model fuses multiple parameters and comprehensive deviation values, and accurately recognizes three types of defects. According to the system, production parameters can be dynamically adjusted, the detection real-time performance and the quality traceability are both considered, and the large-scale production quality control requirement is met.

The invention relates to a high-precision crack segmentation method based on double-flow visual basic model collaboration, belongs to the technical field of computer vision and deep learning, and aims to solve the problems that an existing crack segmentation model is poor in generalization under a complex background, fine cracks are missed and disconnected under high resolution, and the fine tuning cost of a large model is high. The method comprises the following steps: firstly, preprocessing an acquired infrastructure surface image into standard input of 1024 * 1024 pixels, and extracting features by adopting a double-flow encoder containing parallel SAM3 and DINOv3 double branches; freezing double-bone intervention training parameters, and embedding a lightweight adapter to complete efficient fine tuning of the parameters; double-branch multi-scale features are extracted, and multi-scale splicing and dimension reduction fusion are completed after channel alignment; and outputting a pixel-level crack binary segmentation result through a lightweight decoder based on depth separable convolution. According to the method, segmentation precision, cross-domain generalization ability and training deployment cost are considered, and the engineering landing requirement of infrastructure health monitoring is met.

The invention discloses a target detection method and system based on dynamic memory enhancement, relates to the technical field of computer vision and target detection, and aims to solve the problems that a traditional method depends on local features of a single image, is difficult to detect a target, is low in precision and is weak in generalization ability. The method comprises the steps that after a to-be-detected image is preprocessed, multi-stage multi-scale features are extracted through a backbone network; an encoder outputs single image global features for feature interaction fusion, and a global distribution extraction module constructs and updates a data set level global feature distribution library; the decoder adopts a hierarchical structure, and optimizes the target query token layer by layer in combination with self-attention, cross attention and global distribution fusion sub-modules; and finally outputting a target category and bounding box coordinates. Through global context injection, small target and shielding target detection precision is improved, model training stability and generalization ability are enhanced, and the method is suitable for diversified detection scenes.

The invention relates to the technical field of gas detection, and relates to an optimization method and system for SF6 gas detection in a multi-temperature environment, and the optimization method comprises the steps: obtaining dual-band infrared images of a scene to be detected at the same time, the dual-band infrared images comprising a detection band infrared image and a reference band infrared image; preprocessing the dual-band infrared image; performing registration processing on the preprocessed dual-band infrared image; performing differential operation on the registered dual-band infrared image to obtain a differential image; and determining a dynamic segmentation threshold according to the current environment temperature, and performing threshold segmentation on the differential image according to the dynamic segmentation threshold so as to identify the SF6 gas leakage area. According to the optimization method and the optimization system, the dynamic segmentation threshold value is determined according to the current environment temperature, the problem that the detection performance of a fixed threshold value is reduced due to background radiation changes at different environment temperatures can be solved, and stable and reliable detection sensitivity can be kept within a wide temperature range.

The invention discloses a vibration monitoring and displacement identification method for a towering steel structure based on machine vision, and relates to the technical field of towering steel structures. Comprising the following steps: S1, visual acquisition and reference calibration: arranging visual acquisition equipment in the height direction and the circumferential direction of the towering steel structure according to mechanical characteristics of a vertical stiffness mutation region and a dynamic response sensitive part of a geometric asymmetric distribution characteristic of the structure; a three-dimensional coordinate system is established based on a structure installation reference surface, fixed reference monitoring points are arranged in a tower foot symmetric area and a mast antenna root, three-dimensional coordinate data of the reference points are synchronously collected, the collection range completely covers a node concentration area and a key stress part of a structure transparent area, and a continuous image sequence of the structure surface is captured in real time; the resolution and the sampling frequency of the visual acquisition equipment are determined according to the inherent frequency of the structure and the vibration response characteristics, and calibration is completed through reference point coordinates after the equipment is installed; s2, carrying out image preprocessing and feature enhancement; S3, carrying out feature point extraction and trajectory tracking; S4, carrying out vibration displacement calculation and twin fusion; and S5, carrying out multi-source verification and structural state linkage treatment.

The invention discloses a paper archive digital quality self-inspection system based on AI detection, which relates to the technical field of archive management and comprises an image acquisition module, a content extraction module, a threshold adjustment module, a quality detection module, a result evaluation module, a feedback correction module and a data management module. The image acquisition module is responsible for acquiring images of paper archives by using a scanner or a digital camera and performing preliminary image preprocessing. According to the AI detection paper archive digital quality self-inspection system, unified execution of quality inspection standards is ensured through a rule engine, subjective differences of quality standard understanding of different quality inspection personnel are eliminated, and a detection threshold value is dynamically adjusted according to the age, the material and the storage state of the archive so as to adapt to quality inspection requirements of different archives; and particularly, the difficulty in identifying handwritings, faded handwritings, special symbols and the like in historical archives is optimized, so that the comprehensiveness and the efficiency of detection are greatly improved.

The invention provides a hierarchical labeling method and device for a lung cancer pathological image, equipment and a storage medium. Relates to the technical field of medical image processing. The method comprises the following steps: carrying out digital scanning and image preprocessing on a lung cancer pathological section; labeling according to a three-stage progressive sequence of a macroscopic tissue area, a microscopic characteristic structure and a cellular level characteristic, wherein each stage adopts color coding and diagnosis priority rules exclusively corresponding to lung cancer subtypes and pathological characteristics; carrying out post-processing and standardized output on the labeling result; and training an AI model by using the standardized annotation data and applying the AI model to auxiliary diagnosis. Through a unified color coding system, a hierarchical labeling framework and a standardized data processing flow, the problems that an existing labeling system is disordered and poor in reusability are solved.

The invention discloses a multi-mode AI collaborative industrial visual defect detection system, and relates to the technical field of industrial visual defect detection and machine learning, and the system comprises a multi-source image collection module which is composed of a plurality of cameras and sensors and supports multi-mode image parallel collection; the image preprocessing module optimizes the image quality through enhancement, denoising and semantic segmentation; the multi-mode AI model collaboration module integrates three types of core models to realize feature collaboration fusion; the defect hierarchical classification module is used for constructing a secondary classification system association knowledge base; the defect positioning and quantifying module is used for accurately positioning and quantifying defect parameters; the detection result intelligent output module supports multi-form output and alarm; and the closed-loop optimization module is used for updating the model and the knowledge base based on feedback iteration. According to the invention, through multi-mode data fusion and multi-mode AI cooperation, the defect detection precision and scene adaptability are improved; the method has cross-scene rapid adaptation, real-time response and closed-loop optimization capabilities, and adapts to multi-industry detection requirements.

The invention discloses a Crohn disease focus automatic segmentation and activity evaluation system based on deep learning, which belongs to the field of medical artificial intelligence and comprises a data preprocessing unit, a focus automatic segmentation unit, a radiomics feature extraction unit, a feature screening and dimension reduction unit and an activity classification unit. According to the method, an nnU-Net deep learning segmentation model is combined with image omics feature extraction, multi-stage feature screening and machine learning classification technologies, so that full-process automation from CTE image preprocessing, focus automatic segmentation, feature extraction and screening to activity classification is realized. The system can efficiently and accurately segment the focus of Crohn's disease, automatically assesses the disease activity based on the screened key radiomics characteristics, significantly improves the consistency, objectivity and efficiency of diagnosis, and is suitable for clinical auxiliary diagnosis and scientific research analysis.

The invention relates to the technical field of industrial defect detection, and discloses an aluminum surface micro defect detection system for optimizing an RT-DETR model in combination with an attention mechanism, which comprises an image acquisition module, an image preprocessing module, an improved RT-DETR detection module and a result output module. According to the aluminum surface micro-defect detection system for optimizing the RT-DETR model in combination with the attention mechanism, small target copying is executed through an image preprocessing module to increase micro-defect samples, defects and matching backgrounds are fused through image splicing, illumination is optimized through brightness adjustment, Gaussian filtering noise reduction is conducted, and original defect information is strengthened; an orthogonal attention feature extraction module in the improved RT-DETR detection module strengthens channel features, a multi-scale deformable frequency hierarchical attention coding module processes the features according to high and low frequencies, an ELAHS-FPN feature fusion module fuses the multi-scale features, a super-resolution auxiliary branch improves the feature resolution, a prediction frame is corrected in combination with an Inner-GIoU bounding box loss function, and the detection precision is improved. And weak characteristics such as paint bubbles, scratches and jet flow are effectively extracted.

The invention discloses a bionic visual positioning system and method based on multispectral perception and a storage medium, and the system comprises a front-end multidimensional optical perception module, a mesopic vision preprocessing module and a rear-end fusion perception and target positioning module, the front-end multi-dimensional optical sensing module is used for performing optical imaging, spectral decomposition and polarization imaging; the mesopic vision preprocessing module is used for carrying out image preprocessing and optical flow estimation; and the rear-end fusion perception and target positioning module is used for feature fusion and target identification and positioning. According to the bionic visual positioning mechanism, through a bionic compound eye structure + multispectral + polarization + optical flow fusion perception strategy, the perception bottleneck of a traditional visual system in a high-dynamic and complex illumination environment is effectively solved, and the bionic visual positioning mechanism has the advantages of high robustness, low delay, wide field of view, multiple modes and the like; the method is especially suitable for application scenes such as automatic driving, unmanned aerial vehicles, robots and the like with extremely high requirements on real-time performance and reliability.

The invention discloses a method for generating an image description text based on a large model, which relates to the technical field of image processing, and comprises the following steps: an image preprocessing step: dividing a target level through semantic segmentation and extracting key visual information by adopting hybrid denoising and self-adaptive normalization; a feature extraction step: fusing the multi-scale visual features and the semantic features, and generating a high-dimensional fusion feature vector through cross-modal alignment; a large model initialization and adaptation step: loading the pre-training model and performing incremental fine tuning, and dynamically adjusting the Prompt template; a text generation step: generating candidate texts through logic constraint and beam search; and a text optimization adjustment step of outputting a final description text based on multi-dimensional evaluation and user preference iterative correction. According to the method, the semantic matching degree, logic coherence and common sense accuracy of image description are improved, multi-element scenes are adapted through dynamic adaptation and iterative optimization, and high-quality text description support is provided for high-precision and diversified scenes.

The invention discloses an automatic detection system for packaging defects based on computer vision, and the system comprises an image preprocessing module which collects an RGB image, completes the normalization and geometric correction, and generates a standardized image frame; the energy diagram and gradient tensor field generation module is used for respectively calculating color variance, texture response and gray gradient; the initial superpixel division module is used for guiding geometric flow propagation based on the energy diagram and the tensor field to generate a first group of superpixels; the feature extraction and classification module is used for extracting regional features and outputting defect probability and category; the confidence evaluation module is used for constructing a confidence score graph and identifying a low-confidence region; the local re-segmentation module is used for re-dividing superpixels in a specified area; and the result output module is used for outputting the final defect position, category and confidence score. According to the invention, the accuracy and adaptability of defect detection are improved.

The invention discloses a handwritten table structure recognition and Excel cooperative processing method and system, relates to the technical field of computer vision, and comprises the steps of image preprocessing, table structure recognition, cell positioning, content recognition, Excel template analysis and text mapping. The system preprocesses the input image; respectively extracting horizontal and vertical lines based on morphological operation, and identifying a logic rank range of the merged cells; calculating a cell pixel bounding box through the cross points, and carrying out logic sorting and interference filtering; independently cutting each cell and calling a handwriting OCR (Optical Character Recognition) engine to extract text content; matching a preset Excel template according to the header or the code, and analyzing the coordinates of the combined and non-combined cells of the Excel template; and accurately mapping the identification content to the corresponding position of the Excel based on the row and column logic sequence numbers by taking the anchor point cell as a reference, and generating a spreadsheet. According to the method, the problems of inaccurate merging cell recognition, content dislocation and the like are effectively solved, and the electronization precision and efficiency of the handwritten form are remarkably improved.

The invention discloses an edge sea petroliferous basin paleotopography inversion method based on a machine learning algorithm, and belongs to the technical field of geological exploration and data processing. The method comprises the following steps: constructing a seismic profile data pool and carrying out image preprocessing; establishing an affine transformation relationship between pixel coordinates and physical coordinates by using an image digitization tool, and extracting a two-dimensional data sequence; establishing a mapping function of the measuring line distance and the longitude and latitude, and constructing a three-dimensional scatter data set; carrying out gridding interpolation by adopting a K nearest neighbor regression algorithm, and constructing a three-dimensional grid model; performing motion back-pushing and deformation-removing correction by using a plate reconstruction technology to obtain a paleotopography model; and generating a three-dimensional dynamic visualization result of paleotopography evolution through time interpolation. The method solves the problems that seismic profile images cannot be quantitatively analyzed, sparse data interpolation is difficult, and paleotopography inversion neglects structural deformation, and provides technical support for multiple fields such as oil-gas exploration.

The invention relates to the technical field of computer vision, in particular to a three-dimensional reconstruction method and device based on optical polarization and stereoscopic vision principles. The three-dimensional reconstruction method sequentially comprises the steps of image preprocessing, polarization parameter extraction, binocular stereo matching, disparity map generation and optimization, normal vector correction, depth information fusion and three-dimensional point cloud reconstruction and modeling generation. A polarization normal vector field is constrained and corrected as a'skeleton ', and the azimuth angle pi ambiguity problem which puzzles polarization three-dimensional reconstruction for a long time is solved; high-frequency surface normal details contained in corrected polarization information are used as textures to enhance and fill up depth information loss of binocular vision in weak texture and repeated texture areas, the inherent limitation of a single sensing technology in a three-dimensional reconstruction task is overcome, and the three-dimensional reconstruction of the surface of an object, especially a diffuse reflection object, is realized. And high-precision and high-integrity three-dimensional shape recovery is realized.