CN116309788A - 3D point cloud railway contact line cross-sectional area detection method - Google Patents
3D point cloud railway contact line cross-sectional area detection method Download PDFInfo
- Publication number
- CN116309788A CN116309788A CN202310289866.8A CN202310289866A CN116309788A CN 116309788 A CN116309788 A CN 116309788A CN 202310289866 A CN202310289866 A CN 202310289866A CN 116309788 A CN116309788 A CN 116309788A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cross
- data
- cloud data
- effective
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 88
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000004364 calculation method Methods 0.000 claims abstract description 21
- 230000006870 function Effects 0.000 claims description 106
- 238000005299 abrasion Methods 0.000 abstract description 44
- 238000012545 processing Methods 0.000 abstract description 16
- 238000010606 normalization Methods 0.000 description 13
- 238000000605 extraction Methods 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 12
- 238000007405 data analysis Methods 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 7
- 238000001914 filtration Methods 0.000 description 5
- 238000013075 data extraction Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The application provides a 3D point cloud railway contact line cross-sectional area detection method, and relates to the technical field of contact line detection. Acquiring cross-sectional area 3D point cloud data, and effectively extracting outer gallery point cloud to form outer gallery point cloud data; according to the outline point cloud data, a function-based outline area calculation model is established, the outline area is calculated, and cross section point cloud area data are formed; and carrying out wear analysis according to the cross-section point cloud area data and combining the standard cross-section area data. The method can utilize the efficient processing of the 3D point cloud data, and improves the accuracy of acquired data so as to judge the abrasion condition of the contact line more accurately.
Description
Technical Field
The application relates to the technical field of contact line detection, in particular to a 3D point cloud railway contact line cross-sectional area detection method.
Background
Along with the progress and development of technology, the 3D scanning precision is higher and higher, and the ever-increasing living and production needs of people are greatly met. The 3D scanning is used for scanning the target object in an infrared mode and the like to obtain entity figure data of the target object, and the entity figure data is subjected to feature analysis and extraction to form point cloud data with practical reference significance. The point cloud data stores characteristic parameters of the target object on one hand, is convenient for carrying out effective characteristic analysis on the target object, and on the other hand, compared with the original graphic data, the point cloud data is subjected to certain characteristic processing, so that the volume of the data is greatly simplified, and resources and analysis cost are saved to a certain extent.
Contact wires are an important structural part in rail transit, and stable energy and signal data are provided for running vehicles through the contact wires. However, during long-term contact rubbing, the contact line gradually wears out, resulting in poor contact or more serious contact line damage accidents. Health monitoring of contact lines is an important part of rail transit operations. At present, a 3D point cloud technology is also used for monitoring a contact line, but in data processing, point cloud simplification and arrangement are generally carried out by utilizing normalization processing, but data loss can be caused to a certain extent, and the abrasion condition of a contact network cannot be accurately monitored.
Therefore, the design of the 3D point cloud railway contact line cross-sectional area detection method can utilize the efficient processing of 3D point cloud data to improve the accuracy of data acquisition so as to judge the contact line abrasion condition more accurately, and is a problem to be solved urgently at present.
Disclosure of Invention
The embodiment of the application aims to provide a 3D point cloud railway contact line cross-sectional area detection method, which extracts effective point cloud data through the effectiveness analysis of initial contour point cloud data and establishes a related contour function for analysis. The validity extraction can be used for filtering the deviation points existing in the 3D point cloud to obtain all valid point clouds. Therefore, the outline function is built based on the effective point clouds, all the effective point clouds can be utilized, the loss of point cloud data due to normalization processing is avoided, the accuracy of area analysis based on the outline point cloud data is further improved, and the accuracy of loss condition monitoring of the contact line is further effectively guaranteed.
In a first aspect, an embodiment of the present application provides a method for detecting a cross-sectional area of a 3D point cloud railway contact line, including obtaining cross-sectional area 3D point cloud data, and performing effective extraction of a gallery point cloud to form gallery point cloud data; according to the outline point cloud data, a function-based outline area calculation model is established, the outline area is calculated, and cross section point cloud area data are formed; and carrying out wear analysis according to the cross-section point cloud area data and combining the standard cross-section area data.
In the embodiment of the application, the method extracts the effective point cloud data through the effectiveness analysis of the initial contour point cloud data, and establishes the related contour function for analysis. The validity extraction can be used for filtering the deviation points existing in the 3D point cloud to obtain all valid point clouds. Therefore, the outline function is built based on the effective point clouds, all the effective point clouds can be utilized, the loss of point cloud data due to normalization processing is avoided, the accuracy of area analysis based on the outline point cloud data is further improved, and the accuracy of loss condition monitoring of the contact line is further effectively guaranteed.
As one possible implementation manner, acquiring cross-sectional area 3D point cloud data, extracting a gallery point cloud, and forming gallery point cloud data, including: acquiring cross section 3D point cloud data, extracting outer gallery point cloud, and forming initial outer gallery point cloud data; and carrying out accuracy analysis on the initial gallery point cloud data to form the gallery point cloud data.
In the embodiment of the application, certain measurement deviation exists in the 3D point cloud data due to data extraction, and the direct data analysis of the deviation point cloud data can have a certain influence on an analysis result, so that the accuracy of judging the abrasion condition of the contact network finally is influenced. Therefore, effective data extraction is required for the obtained initial data before deep data analysis is performed, so as to ensure that the point cloud data used for analysis are effective and accurate data.
As one possible implementation manner, performing accuracy analysis on the initial gallery point cloud data to form gallery point cloud data, including: establishing a first analysis coordinate system, and giving position parameters P of all initial point clouds in initial corridor point cloud data under the first analysis coordinate system n ＝(X n ，Y n ) Wherein X is n A first direction coordinate parameter representing an initial point cloud with a sequence number n, Y n A second direction coordinate parameter representing an initial point cloud having a sequence number n; sequentially extracting position parameters of three initial point clouds along a first setting direction: p (P) k-1 ＝(X k-1 ，Y k-1 )、P k ＝(X k ，Y k )、P k+1 ＝(X k+1 ，Y k+1 ) Wherein k is a non-zero natural number, and k is more than 1 and less than n; according to parameter P k-1 And P k+1 Establishing a first analytical function f (x n ) And the following two formulas are calculated respectively: a=lim (x→x k -)，B＝lim(X→X k (+) is carried out; according to A, B and P k ＝(X k ，Y k ) Performing accuracy judgment on all initial point clouds to determine effective point clouds; and integrating the effective point cloud to form the gallery point cloud data.
In an embodiment of the present application, a method for extracting an effective point cloud is provided. It can be appreciated that if the point cloud data is correct at the time of initial extraction, the outline point cloud formed by processing can accurately express the contact line outline condition at the time of measurement. Of course, for contact wires that are used for a long period of time, although they are subject to varying degrees of wear loss, the profile of each cross section of the contact wire, including where they are not worn and are subject to severe wear, and where they are between unworn and worn, is capable of forming reasonably new profile boundaries rather than abrupt profile boundary changes such as spikes, concave spikes, etc. Therefore, when the validity analysis of the point clouds is carried out, a first analysis function for extracting the outline valid point clouds is established by utilizing the characteristics, whether the point cloud data are distorted or not is judged by checking the left and right derivative conditions of each point cloud at the position of the point cloud, the screening of the point clouds can be fully and effectively completed, and the point clouds with accurate and valid data are reserved. In addition, the effective extraction of the point cloud is performed in any manner, and the design may be performed as needed, and any means such as tolerance, change rate, and the like may be used. In the scheme, the validity is judged by seeking, the validity of the data can be further improved, and the most effective point cloud is reserved as far as possible.
As a possible implementation, according to A, B and P k ＝(X k ，Y k ) Accuracy judgment is carried out on all initial point clouds, and effective point clouds are determined, including: when a=b=y k When determining P k-1 、P k P k+1 The three initial point clouds are all effective point clouds; when a=b+.y k When determining P k-1 And P k+1 As effective point cloud, P k Not a valid point cloud; when none of a=b=y occurs k And a=b+.y k When the method is used, the first step length is taken as a span reference continuously according to the first setting direction, three adjacent initial point clouds are selected to judge again until A=B=Y appears k Or a=b+.y k Is the case in (a).
In the embodiment of the present application, it is understood that, in determining the effective point cloud, point cloud data about the deviation is not much, and point clouds having measurement deviation are considered unless the problem of the measurement device is solved, and the deviation point clouds are unlikely to be aggregated, that is, the deviation point clouds can only appear in an independent discontinuity. Therefore, in performing the validity analysis, the following several different judgment cases may occur: one is that three point clouds selected sequentially are all effective point clouds; the two are the point clouds which are sequentially selected, wherein the offset point clouds exist in the point clouds, and the offset point clouds are the point clouds of the first position which are sequentially acquired; the three point clouds are sequentially selected, wherein the offset point clouds exist in the sequentially selected point clouds, and the offset point clouds are sequentially acquired point clouds of a second position; the four point clouds are point clouds with deviation in the sequentially selected point clouds, and the deviation point clouds are point clouds of a third position sequentially acquired. For the first and third cases, the positions of the point clouds can be accurately judged, and for the second and fourth cases, the validity conditions of the four point clouds are determined by capturing one point cloud in sequence and removing the point clouds at the original first position to form new three point clouds and carrying out validity analysis again. Through the validity judgment, the validity analysis of all the point clouds can be ensured to be completed, so that the complete reservation of the valid point cloud data is realized, and the accuracy and the precision of the analysis are further improved.
As one possible implementation manner, building a function-based contour area calculation model according to contour point cloud data, and calculating a contour area to form cross-section point cloud area data, including: acquiring outline point cloud data, and establishing an outline function set according to the outline point cloud data; and calculating the cross section area according to the contour function and the outline point cloud data, and obtaining the cross section point cloud area data.
In the embodiment of the application, when the data analysis of the cross section is performed, the scheme avoids a linear programming mode which is generally adopted, aims at utilizing all effective point clouds, ensures the accuracy of analysis results, and avoids the loss and even distortion of partial data caused by the use of a linear programming means. According to the method, the cross-sectional area is calculated by establishing the outline function set based on the outline point cloud data, all the effective point cloud data are utilized to the maximum extent, the point cloud data are completely reserved, and the analysis accuracy and precision are improved.
As one possible implementation manner, obtaining outline point cloud data, and building an outline function according to the outline point cloud data, including: acquiring an effective center reference position in a corridor boundary area according to the corridor point cloud data; establishing a second analysis coordinate system by taking the effective center reference position as a coordinate far point; according to the second analysis coordinate system, giving position parameters of all effective point clouds in the gallery point cloud data under the second analysis coordinate system; and establishing a profile function according to the position parameters of all the effective point clouds.
In the embodiments of the present application, it is understood that if the calculation of the cross-sectional area is performed later on the basis of building the profile function for the contact line, it should be considered that the profile function should not have different point clouds or dependent variables at the same location or independent variable parameters when building the profile function earlier. Based on this, a reasonable determination of the position of the coordinate system on which the profile function is established is required. Because the contact line profile is a profile with a closed shape, when a coordinate system is established by taking any point outside the profile boundary area as the origin of the coordinate system, a plurality of point cloud data can be acquired at the same position or under independent variables, and thus, when the profile function has a non-unique solution, the calculation of the cross-sectional area based on the profile function cannot be completed. So to avoid this, a reasonable coordinate system origin needs to be chosen in the profile to establish a profile function to successfully implement the calculation of the cross-sectional area.
As one possible implementation manner, acquiring an effective center reference position in a corridor boundary area according to corridor point cloud data includes: acquiring two effective point clouds positioned at the bottom of a groove in the outer gallery point cloud data, and establishing a first position connecting line; acquiring effective point clouds positioned in the middle of the semicircle in the outer corridor point cloud data, acquiring the longest position line of the effective point clouds in the outer corridor boundary area, and determining the longest position line as a second position line; an intersection of the first position link and the second position link is determined as an effective center reference position.
In the embodiment of the present application, for determining the origin of the coordinate system, consider that the contour shape of the contact line is a shape in which symmetrical grooves exist and the grooves are connected by circular arcs. For arc segments, the profile function acquired by the coordinate system established at any point in the profile boundary can ensure that the profile function has one-to-one corresponding parameter value, and a proper position needs to be determined for the groove boundary. It will be appreciated that the points located on the tank bottom connection are all functional relationships that satisfy a one-to-one correspondence. Therefore, the position of the connecting point obtained by the connecting line of the groove bottom and the connecting line of the circle center crossing position on the circular arc in the scheme can be determined to be the origin of the coordinate system position which can fully meet the establishment of a reasonable contour function.
As one possible implementation manner, building a profile function set according to the position parameters of all the effective point clouds, including: sequentially acquiring the position parameters Q of adjacent effective point clouds along a second set direction t-1 ＝(L t-1 ，θ t-1 )，Q t ＝(L t ，θ t ) Wherein t represents a sequence value of effective point clouds along a second set direction, and t is more than 1 and less than or equal to n, and n is the total number of the effective point clouds in the outline point cloud data; according to parameter Q t-1 And Q t Establishing a profile function R between two adjacent effective point clouds t (θ t ) The method comprises the steps of carrying out a first treatment on the surface of the Acquiring outline functions among all adjacent effective point clouds in outline point cloud data to form an outline function set H= { R 2 (θ 2 )，R 3 (θ 3 )，…，R n (θ n )}。
In this embodiment of the present application, a most reasonable contour line is obtained by adopting a normalization or fitting manner when a contour function is generally established, and a function of the contour line is determined, which may result in that the contour line determined by the function may not pass through all effective origins one by one, and further result in loss and distortion of data. Meanwhile, considering that the calculation of the cross street area is performed to accurately analyze the wear, if the analysis is performed by adopting a normalization or fitting method, the wear condition of certain positions may be distorted, or the threshold warning of the wear monitoring is delayed, so that the contact line wear condition cannot be accurately judged. According to the scheme, each effective point cloud is fully utilized, the outline function between two adjacent point clouds is independently established, effective point cloud data can be utilized to the greatest extent, accurate determination and analysis of the outline boundary of the contact line can be realized, the precision and accuracy of contact line abrasion detection are greatly improved, and a powerful and accurate data reference basis is provided for timely observation and display of contact line maintenance.
As one possible implementation manner, performing cross-sectional area calculation according to the profile function and the outline point cloud data to obtain cross-sectional point cloud area data, including: acquiring a profile function set H, and acquiring a cross-section point cloud area value S according to the following formula Point cloud ：
In the embodiment of the application, the cross section of the contact line is considered to be a closed contour boundary, the position condition of the contour can be simply and accurately expressed by establishing an angle-based contour function, and meanwhile, the contour function set established by utilizing all effective point clouds is subjected to full-angle integration so as to accurately acquire the real-time cross section area of the contact line, and the accuracy and the calculation precision of the cross section area are further ensured.
As one possible implementation, performing wear-level analysis based on cross-sectional point cloud area data in combination with standard cross-sectional area data, includes: acquiring cross-section point cloud area value S Point cloud And standard cross-sectional area value S Standard of Calculate the consumption value S Consumption of ：S Consumption of ＝S Standard of -S Point cloud 。
In the embodiment of the application, the abrasion condition is determined by utilizing the difference value between the standard cross-section area value and the cross-section point cloud area value, so that the judgment of the abrasion condition of the contact line is powerfully ensured. Compared with the complex determination and judgment of the abrasion position, the simple judgment mode can fully meet the requirement of contact line maintenance, the abrasion of the contact line has fixed area, the obtained abrasion amount can be basically the abrasion amount of a fixed abrasion area without deeply judging the abrasion position, and the abrasion of other positions only needs to reach a threshold value of abrasion on the whole, so that the further judgment of the abrasion position is not needed. On the other hand, the analysis cost can be greatly simplified, and the resources are saved.
The 3D point cloud railway contact line cross-sectional area detection method provided by the embodiment has the beneficial effects that:
according to the method, effective point cloud data are extracted through the effectiveness analysis of initial contour point cloud data, and related contour functions are established for analysis. The validity extraction can be used for filtering the deviation points existing in the 3D point cloud to obtain all valid point clouds. Therefore, the outline function is built based on the effective point clouds, all the effective point clouds can be utilized, the loss of point cloud data due to normalization processing is avoided, the accuracy of area analysis based on the outline point cloud data is further improved, and the accuracy of loss condition monitoring of the contact line is further effectively guaranteed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a step diagram of a method for detecting a cross-sectional area of a contact line of a 3D point cloud railway according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Along with the progress and development of technology, the 3D scanning precision is higher and higher, and the ever-increasing living and production needs of people are greatly met. The 3D scanning is used for scanning the target object in an infrared mode and the like to obtain entity figure data of the target object, and the entity figure data is subjected to feature analysis and extraction to form point cloud data with practical reference significance. The point cloud data stores characteristic parameters of the target object on one hand, is convenient for carrying out effective characteristic analysis on the target object, and on the other hand, compared with the original graphic data, the point cloud data is subjected to certain characteristic processing, so that the volume of the data is greatly simplified, and resources and analysis cost are saved to a certain extent.
Contact wires are an important structural part in rail transit, and stable energy and signal data are provided for running vehicles through the contact wires. However, during long-term contact rubbing, the contact line gradually wears out, resulting in poor contact or more serious contact line damage accidents. Health monitoring of contact lines is an important part of rail transit operations. At present, a 3D point cloud technology is also used for monitoring a contact line, but in data processing, point cloud simplification and arrangement are generally carried out by utilizing normalization processing, but data loss can be caused to a certain extent, and the abrasion condition of a contact network cannot be accurately monitored.
Referring to fig. 1, an embodiment of the application provides a method for detecting a cross-sectional area of a contact line of a 3D point cloud railway. According to the method, effective point cloud data are extracted through the effectiveness analysis of initial contour point cloud data, and related contour functions are established for analysis. The validity extraction can be used for filtering the deviation points existing in the 3D point cloud to obtain all valid point clouds. Therefore, the outline function is built based on the effective point clouds, all the effective point clouds can be utilized, the loss of point cloud data due to normalization processing is avoided, the accuracy of area analysis based on the outline point cloud data is further improved, and the accuracy of loss condition monitoring of the contact line is further effectively guaranteed.
The method for detecting the cross-sectional area of the contact line of the 3D point cloud railway comprises the following main steps:
s1: and acquiring cross-sectional area 3D point cloud data, and effectively extracting the outer gallery point cloud to form outer gallery point cloud data.
This step is mainly a pretreatment step prior to the calculation of the cross-sectional area. Acquiring cross-sectional area 3D point cloud data, extracting outer gallery point cloud, forming outer gallery point cloud data, including: acquiring cross section 3D point cloud data, extracting outer gallery point cloud, and forming initial outer gallery point cloud data; and carrying out accuracy analysis on the initial gallery point cloud data to form the gallery point cloud data.
Because certain measurement deviation exists in the 3D point cloud data, the direct data analysis of the deviation point cloud data can generate certain influence on the analysis result, and the accuracy of judging the abrasion condition of the contact network finally is influenced. Therefore, effective data extraction is required for the obtained initial data before deep data analysis is performed, so as to ensure that the point cloud data used for analysis are effective and accurate data.
The accuracy analysis is performed on the initial gallery point cloud data to form gallery point cloud data, including: establishing a first analysis coordinate system, and giving position parameters P of all initial point clouds in initial corridor point cloud data under the first analysis coordinate system n ＝(X n ，Y n ) Wherein X is n A first direction coordinate parameter representing an initial point cloud with a sequence number n, Y n A second direction coordinate parameter representing an initial point cloud having a sequence number n; sequentially extracting position parameters of three initial point clouds along a first setting direction: p (P) k-1 ＝(X k-1 ，Y k-1 )、P k ＝(X k ，Y k )、P k+1 ＝(X k+1 ，Y k+1 ) Wherein k is a non-zero natural number, and k is more than 1 and less than n; according to parameter P k-1 And P k+1 Establishing a first analytical function f (x n ) And the following two formulas are calculated respectively: a=lim (x→x k -)，B＝lim(X→X k (+) is carried out; according to A, B and P k ＝(X k ，Y k ) Performing accuracy judgment on all initial point clouds to determine effective point clouds; and integrating the effective point cloud to form the gallery point cloud data.
It can be appreciated that if the point cloud data is correct at the time of initial extraction, the outline point cloud formed by processing can accurately express the contact line outline condition at the time of measurement. Of course, for contact wires that are used for a long period of time, although they are subject to varying degrees of wear loss, the profile of each cross section of the contact wire, including where they are not worn and are subject to severe wear, and where they are between unworn and worn, is capable of forming reasonably new profile boundaries rather than abrupt profile boundary changes such as spikes, concave spikes, etc. Therefore, when the validity analysis of the point clouds is carried out, a first analysis function for extracting the outline valid point clouds is established by utilizing the characteristics, whether the point cloud data are distorted or not is judged by checking the left and right derivative conditions of each point cloud at the position of the point cloud, the screening of the point clouds can be fully and effectively completed, and the point clouds with accurate and valid data are reserved. In addition, the effective extraction of the point cloud is performed in any manner, and the design may be performed as needed, and any means such as tolerance, change rate, and the like may be used. In the scheme, the validity is judged by seeking, the validity of the data can be further improved, and the most effective point cloud is reserved as far as possible.
According to A, B and P k ＝(X k ，Y k ) Accuracy judgment is carried out on all initial point clouds, and effective point clouds are determined, including: when a=b=y k When determining P k-1 、P k P k+1 The three initial point clouds are all effective point clouds; when a=b+.y k When determining P k-1 And P k+1 As effective point cloud, P k Not a valid point cloud; when none of a=b=y occurs k And a=b+.y k When the method is used, the first step length is taken as a span reference continuously according to the first setting direction, three adjacent initial point clouds are selected to judge again until A=B=Y appears k Or a=b+.y k Is the case in (a).
It will be appreciated that the determination of the effective point cloud takes into account that the point cloud data due to the deviation is not much and that the point cloud with the measured deviation is considered unless it is a problem of the measuring device, that is, the deviation point clouds are unlikely to be aggregated, i.e. only independent discontinuities can occur. Therefore, in performing the validity analysis, the following several different judgment cases may occur: one is that three point clouds selected sequentially are all effective point clouds; the two are the point clouds which are sequentially selected, wherein the offset point clouds exist in the point clouds, and the offset point clouds are the point clouds of the first position which are sequentially acquired; the three point clouds are sequentially selected, wherein the offset point clouds exist in the sequentially selected point clouds, and the offset point clouds are sequentially acquired point clouds of a second position; the four point clouds are point clouds with deviation in the sequentially selected point clouds, and the deviation point clouds are point clouds of a third position sequentially acquired. For the first and third cases, the positions of the point clouds can be accurately judged, and for the second and fourth cases, the validity conditions of the four point clouds are determined by capturing one point cloud in sequence and removing the point clouds at the original first position to form new three point clouds and carrying out validity analysis again. Through the validity judgment, the validity analysis of all the point clouds can be ensured to be completed, so that the complete reservation of the valid point cloud data is realized, and the accuracy and the precision of the analysis are further improved.
Of course, the effective point cloud judging method provided by the embodiment can also include the situation of offset point clouds causing aggregation due to the fact that the accuracy of equipment is reduced. In the whole judging process, the three effective point clouds can be accurately and directly determined only when the three effective point clouds are effective point clouds or when the middle point cloud in the three point clouds is a deviation point cloud. For other cases, the effective point cloud is further determined by continuously acquiring new point clouds and performing validity analysis.
It should be noted that, for the effective point cloud determining method provided in the present solution, the number of sequentially selected point clouds may be set as required. Accordingly, as the number of the sequentially selected point clouds increases, the judging type of the effective point clouds increases, the complexity of the judgment is increased to a certain extent, and the judging type is also increased when a certain number of effective judgment is performed in the initial stage. Therefore, the effectiveness confirmation of the three point clouds determined in the scheme is the most efficient judgment mode.
S2: and establishing a function-based contour area calculation model according to the contour point cloud data, and calculating the contour area to form cross-section point cloud area data.
According to the outline point cloud data, a function-based outline area calculation model is established, the outline area is calculated, and cross section point cloud area data is formed, and the method comprises the following steps: acquiring outline point cloud data, and establishing an outline function set according to the outline point cloud data; and calculating the cross section area according to the contour function and the outline point cloud data, and obtaining the cross section point cloud area data.
When the data analysis of the cross section is carried out, the scheme avoids a linear programming mode which is generally adopted, aims to utilize all effective point clouds, ensures the accuracy of analysis results, and avoids partial data loss and even distortion caused by the use of the linear programming means. According to the method, the cross-sectional area is calculated by establishing the outline function set based on the outline point cloud data, all the effective point cloud data are utilized to the maximum extent, the point cloud data are completely reserved, and the analysis accuracy and precision are improved.
The method for obtaining the outline point cloud data and establishing the outline function according to the outline point cloud data comprises the following steps: acquiring an effective center reference position in a corridor boundary area according to the corridor point cloud data; establishing a second analysis coordinate system by taking the effective center reference position as a coordinate far point; according to the second analysis coordinate system, giving position parameters of all effective point clouds in the gallery point cloud data under the second analysis coordinate system; and establishing a profile function according to the position parameters of all the effective point clouds.
It will be appreciated that if the cross-sectional area is calculated later on the basis of the profile function, for the contact line, it should be taken into account that the profile function should not have different point clouds or dependent variables at the same location or independent variable parameters when the profile function is established earlier. Based on this, a reasonable determination of the position of the coordinate system on which the profile function is established is required. Because the contact line profile is a profile with a closed shape, when a coordinate system is established by taking any point outside the profile boundary area as the origin of the coordinate system, a plurality of point cloud data can be acquired at the same position or under independent variables, and thus, when the profile function has a non-unique solution, the calculation of the cross-sectional area based on the profile function cannot be completed. So to avoid this, a reasonable coordinate system origin needs to be chosen in the profile to establish a profile function to successfully implement the calculation of the cross-sectional area.
According to the outer gallery point cloud data, acquiring an effective center reference position in the outer gallery boundary area comprises the following steps: acquiring two effective point clouds positioned at the bottom of a groove in the outer gallery point cloud data, and establishing a first position connecting line; acquiring effective point clouds positioned in the middle of the semicircle in the outer corridor point cloud data, acquiring the longest position line of the effective point clouds in the outer corridor boundary area, and determining the longest position line as a second position line; an intersection of the first position link and the second position link is determined as an effective center reference position.
For the determination of the origin of the coordinate system, consider that the contour shape of the contact line is a shape in which symmetrical grooves exist and the grooves are connected by circular arcs. For arc segments, the profile function acquired by the coordinate system established at any point in the profile boundary can ensure that the profile function has one-to-one corresponding parameter value, and a proper position needs to be determined for the groove boundary. It will be appreciated that the points located on the tank bottom connection are all functional relationships that satisfy a one-to-one correspondence. Therefore, the position of the connecting point obtained by the connecting line of the groove bottom and the connecting line of the circle center crossing position on the circular arc in the scheme can be determined to be the origin of the coordinate system position which can fully meet the establishment of a reasonable contour function.
Establishing a profile function set according to the position parameters of all the effective point clouds, wherein the profile function set comprises: sequentially acquiring the position parameters Q of adjacent effective point clouds along a second set direction t-1 ＝(L t-1 ，θ t-1 )，Q t ＝(L t ，θ t ) Wherein t represents a sequence value of effective point clouds along a second set direction, and t is more than 1 and less than or equal to n, and n is the total number of the effective point clouds in the outline point cloud data; according to parameter Q t-1 And Q t Establishing a profile function R between two adjacent effective point clouds t (θ t ) The method comprises the steps of carrying out a first treatment on the surface of the Acquiring outline functions among all adjacent effective point clouds in outline point cloud data to form an outline function set H= { R 2 (θ 2 )，R 3 (θ 3 )，…，R n (θ n )}。
Usually, when building a profile function, a most reasonable profile line is obtained in a normalization or fitting mode, and the function of the profile line is determined, but this results in that the profile line determined by the function does not pass through all effective origins one by one, and further results in data loss and distortion. Meanwhile, considering that the calculation of the cross street area is performed to accurately analyze the wear, if the analysis is performed by adopting a normalization or fitting method, the wear condition of certain positions may be distorted, or the threshold warning of the wear monitoring is delayed, so that the contact line wear condition cannot be accurately judged. According to the scheme, each effective point cloud is fully utilized, the outline function between two adjacent point clouds is independently established, effective point cloud data can be utilized to the greatest extent, accurate determination and analysis of the outline boundary of the contact line can be realized, the precision and accuracy of contact line abrasion detection are greatly improved, and a powerful and accurate data reference basis is provided for timely observation and display of contact line maintenance.
According to the contour function and the outline point cloud data, performing cross-section area calculation to obtain cross-section point cloud area data, including: acquiring a profile function set H, and acquiring a cross-section point cloud area value S according to the following formula Point cloud ：
Considering that the cross section of the contact line is a closed contour boundary, the position condition of the contour can be simply and accurately expressed by establishing an angle-based contour function, and meanwhile, the contour function set established by utilizing all effective point clouds is used for carrying out full-angle integration so as to accurately obtain the real-time cross section area of the contact line, thereby further ensuring the accuracy and the calculation precision of the cross section area.
S3: and carrying out wear analysis according to the cross-section point cloud area data and combining the standard cross-section area data.
Performing wear analysis based on cross-sectional point cloud area data in combination with standard cross-sectional area data, comprising: acquiring cross-section point cloud area value S Point cloud And standard cross-sectional area value S Standard of Calculate the consumption value S Consumption of ：S Consumption of ＝S Standard of -S Point cloud . And the abrasion condition is determined by utilizing the difference value between the standard cross-section area value and the cross-section point cloud area value, so that the judgment of the abrasion condition of the contact line is powerfully ensured. The determination and judgment of the abrasion position is complicated, and the simple judgment methodOn the one hand, the method can fully meet the requirement of contact line maintenance, the abrasion of the contact line has fixed area property, the obtained abrasion quantity can be ensured to be basically the abrasion quantity of a fixed abrasion area without deeply judging the abrasion position, and the abrasion of other positions only needs to reach one abrasion threshold value generally, so that the abrasion position is not required to be judged further. On the other hand, the analysis cost can be greatly simplified, and the resources are saved.
Of course, when the abrasion position determination is performed later to understand the abrasion type in depth, the determination of the abrasion position needs to be performed by using the area of the cross-base point cloud. Based on the profile function set provided by the scheme, the abrasion position can be effectively determined. Specifically, since the profile function set is a profile function between adjacent point clouds, when determining the wear position, the following steps may be employed to make a stepwise determination:
firstly, the contact line wear area is classified according to grades based on historical data, and a grade interval with a small wear probability is formed. And classifying the profile functions according to the grades according to the grade intervals. And simultaneously, calculating the cross-sectional areas of different level intervals by using the profile function. And then obtaining the standard cross-sectional area of each grade interval, and comparing the area differences step by step according to the grade. Different comparison thresholds can be established here for different level regions, since the threshold requirements for the amount of wear are different in different level regions. Thus, the wear amount exceeding the set threshold value is judged by each level, and the level region where the wear occurs can be determined. Of course, the determination of the wear position of the level region can also be further carried out again in the determined wear level region according to the profile function. Because the profile function is directly established on the point cloud data, the determination of the abrasion position can fully meet the requirement of analysis precision, the accuracy of abrasion position analysis is greatly improved, and a reliable and accurate data analysis basis is provided for targeted health maintenance of contact lines.
In summary, the method for detecting the cross-sectional area of the contact line of the 3D point cloud railway has the following beneficial effects:
according to the method, effective point cloud data are extracted through the effectiveness analysis of initial contour point cloud data, and related contour functions are established for analysis. The validity extraction can be used for filtering the deviation points existing in the 3D point cloud to obtain all valid point clouds. Therefore, the outline function is built based on the effective point clouds, all the effective point clouds can be utilized, the loss of point cloud data due to normalization processing is avoided, the accuracy of area analysis based on the outline point cloud data is further improved, and the accuracy of loss condition monitoring of the contact line is further effectively guaranteed.
Because certain measurement deviation exists in the 3D point cloud data, the direct data analysis of the deviation point cloud data can generate certain influence on the analysis result, and the accuracy of judging the abrasion condition of the contact network finally is influenced. Therefore, effective data extraction is required for the obtained initial data before deep data analysis is performed, so as to ensure that the point cloud data used for analysis are effective and accurate data.
The profile of the cross section for each part of the contact line, including where it is not worn and is severely worn and where it is between unworn and worn, is capable of forming reasonably new profile boundaries rather than abrupt profile boundary changes such as spikes, concave spikes, etc. Therefore, when the validity analysis of the point clouds is carried out, a first analysis function for extracting the outline valid point clouds is established by utilizing the characteristics, whether the point cloud data are distorted or not is judged by checking the left and right derivative conditions of each point cloud at the position of the point cloud, the screening of the point clouds can be fully and effectively completed, and the point clouds with accurate and valid data are reserved.
The method avoids a linear programming mode which is usually adopted, aims at utilizing all effective point clouds, ensures the accuracy of analysis results, and avoids partial data loss and even distortion caused by the use of a linear programming means. According to the method, the cross-sectional area is calculated by establishing the outline function set based on the outline point cloud data, all the effective point cloud data are utilized to the maximum extent, the point cloud data are completely reserved, and the analysis accuracy and precision are improved.
When the profile function is established, a most reasonable profile line is obtained in a normalization or fitting mode, and the function of the profile line is determined, but the profile line determined by the function cannot pass through all effective origins one by one, so that data loss and distortion are caused. Meanwhile, considering that the calculation of the cross street area is performed to accurately analyze the wear, if the analysis is performed by adopting a normalization or fitting method, the wear condition of certain positions may be distorted, or the threshold warning of the wear monitoring is delayed, so that the contact line wear condition cannot be accurately judged. According to the scheme, each effective point cloud is fully utilized, the outline function between two adjacent point clouds is independently established, effective point cloud data can be utilized to the greatest extent, accurate determination and analysis of the outline boundary of the contact line can be realized, the precision and accuracy of contact line abrasion detection are greatly improved, and a powerful and accurate data reference basis is provided for timely observation and display of contact line maintenance.
The profile function acquired by the coordinate system established at any point in the profile boundary can ensure that the profile function has one-to-one corresponding parameter value, and a proper position needs to be determined for the groove boundary. It will be appreciated that the points located on the tank bottom connection are all functional relationships that satisfy a one-to-one correspondence. Therefore, the position of the connecting point obtained by the connecting line of the groove bottom and the connecting line of the circle center crossing position on the circular arc in the scheme can be determined to be the origin of the coordinate system position which can fully meet the establishment of a reasonable contour function.
The method has the advantages that the grade area for judging the abrasion position is established to determine the abrasion position, accurate judgment of the abrasion position is fully realized by utilizing the profile function, the judgment accuracy of the abrasion position can be greatly improved on the basis of fully utilizing the data of all effective point clouds, meanwhile, the requirement on the judgment accuracy of the abrasion position can be fully met, the accurate determination of analysis can be carried out according to analysis requirements and actual conditions, the waste and excessive use of molecular resources are avoided, the judgment of the abrasion condition of a contact line is truly ensured, and accurate and effective reference data are provided for the health maintenance of the contact line.
In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the elements and method steps of the examples described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or as a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. The 3D point cloud railway contact line cross-sectional area detection method is characterized by comprising the following steps of:
acquiring cross-sectional area 3D point cloud data, and effectively extracting the outer gallery point cloud to form outer gallery point cloud data;
according to the outline point cloud data, a function-based outline area calculation model is established, outline area calculation is carried out, and cross section point cloud area data are formed;
and carrying out wear analysis according to the cross-section point cloud area data and combining with standard cross-section area data.
2. The method for detecting the cross-sectional area of a 3D point cloud railway contact line according to claim 1, wherein the acquiring cross-sectional area 3D point cloud data, extracting a gallery point cloud, and forming gallery point cloud data comprises:
Acquiring cross section 3D point cloud data, extracting outer gallery point cloud, and forming initial outer gallery point cloud data;
and carrying out accuracy analysis on the initial gallery point cloud data to form the gallery point cloud data.
3. The method for detecting the cross-sectional area of a 3D point cloud railway contact line according to claim 2, wherein the performing accuracy analysis on the initial gallery point cloud data to form the gallery point cloud data comprises:
establishing a first analysis coordinate system, and giving position parameters P of all initial point clouds in the initial gallery point cloud data under the first analysis coordinate system n ＝(X n ，Y n ) Wherein X is n Representing the initial point with the sequence number nFirst direction coordinate parameter of cloud, Y n A second direction coordinate parameter representing the initial point cloud with a sequence number n;
sequentially extracting three position parameters of the initial point cloud along a first set direction:
P k-1 ＝(X k-1 ，Y k-1 )、P k ＝(X k ，Y k )、P k+1 ＝(X k+1 ，Y k+1 ) Wherein k is not
Zero natural number, and k is more than 1 and less than n;
according to parameter P k-1 And P k+1 Establishing a first analytical function f (x n ) And the following two formulas are calculated respectively:
A＝lim(X→X k -)，B＝lim(X→X k +)；
according to A, B and P k ＝(X k ，Y k ) Performing accuracy judgment on all the initial point clouds to determine effective point clouds;
and integrating the effective point cloud to form the gallery point cloud data.
4. A method for detecting the cross-sectional area of a 3D point cloud railway contact line according to claim 3, wherein the method is characterized by comprising the following steps of A, B and P k ＝(X k ，Y k ) Performing accuracy judgment on all the initial point clouds to determine effective point clouds, including:
when a=b=y k When determining P k-1 、P k P k+1 The three initial point clouds are all the effective point clouds;
when a=b+.y k When determining P k-1 And P k+1 For the effective point cloud, P k Not the valid point cloud;
when none of a=b=y occurs k And a=b+.y k When the first setting direction is used for continuously taking the first step length as the span reference, selecting three adjacent initial point clouds to judge again until A=B=Y appears k Or a=b+.y k Is the case in (a).
5. The method for detecting the cross-sectional area of a 3D point cloud railway contact line according to claim 3, wherein the building a function-based contour area calculation model according to the contour point cloud data and calculating a contour area to form cross-sectional point cloud area data comprises:
acquiring the outline point cloud data, and establishing an outline function set according to the outline point cloud data;
and calculating the cross-sectional area according to the contour function and the contour point cloud data, and obtaining the cross-sectional point cloud area data.
6. The method for detecting the cross-sectional area of a 3D point cloud railway contact line according to claim 5, wherein the acquiring the outline point cloud data and establishing a profile function according to the outline point cloud data comprises:
acquiring an effective center reference position in a corridor boundary area according to the corridor point cloud data;
establishing a second analysis coordinate system by taking the effective center reference position as a coordinate far point;
according to the second analysis coordinate system, giving position parameters of all the effective point clouds in the gallery point cloud data under the second analysis coordinate system;
and establishing the outline function according to the position parameters of all the effective point clouds.
7. The method for detecting the cross-sectional area of a 3D point cloud railway contact line according to claim 6, wherein the obtaining an effective center reference position in a corridor boundary area according to the corridor point cloud data comprises:
acquiring two effective point clouds positioned at the bottom of a groove in the gallery point cloud data, and establishing a first position connecting line;
acquiring the effective point cloud positioned in the middle of a semicircle in the outer corridor point cloud data, and acquiring the longest position line of the effective point cloud in the outer corridor boundary area, and determining the longest position line as a second position line;
And determining an intersection point of the first position connecting line and the second position connecting line as the effective center reference position.
8. The method for detecting the cross-sectional area of a contact line of a 3D point cloud railway according to claim 7, wherein the establishing the profile function set according to the position parameters of all the effective point clouds comprises:
sequentially acquiring the position parameters Q of adjacent effective point clouds along a second set direction t-1 ＝(L t-1 ，θ t-1 )，Q t ＝(L t ，θ t ) Wherein t represents the sequence value of the effective point cloud along the second setting direction, and t is more than 1 and less than or equal to n, and n is the total number of the effective point clouds in the outline point cloud data;
according to parameter Q t-1 And Q t Establishing a profile function R between two adjacent effective point clouds t (θ t )；
Acquiring outline functions among all adjacent effective point clouds in the outline point cloud data to form an outline function set H= { R 2 (θ 2 )，R 3 (θ 3 )，…，R n (θ n )}。
9. The method for detecting the cross-sectional area of the 3D point cloud railway contact line according to claim 8, wherein the calculating the cross-sectional area according to the profile function and the outline point cloud data to obtain the cross-sectional point cloud area data comprises:
acquiring the profile function set H, and acquiring the cross-section point cloud area value S according to the following formula Point cloud ：
10. The method for detecting the cross-sectional area of a 3D point cloud railway contact line according to claim 9, wherein the performing wear-level analysis according to the cross-sectional point cloud area data in combination with standard cross-sectional area data comprises:
acquiring the cross-section point cloud area value S Point cloud And standard cross-sectional area value S Standard of Calculate the consumption value S Consumption of ：
S Consumption of ＝S Standard of -S Point cloud 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310289866.8A CN116309788A (en) | 2023-03-23 | 2023-03-23 | 3D point cloud railway contact line cross-sectional area detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310289866.8A CN116309788A (en) | 2023-03-23 | 2023-03-23 | 3D point cloud railway contact line cross-sectional area detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116309788A true CN116309788A (en) | 2023-06-23 |
Family
ID=86812962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310289866.8A Pending CN116309788A (en) | 2023-03-23 | 2023-03-23 | 3D point cloud railway contact line cross-sectional area detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116309788A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117291912A (en) * | 2023-11-24 | 2023-12-26 | 江西中汇云链供应链管理有限公司 | Deep learning and laser radar-based aluminum bar storage checking method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018094383A1 (en) * | 2016-11-21 | 2018-05-24 | University Of New Hampshire | Method of estimating a whole object surface area and volume of a micro-scale three-dimensional model with a partially visible surface |
| CN109085604A (en) * | 2018-08-22 | 2018-12-25 | 上海华测导航技术股份有限公司 | A kind of system and method for power-line patrolling |
| US20210150231A1 (en) * | 2019-11-14 | 2021-05-20 | Toyota Research Institute, Inc. | 3d auto-labeling with structural and physical constraints |
| CN113478295A (en) * | 2020-03-17 | 2021-10-08 | 佛雷萨股份公司 | Method for determining the wear state of a tool |
| CN114782947A (en) * | 2022-06-22 | 2022-07-22 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN115797288A (en) * | 2022-11-30 | 2023-03-14 | 安徽开源路桥有限责任公司 | Method for calculating filling and excavating volume based on ground point cloud data |
-
2023
- 2023-03-23 CN CN202310289866.8A patent/CN116309788A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018094383A1 (en) * | 2016-11-21 | 2018-05-24 | University Of New Hampshire | Method of estimating a whole object surface area and volume of a micro-scale three-dimensional model with a partially visible surface |
| CN109085604A (en) * | 2018-08-22 | 2018-12-25 | 上海华测导航技术股份有限公司 | A kind of system and method for power-line patrolling |
| US20210150231A1 (en) * | 2019-11-14 | 2021-05-20 | Toyota Research Institute, Inc. | 3d auto-labeling with structural and physical constraints |
| CN113478295A (en) * | 2020-03-17 | 2021-10-08 | 佛雷萨股份公司 | Method for determining the wear state of a tool |
| CN114782947A (en) * | 2022-06-22 | 2022-07-22 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN115797288A (en) * | 2022-11-30 | 2023-03-14 | 安徽开源路桥有限责任公司 | Method for calculating filling and excavating volume based on ground point cloud data |
Non-Patent Citations (6)
| Title |
|---|
| 宋爽: "基于机载LiDAR点云的电力走廊三维要素提取技术", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 08, pages 1 - 66 * |
| 张昌赛: "机载LiDAR输电线走廊点云数据自动分类和树障预警分析方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 01, pages 1 - 55 * |
| 段晓峰 等: "铁路线路点云数据可视化重构方法研究", 《铁道标准设计》, vol. 61, no. 04, pages 14 - 18 * |
| 董晓宇 等: "持续荷载作用下锈蚀钢筋横截面积概率分布模型", 《混凝土》, no. 10, pages 1 - 5 * |
| 陈科羽 等: "无人机载多载荷输电线路巡检方法研究", 《电力大数据》, vol. 23, no. 02, pages 80 - 86 * |
| 麻卫峰: "机载激光点云输电线路巡检关键技术研究", 《中国博士学位论文全文数据库 基础科学辑》, no. 04, pages 1 - 137 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117291912A (en) * | 2023-11-24 | 2023-12-26 | 江西中汇云链供应链管理有限公司 | Deep learning and laser radar-based aluminum bar storage checking method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106251361B (en) | A kind of rail surface defects image self-adapting division method | |
| CN105975913B (en) | Road network extraction method based on adaptive cluster learning | |
| JP2017520029A (en) | Capacity prediction method, system and computer equipment based on Kalman filter | |
| CN116309788A (en) | 3D point cloud railway contact line cross-sectional area detection method | |
| Wu et al. | Watershed-based morphological separation of wear debris chains for on-line ferrograph analysis | |
| CN103440644A (en) | Multi-scale image weak edge detection method based on minimum description length | |
| CN107358177A (en) | A kind of medium and long distance pedestrian detection method and terminal device based on graphical analysis | |
| Qiu et al. | Methodology for accurate AASHTO PP67-10–based cracking quantification using 1-mm 3D pavement images | |
| CN116152749B (en) | Intelligent gear wear monitoring method based on digital twin | |
| CN115115627B (en) | Soil saline-alkali soil monitoring method based on data processing | |
| CN115797473B (en) | Concrete forming evaluation method for civil engineering | |
| CN104036485A (en) | Method about image resampling tampering detection | |
| CN111764208A (en) | Steel rail grinding profile rapid prediction method based on interval segmentation | |
| CN109214522B (en) | Equipment performance degradation evaluation method based on multiple attributes | |
| CN108931206A (en) | Method for distinguishing is known for rail profile outlier detection and effective profile | |
| Ou et al. | A data‐driven approach to determining freeway incident impact areas with fuzzy and graph theory‐based clustering | |
| CN114817228A (en) | Abnormal value removing method for long-time sequence monitoring data of lake water level | |
| CN105452803A (en) | Data generation method and data generation device | |
| CN115330799A (en) | Automatic fault diagnosis method for instrument | |
| CN103996266B (en) | Tailing reservoir safety monitoring device based on video analysis | |
| CN113779672B (en) | Rail profile abrasion calculation method, device, equipment and storage medium | |
| CN114240916A (en) | Multi-polarized light point cloud data fusion method and device for appearance state of steel rail | |
| CN114244594A (en) | Network flow abnormity detection method and detection system | |
| Jiang | A crack detection and diagnosis methodology for automated pavement condition evaluation | |
| CN106153507B (en) | A kind of method of mini-frac proppant sphericity |
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 |