CN-122019677-A - Multi-source spatial data processing method and system for urban design

CN122019677ACN 122019677 ACN122019677 ACN 122019677ACN-122019677-A

Abstract

The application discloses a multisource spatial data processing method and system for urban design, and relates to the field of urban design; the method comprises the steps of collecting multisource space data of a city target area in real time, judging whether first multisource space data of abnormality exists in the multisource space data, correcting the first multisource space data, calculating first confidence coefficient of the corrected multisource space correction data, providing planning decision risk early warning and suggestion for the city target area according to the multisource space correction data and the first confidence coefficient, or calculating second confidence coefficient of the first multisource space data, and providing planning decision risk early warning and suggestion for the city target area according to the first multisource space data and the second confidence coefficient. The method can effectively identify and process the abnormal situation of the multisource space data in the urban design, and provide more accurate risk early warning and suggestion for urban planning decision-making by correcting the abnormal data or evaluating the confidence coefficient of the abnormal data, so as to avoid decision-making deviation caused by data distortion.

Inventors

ZHANG SHU
ZUO QI
WANG NING
YUAN SHENGMING

Assignees

青岛市城市规划设计研究院

Dates

Publication Date: 20260512
Application Date: 20251205

Claims (10)

1. A multi-source spatial data processing method for urban design, comprising the steps of: Acquiring multisource space data of a city target area in real time; Judging whether abnormal first multi-source space data exists in the multi-source space data or not; When the first multi-source space data exists, correcting the first multi-source space data to obtain multi-source space correction data, calculating a first confidence coefficient of the multi-source space correction data, and providing planning decision risk early warning and suggestion for the urban target area according to the multi-source space correction data and the first confidence coefficient, or And calculating a second confidence coefficient of the first multi-source space data, and providing planning decision risk early warning and suggestion for the urban target area according to the first multi-source space data and the second confidence coefficient.
2. The multi-source spatial data processing method for urban design according to claim 1, wherein the multi-source spatial data includes point cloud data and environmental data; the step of acquiring the multisource spatial data of the urban target area in real time further comprises the following steps: acquiring a time table and a space range of temporary activities of the urban target area; The step of judging whether the multi-source spatial data has abnormal first multi-source spatial data specifically comprises the following steps: Extracting multispectral reflection characteristics of first point cloud data with reflection intensity values exceeding preset intensity values from the point cloud data, searching a spectrum curve matched with the multispectral reflection characteristics in a preset hyperspectral characteristic library, and defining the first point cloud data as false space data after searching; Extracting first environmental data affected by temporary activities from the environmental data according to the schedule and the spatial range; When a first difference value between the first environmental data and second environmental data normalized by the urban target area history exceeds a first preset value, and a second difference value between the first environmental data and the urban target area environmental data which is not affected by temporary activities exceeds a second preset value, defining that the first environmental data lose space representativeness; when the first point cloud data is false space data and/or the first environment data loses space representativeness, judging and determining first multi-source space data with abnormality in the multi-source space data; the first multi-source spatial data includes first point cloud data and/or first environment data.
3. The method for processing multi-source spatial data for urban design according to claim 2, wherein the step of calculating the first confidence level of the multi-source spatial correction data comprises: Evaluating a data quality score, a context interference degree score, a correction effect score, and a cross-source consistency score of the first multi-source spatial data; Respectively distributing weight coefficients for the data quality score, the situation interference degree score, the correction effect score and the cross-source consistency score; and calculating the first confidence coefficient of the multisource spatial correction data according to the data quality score, the situation interference degree score, the correction effect score, the cross-source consistency score and the weight coefficient corresponding to each of the data quality score, the situation interference degree score and the correction effect score.
4. The method of claim 3, wherein the multi-source spatial data further comprises video stream data, audio data, and reflected light intensity and reflected light direction of the point cloud data; the step of evaluating the contextual interference level score of the first multi-source spatial data specifically comprises: Calculating the variance of the reflected light intensity of the point cloud data in the set time according to the reflected light intensity and the reflected light direction, and the directional change frequency of the reflected peak value; Calculating a dynamic reflection liveness value of the point cloud data according to the variance and the directional change frequency; Calculating the gradient change rate of an image in the video stream data, and calculating the inter-frame motion blur index in the video stream data according to the gradient change rate of the image; searching first voiceprint data matched with the voiceprint of the audio data in a voiceprint database operated by the preset heat radiation equipment; When the first voiceprint data is found, calculating the temperature gradient in the environmental temperature data and the area of the area where the temperature gradient exceeds a preset threshold value; calculating a heat source intensity index of the environmental temperature data according to the temperature gradient and the area of the region; And evaluating the context interference degree score of the first multi-source spatial data according to the dynamic reflection liveness value, the motion blur index and the heat source intensity index.
5. A multi-source spatial data processing method for urban design according to claim 3, wherein the step of correcting the first multi-source spatial data to obtain multi-source spatial correction data comprises: Collecting historical normalized point cloud data of a region corresponding to the first point cloud data and/or normalized point cloud data in a city target region which is not affected by temporary activities; reconstructing the first point cloud data according to the historical normalized point cloud data and/or the normalized point cloud data to obtain point cloud reconstruction correction data, and/or, Collecting historical normalized environment data of a region corresponding to the first environment data and/or normalized environment data in a city target region which is not affected by temporary activities; Correcting the first environmental data according to the historical normalized environmental data and/or normalized environmental data to obtain environmental correction data; the multi-source spatial correction data includes point cloud reconstruction correction data and/or environmental correction data.
6. The method of claim 5, wherein the step of evaluating the correction effect score for the first multi-source spatial data comprises: Calculating a point cloud deviation root mean square error between the point cloud reconstruction correction data and preset standard reference data; calculating the matching degree between the reflection intensity statistical distribution of the point cloud reconstruction correction data and the reflection intensity distribution of the preset material; calculating a first correction effect score of the point cloud reconstruction correction data according to the point cloud deviation root mean square error and the matching degree; calculating a temperature standard residual error and a humidity calibration residual error of the environment correction data and preset standard environment data; calculating a second correction effect score of the environment correction data according to the temperature standard residual error and the humidity standard residual error; and carrying out weighted aggregation calculation on the first correction effect score and the second correction effect score to obtain the correction effect score of the first multi-source space data.
7. A multi-source spatial data processing method for urban design according to claim 3, characterized in that the step of evaluating the data quality score of the first multi-source spatial data comprises in particular: calculating sparsity and noise level of the first point cloud data, and calculating a first quality score of the first point cloud data according to the sparsity and the noise level; Calculating stability and a loss rate of the first environmental data during acquisition, and calculating a second mass fraction of the first environmental data according to the stability and the loss rate; evaluating a data quality score of the first multi-source spatial data according to the first quality score and the second quality score; the step of evaluating the contextual interference level score of the first multi-source spatial data specifically comprises: calculating a degree value of the temporary activity of the first point cloud data and a first degree value of the temporary activity of the first environment data according to a time table and a space range of the temporary activity; and evaluating the context interference degree score of the first multi-source spatial data according to the degree value and the first degree value.
8. The method for processing multi-source spatial data for urban design according to claim 1, wherein the multi-source spatial data comprises laser pulse reflected signals of different polarization directions; the step of judging whether the multi-source spatial data has abnormal first multi-source spatial data comprises the following steps: Extracting a first laser pulse reflected signal matched with the laser pulse transmitting signal mark from the laser pulse reflected signal; Calculating the linear polarization degree and the polarization angle of the first laser pulse reflected signal within a first set time; Judging whether the first laser pulse reflected signal has a second laser pulse reflected signal with the linear polarization degree and the polarization angle changing mode consistent with the preset mode in the second set time; if yes, judging whether the geometric forms of the second laser pulse reflected signal and the historical normalized point cloud data are consistent, and if not, defining the second laser pulse reflected signal as false space data; if not, judging whether the first laser pulse reflected signal has a third laser pulse reflected signal with a reflected intensity value exceeding a preset reflected intensity threshold value or not, if so, defining the third laser pulse reflected signal as saturation artifact data; when a second laser pulse reflected signal or a third laser pulse reflected signal exists in the first laser pulse reflected signal, judging and determining that abnormal first multi-source space data exists in the multi-source space data; the first multi-source spatial data includes either dummy spatial data or saturation artifact data.
9. The method for processing multi-source spatial data for a city design of claim 8, wherein the step of calculating the second confidence of the first multi-source spatial data comprises: Calculating the matching intensity of the laser pulse reflected signal and the laser pulse transmitted signal, the degree of modeling of the linear polarization degree and the polarization angle of the second laser pulse reflected signal, the degree of deviation between the geometric form formed by the second laser pulse reflected signal and the normalized ground object, and the degree of approaching the reflection intensity value of the third laser pulse reflected signal to a preset reflection intensity threshold value; respectively distributing first weight coefficients for the matching strength, the modeling degree, the deviation degree and the approaching degree; and calculating a second confidence coefficient of the first multisource spatial data according to the matching strength, the modeling degree, the deviation degree, the proximity degree and the corresponding first weight coefficient.
10. A multi-source spatial data processing system for urban design, comprising: the acquisition module is used for acquiring multisource space data of the urban target area in real time; The judging module is used for judging whether the multi-source space data has abnormal first multi-source space data or not; The processing module is used for correcting the first multi-source space data to obtain multi-source space correction data, calculating first confidence coefficient of the multi-source space correction data, providing planning decision risk early warning and suggestion for the urban target area according to the multi-source space correction data and the first confidence coefficient, or calculating second confidence coefficient of the first multi-source space data, and providing planning decision risk early warning and suggestion for the urban target area according to the first multi-source space data and the second confidence coefficient.

Description

Multi-source spatial data processing method and system for urban design Technical Field The application relates to the field of urban design, in particular to a multi-source spatial data processing method and system for urban design. Background In modern city planning and management, the processing of urban space data is a core link, and particularly in the aspect of improving resident livability experience, it is increasingly important to perform fine assessment on walking comfort and microclimate of a specific urban area. This typically requires integration of high resolution satellite remote sensing images, unmanned laser radar point cloud data, and ground environment sensor networks from multiple sources of spatial data to form a comprehensive and detailed digital view of the urban environment. However, urban environments are not static systems. In urban design, when the multisource spatial data processing method needs to integrate laser radar point cloud and ground environment sensor data, the prior art faces a significant technical problem of how to construct a fusion mechanism capable of adaptively evaluating and correcting the inherent bias of the data source, which is derived from the composite scenario. On the one hand, the physical structures introduced by temporary urban activities, such as metal sculptures or glass art devices of high reflectivity, can lead to false spatial information or anomalous reflection areas in the lidar data that cannot be effectively identified by existing cleaning logic. The strong reflected signals or multipath reflected signals generated by these temporary structures may cause the lidar receiver to saturate, generate data overflow or artifacts, or record false point cloud data, and the system preset cleaning logic has difficulty in effectively identifying and rejecting these anomalies. On the other hand, the contemporaneous construction activities change the local microenvironment of the ground sensor, for example stacking power generation equipment or building large tents in the vicinity of the sensor, so that their data, although physically accurate, lose spatial representation of the normalized urban environment. Heat and exhaust gases from power plants, or large tents, from blocking air circulation, can cause the sensor measurements to deviate significantly from the normalized level in the area, making it unusable for assessing normalized urban microclimate. In the complex case of such multiple factor interleaving, in existing data processing flows, engineers based on experience give higher weights to specific data sources, may instead amplify these hidden, context-dependent data distortions. The system may rely excessively on temperature, humidity and wind speed data distorted by temporary facility effects, while false point clouds or abnormally reflected areas contained in the lidar data may be "corrected" by mistake or given less confidence in the fusion process, resulting in "ignoring" or "warping" the critical information it carries about the real urban space structure. Finally, when the city planner makes design decisions based on the fusion result with deviation, the microclimate comfort level and the pedestrian crowding degree of the area under the normal operation can be erroneously estimated, so that the design scheme is invalid, and the actual comfort experience of residents can not be effectively improved. In view of the above, there is a need in the art for improvements. Disclosure of Invention The application discloses a multisource spatial data processing method for urban design, and aims to solve the problem that false information, abnormal reflection areas or data losing spatial representativeness in multisource spatial data are difficult to effectively identify and correct in the existing urban spatial data processing method in the face of complex situations, so that urban planning decision deviation is caused. The technical scheme of the application is as follows: In a first aspect, the application discloses a multi-source spatial data processing method for urban design, comprising the following steps: Acquiring multisource space data of a city target area in real time; Judging whether abnormal first multi-source space data exists in the multi-source space data or not; When the first multi-source space data exists, correcting the first multi-source space data to obtain multi-source space correction data, calculating a first confidence coefficient of the multi-source space correction data, and providing planning decision risk early warning and suggestion for the urban target area according to the multi-source space correction data and the first confidence coefficient, or And calculating a second confidence coefficient of the first multi-source space data, and providing planning decision risk early warning and suggestion for the urban target area according to the first multi-source space data and the second confidence coefficient. According to t