CN118447196A - AR landscape automatic observation method and system - Google Patents
AR landscape automatic observation method and system Download PDFInfo
- Publication number
- CN118447196A CN118447196A CN202410903219.6A CN202410903219A CN118447196A CN 118447196 A CN118447196 A CN 118447196A CN 202410903219 A CN202410903219 A CN 202410903219A CN 118447196 A CN118447196 A CN 118447196A
- Authority
- CN
- China
- Prior art keywords
- landscape
- size
- data
- model
- light
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000008859 change Effects 0.000 claims abstract description 88
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 238000005516 engineering process Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 25
- 230000000007 visual effect Effects 0.000 claims abstract description 20
- 238000009877 rendering Methods 0.000 claims abstract description 19
- 230000009466 transformation Effects 0.000 claims abstract description 9
- 238000013507 mapping Methods 0.000 claims description 44
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000013473 artificial intelligence Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 6
- 230000002452 interceptive effect Effects 0.000 abstract description 2
- 210000001503 joint Anatomy 0.000 abstract 1
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 208000025174 PANDAS Diseases 0.000 description 2
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 2
- 240000004718 Panda Species 0.000 description 2
- 235000016496 Panda oleosa Nutrition 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007634 remodeling Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000000692 Student's t-test Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000000528 statistical test Methods 0.000 description 1
- 238000012353 t test Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to the technical field of three-dimensional images, in particular to an AR landscape automatic observation method and system, comprising the following steps: based on the ambient light data around the AR landscape, calculating an edge intensity map of the AR landscape object by comparing the color and the light intensity, and generating a light edge map. According to the invention, through a digital image processing technology, the accurate edge of an object can be captured in real time, the recognition process of the outline of the object is improved, the light change can be responded faster and more accurately under a dynamic environment, the detail level of landscape analysis is improved, the AR landscape size data is accurately calibrated by utilizing a geometric transformation technology, the timeliness of the data is optimized by intelligently comparing the AR landscape size data with historical data, the real-time performance and accuracy of AR display are ensured, richer and finer interactive experience is provided for a user, and the AR model is more vivid in visual effect and is in seamless butt joint with the actual visual experience of the user by updating a three-dimensional database and optimizing a rendering process.
Description
Technical Field
The invention relates to the technical field of three-dimensional images, in particular to an AR landscape automatic observation method and system.
Background
In the technical field of three-dimensional images, an AR landscape automatic observation method relates to computer vision and image processing technology, and image data captured from the real world is processed and analyzed by using an advanced algorithm and is displayed in a layered manner with a preset virtual image object or information, so that a mixed reality visual experience is created, and the method is widely applied to multiple fields of navigation, urban planning, entertainment, education and the like, and a brand new mode of interaction with the environment is provided for users.
The AR landscape automatic observation method is a technical method for automatically analyzing and presenting a real world landscape by using an augmented reality technology, and aims to improve the automation level and efficiency of observation, and the understanding and interaction of a user to the surrounding environment are enhanced by embedding virtual data in a visual scene of the user. For example, in a building planning or travel application, a user may see a three-dimensional preview of future building projects in the real world or restoration of historical scenes, thereby providing a richer information and enhanced experience.
The existing AR landscape automatic observation method lacks enough flexibility and self-adaptation capability when processing dynamic environment changes, relies on preset environment parameters and slower data updating frequency, limits the effectiveness under the rapid change external conditions, lacks real-time data processing capability, causes information hysteresis in navigation, city planning and other applications, thereby affecting timeliness and accuracy of decision making, the traditional AR landscape automatic observation method needs complicated manual intervention when performing size adjustment and updating of landscape elements, not only increases the complexity of operation, but also improves the error probability, remarkably reduces efficiency and reliability due to dependence of manual input and updating, and especially lacks automatic and intelligent processing procedures when processing large-scale data, and the prior art fails to fully utilize the advantages of modern computing resources and realize efficient data circulation and utilization.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an AR landscape automatic observation method and an AR landscape automatic observation system.
In order to achieve the above purpose, the invention adopts the following technical scheme that the AR landscape automatic observation method comprises the following steps:
s1: calculating an edge intensity map of the AR landscape object based on ambient light data around the AR landscape by comparing color and light intensity, and generating a light edge map;
s2: positioning the object outline of the AR landscape based on the light edge mapping, and analyzing the mountain, building and road characteristics in the AR landscape to obtain AR landscape outline characteristic mapping;
s3: based on the AR landscape contour feature mapping, adopting a digital image processing technology to observe real-time dimension parameters of an AR landscape object, calibrating dimension errors in an AR landscape image, and adjusting proportional dimensions to obtain AR landscape dimension calibration data;
S4: based on the AR landscape size calibration data, comparing the AR landscape size calibration data with historical AR landscape size data, and automatically observing real-time changes of the AR landscape by using artificial intelligence to obtain updated deviation data;
s5: based on the updating deviation data, the differentiated geographic deviation points are analyzed and identified, and the landscape information points needing to be changed and added are calibrated to obtain geographic information updating points;
S6: based on the geographic information updating points, a geometric transformation algorithm is adopted to update a three-dimensional AR landscape database, AR landscape elements in the database are adjusted, and landscape layers in the three-dimensional model are rendered to generate a three-dimensional AR landscape model.
As a further scheme of the invention, the light ray edge map comprises a light intensity difference map, a color gradient map and a combination result, the AR landscape outline feature map comprises an image data set of a terrain outline, a building outline and a road outline, the AR landscape size calibration data comprises a size proportion map with calibrated parameters consistent with real world proportions, the updating deviation data comprises a record of size change, position movement and landscape elements, the geographic information updating point comprises positions of mountains, buildings and roads which need to be updated and added, and the three-dimensional AR landscape model comprises a calibrated landscape element, a multi-level landscape and a visual display of landscape features.
As a further scheme of the invention, based on the ambient light data around the AR landscape, the edge intensity map of the AR landscape object is calculated by comparing the color and the light intensity, and the step of generating the light edge map is specifically as follows:
S101: based on the ambient light data around the AR landscape, measuring the intensity and color of light in a differential time period, recording data of a plurality of time points, and analyzing the light change rule to obtain an ambient light change trend graph;
S102: identifying the change of light reflection intensity based on the environment light change trend graph, marking key change points, and positioning potential object edge positions to obtain an edge initialization mark graph;
S103: and processing the marked edges in the edge initialization mark graph based on the edge initialization mark graph, adjusting the recognition degree of the edges, optimizing the edge line representation in the image, and generating the light edge mapping.
As a further scheme of the invention, based on the light edge mapping, the object contour of the AR landscape is positioned, and the characteristics of mountains, buildings and roads in the AR landscape are analyzed, so that the steps for obtaining the AR landscape contour feature mapping are specifically as follows:
s201: based on the ray edge mapping, measuring edge intensity in an edge initialization mark image, and analyzing and positioning the edges of the geographic shape and the artificial structure through an edge intensity map to obtain an object boundary map;
S202: distinguishing AR landscapes of natural and artificial structures based on the object boundary map, classifying mountain, building and road elements, drawing and identifying the distinction of each type of elements, and obtaining a category contour map;
S203: based on the category profile, integrating the analysis data, defining visual representation parameters, including color and texture, for each landscape, analyzing the view of geographic and artificial features, and generating an AR landscape profile map.
As a further scheme of the invention, based on the AR landscape outline feature mapping, a digital image processing technology is adopted to observe real-time dimension parameters of an AR landscape object, calibrate dimension errors in an AR landscape image, and the steps of adjusting proportional dimensions to obtain AR landscape dimension calibration data are specifically as follows:
S301: based on the AR landscape outline feature mapping, collecting real-time dimension parameters associated with the AR landscape object, and re-measuring the dimension of the AR landscape object if the mapping data deviate from the real-time observation data, so as to generate updated dimension parameter data;
S302: based on the updated size parameter data, performing contrast analysis on the image size of each AR landscape object by adopting a Kalman filtering algorithm, and if the detected size error exceeds a preset threshold, adjusting the error according to the proportional size to generate size calibration intermediate data;
The Kalman filtering algorithm is according to the formula
；
Wherein,To update the state estimate based on real-time observations,In order to be based on the predicted state at the last moment,For the purpose of real-time observation of the values,In order for the kalman gain to be achieved,In order to observe the model, the model is,For the purpose of innovative noise adjustment parameters,In order to dynamically adjust the coefficient of the coefficient,Is an environment dependent parameter;
s303: based on the size calibration intermediate data, the adjusted proportional size data is applied to an AR landscape model, and the size of the landscape object is matched with the real-time measured value to obtain AR landscape size calibration data.
As a further scheme of the invention, based on the AR landscape size calibration data, the AR landscape size calibration data is compared with historical AR landscape size data, and real-time changes of the AR landscape are automatically observed by utilizing artificial intelligence, and the steps for obtaining updated deviation data are specifically as follows:
S401: based on the AR landscape size calibration data, analyzing historical size information of the AR landscape position, and recording size parameters including landscape element data through numerical comparison to obtain historical and real-time size comparison records;
S402: based on the history and real-time size comparison record, performing difference analysis of the history and the real-time size, determining the size change of the region, including the establishment of a new building and the dismantling of an old building, marking the changed size region, and generating a size change analysis result;
S403: based on the size change analysis result, the identified regional size change is automatically observed and recorded by using artificial intelligence, the position of the change area and the value of the size change are measured, and the value is updated into an AR landscape model to generate updated deviation data.
As a further scheme of the invention, based on the updating deviation data, the differentiated geographic deviation points are analyzed and identified, and the landscape information points needing to be changed and added are calibrated, so that the steps of obtaining the geographic information updating points are specifically as follows:
S501: based on the updated deviation data, analyzing the size and position changes of AR landscape records, classifying and recording the changes of each landscape element, and recording the size changes and the space movements of various objects to obtain a changed geographic coordinate record;
S502: analyzing and recording key places of geographic coordinate change based on the change geographic coordinate record, including areas of natural terrain change, classifying and marking update requirements of place change, and generating change place classification marks;
s503: and analyzing the adjusted and newly added landscape information points based on the change place classification marks, including new building outlines, road extension and adjustment and remodelling of terrains, distributing geographic coordinates and descriptions for each point, and generating geographic information updating points.
As a further scheme of the invention, based on the geographic information updating point, a geometric transformation algorithm is adopted to update a three-dimensional AR landscape database, AR landscape elements in the database are adjusted, and a landscape layer in a three-dimensional model is rendered, so that the three-dimensional AR landscape model is generated specifically by the following steps:
S601: selecting the associated geographic coordinates in the three-dimensional AR landscape database based on the geographic information updating points, and comparing attribute differences between the geographic information updating points and the coordinates in the database if the coordinates exist in the database, updating the geographic attribute information of the AR landscape elements according to the attribute differences, and generating geographic information matching results;
S602: based on the geographic information matching result, detecting a micro-model structure of an AR landscape element in a database, and if the structure is marked as outdated and does not accord with new attribute information, adjusting the layout of the micro-model by using the new attribute parameters, including modifying the texture, the size and the position of the micro-model, and generating a micro-model adjustment result;
s603: and rendering the adjusted micro model based on the micro model adjustment result, and performing light shadow and texture rendering to strengthen the visual effect of the micro model to match with the AR display requirement and obtain the three-dimensional AR landscape model.
An AR landscape automatic observation system for performing the above-described AR landscape automatic observation method, the system comprising:
the environment monitoring module records the change of light along with time based on the ambient light data around the AR landscape, identifies and marks the area where the light changes, and positions objects to obtain light edge mapping;
The size capturing module is used for measuring the sizes of a plurality of objects in the AR landscape in real time based on the light edge mapping, and generating an AR landscape contour feature mapping by analyzing the sizes of the objects and positioning the contours of the objects;
the error analysis module is used for comparing the AR landscape outline feature mapping with the historical size data of the AR landscape object, identifying and calculating the size error, and calibrating the size to be adjusted to obtain AR landscape size calibration data;
the data synchronization module updates size and position information in a three-dimensional AR landscape database based on the AR landscape size calibration data, automatically observes and records the size change of the differential area, and generates updated deviation data;
The micro-model rendering module analyzes and records key places of geographic coordinate changes based on the updating deviation data, updates geographic position information of AR landscape elements, and updates vision hierarchy matching real-time data of the landscape by rendering the micro-model of the AR landscape to obtain a three-dimensional AR landscape model.
Compared with the prior art, the invention has the advantages and positive effects that:
According to the invention, the edge intensity map is calculated by utilizing the environment light data through a digital image processing technology, the accurate edge of an object can be captured in real time, the recognition process of the object outline is improved, the light change can be responded faster and more accurately under a dynamic environment, the edge data is used for mapping the detailed outline of the object, the detail level of landscape analysis is improved, the visual manifestation of elements such as mountains, buildings and roads is clearer, the AR landscape size data is accurately calibrated by utilizing a geometric transformation technology, the timeliness of the data is optimized by intelligent comparison with the history data, the manual participation degree is reduced by automatically updating deviation data, the data processing flow is accelerated, the real-time and accuracy of AR display are ensured, richer and finer interactive experience is provided for users, the three-dimensional database is updated, the rendering process is optimized, the AR model is more vivid in visual effect, and the AR model is in seamless joint with the actual visual experience of the users.
Drawings
FIG. 1 is a schematic workflow diagram of the present invention;
FIG. 2 is a S1 refinement flowchart of the present invention;
FIG. 3 is a S2 refinement flowchart of the present invention;
FIG. 4 is a S3 refinement flowchart of the present invention;
FIG. 5 is a S4 refinement flowchart of the present invention;
FIG. 6 is a S5 refinement flowchart of the present invention;
FIG. 7 is a S6 refinement flowchart of the present invention;
Fig. 8 is a system flow diagram of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Example 1
Referring to fig. 1, the present invention provides a technical solution, an automatic observation method for AR landscape, comprising the following steps:
s1: measuring the edge of an AR landscape object based on ambient light data around the AR landscape, including the color and the intensity of the light, calculating the edge intensity according to the light data, and performing contrast analysis on the light to generate a light edge map;
S2: positioning the object outline of the AR landscape based on the ray edge mapping, analyzing the mountain, building and road characteristics in the AR landscape, and identifying and classifying the outline information of each geographic characteristic to obtain the AR landscape outline characteristic mapping;
S3: based on AR landscape contour feature mapping, adopting a digital image processing technology to observe real-time dimension parameters of an AR landscape object, calibrating dimension errors in an AR landscape image, and adjusting proportional dimensions to obtain AR landscape dimension calibration data;
S4: based on AR landscape size calibration data, comparing the AR landscape size calibration data with historical AR landscape size data, automatically observing real-time changes of the AR landscape by using artificial intelligence, and monitoring and recording the real-time changes in size to obtain updated deviation data;
S5: based on the updated deviation data, the differentiated geographic deviation points are analyzed and identified, the landscape information points needing to be changed and added are calibrated, and the deviation points are positioned and marked to obtain geographic information updating points;
S6: based on the geographic information updating points, a geometric transformation algorithm is adopted to update a three-dimensional AR landscape database, AR landscape elements in the database are adjusted, and landscape layers in the three-dimensional model are rendered to generate a three-dimensional AR landscape model.
The light edge map comprises a light intensity difference map, a color gradient map and a combination result, the AR landscape outline feature map comprises an image data set of a terrain outline, a building outline and a road outline, the AR landscape size calibration data comprises a size proportion map with calibrated parameters consistent with real world proportion, the updating deviation data comprises size change, position movement and record of landscape elements, the geographic information updating point comprises positions of mountains, buildings and roads which need to be updated and added, and the three-dimensional AR landscape model comprises calibrated landscape elements, multi-level landscape and visual display of landscape features.
Referring to fig. 2, based on the ambient light data around the AR landscape, the edge intensity map of the AR landscape object is calculated by comparing the color and the light intensity, and the step of generating the light edge map is specifically as follows:
s101: based on the ambient light data around the AR landscape, measuring the intensity and color of light in a differential time period, recording data of a plurality of time points, and analyzing the light change rule to obtain an execution flow of an ambient light change trend chart as follows;
S101, based on ambient light data around AR landscapes, a linear regression analysis method is adopted, a Scikit-learn library of Python is utilized to execute time sequence prediction of light intensity and color, a time point is set to be an independent variable, light readings are set to be dependent variables, a relation between least square fitting time and the light intensity and color is adopted, data in each time period is subjected to data format conversion by using a Numpy library, a DATAFRAME of a time index is created by using a Pandas library, a plot function in the Matplotlib library is applied to draw a time sequence diagram, light changes at different time points are reflected, and light changes at future time points are predicted by using a linear model, so that an ambient light change trend diagram is generated.
S102: based on the environment light change trend graph, identifying the change of light reflection intensity, marking key change points, positioning potential object edge positions, and obtaining an edge initialization mark graph, wherein the execution flow is as follows;
S102, based on an ambient light change trend graph, performing edge detection by adopting a Sobel algorithm, performing gray level conversion on an image by utilizing an OpenCV library of Python, calculating gradients in X and Y directions by adopting a Sobel operator, combining the gradients to determine the edge of light reflection intensity, setting the kernel size of the Sobel operator to be 3 and the step length to be 1 so as to accurately capture edge details in the image, performing binarization processing on the image by using a threshold segmentation method and setting a threshold to be a fixed numerical value, thereby obviously marking key points with larger change, regarding the key points as potential object edge positions, and generating an edge initialization mark graph.
S103: based on the edge initialization mark graph, processing the marked edge in the edge initialization mark graph, adjusting the recognition degree of the edge, optimizing the edge line representation in the image, and generating the execution flow of the light edge mapping as follows;
S103, sub-step is based on an edge initialization mark graph, the image edge is optimized by adopting a Gaussian blur technology, edge smoothing processing is carried out by utilizing GaussianBlur functions in an OpenCV library, the size of a Gaussian kernel is set to be 5x5, the standard deviation is set to be 1.5, edge definition is maintained while image noise is reduced, parameters of a Canny edge detection algorithm are further adjusted, a low threshold is set to be 50, a high threshold is set to be 150, through parameter adjustment, the representation of edge lines is optimized, the image is more vivid, bilateral filtering is carried out by utilizing BilateralFilter, edge representation is thinned, and a light edge map is generated.
Referring to fig. 3, based on the ray edge mapping, the object contour of the AR landscape is located, and features of mountains, buildings and roads in the AR landscape are analyzed, so as to obtain the AR landscape contour feature mapping specifically as follows:
S201: based on ray edge mapping, measuring edge intensity in an edge initialization mark image, analyzing and positioning the edges of the geographic shape and the artificial structure through an edge intensity map, and obtaining an execution flow of an object boundary map as follows;
S201, measuring edge intensity in an edge initialization marked image by adopting an image processing technology based on ray edge mapping, smoothing the image by using a Python OpenCV library, reducing noise interference by using a 5x5 Gaussian kernel by a GaussianBlur method, detecting the edge by using a Canny algorithm, setting double thresholds as 100 and 200 respectively to accurately capture significant edges, extracting linear edges in the image by utilizing Hough transformation, executing by setting the threshold as 50, setting the minimum line length as 100 and setting the maximum line interval as 10, analyzing and positioning the edges of geographic shapes and artificial structures by edge lines, and generating an object boundary map.
S202: based on the object boundary diagram, distinguishing natural and artificial AR landscapes, classifying mountain, building and road elements, drawing and identifying the distinction of each type of elements, and obtaining the execution flow of a category contour diagram as follows;
S202, distinguishing AR landscapes of natural and artificial structures based on an object boundary map, constructing a convolutional neural network model by using a TensorFlow framework and a Keras library by adopting a deep learning method, connecting a maximum pooling layer behind each layer for extracting image features, wherein a classifier part consists of two full-connection layers, using a ReLU activation function, performing multi-class classification by adopting a Softmax activation function on an output layer, distinguishing mountain ranges, buildings and road elements in the images by using a cross entropy as a loss function in model training, selecting Adam by using an optimizer, training the model by using a training dataset, applying the model on the object boundary map, identifying and labeling elements of different classes, and generating a class contour map.
S203: based on the category contour map, integrating the analysis data, defining visual representation parameters for each landscape, including colors and textures, analyzing the views of geographic and artificial features, and generating an AR landscape contour feature map as follows;
S203, the substep is based on category contour diagrams, analysis data are integrated, the image segmentation technology is used for refining boundaries of different landscape categories at the stage, the k-means clustering algorithm in the OpenCV library is used for carrying out color segmentation on the images, the clustering number is set to be 3, visual characteristics corresponding to natural landscape, building and road are respectively defined, each category is respectively defined with visual representation parameters including color and texture, the color range of each category is determined by using a color histogram comparison method, the texture parameters are obtained through gray level symbiotic matrix analysis, detailed views of geographic and artificial characteristics are analyzed, and AR landscape contour feature mapping is generated.
Referring to fig. 4, based on the AR landscape contour feature map, the real-time dimension parameter of the AR landscape object is observed by adopting a digital image processing technology, the dimension error in the AR landscape image is calibrated, the proportional dimension is adjusted, and the steps for obtaining the AR landscape dimension calibration data are specifically as follows:
s301: based on the AR landscape outline feature mapping, collecting real-time dimension parameters associated with the AR landscape object, and re-measuring the dimension of the AR landscape object if the mapping data deviate from the real-time observation data, wherein the execution flow of generating updated dimension parameter data is as follows;
S301, based on AR landscape outline feature mapping, collecting real-time dimension parameters of an AR landscape object by adopting a real-time data monitoring technology, accurately measuring the dimension of the object by utilizing a laser range finder, transmitting real-time monitoring data to a central processing unit through a wireless network, carrying out data analysis by using a NumPy library of Python, triggering a re-measurement mechanism if deviation exists between mapping data and real-time observation data, measuring the dimension of the AR landscape object by using a three-dimensional scanning technology again, comparing original dimension data with new measurement data, calculating the difference between the original dimension data and the new measurement data, and confirming that the deviation exceeds a preset tolerance range to generate updated dimension parameter data.
S302: based on the updated size parameter data, performing contrast analysis on the image size of each AR landscape object by adopting a Kalman filtering algorithm, and if the detected size error exceeds a preset threshold, adjusting the error according to the proportional size, wherein the execution flow for generating the size calibration intermediate data is as follows;
S302, carrying out contrast analysis on the image size of each AR landscape object based on the updated size parameter data, using an image processing technology, carrying out size error detection by adopting a pixel comparison method after normalizing the image size by utilizing a function of an OpenCV library, if the detected size error exceeds a preset threshold, namely, setting the pixel difference with the error threshold to be 5%, adjusting by using an image scaling technology according to the error scale, and carrying out scaling operation to calibrate the image size by setting the scaling coefficient of the image, such as setting the image scaling coefficient to be the ratio of the original size to the measured size, so as to generate size calibration intermediate data.
Kalman filtering algorithm is according to formula
；
Wherein,To update the state estimate based on real-time observations,In order to be based on the predicted state at the last moment,For the purpose of real-time observation of the values,In order for the kalman gain to be achieved,In order to observe the model, the model is,For the purpose of innovative noise adjustment parameters,In order to dynamically adjust the coefficient of the coefficient,Is an environment dependent parameter;
the execution flow is as follows:
Updating state estimates based on previous state and real-time observations Introducing innovative noise tuning parametersIncreasing the adaptability of the model to unforeseen noise, and calculating a dynamic adjustment coefficientAutomatically adjusting according to the change of the environmental data for optimizing the prediction precision and depending on the environmental parametersAnd adjusting error estimation according to real-time data collected in an actual application scene, improving the response speed of the system to environmental changes, and generating a calibrated size parameter value.
S303: based on the size calibration intermediate data, applying the adjusted proportional size data to an AR landscape model, and matching the size of a landscape object with a real-time measured value to obtain an AR landscape size calibration data, wherein the execution flow of the AR landscape size calibration data is as follows;
The step S303 is substep based on the size calibration intermediate data, applies the adjusted proportional size data to the AR landscape model, involves updating the size parameters of the AR model, adopts three-dimensional modeling software such as Autodesk 3ds Max, adjusts the size of the landscape objects to match real-time measurement values, the updating operation includes modifying the proportional attributes of the model, ensures that the three-dimensional size of each object is consistent with the latest calibration data, verifies the accuracy of the size through the rendering process, ensures that all the landscape objects are visually matched with the actual measured size, and generates AR landscape size calibration data.
Referring to fig. 5, based on AR landscape size calibration data, comparing with historical AR landscape size data, using artificial intelligence, automatically observing real-time changes of AR landscape, the steps of obtaining updated deviation data are specifically as follows:
S401: based on AR landscape size calibration data, analyzing historical size information of AR landscape positions, and recording size parameters including landscape element data through numerical comparison, wherein the execution flow of historical and real-time size comparison records is as follows;
S401, analyzing historical size information of AR landscape positions based on AR landscape size calibration data by adopting a historical data analysis technology, storing historical and real-time size data by utilizing a database management system such as MySQL, combining the historical and real-time data tables by using SQL query language through JOIN operation, carrying out numerical comparison on the length, width and height data of landscape elements, processing and analyzing the data by using a Pandas library of Python, recording size parameters of each time point, and generating a visual chart of size change by using a Matplotlib library to obtain a history and real-time size comparison record.
S402: based on the comparison record of the history and the real-time size, performing difference analysis of the history and the real-time size, determining the size change of the region, including the establishment of a new building and the dismantling of an old building, marking the changed size region, and generating an execution flow of a size change analysis result as follows;
The S402 substep is based on the comparison record of the history and the real-time size, performs the difference analysis of the history and the real-time size, uses a statistical analysis method, comprises using a SciPy library of Python to perform statistical tests, such as t-test to determine the significance change of the size, analyzes the trend of revealing the regional size change, comprises the establishment of a new building and the dismantling of an old building, uses an OpenCV library to perform image processing, marks out a size area with significant change, identifies the significantly changed building size by setting a threshold, and generates a size change analysis result.
S403: based on the analysis result of the size change, the artificial intelligence is utilized to automatically observe and record the identified regional size change, the position of the change area and the numerical value of the size change are measured and updated into the AR landscape model, and the execution flow for generating the update deviation data is as follows;
S403, based on the analysis result of the size change, automatically observing and recording the identified regional size change by using an artificial intelligence technology, adopting a machine learning model, such as a neural network model constructed by using a TensorFlow library of Python, automatically identifying the mode and trend of the size change, measuring the position of a change area and the value of the size change, integrating and updating the measurement result into an AR landscape model, adjusting the model size by using a 3D modeling tool such as Blender to match new data, ensuring the real-time accuracy of the model, and generating updated deviation data.
Referring to fig. 6, based on the updated deviation data, the steps of analyzing and identifying the differentiated geographic deviation points, calibrating the landscape information points to be changed and added, and obtaining the geographic information update points are specifically as follows:
S501: based on the updated deviation data, analyzing the size and position changes of AR landscape records, classifying and recording the changes of each landscape element, and recording the size changes and the space movements of various objects, wherein the execution flow of the obtained change geographic coordinate records is as follows;
s501, analyzing the size and position change of AR landscape records by adopting a Geographic Information System (GIS) technology based on the updated deviation data, importing the updated deviation data by utilizing ArcGIS software, including the size and position information of each landscape element, classifying and recording the change of each landscape element by a space analysis tool, analyzing the geographic position and the size change of each landscape element by using a space query function, recording the size change and the space movement of various objects including buildings, roads, natural landscapes and the like, and screening out the objects with obvious change by setting query parameters to obtain a changed geographic coordinate record.
S502: based on the change geographic coordinate record, analyzing and recording key places of geographic coordinate change, including areas of natural terrain change, classification and updating requirements of mark place change, and generating an execution flow of change place classification marks as follows;
The S502 substep is based on the changed geographic coordinate record, analyzes and records key places of geographic coordinate change by utilizing a geographic information analysis technology including a high-level analysis function using QGIS software, identifies the terrain change caused by landslide or river erosion by utilizing a Digital Elevation Model (DEM) to perform terrain analysis on a natural terrain change area, and simultaneously, classifies and marks the update requirements of the place change by utilizing an attribute query and a space filtering technology, including a new construction area, a road adjustment area and corroded terrain to generate a changed place classification mark.
S503: based on the change place classification marks, analyzing the adjusted and newly added landscape information points, including new building outlines, road extension and adjustment and terrain remodeling, distributing geographic coordinates and description for each point, and generating an execution flow of a geographic information update point as follows;
S503 substep adopts city planning and geographic modeling technology based on the change place classification mark, analyzes the adjusted and newly added landscape information points, uses AutoCAD Civil 3D to carry out three-dimensional geographic modeling, designs and models new building outline, road extension and adjustment and remodeling of terrain, distributes accurate geographic coordinates and detailed description including building height, road width and terrain characteristics for each updated point, ensures that all updated information points are accurately reflected in the AR landscape model, and generates geographic information updated points.
Referring to fig. 7, based on the geographic information update points, a geometric transformation algorithm is adopted to update a three-dimensional AR landscape database, AR landscape elements in the database are adjusted, and a landscape layer in a three-dimensional model is rendered, so that the three-dimensional AR landscape model is generated specifically by the following steps:
S601: based on the geographic information updating points, selecting the associated geographic coordinates in the three-dimensional AR landscape database, if the coordinates exist in the database, comparing attribute differences between the geographic information updating points and the coordinates in the database, updating the geographic attribute information of the AR landscape elements according to the attribute differences, and generating an execution flow of geographic information matching results as follows;
S601, based on geographic information UPDATE points, selecting associated geographic coordinates in a three-dimensional AR landscape database by using a database query technology, executing through SQL query language, connecting to a PostgreSQL database storing geographic information, comparing coordinates of the geographic information UPDATE points with the coordinates stored in the database by using a SELECT statement and INNER JOIN operation, if the coordinates exist in the database, finding out attribute differences, such as the height of coordinate points and the type of a used region by using a difference set query (EXCEPT), updating geographic attribute information of AR landscape elements by using an UPDATE statement according to the attribute differences, such as the floor number and the occupied area of a building, and generating geographic information matching results.
S602: based on the geographic information matching result, detecting the micro-model structure of the AR landscape element in the database, and if the structure is marked as outdated and does not accord with new attribute information, adjusting the layout of the micro-model by using new attribute parameters, wherein the execution flow of generating the micro-model adjustment result is as follows, including modifying the texture, size and position of the micro-model;
S602, based on a geographic information matching result, detecting a micro-model structure of an AR landscape element in a database, using a Python script to operate in combination with an SQL query language, identifying the micro-model structure marked as outdated, comparing the creation date of the micro-model with the latest update date, and if the new attribute information is not met, adjusting the layout of the micro-model by using a Blender API according to the new attribute parameters, such as the new height and area of a building, including modifying the texture, the size and the position of the micro-model, and executing by adjusting texture mapping and size scaling parameters in Blender to generate a micro-model adjustment result.
S603: based on the micro-model adjustment result, rendering the adjusted micro-model, performing light shadow and texture rendering, enhancing the visual effect of the micro-model to match with the AR display requirement, and obtaining the execution flow of the three-dimensional AR landscape model as follows;
And S603, performing rendering processing on the adjusted micro model based on the micro model adjustment result, using advanced rendering technology, such as using the light shadow and texture rendering function of the Unity engine, importing the adjusted micro model into the Unity environment, setting environment light source parameters and material properties, such as light source intensity, light source color and material reflectivity and texture details, executing the rendering process, and obtaining the three-dimensional AR landscape model by setting the visual effect of the enhanced micro model, matching with the AR display requirement.
Referring to fig. 8, an AR landscape automatic observation system for executing the above-mentioned AR landscape automatic observation method includes:
the environment monitoring module records the change of light along with time based on the ambient light data around the AR landscape, identifies and marks the area where the light changes, and positions objects to obtain light edge mapping;
the size capturing module is used for measuring the sizes of a plurality of objects in the AR landscape in real time based on the ray edge mapping, and positioning the outline of the object by analyzing the sizes of the objects to generate an AR landscape outline feature mapping;
The error analysis module is used for comparing the AR landscape outline feature mapping with the historical size data of the AR landscape object, identifying and calculating the size error, and calibrating the size to be adjusted to obtain AR landscape size calibration data;
The data synchronization module updates size and position information in a three-dimensional AR landscape database based on AR landscape size calibration data, automatically observes and records the size change of the differential area, and generates update deviation data;
The micro-model rendering module analyzes and records key places of geographic coordinate changes based on the updating deviation data, updates geographic position information of AR landscape elements, and obtains a three-dimensional AR landscape model by rendering the micro-model of the AR landscape and updating vision hierarchy matching real-time data of the landscape.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (9)
1. An automatic observation method for AR landscapes is characterized by comprising the following steps:
Calculating an edge intensity map of the AR landscape object based on ambient light data around the AR landscape by comparing color and light intensity, and generating a light edge map;
positioning the object outline of the AR landscape based on the light edge mapping, and analyzing the mountain, building and road characteristics in the AR landscape to obtain AR landscape outline characteristic mapping;
Based on the AR landscape contour feature mapping, adopting a digital image processing technology to observe real-time dimension parameters of an AR landscape object, calibrating dimension errors in an AR landscape image, and adjusting proportional dimensions to obtain AR landscape dimension calibration data;
Based on the AR landscape size calibration data, comparing the AR landscape size calibration data with historical AR landscape size data, and automatically observing real-time changes of the AR landscape by using artificial intelligence to obtain updated deviation data;
Based on the updating deviation data, the differentiated geographic deviation points are analyzed and identified, and the landscape information points needing to be changed and added are calibrated to obtain geographic information updating points;
based on the geographic information updating points, a geometric transformation algorithm is adopted to update a three-dimensional AR landscape database, AR landscape elements in the database are adjusted, and landscape layers in the three-dimensional model are rendered to generate a three-dimensional AR landscape model.
2. The AR landscape automatic observation method according to claim 1, wherein the light ray edge map comprises a light intensity difference map, a color gradient map and a combination result, the AR landscape contour feature map comprises an image data set of a terrain contour, a building contour and a road contour, the AR landscape size calibration data comprises a size ratio map with calibrated parameters consistent with real world proportions, the update deviation data comprises a record of size change, position movement and landscape elements, the geographic information update points comprise positions of mountains, buildings and roads needing to be updated and added, and the three-dimensional AR landscape model comprises a visual display of calibrated landscape elements, multi-level landscape and landscape features.
3. The automatic observation method for AR landscape according to claim 1, wherein the step of calculating an edge intensity map of an AR landscape object based on ambient light data around the AR landscape by comparing color and light intensity, and generating a light edge map is specifically as follows:
based on the ambient light data around the AR landscape, measuring the intensity and color of light in a differential time period, recording data of a plurality of time points, and analyzing the light change rule to obtain an ambient light change trend graph;
identifying the change of light reflection intensity based on the environment light change trend graph, marking key change points, and positioning potential object edge positions to obtain an edge initialization mark graph;
and processing the marked edges in the edge initialization mark graph based on the edge initialization mark graph, adjusting the recognition degree of the edges, optimizing the edge line representation in the image, and generating the light edge mapping.
4. The automatic observation method for AR landscape according to claim 1, wherein the step of locating the object contour of the AR landscape based on the ray edge map, analyzing the features of mountain, building and road in the AR landscape, and obtaining the AR landscape contour feature map is specifically:
based on the ray edge mapping, measuring edge intensity in an edge initialization mark image, and analyzing and positioning the edges of the geographic shape and the artificial structure through an edge intensity map to obtain an object boundary map;
Distinguishing AR landscapes of natural and artificial structures based on the object boundary map, classifying mountain, building and road elements, drawing and identifying the distinction of each type of elements, and obtaining a category contour map;
Based on the category profile, integrating the analysis data, defining visual representation parameters, including color and texture, for each landscape, analyzing the view of geographic and artificial features, and generating an AR landscape profile map.
5. The automatic observation method for AR landscape according to claim 1, wherein based on the AR landscape contour feature map, using a digital image processing technique, real-time dimension parameters of an AR landscape object are observed, dimension errors in an AR landscape image are calibrated, and proportional dimensions are adjusted, so as to obtain AR landscape dimension calibration data, which comprises the steps of:
based on the AR landscape outline feature mapping, collecting real-time dimension parameters associated with the AR landscape object, and re-measuring the dimension of the AR landscape object if the mapping data deviate from the real-time observation data, so as to generate updated dimension parameter data;
based on the updated size parameter data, performing contrast analysis on the image size of each AR landscape object by adopting a Kalman filtering algorithm, and if the detected size error exceeds a preset threshold, adjusting the error according to the proportional size to generate size calibration intermediate data;
The Kalman filtering algorithm is according to the formula
；
Wherein,To update the state estimate based on real-time observations,In order to be based on the predicted state at the last moment,For the purpose of real-time observation of the values,In order for the kalman gain to be achieved,In order to observe the model, the model is,For the purpose of innovative noise adjustment parameters,In order to dynamically adjust the coefficient of the coefficient,Is an environment dependent parameter;
Based on the size calibration intermediate data, the adjusted proportional size data is applied to an AR landscape model, and the size of the landscape object is matched with the real-time measured value to obtain AR landscape size calibration data.
6. The automatic observation method for AR landscape according to claim 1, wherein based on the AR landscape size calibration data, comparing with the historical AR landscape size data, using artificial intelligence, automatically observing real-time changes of AR landscape, the step of obtaining updated deviation data is specifically:
Based on the AR landscape size calibration data, analyzing historical size information of the AR landscape position, and recording size parameters including landscape element data through numerical comparison to obtain historical and real-time size comparison records;
Based on the history and real-time size comparison record, performing difference analysis of the history and the real-time size, determining the size change of the region, including the establishment of a new building and the dismantling of an old building, marking the changed size region, and generating a size change analysis result;
Based on the size change analysis result, the identified regional size change is automatically observed and recorded by using artificial intelligence, the position of the change area and the value of the size change are measured, and the value is updated into an AR landscape model to generate updated deviation data.
7. The AR landscape automatic observation method according to claim 1, wherein the steps of analyzing and identifying differentiated geographical deviation points based on the updated deviation data, calibrating landscape information points to be changed and added, and obtaining geographical information update points are specifically as follows:
Based on the updated deviation data, analyzing the size and position changes of AR landscape records, classifying and recording the changes of each landscape element, and recording the size changes and the space movements of various objects to obtain a changed geographic coordinate record;
Analyzing and recording key places of geographic coordinate change based on the change geographic coordinate record, including areas of natural terrain change, classifying and marking update requirements of place change, and generating change place classification marks;
And analyzing the adjusted and newly added landscape information points based on the change place classification marks, including new building outlines, road extension and adjustment and remodelling of terrains, distributing geographic coordinates and descriptions for each point, and generating geographic information updating points.
8. The automatic observation method for AR landscape according to claim 1, wherein based on the geographical information update points, a geometric transformation algorithm is adopted to update a three-dimensional AR landscape database, AR landscape elements in the database are adjusted, and a landscape layer in a three-dimensional model is rendered, and the step of generating the three-dimensional AR landscape model is specifically as follows:
selecting the associated geographic coordinates in the three-dimensional AR landscape database based on the geographic information updating points, and comparing attribute differences between the geographic information updating points and the coordinates in the database if the coordinates exist in the database, updating the geographic attribute information of the AR landscape elements according to the attribute differences, and generating geographic information matching results;
Based on the geographic information matching result, detecting a micro-model structure of an AR landscape element in a database, and if the structure is marked as outdated and does not accord with new attribute information, adjusting the layout of the micro-model by using the new attribute parameters, including modifying the texture, the size and the position of the micro-model, and generating a micro-model adjustment result;
And rendering the adjusted micro model based on the micro model adjustment result, and performing light shadow and texture rendering to strengthen the visual effect of the micro model to match with the AR display requirement and obtain the three-dimensional AR landscape model.
9. An AR landscape automatic observation system, characterized in that it is an AR landscape automatic observation method according to any one of claims 1 to 8, the system comprising:
the environment monitoring module records the change of light along with time based on the ambient light data around the AR landscape, identifies and marks the area where the light changes, and positions objects to obtain light edge mapping;
The size capturing module is used for measuring the sizes of a plurality of objects in the AR landscape in real time based on the light edge mapping, and generating an AR landscape contour feature mapping by analyzing the sizes of the objects and positioning the contours of the objects;
the error analysis module is used for comparing the AR landscape outline feature mapping with the historical size data of the AR landscape object, identifying and calculating the size error, and calibrating the size to be adjusted to obtain AR landscape size calibration data;
the data synchronization module updates size and position information in a three-dimensional AR landscape database based on the AR landscape size calibration data, automatically observes and records the size change of the differential area, and generates updated deviation data;
The micro-model rendering module analyzes and records key places of geographic coordinate changes based on the updating deviation data, updates geographic position information of AR landscape elements, and updates vision hierarchy matching real-time data of the landscape by rendering the micro-model of the AR landscape to obtain a three-dimensional AR landscape model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410903219.6A CN118447196B (en) | 2024-07-08 | 2024-07-08 | AR landscape automatic observation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410903219.6A CN118447196B (en) | 2024-07-08 | 2024-07-08 | AR landscape automatic observation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118447196A true CN118447196A (en) | 2024-08-06 |
| CN118447196B CN118447196B (en) | 2024-08-30 |
Family
ID=92314545
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410903219.6A Active CN118447196B (en) | 2024-07-08 | 2024-07-08 | AR landscape automatic observation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118447196B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835202A (en) * | 2015-05-20 | 2015-08-12 | 中国人民解放军装甲兵工程学院 | Quick three-dimensional virtual scene constructing method |
| US20180314888A1 (en) * | 2017-05-01 | 2018-11-01 | Microsoft Technology Licensing, Llc | Real time object surface identification for augmented reality environments |
| KR101989969B1 (en) * | 2018-10-11 | 2019-06-19 | 대한민국 | Contents experience system of architectural sites based augmented reality |
| US20190303725A1 (en) * | 2018-03-30 | 2019-10-03 | Fringefy Ltd. | Neural network training system |
| CN112668085A (en) * | 2020-12-31 | 2021-04-16 | 杭州群核信息技术有限公司 | Home decoration plane automatic design method and device, computer equipment and storage medium |
| CN113552942A (en) * | 2021-07-14 | 2021-10-26 | 海信视像科技股份有限公司 | Method and equipment for displaying virtual object based on illumination intensity |
| US20230089366A1 (en) * | 2017-08-02 | 2023-03-23 | State Farm Mutual Automobile Insurance Company | Augmented reality system for real-time damage assessment |
| CN116563503A (en) * | 2022-01-27 | 2023-08-08 | 腾讯科技（深圳）有限公司 | Augmented reality-based display processing method, device, equipment and storage medium |
| CN116630429A (en) * | 2023-07-26 | 2023-08-22 | 成都物天物联网科技有限责任公司 | Visual guiding and positioning method and device for docking of vehicle and box and electronic equipment |
| CN117523125A (en) * | 2023-11-14 | 2024-02-06 | 江苏兰德数码科技有限公司 | Rapid building method for three-dimensional block model of building |
-
2024
- 2024-07-08 CN CN202410903219.6A patent/CN118447196B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835202A (en) * | 2015-05-20 | 2015-08-12 | 中国人民解放军装甲兵工程学院 | Quick three-dimensional virtual scene constructing method |
| US20180314888A1 (en) * | 2017-05-01 | 2018-11-01 | Microsoft Technology Licensing, Llc | Real time object surface identification for augmented reality environments |
| US20230089366A1 (en) * | 2017-08-02 | 2023-03-23 | State Farm Mutual Automobile Insurance Company | Augmented reality system for real-time damage assessment |
| US20190303725A1 (en) * | 2018-03-30 | 2019-10-03 | Fringefy Ltd. | Neural network training system |
| KR101989969B1 (en) * | 2018-10-11 | 2019-06-19 | 대한민국 | Contents experience system of architectural sites based augmented reality |
| CN112668085A (en) * | 2020-12-31 | 2021-04-16 | 杭州群核信息技术有限公司 | Home decoration plane automatic design method and device, computer equipment and storage medium |
| CN113552942A (en) * | 2021-07-14 | 2021-10-26 | 海信视像科技股份有限公司 | Method and equipment for displaying virtual object based on illumination intensity |
| CN116563503A (en) * | 2022-01-27 | 2023-08-08 | 腾讯科技（深圳）有限公司 | Augmented reality-based display processing method, device, equipment and storage medium |
| CN116630429A (en) * | 2023-07-26 | 2023-08-22 | 成都物天物联网科技有限责任公司 | Visual guiding and positioning method and device for docking of vehicle and box and electronic equipment |
| CN117523125A (en) * | 2023-11-14 | 2024-02-06 | 江苏兰德数码科技有限公司 | Rapid building method for three-dimensional block model of building |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118447196B (en) | 2024-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111563442B (en) | Slam method and system for fusing point cloud and camera image data based on laser radar | |
| CN113139453B (en) | Orthoimage high-rise building base vector extraction method based on deep learning | |
| Haala et al. | Extraction of buildings and trees in urban environments | |
| Brilakis et al. | Toward automated generation of parametric BIMs based on hybrid video and laser scanning data | |
| US8396284B2 (en) | Smart picking in 3D point clouds | |
| CN108052624A (en) | Processing Method of Point-clouds, device and computer readable storage medium | |
| US10115165B2 (en) | Management of tax information based on topographical information | |
| US20220044072A1 (en) | Systems and methods for aligning vectors to an image | |
| Mousa et al. | Building detection and regularisation using DSM and imagery information | |
| Zhang et al. | Lidar-guided stereo matching with a spatial consistency constraint | |
| Khayyal et al. | Creation and spatial analysis of 3D city modeling based on GIS data | |
| CN115222884A (en) | Space object analysis and modeling optimization method based on artificial intelligence | |
| CN115035251B (en) | Bridge deck vehicle real-time tracking method based on field enhanced synthetic data set | |
| CN115512247A (en) | Regional building damage grade assessment method based on image multi-parameter extraction | |
| CN105631849B (en) | The change detecting method and device of target polygon | |
| Forlani et al. | Building reconstruction and visualization from lidar data | |
| CN118447196B (en) | AR landscape automatic observation method and system | |
| CN112069445A (en) | 2D SLAM algorithm evaluation and quantification method | |
| CN116740307A (en) | Smart city three-dimensional model construction method | |
| CN116524143A (en) | GIS map construction method | |
| CN113487741B (en) | Dense three-dimensional map updating method and device | |
| CN109598793B (en) | Manufacturing method and device for quickly modifying vegetation and water body based on oblique photogrammetry | |
| Wang et al. | Least-squares building model fitting using aerial photos and LiDAR data | |
| Ahmed et al. | Delineating planner surfaces from correlation-based DEMS | |
| CN110796042A (en) | High-resolution remote sensing image building extraction method based on form transformation of offset shadow sample |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |