151 results about "Street scene" patented technology

The invention relates to the technical field of landscape evaluation, and discloses an urban green land landscape evaluation method based on a large model, and the method comprises the steps: carrying out the real-time analysis and standardization processing of a streetscape image, IoT environment data, satellite vegetation coverage data and RTK high-precision positioning information of a target city district, extracting core landscape elements, building cross-scene semantic mapping, and carrying out the calculation of the cross-scene semantic mapping. Transmitting the standardized data to a central database and deploying edge nodes; extracting a multi-dimensional landscape index by adopting an improved semantic segmentation model, dynamically adjusting an index weight in combination with regional features and seasonal changes, and classifying and correcting deviation data by edge nodes; a visual evaluation result is generated based on a cooperative computing architecture and a digital twinborn model, a landscape space to be promoted is identified, and optimization suggestions are generated; and obtaining planner feedback information, updating the model, the weight rule and the suggestion generation strategy, and forming a closed loop iteration mechanism. According to the method, the dynamic and practical evaluation requirements of the current urban green land landscape can be met.

The invention discloses a mobile terminal streetscape image real-time segmentation method based on a lightweight neural network, and relates to the technical field of image segmentation. The method comprises the following steps: firstly, carrying out 320 * 320 adjustment, Z-score standardization, adaptive histogram equalization and 3 * 3 Gaussian filtering preprocessing on an input streetscape image; then, an improved MobileNetV3 backbone network is used, and a five-scale feature map is output in combination with DropBlock regularization through eight feature extraction stages including depth separable convolution and an SE attention module; multi-scale features are fused through a U-shaped structure, and a fusion feature map is generated through up-sampling, element-by-element addition of dimension reduction low-layer features and an attention gating module; and during reasoning, outputting a segmentation mask by using a convolutional layer, Softmax and a conditional random field, and finally performing knowledge distillation, weight pruning, 8-bit quantization and TensorRT optimization. According to the invention, high-precision real-time street view segmentation is realized, the robustness is high, and the method is suitable for different devices and scenes.

The invention discloses a shielding complementing method based on a continuous streetscape panoramic image, and aims to solve the problem of information loss caused by shielding of dynamic objects (such as vehicles and pedestrians) in the existing streetscape image, and the method comprises the following steps: S1, recognizing and positioning a dynamic shielding object area in a continuous streetscape panoramic image sequence; s2, providing a continuous panoramic image-oriented feature extraction and matching algorithm (FDMPano), realizing robust feature retrieval and matching in a cross-view angle, and accurately positioning a reference image region which can be complemented; and S3, carrying out feature alignment and content mapping on the sheltered area based on a matching result, and generating an unsheltered panoramic image with consistent vision. According to the method, the internal relevance of continuous streetscape data is fully utilized, the occlusion area can be automatically completed with high quality, the integrity and availability of streetscape images are remarkably improved, and the method has wide application value in the fields of automatic driving, digital cities, virtual reality and the like.

The invention relates to the field of smart cities, in particular to an urban landscape semantic segmentation method and system based on a large model, and the method comprises the steps: obtaining street view image data of a target geographic region; inputting the streetscape image data into a preset image semantic segmentation model, analyzing the streetscape image data through the image semantic segmentation model, and identifying various predefined environmental element categories contained in each image; calculating an urban landscape quantitative index based on the recognition result of the environmental element category; associating the calculated value of the urban landscape quantitative index to a corresponding road section or node in the road network spatial data corresponding to the target geographic area; generating a road network space visualization layer representing the value of the index value in a color grading manner based on the result after association; and according to a preset index threshold value, identifying the spatial road sections or nodes meeting the early warning conditions in the visual layer and generating prompt information. And the scientificity and comparability of an analysis result are ensured.

The invention relates to the technical field of image segmentation, and discloses a street view image semantic segmentation system for a complex city scene, and the system comprises a double-edge energy ratio calculation module which obtains a double-edge energy ratio through calculation; the priori mask generation module is used for generating a priori mask; the segmentation network construction module is used for outputting logarithmic probabilities and probabilities of various categories through a trunk segmentation network; the total loss construction module is used for constructing total loss; the mutual suppression optimization module is used for calculating to obtain a preliminary semantic segmentation result; and the semantic segmentation output module is used for calculating to obtain a final semantic segmentation result. According to the method, a unified process of double-edge energy ratio driving direction convolution, separation loss and reasoning period mutual suppression is adopted, repeated boundaries and false objects caused by reflection and transmission mixing in a complex city scene containing glass and a water surface are reduced, pixel-level boundary positions are stabilized, and road space, building facades and traffic element division are consistent.

The invention relates to the field of city analysis, and discloses a method for analyzing the nonlinear influence of a city environment on city vitality, and the method comprises the steps: carrying out the preprocessing of multi-source geographic big data and multi-source remote sensing data; according to a Deeplab V3 + deep learning semantic segmentation algorithm, predicting the pixel ratio of each category in each streetscape image, and constructing streetscape features based on the pixel ratio; constructing urban vitality evaluation indexes, and aggregating the urban vitality evaluation indexes by using a TOPSIS algorithm to obtain an evaluation result of the urban vitality; constructing an urban environment index according to the preprocessed multi-source remote sensing data; analyzing the spatial distribution difference of the non-linear influence of the urban environment on the urban vitality by using a geographically weighted random forest algorithm; and analyzing the threshold effect of the non-linear influence of the urban environment on the urban vitality by using a Gaussian fitting line algorithm. According to the method, street view features are extracted through a semantic segmentation technology, and comprehensive, scientific and refined quantitative evaluation of urban vitality is realized.

The invention discloses a multi-fractal-based urban green vision rate dynamic evolution mode identification method. The method comprises the following steps: S100, acquiring urban street green vision rate data; s200, acquiring urban multi-scale walking isochronous circle data, and acquiring walking reachable areas within 5 minutes, 10 minutes, 15 minutes and 20 minutes through an API (Application Program Interface) of an OpenRouteService platform on the basis of an urban road network; s300, identifying a dynamic evolution mode of the green vision rate; and S400, identification result demonstration, including spatial distribution of a green vision rate dynamic evolution mode, key threshold identification and spatial structure differentiation, is used for assisting urban greening structure optimization and scientific intervention strategy formulation. According to the method, the problems of staticization, single scale and insufficient structure expression in the existing urban street view green visual rate analysis are solved.

The invention relates to the field of city planning, and discloses a city spatial evolution prediction system fusing multi-modal data, and the system comprises a data preprocessing and multi-modal knowledge graph construction module which is used for configuring a knowledge graph ontology architecture and preprocessing multi-source city data; establishing a multi-modal knowledge graph based on the preprocessed multi-source city data and the knowledge graph ontology architecture; the model setting module is used for configuring a multi-modal representation learning model; the data integration module is used for a multi-modal representation learning model and performing deep integration on multi-modal data in a vector space to obtain vector representation with remote sensing and streetscape semantic information; and the knowledge reasoning and predicting module is used for performing knowledge reasoning on the missing part in the multi-modal knowledge graph based on the vector representation so as to predict the urban spatial evolution event. The urban spatial evolution event prediction can be realized, and the problem that the remote sensing image and the streetscape image are difficult to be deeply fused is effectively solved.

Embodiments of the present application relate to the technical field of artificial intelligence. Disclosed is a training method for a street scene understanding model assisted by a large vision model, comprising: extracting a street scene instantaneous feature of the current street scene image frame, and extracting street scene robust invariant features of all historical street scene image frames; respectively acquiring the difference between the current street scene image frame and each historical street scene image frame, and extracting street scene dynamic features of all street scene difference images; randomly mixing the street scene instantaneous feature, the street scene robust invariant features, and the street scene dynamic features to obtain a mixed street scene feature; performing street scene semantic segmentation on the mixed street scene feature by means of an initial street scene understanding model to obtain a predicted street scene mask of the current street scene image frame; generating a sample street scene mask of the mixed street scene feature by means of a large vision model; and updating model parameters of the initial street scene understanding model on the basis of the predicted street scene mask and the sample street scene mask to obtain a target street scene understanding model. Thus, the accuracy of street scene understanding is improved.

The invention discloses a streetscape image semantic segmentation method and system based on feature perception, and relates to the technical field of computer vision, and the method comprises the steps: employing a panoramic segmentation large model to carry out the preliminary segmentation of a streetscape image, outputting a coarse segmentation mask image, and dividing the streetscape image into an identified region set and an unidentified region set; for the recognized region set, combining similar fracture regions based on the intersection-to-union ratio and feature similarity of adjacent recognized regions, matching a small segmentation model according to the label of each combined region, and performing secondary segmentation by using the matched small segmentation model to generate semantic elements of the recognized region set; for the unidentified region set, performing secondary segmentation on the unidentified region by using all the small segmentation models to generate semantic elements of the unidentified region set; and finally, outputting a panoramic semantic segmentation result of the streetscape image, and through progressive processing from coarse segmentation to fine segmentation, realizing accurate distinguishing of similar confusion elements and completeness of semantic segmentation in a complex scene.

The invention relates to a traffic facility attribute mining method and system based on multi-modal network open source data. The method comprises the following steps: extracting traffic facility information from a webpage to construct a knowledge graph; extracting positions and appearances of traffic facilities from the images, and analyzing streetscape images to obtain attributes such as road traffic; collecting map images, tiles and vector data to construct a road network topology and attribute database; associating webpage texts, pictures, streetscape images and network map multi-source data according to the spatial position of the traffic facility; through comprehensive and deep attribute mining, different modal data are integrated to improve the accuracy and reliability of attribute mining, the real-time and dynamic updating capability, the convenient visualization and interaction operation, the data sharing and integration convenience, and the traffic facility management efficiency and collaboration are improved. According to the method, comprehensive, accurate and real-time traffic facility attribute data support can be provided for urban traffic planning, traffic management and intelligent traffic system construction, so that the efficiency and the intelligent level of traffic facility management are remarkably improved.

The invention discloses an urban village identification method based on a graph neural network and multi-source geographic big data, and relates to the technical field of geographic images, and the method comprises the steps: obtaining remote sensing data, social perception data and building footprint data of an urban village; based on road network trajectory data, cutting built-up area boundary data through a hierarchical buffer area strategy to obtain a basic evaluation unit; the streetscape image data, the satellite image data, the interest point data, the building attribute data and the building form data are preprocessed respectively, and visual features, social economic features and building form features are constructed; constructing a graph network structure of the graph neural network model; and according to the instance sample group, in combination with a graph network structure of the graph neural network model, constructing and training a GraphSAGE model so as to improve the recognition probability of the villages in the city. According to the method, the spatial interaction and regional relation between the network spatial structure and the multi-dimensional attributes are effectively understood through the GNN.

The invention discloses a lightweight traffic sign recognition method fusing time sequence characteristics in a shielding scene, and relates to the field of computer vision and intelligent traffic, in particular to a traffic sign recognition technology. Respectively constructing a single-frame data set with slight occlusion and a time sequence data set with severe occlusion; for a street scene image containing a complex background, training a lightweight target detector YOLOv8-N based on an existing bounding box label in a data set; secondly, a depth separable convolution structure with MobileNetV2 as a trunk network is adopted, and a high-dimensional feature map is extracted from the candidate mark image; then, a space attention mechanism is introduced, weighted correction is carried out on input features, an unshielded region is strengthened, and a shielded and noise region is suppressed; and finally, extracting a feature sequence of a historical frame of a heavily shielded sample, and inputting the feature sequence into an extended long-short-term memory network xLSTM for time sequence fusion.

The invention discloses a dynamic shelter restoration method and system based on continuous streetscape panoramic images, and the method comprises the steps: firstly obtaining a to-be-restored target panoramic image A and a to-be-restored reference panoramic image B, and generating an original pixel-level shelter mask; secondly, extracting matching points among the panoramic images, realizing cross-view geometric alignment of the images, and obtaining a target perspective view C and a reference perspective view D through perspective re-projection; and then inputting the target perspective view C and the reference perspective view D into a three-dimensional reconstruction framework, and performing three-dimensional point cloud reimaging under the camera pose of the target perspective view C by using a depth inspection mechanism. And finally, carrying out image restoration on a three-dimensional point cloud re-imaging result, restoring to a panoramic coordinate system, splicing with an original panoramic image, and outputting a shielding-free panoramic image. According to the method, it is ensured that the repairing result conforms to the authenticity and geometric consistency of the geographic space, and the problems of overlapping conflicts and visual tearing during multi-view projection fusion are effectively solved.

The invention provides a semantic segmentation method, system and equipment based on a traditional village multi-source image. The method comprises the following steps: acquiring a multi-source image and preprocessing the multi-source image; performing pixel-level labeling on the multi-source image to obtain a corresponding label graph; calculating the class imbalance weight of each class based on the tag graph, and obtaining a normalized class weight; inputting the label graph into a multi-scale context-aware coding-decoding network for feature extraction and fusion to obtain a prediction probability, constructing weighted multi-classification cross entropy loss based on a normalized category weight and the prediction probability, constructing a composite loss function in combination with boundary sensitive loss, and carrying out iterative updating on the network until convergence, so as to obtain a multi-scale context-aware coding-decoding network; through the setting, a synergistic effect is formed in four levels of data construction, a network structure, a training strategy and result output, so that objective indexes of traditional village street view scale semantic segmentation are improved, and the labor burden in an engineering use scene is remarkably reduced.

The invention discloses a universal streetscape multi-dimensional perception method based on a multi-modal large language model, and relates to the technical field of computer vision, and the method comprises the steps: obtaining a multi-source streetscape image, carrying out the preprocessing, generating a streetscape text description result, carrying out the analysis processing of the streetscape text description result based on a preset rule, and generating a streetscape text description data set; based on the streetscape text description data set, training a pre-configured multi-modal large language model through a low-rank adaptation mechanism to obtain a streetscape perception model; and carrying out secondary training on the streetscape perception model by utilizing an improved thinking chain mechanism to obtain a second-order streetscape perception model which is used for perceiving multi-dimensional complex information such as visual sense, emotion, sound sense and the like. According to the method, the multi-modal large language model is utilized, the cross-modal representation capability, the context reasoning mechanism and the zero sample migration capability are achieved, and large-scale pre-training data and an advanced deep learning architecture are utilized, so that deep fusion understanding of vision and language information and intelligent analysis of complex scenes are achieved.

The application discloses a risk road section prediction method and system, computer equipment and a storage medium, and relates to the technical field of road safety. The method comprises the following steps: acquiring street view image data of traffic accidents and accident-free road sections, inputting the street view image data of the traffic accidents and the accident-free road sections into a semantic segmentation model, outputting a predicted segmentation image, and obtaining the pixel proportion of different environmental elements of the road according to the segmented image; meanwhile, a risk road section prediction model is constructed based on an XGBOOST algorithm; the pixel proportions of different environmental elements are input into the risk road section prediction model, and the prediction probability of each street view image for an accident is output; the accuracy and stability of XGBOOST prediction are enhanced by deeply analyzing the pixel proportions of various objects in the visual environment of drivers, the risk of local transportation lines is accurately evaluated and analyzed in terms of environmental elements, and the method has a wide application prospect.

The application discloses a flood simulation method based on urban infrastructure and a device thereof, and the method comprises the following steps: collecting street view images of a city, wherein the street view images comprise street view data collected from different urban infrastructures at different angles and different times; classifying and processing the street view data according to the types of the infrastructures, and extracting urban infrastructure data; fusing the infrastructure data and terrain data of the city to obtain fused terrain data of the city; dividing catchment areas of the city based on the fused terrain data and extracting water system data, and establishing a flood simulation model based on urban infrastructure according to the water system data, so that the influence of urban street networks, fence systems, buildings and other infrastructures on urban flood processes is fully considered, the simulation accuracy of a city rainstorm flood model is improved, and urban flood disasters are reduced.

The application discloses a road centerline determination method and system based on a deep neural network satellite map, and relates to the technical field of satellite image processing; the method comprises the following steps: preprocessing time-phase satellite images of a collected to-be-processed region, vehicle GPS track data and street view image sequences to obtain a dynamic region in the to-be-processed region, a track density map and a street view feature mapping table; inputting the time-phase satellite images into a pre-trained road segmentation model to obtain multiple road probability maps; based on the multiple road probability maps, performing dynamic region weighted fusion, non-dynamic region logical or operation and threshold determination to obtain an initial road mask; vectorizing the initial road mask into a centerline network and extracting cross nodes to obtain an initial road network topology; and the application has the advantages of improving the accuracy of the road network topology and guaranteeing the rationality of path planning.

The invention discloses a non-motor vehicle road network construction method based on streetscape images. The non-motor vehicle road network construction method comprises the following steps of S1, obtaining a plurality of streetscape images and metadata and track sequence data of the streetscape images; s2, extracting a motor vehicle lane area and a non-motor vehicle lane area from each streetscape image, identifying road infrastructures and states related to non-motor vehicle lanes, and classifying tracks; s3, fusing the obtained road area, road infrastructure and state and track sequence data to obtain non-motor vehicle geometric road section information, and constructing a topological relation between non-motor vehicle road sections; s4, determining the actual width of the non-motor vehicle lane according to the vanishing points in the directions of the motor vehicle lane and the non-motor vehicle lane and the vanishing points in the horizontal direction; and S5, attaching the attributes of the non-motor vehicle lanes to the road network geometric data to form a non-motor vehicle road network. According to the method, the non-motor vehicle road network containing geometric road section information, a road section topological relation and lane attribute information is constructed.

An integrated branch city street scene real-time semantic segmentation method based on semantic information distillation comprises the following steps: S1, constructing an integrated branch network model: inputting a basic feature map F into a stacked channel enhanced residual block, and outputting a spatial detail feature map X2; the space detail feature map X2 is input into a stacked CNN-Transform block, and a high-level semantic feature map X4 is output; inputting the X4 into a rapid aggregation pyramid pooling module, and extracting and outputting an aggregation feature map X5; processing the spatial detail feature map X2 and the aggregated feature map X5 to obtain a feature map X6, and inputting the feature map X6 into a second solution terminal to generate a semantic segmentation map X8 of the urban streetscape; s2, constructing a semantic branch network model for knowledge distillation training: inputting the basic feature map F into a multi-scale feature encoder to generate intermediate semantic feature maps Y3 and Y4, and inputting the intermediate semantic feature map Y4 into a first solution code to generate a high-level semantic feature map Y5; s3, training the integrated branch network model; and S4, carrying out semantic segmentation by using the trained integrated branch network model.

The invention relates to a street view image recognition method and system based on quantum transfer learning. The method comprises the following steps: acquiring a streetscape image data set, and preprocessing the streetscape image data set; pre-training a DenseNet classical neural network based on the preprocessed streetscape digital image data to obtain pre-training parameters; removing the last layer of full-connection neural network of the DenseNet classical neural network, combining the last layer of full-connection neural network with a quantum convolutional neural network to form a mixed quantum classical neural network, fixing parameters of the DenseNet classical neural network based on pre-training parameters, and training the mixed quantum classical neural network by adopting a quantum machine learning framework based on an ISQ quantum compiler; and street scene image recognition is carried out by using the trained hybrid quantum classical neural network. According to the method, strong parallelism and non-local characteristics of quantum computing are applied, hidden information in data is potentially learned by using new computational logic, data training is accelerated, computing resources are saved, and street view digital image recognition can be realized.

The application provides a city resident population distribution trend prediction method based on a geographic detector, comprising the following steps: acquiring panoramic street view data of a research area; performing semantic segmentation to obtain visual perception elements and establish visual perception factors; establishing spatial perception factors through the accessibility of different facility types under different travel modes; using the geographic detector to calculate the explanation rate of the visual perception factors and the spatial perception factors on the resident population distribution density; obtaining several high-explanation-rate perception factors, obtaining corresponding weights based on a judgment matrix, establishing a resident intention index, and predicting the city resident population distribution trend. The prediction method is based on the perception of people to the real city environment, takes into account the subjectivity and objectivity of evaluation, and has high reference value for city planning related to city resident population distribution.

The present case relates to a kind of street scene infrared target detection method, after training, the model is too complex and the effect of extracting target feature from complex background such as street scene is not good for existing target detection model, the feature information of specified target is obtained by inputting the real-time acquisition street scene infrared image into infrared target detector, and the target is positioned and identified.The infrared target detector adopts YOLOv5 network and parameter-free attention module SimAM to be combined, realizes each repeated part of C3 residual module in YOLOv5 network structure, parameter-free attention module SimAM is added in series behind each repeated part, while not increasing parameter quantity, the purpose of suppressing background noise and enhancing detection performance is realized.Furthermore, different dilated convolution module of expansion rate is added after each SPPF module maximum pooling operation, so that the model obtains flexible receptive field, and the performance of detecting the target with large size difference is enhanced.

The present disclosure provides a street scene semantic segmentation method and device based on deep spatial structure information. The method comprises: collecting a plurality of street scene images to form a data set, and preprocessing the street scene images in the data set; inputting the preprocessed street scene images into an encoder of a preset network model for feature extraction and compression; calculating spatial structure information for the extracted features; completing up-sampling using a decoder; outputting a prediction result and optimizing the model. The accuracy of the model can be increased without increasing the amount of calculation.

The application discloses a kind of multi-modal information comprehensive retrieval street view image positioning method and system, by establishing multi-modal information database, using visual feature extraction model and scene text recognition model establish multi-modal information database;By fusion feature retrieval, global feature and local feature are fused and preliminary recall search is carried out;By geometric verification rearrangement, the geometric verification algorithm based on local feature is used to rearrange preliminary recall search result, and obtain refined retrieval result;By scene text retrieval, the scene text set overlap degree of query picture and database picture is calculated, and the final retrieval result is obtained based on this score ranking. The application considers the comprehensive retrieval scheme of multi-modal information, can greatly improve the image positioning accuracy in practical application, and to a certain extent, solves the complete positioning failure problem of single modal information in some scenes.

The invention belongs to the technical field of computer vision, and particularly relates to a street scene ground object real-time semantic segmentation and geographic positioning method and system based on a camera, and the method comprises the steps: S1, carrying out the image collection and preprocessing; s2, performing semantic segmentation; s3, panoramic monocular depth estimation and scale recovery are carried out; s4, target detection and pixel extraction are carried out; step S5, resolving a space coordinate; and S6, performing Kalman filtering fusion based on a time sequence, and outputting a final convergence coordinate of a filter as a final geographic position of the ground feature. Different from a vehicle positioning technology which depends on a prior high-precision map for matching, the method provided by the invention has the advantages that a panoramic depth estimation and space coordinate resolving algorithm is utilized, the three-dimensional space position of a ground object can be directly deduced reversely from two-dimensional image pixels under the condition of no prior map data, and the WGS84 absolute geographic coordinate of the ground object is calculated in real time in combination with GNSS / IMU data.

The invention discloses a road center line determination method and system based on a deep neural network satellite map, and relates to the technical field of satellite image processing. The method comprises the following steps: preprocessing a collected time phase satellite image, vehicle GPS track data and a streetscape image sequence of a to-be-processed area to obtain a dynamic area, a track density map and a streetscape feature mapping table in the to-be-processed area; inputting the time-phase satellite image into a pre-trained road segmentation model to obtain a plurality of road probability graphs; based on the multiple road probability maps, after dynamic region weighted fusion and non-dynamic region logic or operation and threshold judgment are carried out, an initial road mask is obtained; vectorizing the initial road mask into a center line network and extracting cross nodes to obtain an initial road network topology; the method has the advantages that the road network topology accuracy is improved, and the path planning reasonability is guaranteed.

The invention discloses a street facade micro-update identification method based on a grid network. The method comprises the steps of acquisition range determination, road network grading and sampling point arrangement, street scene image acquisition and building facade rasterization processing, building construction or dismantling identification through large and small granularities, building facade material identification, micro-update determination and the like. According to the method, the material change of the building facade is automatically identified through the streetscape image, efficient and accurate monitoring of city micro-updating is realized, and the method is suitable for the fields of city planning, updating evaluation and the like.

The invention provides an information verification method and device and related equipment, and particularly relates to the technical field of communication equipment management.The method comprises the steps that in a plurality of road network segments of a first area, N adjacent road network segments are determined, and a plurality of target streetscape images are obtained, the plurality of target street view images comprise street view images acquired towards a to-be-verified position point based on street view acquisition equipment in the N adjacent road network segments; according to a set station identification model, image identification is carried out on the multiple target streetscape images, station verification information is obtained, the station verification information is used for representing whether the to-be-verified position point has an equipment station or not, and under the condition that the to-be-verified position point has the equipment station, the to-be-verified position point is subjected to station verification, and the to-be-verified position point is subjected to station verification. And representing the station type of the equipment station existing at the to-be-verified position point. According to the invention, the verification efficiency of the base station position point can be improved, the identification of the base station type can be supported, and the state of the base station and the surrounding environment can be dynamically displayed.