CN114663883B - Point cloud data correction method and device, electronic equipment and storage medium - Google Patents
Point cloud data correction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114663883B CN114663883B CN202210573707.6A CN202210573707A CN114663883B CN 114663883 B CN114663883 B CN 114663883B CN 202210573707 A CN202210573707 A CN 202210573707A CN 114663883 B CN114663883 B CN 114663883B
- Authority
- CN
- China
- Prior art keywords
- weather
- target area
- point cloud
- cloud data
- data
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/02—Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Environmental & Geological Engineering (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Image Processing (AREA)
Abstract
The application relates to the field of joint processing of actual scene environment information and 3D point cloud data, in particular to a point cloud data correction method, a point cloud data correction device, electronic equipment and a storage medium, wherein the point cloud data correction method comprises the steps of obtaining environment information of a target area, judging whether the environment information is abnormal weather of a preset type or not based on the environment information, and judging whether the environment information is abnormal weather of the preset type or not; if the prediction result is abnormal weather, determining a correction coefficient according to the environmental information and the mapping relation between the environmental information and the correction coefficient; after point cloud data of a target area are obtained, denoising processing is carried out on the point cloud data, denoising data can be obtained, and then the denoising data are corrected based on a correction coefficient. The method and the device are convenient for obtaining more accurate point cloud data in abnormal weather.
Description
Technical Field
The present disclosure relates to the field of joint processing of actual scene environment information and 3D point cloud data, and in particular, to a method and an apparatus for correcting point cloud data, an electronic device, and a storage medium.
Background
With the continuous development of novel 3D sensors and creation technologies, it is possible to capture a 3D point cloud scene and a model with good visual quality in real time. The point cloud data refers to a set of vectors in a three-dimensional coordinate system, namely a plurality of data points, and the common point cloud data file is in the form of a 3D coordinate file. These vectors are usually expressed in terms of X, Y, Z three-dimensional coordinates and are generally used primarily to represent the shape of the external surface of an object; the point cloud data may also include parameters such as RGB color, gray value, reflection intensity, and acquisition time of a point.
The measurement of the road is the conventional application field of point cloud data, and when the road is measured, the point cloud data of the road is usually obtained by adopting a loading laser radar, but in abnormal weather, such as rainy days or haze weather, the reflection intensity parameters in the point cloud data are greatly influenced by the abnormal weather, and further the measured data are inaccurate.
Disclosure of Invention
In order to obtain more accurate point cloud data in abnormal weather, the application provides a point cloud data correction method and device, electronic equipment and a storage medium.
In a first aspect, the present application provides a method for correcting point cloud data, which adopts the following technical scheme:
a method for correcting point cloud data comprises the following steps:
acquiring environmental information of a target area, wherein the environmental information comprises a weather type and pollutant concentration;
judging whether the weather is abnormal weather of a preset type or not based on the environmental information;
if yes, determining a correction coefficient based on the environmental information and the mapping relation between the environmental information and the correction coefficient;
acquiring point cloud data of the target area;
denoising the point cloud data to obtain denoised data;
and correcting the de-noised data based on the correction coefficient.
By adopting the technical scheme, after the environmental information of the target area is judged to be abnormal weather of the preset type, the correction coefficient for correcting the reflection intensity in the point cloud data corresponding to the current environmental information can be determined based on the environmental information; and after the point cloud data are subjected to denoising processing, the denoising data are corrected through a correction coefficient, and then accurate point cloud data can be obtained.
In one possible implementation manner, the obtaining environmental information of the target area includes:
acquiring position information of a target area;
and acquiring the weather type and the pollutant concentration of the target area based on the position information.
By adopting the technical scheme, the weather type and the pollutant concentration are obtained through the position information of the target area, the boundary is simple, the calculated amount is small, the real-time obtaining is convenient, and the efficiency is high.
In one possible implementation manner, the obtaining environmental information of the target area includes:
acquiring a live-action image acquired aiming at the target area;
determining the weather type of the target area based on the live-action image and the trained weather classification model;
and acquiring the pollutant concentration of the target area.
By adopting the technical scheme, the weather type acquired through the position information has regional limitation, so that the type of abnormal weather is judged through the live-action image in the target area, the accuracy is higher, and more accurate correction parameters can be conveniently determined.
In a possible implementation manner, the live-action image includes a shooting location and a shooting time, and the determining the weather type of the target area based on the live-action image and the trained weather classification model includes:
inputting the live-action image into a trained weather classification model to obtain a predicted weather type;
determining qualified weather types based on the shooting position and the shooting time, wherein the qualified weather types are all weather types which can be present in the target area;
judging whether the predicted weather type belongs to the qualified weather type;
and if so, determining the predicted weather type as the weather type of the target area.
By adopting the technical scheme, after the weather type represented in the live-action image, namely the forecast weather type, is obtained through the weather classification model, the obtained forecast weather type is further judged through the shooting time and the shooting position of the live-action image, the probability of obtaining the wrong abnormal weather type is further reduced, and further the parameters can be corrected more accurately.
In one possible implementation manner, the modifying the denoised data based on the modification coefficient includes:
acquiring the duration period of the abnormal weather;
determining an abnormal data point based on the acquisition time of each data point in the de-noised data, wherein the abnormal data point is a data point with the acquisition time within the duration period;
and correcting the abnormal data points based on the correction coefficient.
By adopting the technical scheme, the point cloud data is corrected, namely the data points in the point cloud data collected within the duration of the abnormal weather are corrected, so that the duration of the abnormal weather needs to be determined, and then the data points affected by the abnormal weather are determined based on the duration.
In one possible implementation manner, the modifying the denoised data based on the modification coefficient includes:
if the weather types are at least two types and at least one abnormal weather type is included in the weather types, judging whether the abnormal weather type is a preset marked abnormal weather;
if so, acquiring the acquisition period of the de-noising data;
and if the acquisition period is smaller than a preset period, correcting all the de-noising data based on the correction coefficient, wherein the preset period is the influence time on the reflection intensity before and after the marked abnormal weather appears.
By adopting the technical scheme, in practice, before and after the abnormal weather is marked, the environment in the target area still influences the reflection intensity in the point cloud data, for example, the rainstorm weather, before and after the rainstorm, the water vapor content in the air is high, and meanwhile, rainwater exists on a building or a road surface, so that a reflecting mirror surface is easily formed, and therefore, all the point cloud data should be corrected.
In a possible implementation manner, the obtaining of the duration period of the abnormal weather includes:
determining the starting time of the target area entering the abnormal weather, and determining the ending time of the target area ending the abnormal weather;
determining a duration period of the exceptional weather based on the start time and the end time.
In a second aspect, the present application provides a device for correcting point cloud data, which adopts the following technical scheme:
an apparatus for correcting point cloud data, comprising:
the environment information acquisition module is used for acquiring environment information of a target area, wherein the environment information comprises a weather type and pollutant concentration;
the judging module is used for judging whether the weather is abnormal weather of a preset type or not based on the environmental information;
the correction coefficient determining module is used for determining a correction coefficient based on the environment information and the mapping relation between the environment information and the correction coefficient;
the point cloud data acquisition module is used for acquiring point cloud data of the target area;
the denoising module is used for denoising the point cloud data to obtain denoised data;
and the correction module is used for correcting the de-noising data based on the correction coefficient.
By adopting the technical scheme, after the environmental information of the target area is judged to be abnormal weather of the preset type, the device can determine a correction coefficient for correcting the reflection intensity in the point cloud data corresponding to the current environmental information based on the environmental information; and after the point cloud data are subjected to denoising processing, the denoising data are corrected through the correction coefficient, and accurate point cloud data can be obtained.
In a possible implementation manner, when the environment information obtaining module obtains the environment information of the target area, the environment information obtaining module is specifically configured to:
acquiring position information of a target area;
and acquiring the weather type and the pollutant concentration of the target area based on the position information.
In a possible implementation manner, when the environment information obtaining module obtains the environment information of the target area, the environment information obtaining module is specifically configured to:
acquiring a live-action image acquired aiming at the target area;
determining the weather type of the target area based on the live-action image and the trained weather classification model;
and acquiring the pollutant concentration of the target area.
In a possible implementation manner, when the environment information obtaining module obtains the environment information of the target area, the environment information obtaining module is specifically configured to:
the live-action image comprises a shooting position and shooting time;
inputting the live-action image into a trained weather classification model to obtain a predicted weather type;
determining qualified weather types based on the shooting position and the shooting time, wherein the qualified weather types are all weather types which can be present in the target area;
judging whether the predicted weather type belongs to the qualified weather type or not based on the shooting position and the shooting time;
and if so, determining the predicted weather type as the weather type of the target area.
In a possible implementation manner, when the modification module modifies the de-noised data based on the modification coefficient, the modification module is specifically configured to:
acquiring the duration period of the abnormal weather;
determining an abnormal data point based on the acquisition time of each data point in the de-noised data, wherein the abnormal data point is a data point with the acquisition time within the duration period;
and correcting the abnormal data points based on the correction coefficient.
In a possible implementation manner, when the modification module modifies the de-noised data based on the modification coefficient, the modification module is specifically configured to:
if the weather types are at least two types and at least one abnormal weather type is included in the weather types, judging whether the abnormal weather type is a preset marked abnormal weather or not;
if so, acquiring the acquisition period of the de-noising data;
and if the acquisition period is smaller than a preset period, correcting all the de-noising data based on the correction coefficient, wherein the preset period is the influence time on the reflection intensity before and after the abnormal weather is marked.
In a possible implementation manner, when the modification module modifies the de-noised data based on the modification coefficient, the modification module is specifically configured to;
determining the starting time of the target area entering the abnormal weather, and determining the ending time of the target area ending the abnormal weather;
determining a duration period of the exceptional weather based on the start time and the end time.
In a third aspect, the present application provides an electronic device, which adopts the following technical solutions:
an electronic device, comprising:
at least one processor;
a memory;
at least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, the at least one application configured to: and executing the point cloud data correction method.
In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solutions:
a computer-readable storage medium, comprising: a computer program is stored which can be loaded by a processor and which implements the above-described method of correcting point cloud data.
In summary, the present application includes at least one of the following beneficial technical effects:
1. after the environmental information of the target area is judged to be abnormal weather of a preset type, a correction coefficient for correcting the reflection intensity in the point cloud data corresponding to the current environmental information can be determined based on the environmental information; after the point cloud data are subjected to denoising processing, the denoising data are corrected through a correction coefficient, and then accurate point cloud data can be obtained;
2. the weather type acquired through the position information has regional limitation, so that the type of abnormal weather is judged through the live-action image in the target area, the accuracy is higher, and more accurate correction parameters can be conveniently determined;
3. after the weather type represented in the live-action image, namely the predicted weather type, is obtained through the weather classification model, the obtained predicted weather type is further judged according to the shooting time and the shooting position of the live-action image, the probability of obtaining the wrong abnormal weather type is further reduced, and therefore the parameters can be conveniently determined and corrected more accurately.
Drawings
FIG. 1 is a schematic flow chart of a method for correcting point cloud data according to an embodiment of the present disclosure;
FIG. 2 is a schematic structural diagram of an apparatus for correcting point cloud data according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
The present application is described in further detail below with reference to figures 1-3.
A person skilled in the art, after reading the present description, may make modifications as required without inventive contribution to the present embodiments, but shall be protected by the patent laws within the scope of the claims of the present application.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship, unless otherwise specified.
The laser emitted by the laser emitting device of the laser radar is reflected by the surface of a measured target and then is received by the laser collecting device, and the echo intensity, namely the reflection intensity in the point cloud data, is measured. Typically, the reflection intensity is related to the surface material of the object to be measured, the roughness, the direction of the incident angle, the emission energy of the instrument, and the laser wavelength. However, in abnormal weather conditions, such as haze, sand, rain and snow, the laser may be additionally reflected/refracted in the propagation path to consume energy, thereby causing a large difference between the reflection intensity measured by the laser collecting device and the actual reflection intensity.
The laser radar can be applied to various scenes, but in reality, the laser radar is applied to more or outdoor road measurement/mapping work, in the embodiment of the application, the scene where the laser radar is applied to road measurement is taken as an example, point cloud data obtained in road measurement is processed, but the application field and the scene of the point cloud data correction method in the embodiment of the application are not limited.
The embodiment of the application provides a point cloud data trimming method, which is executed by electronic equipment, and with reference to fig. 1, the method includes steps S101 to S106, where:
step S101, obtaining environmental information of a target area, wherein the environmental information comprises weather types and pollutant concentrations.
In the embodiment of the present application, the environment information of the target area may be updated through real-time measurement, or may be obtained within a preset time. The specific classification of weather types is not limited in any way in the embodiment of the present application, and may be, for example, sunny days, cloudy days, haze, and raised sand; reference may be made to the weather classification criteria rules published by the weather bureau. Meanwhile, the concentration of the pollutants can also affect the propagation of the laser, for example, in dust raising weather, when the concentration of the dust in the air is high and when the concentration of the dust is low, the influence on the reflection intensity in the point cloud data is different. Pollutant concentration is under different weather types, and its pollutant that corresponds is also different, for example when haze weather, is exactly the concentration of measuring the haze.
And S102, judging whether the weather is abnormal weather of a preset type or not based on the environmental information.
In the embodiment of the present application, the preset type of abnormal weather is a weather type that can have a large influence on propagation of laser light in the air, such as rainy days, haze, sand dust, snow days, hail, and the like, but the specific preset type of abnormal weather is not specifically limited in the embodiment of the present application.
Step S103, if the weather is abnormal weather of a preset type, determining a correction coefficient based on the environmental information and the mapping relation between the environmental information and the correction coefficient;
specifically, for each abnormal weather of a preset type, a correction coefficient corresponding to each abnormal weather should be set in advance, and meanwhile, for the same type of abnormal weather, different correction coefficients should be corresponding to different degrees, for example, in heavy rain, the correction coefficient is a1, and in medium rain, the correction coefficient is a 2.
And step S104, point cloud data of the target area are obtained.
In the embodiment of the application, the point cloud data of the target area can be obtained in real time, that is, while the laser radar measures the point cloud data, the generated point cloud data is obtained by the electronic device in real time, and at this time, the environmental information of the target area obtained by the electronic device should also be real-time; of course, the electronic device may also acquire complete point cloud data of the target area after the target area is measured, and at this time, the electronic device should acquire historical environment information corresponding to the target area within a time period of point cloud data acquisition.
And S105, denoising the point cloud data to obtain denoised data.
In the embodiment of the application, the original point cloud data often contains a large number of hash points and isolated points, and when the point cloud data is obtained, some noise inevitably appears in the point cloud data due to equipment precision and experience factors of an operator, and the sampling resolution is different. Therefore, denoising of the point cloud data, that is, filtering processing of the point cloud data, is generally the first step flow of the point cloud processing. Only if noise points, outliers, holes, data compression and the like are customized according to subsequent processing in the filtering preprocessing, subsequent application processing such as registration, feature extraction, curved surface reconstruction, visualization and the like can be better performed.
And S106, correcting the de-noised data based on the correction coefficient.
In the embodiment of the application, after the point cloud data is subjected to denoising processing, noise points, discrete points and the like are stripped from the obtained denoising data, that is, most of the denoising data are effective data points. The denoising data is corrected after denoising processing, and compared with the correction of the point cloud data, the processing calculation amount of the electronic equipment can be reduced.
After judging that the environmental information of the target area is abnormal weather of a preset type, the electronic equipment can determine a correction coefficient for correcting the reflection intensity in the point cloud data corresponding to the current environmental information based on the environmental information; and after the point cloud data are subjected to denoising processing, the denoising data are corrected through the correction coefficient, and accurate point cloud data can be obtained.
Further, step S101 may include step SA1 (not shown in the figure) and step SA2 (not shown in the figure), wherein:
step SA1, position information of the target area is acquired.
Specifically, the position information of the target area may be acquired by a GPS or beidou positioning device, or the position information may be inputted by the user.
Step SA2, obtaining the weather type and pollutant concentration of the target area based on the position information.
Specifically, after the location information is determined, the weather information of the target area, that is, including the weather type and the pollutant concentration, may be acquired on the internet based on the location information. It should be noted that, if it is rainy or snowy, the pollutant concentration is the magnitude of the rainfall/snow, and if it is dust and haze, the pollutant concentration is the concentration of the particulate matter in the air.
Further, step S101 may further include step SB1 (not shown), step SB2 (not shown), and step SB3 (not shown), wherein:
and step SB1, acquiring the live-action image collected aiming at the target area.
Specifically, when the laser radar tests the road, the preset image acquisition device acquires live-action images in the target area, and the live-action images may be shot at preset time intervals or shot in real time.
And step SB2, determining the weather type of the target area based on the live-action image and the trained weather classification model.
Specifically, the weather classification model is used for analyzing the live-action image of the target area, so that the weather type can be obtained more accurately. Since the weather information acquired based on the position information is regional, for example, the positions of the point a and the point B in the first area are both predicted to be rainy, but in practice, the area where rain falls is localized, which may cause a situation where the point a actually falls rain and the point B actually falls rain.
And step SB3, acquiring the pollutant concentration of the target area.
In particular, the measurement of the concentration of the contaminant is performed by a sensor. As can be seen from step S101, the concentration of the pollutants may be the magnitude of the rainfall or the concentration of the particulate matters, and therefore, the rainfall sensor, the haze sensor, and the particulate concentration sensor should be set at the setting position of the laser radar correspondingly to the concentration sensors corresponding to various weather types.
Further, step SB2 may include step SB21 (not shown in the figure) -step SB25 (not shown in the figure), in which:
in step SB21, the live view image includes the shooting position and the shooting time.
Specifically, the live view image acquired for the target area should be a full-color image.
And step SB22, inputting the live-action image into the trained weather classification model to obtain the predicted weather type.
Specifically, the trained neural network model, i.e., the weather classification model, can determine scene information in the input live-action image, and further obtain a weather type in the live-action image, i.e., in the target area.
Step SB23, determining a qualified weather type based on the shooting location and the shooting time, the qualified weather type being all weather types that the target area can currently appear.
Specifically, because the weather type and the geographical location are closely related, for example, there are regions where sand-blown weather occurs, but there are regions where sand-blown weather does not occur. By acquiring the shooting position, all weather types which can appear in the area where the shooting position is located are acquired. Each region and all corresponding weather types which can appear in the regions can be preset, after the shooting position is obtained, the region where the position is located is judged, and then all weather types which can appear in the region where the shooting position is located are further determined.
After the weather types possibly appearing in the area where the shooting position is located are determined, screening is performed based on the shooting time, and all the weather types possibly appearing in the shooting area within the shooting time, namely qualified weather types, are determined. For example, in summer, the area a does not snow but rains, and if the shooting area is the area a and the shooting time is summer, the snowing weather is a non-qualified weather type, and the raining weather is a qualified weather type.
Step SB24, judging whether the predicted weather type belongs to a qualified weather type;
and step SB25, if yes, determining that the predicted weather type is the weather type of the target area.
Further, after the corresponding predicted weather type in the live-action image is determined through the weather classification model, the reasonability and the accuracy of the pre-stored weather type are further judged through the shooting position and the shooting time, so that the weather type at the shooting position can be more accurately determined, and further, the parameters can be more accurately corrected.
Further, before step SB22, a process of training the initial neural network model to obtain a weather classification model is included, that is, step SQ1 (not shown) to step SQ2 (not shown), wherein:
step SQ1, acquiring image information of a plurality of target scenes, where each image information includes weather images representing various weathers collected for a corresponding target scene, and each weather image is associated with a weather type;
and SQ2, taking each weather image and the weather type corresponding to the weather image as a training sample, and training the initial network model based on all the image information as a training sample set to obtain a weather classification model.
Further, step S106 may include step SN1 (not shown), step SN2 (not shown), and step SN3 (not shown), wherein:
and step SN1, acquiring the duration period of abnormal weather.
In particular, the duration of some abnormal weather is relatively short, such as foggy weather, and the duration may be 1-2 hours; some abnormal weather may last longer, for example, rainy weather, which may last for more than 2 hours. If all the point cloud data are obtained after the target area is measured, the duration period of the abnormal weather of the target area can be obtained from the internet based on the position information of the target area.
Step SN2, determining abnormal data points based on the acquisition time of each data point in the de-noised data, wherein the abnormal data points are data points with the acquisition time in a continuous period;
step SN3 corrects the abnormal data point based on the correction factor.
Specifically, each data point in the point cloud data is associated with a corresponding acquired time, or a plurality of data points at the same time. In practice, the periods of collecting the point cloud data do not necessarily all coincide with the duration periods of the abnormal weather. For example, the point cloud data is collected starting at 12:00 and ending at 2: 00. The starting time of the abnormal weather is 10:00, and the ending time is 1:00, then only 12: point cloud data collected between 00 and 1:00 need to be corrected, while point cloud data collected between 1:00 and 2:00 need not be corrected.
Further, step SN1 may include step SN11 (not shown in the figure) and step SN12 (not shown in the figure), wherein:
step SN11, determining the starting time of entering the abnormal weather of the target area, and determining the ending time of ending the abnormal weather of the target area;
step SN12, determines the duration of the exceptional weather based on the start time and the end time.
Specifically, the real-time acquisition of the environment information of the target area, that is, the real-time acquisition of the environment information in the manner of step SB2, requires the real-time acquisition of the live-action image, that is, the real-time video of the target area, for the target area in step SB 2.
Specifically, if abnormal weather occurs before the measurement of the target area is started, the duration period for measuring abnormal weather should be calculated at the time when the measurement of the target area is started.
Further, step S106 may further include step SM1 (not shown in the figure), step SM2 (not shown in the figure), and SM3 (not shown in the figure), wherein:
step SM1, if the weather types are at least two and at least one abnormal weather type is included in the weather types, judging whether the abnormal weather type is a preset marked abnormal weather;
in particular, before and after marking the beginning and the end of abnormal weather, the reflection intensity parameters in the point cloud data can be influenced for a period of time. For example, when the abnormal weather type is rainstorm, after the rainstorm is over, the water vapor content in the air is high, meanwhile, the surface water accumulation and the building surface water are more, and a reflecting mirror surface may exist; before the rainstorm, the air contains more water and may be accompanied by wind and sand, so that before the rainstorm and in a period of time after the rainstorm is over, the parameter of the reflection intensity in the point cloud data can still be influenced.
In fact, during the collection period of the point cloud data, two weather types may occur, for example, rainstorm weather first, followed by sunny weather; or first sunny day and then rainstorm weather, wherein the rainstorm weather is abnormal weather and also marks the abnormal weather. In the embodiment of the present application, specific types of marked abnormal weather are not specifically limited, as long as the influence of the abnormal weather on reflection parameters in the point cloud data is reduced.
Step SM2, if yes, acquiring an acquisition cycle of point cloud data;
and step SM3, if the acquisition period is smaller than a preset period, correcting all the de-noising data based on the correction coefficient, wherein the preset period is the influence time on the reflection intensity before and after the abnormal weather is marked.
Specifically, the acquisition period of the denoised data is an acquisition period corresponding to the point cloud data of the target area. If the acquisition period is smaller than the preset period, it is indicated that, except for the reflection intensity in the point cloud data which is influenced when the abnormal weather is marked, the reflection intensity in the point cloud data is influenced before and after the abnormal weather is marked, so that the denoising data needs to be completely corrected.
The above embodiments describe a method for correcting point cloud data from the perspective of a method flow, and the following embodiments describe a device for correcting point cloud data from the perspective of a virtual module or a virtual unit, which will be described in detail in the following embodiments.
The embodiment of the present application provides a correcting apparatus, as shown in fig. 2, the apparatus 200 may specifically include an environmental information obtaining module 201, a determining module 202, a correction coefficient determining module 203, a point cloud data obtaining module 204, a denoising module 205, and a correcting module 206, wherein:
an environmental information obtaining module 201, configured to obtain environmental information of a target area, where the environmental information includes a weather type and a pollutant concentration;
the judging module 202 is configured to judge whether the weather is abnormal weather of a preset type based on the environmental information;
a correction coefficient determining module 203, configured to determine a correction coefficient based on the environmental information and a mapping relationship between the environmental information and the correction coefficient;
a point cloud data acquisition module 204, configured to acquire point cloud data acquired for a target area;
the denoising module 205 is configured to perform denoising processing on the point cloud data to obtain denoised data;
and a modification module 206, configured to modify the denoised data based on the modification coefficient.
In a possible implementation manner, when the environment information acquiring module 201 acquires the environment information of the target area, specifically:
acquiring position information of a target area;
and acquiring the weather type and the pollutant concentration of the target area based on the position information.
In a possible implementation manner, when the environment information obtaining module 201 obtains the environment information of the target area, it is specifically configured to:
acquiring a live-action image collected aiming at a target area;
determining the weather type of the target area based on the live-action image and the trained weather classification model;
and acquiring the pollutant concentration of the target area.
In a possible implementation manner, when the environment information obtaining module 201 obtains the environment information of the target area, it is specifically configured to:
the live-action image comprises shooting position information and shooting time information;
inputting the live-action image into the trained weather classification model to obtain a predicted weather type;
determining qualified weather types based on the position information and the time information, wherein the qualified weather types are all weather types which can appear in a target area at present;
judging whether the predicted weather type belongs to a qualified weather type;
and if so, determining that the predicted weather type is the weather type of the target area.
In a possible implementation manner, when the modification module 206 modifies the denoised data based on the modification coefficient, the modification module is specifically configured to:
acquiring a duration period of abnormal weather;
determining an abnormal data point based on the acquisition time of each data point in the de-noised data, wherein the abnormal data point is a data point with the acquisition time in a continuous period;
and correcting the abnormal data points based on the correction coefficient.
In a possible implementation manner, when the modification module 206 modifies the denoised data based on the modification coefficient, the modification module is specifically configured to:
if the weather types are at least two and at least one abnormal weather type is included in the weather types, judging whether the abnormal weather type is a preset marked abnormal weather;
if so, acquiring the acquisition period of the de-noising data;
and if the acquisition period is less than a preset period, correcting all the de-noising data based on the correction coefficient, wherein the preset period is the influence time on the reflection intensity before and after the abnormal weather is marked.
In one possible implementation, when the modification module 206 modifies the denoised data based on the modification coefficient, it is specifically configured to;
determining the starting time of the target area entering the abnormal weather, and determining the ending time of the target area ending the abnormal weather;
the duration of the abnormal weather is determined based on the start time and the end time.
In an embodiment of the present application, an electronic device is provided, as shown in fig. 3, where the electronic device 300 shown in fig. 3 includes: a processor 301 and a memory 303. Wherein processor 301 is coupled to memory 303, such as via bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that the transceiver 304 is not limited to one in practical applications, and the structure of the electronic device 300 is not limited to the embodiment of the present application.
The Processor 301 may be a CPU (Central Processing Unit), a general-purpose Processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other Programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 301 may also be a combination of computing functions, e.g., comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
The Memory 303 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), a magnetic Disc storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to these.
The memory 303 is used for storing application program codes for executing the scheme of the application, and the processor 301 controls the execution. The processor 301 is configured to execute application program code stored in the memory 303 to implement the aspects illustrated in the foregoing method embodiments.
Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. But also a server, etc. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
The present application provides a computer-readable storage medium, on which a computer program is stored, which, when running on a computer, enables the computer to execute the corresponding content in the foregoing method embodiments.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.
Claims (7)
1. A method for correcting point cloud data is characterized by comprising the following steps:
acquiring environmental information of a target area, wherein the environmental information comprises a weather type and pollutant concentration;
judging whether the weather is abnormal weather of a preset type or not based on the environmental information;
if yes, determining a correction coefficient based on the environmental information and the mapping relation between the environmental information and the correction coefficient;
acquiring point cloud data of the target area; acquiring point cloud data of a target area in real time or acquiring complete point cloud data after the target area is measured;
denoising the point cloud data to obtain denoised data;
modifying the de-noising data based on the modification coefficient;
the acquiring of the environmental information of the target area includes:
acquiring a live-action image acquired aiming at the target area;
determining the weather type of the target area based on the live-action image and the trained weather classification model;
acquiring the pollutant concentration of the target area;
the live-action image comprises a shooting position and shooting time, and the determining of the weather type of the target area based on the live-action image and the trained weather classification model comprises the following steps:
inputting the live-action image into a trained weather classification model to obtain a predicted weather type;
determining qualified weather types based on the shooting position and the shooting time, wherein the qualified weather types are all weather types which can be present in the target area;
judging whether the predicted weather type belongs to the qualified weather type;
if so, determining the predicted weather type as the weather type of the target area;
the modifying the de-noised data based on the modification coefficient includes:
if the weather types are at least two types and at least one abnormal weather type is included in the weather types, judging whether the abnormal weather type is a preset marked abnormal weather or not;
if yes, acquiring the acquisition cycle of the de-noising data;
and if the acquisition period is smaller than a preset period, correcting all the de-noising data based on the correction coefficient, wherein the preset period is the influence time on the reflection intensity before and after the marked abnormal weather appears.
2. The method for correcting point cloud data according to claim 1, wherein the acquiring environmental information of the target area includes:
acquiring position information of a target area;
and acquiring the weather type and the pollutant concentration of the target area based on the position information.
3. The method for correcting point cloud data according to claim 1, wherein the correcting the de-noised data based on the correction coefficient includes:
acquiring the duration period of the abnormal weather;
determining an abnormal data point based on the acquisition time of each data point in the de-noised data, wherein the abnormal data point is a data point with the acquisition time within the duration period;
and correcting the abnormal data points based on the correction coefficient.
4. The method for correcting point cloud data according to claim 3, wherein: the acquiring the duration period of the abnormal weather comprises the following steps:
determining the starting time of the target area entering the abnormal weather, and determining the ending time of the target area ending the abnormal weather;
determining a duration period of the exceptional weather based on the start time and the end time.
5. An apparatus for correcting point cloud data, comprising:
the environment information acquisition module is used for acquiring environment information of a target area, wherein the environment information comprises a weather type and pollutant concentration;
the judging module is used for judging whether the weather is abnormal weather of a preset type or not based on the environment information;
the correction coefficient determining module is used for determining a correction coefficient based on the environment information and the mapping relation between the environment information and the correction coefficient;
the point cloud data acquisition module is used for acquiring point cloud data of the target area; acquiring point cloud data of a target area in real time or acquiring complete point cloud data after the target area is measured;
the denoising module is used for denoising the point cloud data to obtain denoised data;
the correction module is used for correcting the de-noising data based on the correction coefficient;
when the environment information obtaining module obtains the environment information of the target area, the environment information obtaining module is specifically configured to:
acquiring a live-action image acquired aiming at the target area;
determining the weather type of the target area based on the live-action image and the trained weather classification model;
acquiring the pollutant concentration of the target area;
when the environment information obtaining module obtains the environment information of the target area, the environment information obtaining module is specifically configured to:
the live-action image comprises a shooting position and shooting time;
inputting the live-action image into a trained weather classification model to obtain a predicted weather type;
determining qualified weather types based on the shooting position and the shooting time, wherein the qualified weather types are all weather types which can be present in the target area;
judging whether the predicted weather type belongs to the qualified weather type or not based on the shooting position and the shooting time;
if so, determining the predicted weather type as the weather type of the target area;
when the correction module corrects the de-noising data based on the correction coefficient, the correction module is specifically configured to:
if the weather types are at least two types and at least one abnormal weather type is included in the weather types, judging whether the abnormal weather type is a preset marked abnormal weather;
if yes, acquiring the acquisition cycle of the de-noising data;
and if the acquisition period is smaller than a preset period, correcting all the de-noising data based on the correction coefficient, wherein the preset period is the influence time on the reflection intensity before and after the marked abnormal weather appears.
6. An electronic device, comprising:
at least one processor;
a memory;
at least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, the at least one application configured to: performing a method of correction of the point cloud data of any of claims 1-4.
7. A computer-readable storage medium, comprising: a computer program which can be loaded by a processor and which executes a method for correction of point cloud data according to any of claims 1 to 4 is stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210573707.6A CN114663883B (en) | 2022-05-25 | 2022-05-25 | Point cloud data correction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210573707.6A CN114663883B (en) | 2022-05-25 | 2022-05-25 | Point cloud data correction method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114663883A CN114663883A (en) | 2022-06-24 |
| CN114663883B true CN114663883B (en) | 2022-09-09 |
Family
ID=82038365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210573707.6A Active CN114663883B (en) | 2022-05-25 | 2022-05-25 | Point cloud data correction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114663883B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116448949B (en) * | 2023-03-22 | 2023-10-31 | 宁波远亚车辆检测有限公司 | Automobile pollutant detection method, system, intelligent terminal and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417757A (en) * | 2020-11-18 | 2021-02-26 | 中国汽车技术研究中心有限公司 | Vehicle-mounted radar signal level simulation method, device, equipment and readable storage medium |
| CN112433934A (en) * | 2020-11-03 | 2021-03-02 | 腾讯科技（深圳）有限公司 | Simulation test method, simulation test device, computer equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109239808A (en) * | 2018-08-01 | 2019-01-18 | 平安科技（深圳）有限公司 | Weather forecast method, device, computer equipment and storage medium |
| CN109444904B (en) * | 2018-10-30 | 2020-09-22 | 百度在线网络技术（北京）有限公司 | Method, device and equipment for generating positioning test data and storage medium |
| CN110750734A (en) * | 2019-10-18 | 2020-02-04 | 腾讯数码（天津）有限公司 | Weather display method and device, computer equipment and computer-readable storage medium |
| CN111507388A (en) * | 2020-04-10 | 2020-08-07 | 上海眼控科技股份有限公司 | Weather image classification method and equipment |
-
2022
- 2022-05-25 CN CN202210573707.6A patent/CN114663883B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112433934A (en) * | 2020-11-03 | 2021-03-02 | 腾讯科技（深圳）有限公司 | Simulation test method, simulation test device, computer equipment and storage medium |
| CN112417757A (en) * | 2020-11-18 | 2021-02-26 | 中国汽车技术研究中心有限公司 | Vehicle-mounted radar signal level simulation method, device, equipment and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 点云智能研究进展与趋势;杨必胜等;《测绘学报》;20191215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114663883A (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109459734B (en) | Laser radar positioning effect evaluation method, device, equipment and storage medium | |
| CN113436238B (en) | Point cloud registration accuracy evaluation method and device and electronic equipment | |
| Li et al. | Automatic bridge crack identification from concrete surface using ResNeXt with postprocessing | |
| CN110473221B (en) | Automatic target object scanning system and method | |
| CN113341397A (en) | Reflection value map construction method and device | |
| CN111489352A (en) | Tunnel gap detection and measurement method and device based on digital image processing | |
| CN114663883B (en) | Point cloud data correction method and device, electronic equipment and storage medium | |
| CN113920420A (en) | Building extraction method and device, terminal equipment and readable storage medium | |
| CN114882316A (en) | Target detection model training method, target detection method and device | |
| CN112733782B (en) | Urban functional area identification method based on road network, storage medium and electronic equipment | |
| CN117218148B (en) | Channel boundary determining method and system based on satellite image and readable storage medium | |
| CN116340863B (en) | Air pollutant prediction method and device, electronic equipment and readable storage medium | |
| CN104157009A (en) | Multi-source remote sensing image quality quantification comparison and selection method | |
| CN117036457A (en) | Roof area measuring method, device, equipment and storage medium | |
| CN116935369A (en) | Ship water gauge reading method and system based on computer vision | |
| CN107451992B (en) | Method and device for detecting SAR image change | |
| CN113786616B (en) | Indirect illumination implementation method and device, storage medium and computing equipment | |
| CN115797310A (en) | Method for determining inclination angle of photovoltaic power station group string and electronic equipment | |
| CN111818557B (en) | Network coverage problem identification method, device and system | |
| CN115236643A (en) | Sensor calibration method, system, device, electronic equipment and medium | |
| CN113096129A (en) | Method and device for detecting cloud cover in hyperspectral satellite image | |
| CN108564603B (en) | SAR image change detection method based on improved Gaussian mixture model | |
| CN114119389A (en) | Image restoration method, system and storage module | |
| CN108563674B (en) | Sea area geographic element measurement method, system and device based on RS and GIS | |
| CN112697724A (en) | Hyperspectral field tobacco leaf potassium oxide content prediction method and system based on unmanned aerial vehicle |
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 |