CN115824231B - Intelligent positioning management system for automobile running - Google Patents
Intelligent positioning management system for automobile running Download PDFInfo
- Publication number
- CN115824231B CN115824231B CN202310148003.9A CN202310148003A CN115824231B CN 115824231 B CN115824231 B CN 115824231B CN 202310148003 A CN202310148003 A CN 202310148003A CN 115824231 B CN115824231 B CN 115824231B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- positioning
- unmanned automobile
- moment
- abnormal
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of automobile positioning management, and discloses an intelligent automobile driving positioning management system.
Description
Technical Field
The invention relates to the technical field of automobile positioning management, in particular to an unmanned automobile positioning management technology, and specifically relates to an intelligent automobile driving positioning management system.
Background
In recent years, with the continuous progress of information technology and the rapid development of artificial intelligence, the traditional automobile industry is also coming into new reform. The appearance of unmanned automobiles improves the efficiency of transportation to a certain extent, and reduces the potential traffic hazard.
Because unmanned vehicles have the demand of position location in the driving process, all can be equipped with the location terminal on the unmanned vehicles now, and wherein the location terminal of mainstream is the GPS locator, but the GPS locator can receive external environment (for example satellite signal interference, bad weather etc.) influence at actual application in-process and lead to unable real-time guarantee location accuracy. In this case, it is necessary to correct the abnormal positioning.
In the prior art, as disclosed in Chinese patent application with application publication number of CN109581449A, a positioning method and a system for an automatic driving automobile are used for acquiring traffic environment information around the automobile through an on-board camera and calculating to obtain theoretical positioning coordinates of the automobile according to the traffic environment information and the high-precision map; and acquiring satellite positioning coordinates of the vehicle through a navigation positioning system, and correcting according to a comparison result of the theoretical coordinates and the satellite positioning coordinates. The invention has the following defects in the practical application process: according to the invention, the correction of the abnormal positioning is carried out in real time, so that the vehicle-mounted camera is required to be in a working state in the whole course, and the situation that the correction is not required actually exists, so that the vehicle-mounted camera is difficult to operate according to the requirement, the invalid work of the vehicle-mounted camera is easy to cause, the practicability is poor, and the service life of the vehicle-mounted camera is reduced due to the long-term use of the high frequency of the vehicle-mounted camera.
In the second aspect, the determination of the theoretical positioning coordinates of the vehicle is based on the traffic environment information acquired by the vehicle-mounted camera, so that the driving scene for implementing the abnormal positioning correction is singly fixed on the road, and the similar positions of the traffic environment are possible to exist in reality, so that the reliability of the abnormal positioning correction result is affected to a certain extent, and the driving scene on which the abnormal positioning correction is based is too one-sided, so that the application limitation exists and the complex and various driving scenes in reality are not adapted.
Disclosure of Invention
In order to solve the technical problems, the invention is realized by the following technical scheme: an intelligent positioning management system for automobile running, comprising: and the positioning equipment setting module is used for setting a GPS (global positioning system) positioning instrument and positioning auxiliary equipment on the unmanned automobile.
And the initial navigation route planning module is used for inputting a driving starting point and a driving end point on a navigation terminal of the unmanned automobile, and planning an initial navigation route of the unmanned automobile according to the driving starting point and the driving end point.
And the positioning information acquisition module is used for acquiring the driving position and positioning auxiliary information of the unmanned automobile according to the defined monitoring moments by the GPS positioning instrument and the positioning auxiliary equipment respectively in the driving process of the unmanned automobile according to the planned initial navigation route.
And the positioning abnormality judging module is used for judging whether the positioning of the unmanned automobile at each monitoring moment is abnormal or not.
And the normal monitoring moment identification module is used for marking the monitoring moment as the abnormal monitoring moment when the positioning abnormality of the unmanned automobile at a certain monitoring moment is judged, and reversely pushing the abnormal monitoring moment forward to obtain the normal monitoring moment.
And the normal monitoring moment positioning and extracting module is used for extracting the driving position of the unmanned automobile positioned at the normal monitoring moment.
And the positioning monitoring area demarcation module is used for demarcating the positioning monitoring area of the unmanned vehicle at the abnormal monitoring moment on the electronic map according to the running position of the unmanned vehicle at the normal monitoring moment.
And the positioning correction module is used for determining the corrected driving position of the unmanned automobile at the abnormal monitoring moment according to the positioning monitoring area of the unmanned automobile at the abnormal monitoring moment.
And the initial navigation route changing module is used for changing the initial navigation route based on the corrected driving position of the unmanned automobile at the abnormal monitoring moment.
Preferably, the positioning assistance device includes a GPS detector, a panoramic camera, and a vehicle speed detector.
Preferably, the positioning device setting module further includes obtaining setting parameters corresponding to each panoramic camera, where the setting parameters include a view angle range, a setting azimuth, and a setting focal length.
Preferably, the positioning assistance information includes GPS signal strength and travel speed.
Preferably, the determining whether the positioning of the unmanned automobile at each monitoring time is abnormal is as follows: s1, extracting GPS signal intensity from positioning auxiliary information of the unmanned automobile at each monitoring moment, and enabling the GPS signal intensity to pass through a formula
Calculating the positioning accuracy of the unmanned automobile at each monitoring moment>
T is denoted as monitoring time number, +.>
，/>
GPS signal strength, expressed as unmanned car at time t monitoring time,/for>
Expressed as standard GPS signal strength, e is expressed as a natural constant.
S2, comparing the positioning accuracy of the unmanned automobile at each monitoring moment with a set threshold value, and judging that the positioning of the unmanned automobile at a certain monitoring moment is abnormal if the positioning accuracy of the unmanned automobile at the certain monitoring moment is smaller than the set threshold value.
Preferably, the specific operation mode of the normal monitoring time is obtained by pushing the abnormal monitoring time forward in a reverse way: and sequentially extracting the last monitoring time corresponding to the abnormal monitoring time, judging whether the positioning of the unmanned automobile at the monitoring time is abnormal according to S1-S2, and further taking the monitoring time which is the normal judgment result and is closest to the abnormal monitoring time as the normal monitoring time.
Preferably, the defining the positioning monitoring area of the unmanned vehicle at the abnormal monitoring moment refers to the following steps: and marking a travel position point on the electronic map according to the travel position of the unmanned automobile positioned at the normal monitoring moment.
The driving speeds of the unmanned automobile at the normal monitoring moment and the abnormal monitoring moment are respectively extracted from the positioning auxiliary information of the unmanned automobile at each monitoring moment, and a formula is utilized
Calculating the corresponding driving speed fluctuation degree of the unmanned automobile>
，/>
、/>
Respectively representing the running speeds of the unmanned automobile at the normal monitoring moment and the abnormal monitoring moment.
Comparing the driving speed fluctuation degree corresponding to the unmanned automobile with a set critical value, and if the driving speed fluctuation degree corresponding to the unmanned automobile is smaller than or equal to the set critical value, then
The result obtained is the effective driving speed of the unmanned vehicle, whereas +.>
As an effective travel speed for the unmanned vehicle.
And acquiring the driving time length between the normal monitoring time and the abnormal monitoring time.
And calculating the driving distance from the normal monitoring moment to the abnormal monitoring moment of the unmanned automobile according to the effective driving speed and the driving duration corresponding to the unmanned automobile.
And taking a running position point marked on the electronic map as a circle center, taking a running distance from a normal monitoring moment to an abnormal monitoring moment of the unmanned automobile as a radius to make a circle, wherein an area in the circle is a positioning monitoring area of the unmanned automobile at the abnormal monitoring moment.
Preferably, the determining the corrected driving position of the unmanned automobile at the abnormality monitoring time includes the steps of: (1) Surrounding environment collection areas corresponding to the panoramic cameras in the unmanned automobile are identified, surrounding environment collection area outlines are extracted from the surrounding environment collection areas, and then the panoramic cameras in the positioning auxiliary equipment are started at abnormal monitoring moments to collect surrounding environment panoramic images of the running positions of the unmanned automobile.
(2) And (3) equally-spaced concentric circle division is carried out on the positioning monitoring area of the unmanned automobile at the abnormal monitoring moment.
(3) Determining the arrangement intervals of the monitoring points from the outline of the surrounding environment acquisition area, arranging the monitoring points on each concentric circle according to the arrangement intervals to obtain a plurality of monitoring points, and further demarcating the reference area according to the outline of the surrounding environment acquisition area by taking the positions of the monitoring points arranged on each concentric circle as the center to obtain the reference area corresponding to each monitoring point on each concentric circle.
(4) And extracting a live-action image corresponding to a positioning monitoring area of the unmanned automobile at an abnormal monitoring moment from the live-action map, and intercepting a reference area live-action image corresponding to each monitoring point on each concentric circle from the live-action image.
(5) And respectively carrying out superposition comparison on the reference area live-action image corresponding to each monitoring point on each concentric circle and the surrounding environment panoramic image of the running position of the unmanned vehicle to obtain the reference area superposition rate corresponding to each monitoring point on each concentric circle, comparing the reference area superposition rate with the effective superposition rate, extracting the position of the monitoring point from the electronic map if the reference area superposition rate is greater than or equal to the monitoring point of the effective superposition rate, taking the position of the monitoring point as the corrected running position of the unmanned vehicle at the abnormal monitoring moment, and executing according to the determination algorithm of the special corrected running position if the reference area superposition rates of all the monitoring points on all the concentric circles are smaller than the effective superposition rate.
Preferably, the algorithm for determining the special corrected travel position performs the following steps: and in the first step, key monitoring points are screened from all monitoring points distributed on all concentric circles, and adjacent monitoring points corresponding to the key monitoring points are acquired according to the positions of the key monitoring points and recorded as auxiliary monitoring points.
And secondly, extracting an effective monitoring area from a reference area corresponding to the key monitoring point, further intercepting a live-action image corresponding to the effective monitoring area from a live-action image of the reference area corresponding to the key monitoring point, performing superposition comparison between the live-action image and a surrounding environment panoramic image of a running position of the unmanned automobile, and intercepting an uncombined part image.
And thirdly, matching the real images of the reference areas corresponding to the auxiliary monitoring points with the non-overlapping part images, identifying specific monitoring points from the real images, and further outlining the areas corresponding to the non-overlapping part images in the reference areas corresponding to the monitoring points, and recording the areas as key monitoring areas.
And fourthly, fusing the effective monitoring areas corresponding to the key monitoring points with the key monitoring areas to obtain a complete monitoring area, further taking the central point corresponding to the complete monitoring area, extracting the position of the central point from the electronic map, and taking the position as the corrected driving position of the unmanned automobile at the abnormal monitoring moment.
Preferably, the determining the surrounding environment acquisition area corresponding to the panoramic camera in the unmanned automobile includes the following steps: (11) And extracting the view angle range and the setting azimuth from the setting parameters corresponding to the panoramic cameras on the unmanned automobile, so as to obtain the shooting angle interval of the panoramic cameras on one circumference.
(12) And extracting a set focal length from set parameters corresponding to all the panoramic cameras on the unmanned automobile, so as to match the adaptive visual distance corresponding to all the panoramic cameras.
(13) And outlining a surrounding environment acquisition area corresponding to the panoramic cameras in the unmanned automobile according to the shooting angle interval and the adaptive visual distance of each panoramic camera on one circumference of the unmanned automobile.
Compared with the prior art, the invention has the following advantages: 1. according to the invention, the GPS signal intensity is acquired in real time in the running process of the unmanned automobile, whether the positioning is abnormal or not is identified according to the GPS signal intensity, and the front end identification of the positioning abnormality is realized, so that the panoramic camera is started to work when the positioning abnormality is identified, the panoramic camera can work as required, the incidence rate of invalid work of the panoramic camera is greatly reduced, and the service life of the panoramic camera is prolonged.
2. According to the invention, when the positioning abnormality is identified, the real-scene image of the positioning monitoring area of the unmanned automobile at the abnormality monitoring moment is intercepted, and meanwhile, the panoramic camera is started to acquire the surrounding environment panoramic image of the running position of the unmanned automobile, so that the abnormal positioning correction is carried out based on the matching result of the real-scene image and the surrounding environment panoramic image.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings.
FIG. 1 is a schematic diagram of a system connection according to the present invention.
Fig. 2 is a schematic diagram of concentric circles and monitoring point layout on a positioning monitoring area according to the present invention.
Fig. 3 is a schematic diagram of a reference area corresponding to each monitoring point on each concentric circle according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an intelligent positioning management system for automobile driving includes a positioning device setting module, an initial navigation route planning module, a positioning information acquisition module, a positioning abnormality judgment module, a normal monitoring time identification module, a normal monitoring time positioning extraction module, a positioning monitoring area demarcation module, a positioning correction module and an initial navigation route changing module.
The positioning equipment setting module and the initial navigation route planning module are respectively connected with the positioning information acquisition module, the positioning information acquisition module is respectively connected with the positioning abnormality judgment module and the positioning monitoring area demarcation module, the positioning information acquisition module is connected with the positioning abnormality judgment module, the positioning abnormality judgment module is connected with the normal monitoring moment identification module, the normal monitoring moment identification module is connected with the normal monitoring moment positioning extraction module, the normal monitoring moment positioning extraction module is connected with the positioning monitoring area demarcation module, the positioning monitoring area demarcation module is connected with the positioning correction module, and the positioning correction module and the initial navigation route planning module are both connected with the initial navigation route changing module.
The positioning equipment setting module is used for setting a GPS (global positioning system) positioning instrument and positioning auxiliary equipment on the unmanned automobile, and the positioning auxiliary equipment comprises a GPS detector, a panoramic camera and a vehicle speed detector, wherein the GPS detector is used for collecting GPS signal intensity, the panoramic camera is used for collecting panoramic images, and the vehicle speed detector is used for collecting running speed.
As a preferable scheme of the invention, the positioning equipment setting module further comprises a step of obtaining setting parameters corresponding to all panoramic cameras, wherein the setting parameters comprise a visual angle range, a setting azimuth and a setting focal length.
The initial navigation route planning module is used for inputting a driving starting point and a driving end point on a navigation terminal of the unmanned automobile, and planning an initial navigation route of the unmanned automobile according to the driving starting point and the driving end point.
The positioning information acquisition module is used for acquiring the driving position and positioning auxiliary information of the unmanned automobile according to each defined monitoring moment by the GPS positioning instrument and the positioning auxiliary equipment respectively in the driving process of the unmanned automobile according to the planned initial navigation route, wherein the positioning auxiliary information comprises GPS signal intensity and driving speed.
The above-mentioned method of defining the monitoring time is to record the starting travel time point when the unmanned vehicle starts traveling, and further obtain each monitoring time at a predetermined fixed time interval.
The positioning abnormality judging module is used for judging whether the positioning of the unmanned automobile at each monitoring moment is abnormal or not, and the specific implementation mode is as follows S1, the GPS signal intensity is extracted from the positioning auxiliary information of the unmanned automobile at each monitoring moment, and the GPS signal intensity is processed through a formula
Calculating the positioning accuracy of the unmanned automobile at each monitoring moment>
T is denoted as monitoring time number, +.>
M is denoted by the number of delimited monitoring instants, < >>
GPS signal strength, expressed as unmanned car at time t monitoring time,/for>
Expressed as standard GPS signal intensity, e is expressed as a natural constant, wherein the closer the GPS signal intensity of the unmanned automobile at a certain monitoring moment is to the standard GPS signal intensity, the higher the positioning accuracy of the unmanned automobile at the monitoring moment is.
S2, comparing the positioning accuracy of the unmanned automobile at each monitoring moment with a set threshold value, and judging that the positioning of the unmanned automobile at a certain monitoring moment is abnormal if the positioning accuracy of the unmanned automobile at the certain monitoring moment is smaller than the set threshold value.
According to the invention, the GPS signal intensity is acquired in real time in the running process of the unmanned automobile, whether the positioning is abnormal or not is identified according to the GPS signal intensity, and the front end identification of the positioning abnormality is realized, so that the panoramic camera is started to work when the positioning abnormality is identified, the panoramic camera can work as required, the incidence rate of invalid work of the panoramic camera is greatly reduced, and the service life of the panoramic camera is prolonged.
The normal monitoring time identification module is used for marking the monitoring time as an abnormal monitoring time when the unmanned automobile is judged to be abnormal in positioning at a certain monitoring time, and pushing the abnormal monitoring time forwards to obtain the normal monitoring time, and the specific operation mode is as follows: and sequentially extracting the last monitoring time corresponding to the abnormal monitoring time, judging whether the positioning of the unmanned automobile at the monitoring time is abnormal according to S1-S2, and further taking the monitoring time which is the normal judgment result and is closest to the abnormal monitoring time as the normal monitoring time.
The normal monitoring time positioning extraction module is used for extracting the driving position of the unmanned automobile positioned at the normal monitoring time from the driving positions of the unmanned automobile positioned at each monitoring time based on the normal monitoring time.
The positioning monitoring area demarcation module is used for demarcating the positioning monitoring area of the unmanned vehicle at the abnormal monitoring moment on the electronic map according to the running position of the unmanned vehicle at the normal monitoring moment, and the following steps are specifically referred to: and marking a travel position point on the electronic map according to the travel position of the unmanned automobile positioned at the normal monitoring moment.
The driving speeds of the unmanned automobile at the normal monitoring moment and the abnormal monitoring moment are respectively extracted from the positioning auxiliary information of the unmanned automobile at each monitoring moment, and a formula is utilized
Calculating the corresponding driving speed fluctuation degree of the unmanned automobile>
，/>
、/>
The driving speed of the unmanned automobile at the normal monitoring moment and the abnormal monitoring moment is respectively expressed as the driving speed of the unmanned automobile, wherein the closer the driving speed of the unmanned automobile is between the normal monitoring moment and the abnormal monitoring moment, the smaller the driving speed fluctuation degree corresponding to the unmanned automobile is.
Comparing the driving speed fluctuation degree corresponding to the unmanned automobile with a set critical value, and if the driving speed fluctuation degree corresponding to the unmanned automobile is smaller than or equal to the set critical value, then
The result is obtained as an effective travel speed corresponding to the unmanned vehicle,otherwise, use +.>
As an effective travel speed for the unmanned vehicle.
According to the invention, the analysis of the effective running speed corresponding to the unmanned automobile is carried out by taking the relation between the running speeds of the unmanned automobile at the normal monitoring moment and the abnormal monitoring moment as an analysis basis instead of taking the running speeds of the unmanned automobile at the normal monitoring moment and the abnormal monitoring moment as the effective running speeds, so that the accuracy of an analysis result can be effectively improved, and the reliable reference is improved for defining the positioning monitoring area of the unmanned automobile at the abnormal monitoring moment subsequently.
And acquiring the driving time length between the normal monitoring time and the abnormal monitoring time.
And multiplying the effective running speed and the running duration corresponding to the unmanned automobile to obtain the running distance from the normal monitoring moment to the abnormal monitoring moment of the unmanned automobile.
And taking a running position point marked on the electronic map as a circle center, taking a running distance from a normal monitoring moment to an abnormal monitoring moment of the unmanned automobile as a radius to make a circle, wherein an area in the circle is a positioning monitoring area of the unmanned automobile at the abnormal monitoring moment.
The method and the device for locating and correcting the abnormal monitoring time of the unmanned automobile define the locating and monitoring area of the unmanned automobile at the abnormal monitoring time, and consider that the unmanned automobile is not stationary but moves between the normal monitoring time and the abnormal monitoring time, so that the abnormal locating and correcting cannot be carried out by the driving position of the unmanned automobile located at the normal monitoring time, and the locating and monitoring area is defined on the basis of the moving state of the unmanned automobile between the normal monitoring time and the abnormal monitoring time, thereby being beneficial to providing an accurate and reliable correcting range for locating and correcting the unmanned automobile at the abnormal monitoring time.
The positioning correction module is used for determining a corrected driving position of the unmanned automobile at the abnormal monitoring moment according to the positioning monitoring area of the unmanned automobile at the abnormal monitoring moment, and comprises the following steps: (1) Surrounding environment collection areas corresponding to the panoramic cameras in the unmanned automobile are identified, and surrounding environment collection area outlines are extracted from the surrounding environment collection areas, so that the surrounding environment collection area is obtained, and then the panoramic cameras in the positioning auxiliary equipment are started at abnormal monitoring time to collect surrounding environment panoramic images of the running position of the unmanned automobile.
In a specific embodiment of the invention, the surrounding environment acquisition area corresponding to the panoramic camera in the unmanned automobile is identified by the following steps: (11) And extracting the view angle range and the setting azimuth from the setting parameters corresponding to the panoramic cameras on the unmanned automobile, so as to obtain the shooting angle interval of the panoramic cameras on one circumference.
(12) And extracting the set focal length from the set parameters corresponding to the panoramic cameras on the unmanned automobile, and matching the set focal length with the adaptive visual distance corresponding to each set focal length to obtain the adaptive visual distance corresponding to each panoramic camera.
(13) And outlining a surrounding environment acquisition area corresponding to the panoramic cameras in the unmanned automobile according to the shooting angle interval and the adaptive visual distance of each panoramic camera on one circumference of the unmanned automobile.
It should be noted that, the above-mentioned surrounding environment collection area outline is specifically that when the front, back, left and right sides of the unmanned vehicle all have panoramic cameras, and the shooting angle that all panoramic cameras formed can enclose into a circumference, the surrounding environment collection area outline is a circular at this moment, and when the unmanned vehicle only has the panoramic cameras at the front, left and right sides, the surrounding environment collection area outline is a fan-shaped at this moment.
(2) And (3) equally-spaced concentric circle division is carried out on the positioning monitoring area of the unmanned automobile at the abnormal monitoring moment.
(3) Determining the arrangement intervals of the monitoring points from the outline of the surrounding environment acquisition area, arranging the monitoring points on each concentric circle according to the arrangement intervals to obtain a plurality of monitoring points, and further demarcating the reference area according to the outline of the surrounding environment acquisition area by taking the positions of the monitoring points arranged on each concentric circle as the center to obtain the reference area corresponding to each monitoring point on each concentric circle.
It is to be reminded that concentric circles and monitoring point layout on the positioning monitoring area are shown with reference to fig. 2.
The reference areas corresponding to the monitoring points on the concentric circles are schematically shown with reference to fig. 3, taking the outline of the surrounding environment collection area as a circle as an example.
As a preferred embodiment of the present invention, the specific determination method for determining the arrangement space of the monitoring points from the outline of the surrounding environment collection area is as follows: when the contour of the surrounding environment collecting area is a circle, the diameter of the circle is used as the arrangement interval of the monitoring points, and when the contour of the surrounding environment collecting area is a sector, the radius of the sector is used as the arrangement interval of the monitoring points.
According to the method, the arrangement interval of the monitoring points on the concentric circle is determined according to the outline of the surrounding environment acquisition area, so that the arrangement quantity of the monitoring points can be reduced to the greatest extent, the comparison times of the monitoring points are further reduced, and the abnormal positioning correction efficiency is improved while the abnormal positioning correction target is guaranteed to be realized.
(4) And extracting a live-action image corresponding to a positioning monitoring area of the unmanned automobile at an abnormal monitoring moment from the live-action map, and intercepting a reference area live-action image corresponding to each monitoring point on each concentric circle from the live-action image.
(5) The real images of the reference areas corresponding to the monitoring points on the concentric circles are respectively overlapped and compared with the surrounding environment panoramic images of the running positions of the unmanned vehicles to obtain the overlapping areas of the reference areas corresponding to the monitoring points on the concentric circles, and the overlapping areas pass through the formula
And calculating the coincidence rate of the reference area corresponding to each monitoring point on each concentric circle, comparing the coincidence rate with the effective coincidence rate, and if the monitoring point with the coincidence rate of the reference area being larger than or equal to the effective coincidence rate exists, extracting the position of the monitoring point from the electronic map, and taking the position as the corrected driving position of the unmanned automobile at the abnormal monitoring moment.
Before the reference area live-action image corresponding to each monitoring point on each concentric circle is overlapped and compared with the surrounding environment panoramic image of the driving position of the unmanned vehicle, the comparison sequence of each concentric circle and each monitoring point is analyzed, and the specific analysis process is as follows: a1, sequencing all concentric circles according to the sequence from far to near from the circle center.
A2, extracting regional environment elements, such as road signs, buildings, trees and the like, from the reference region live-action images corresponding to the monitoring points on the concentric circles.
A3, extracting surrounding environment elements from the surrounding environment panoramic image of the driving position of the unmanned automobile.
And A4, comparing the environment elements extracted from the reference area live-action images corresponding to the monitoring points on the concentric circles with the surrounding environment elements extracted from the surrounding environment panoramic images of the driving positions of the unmanned vehicles, counting the number of successfully matched environment elements in the reference area live-action images corresponding to the monitoring points on the concentric circles, and sequencing the monitoring points distributed on the concentric circles according to the sequence of the successfully matched environment elements from large to small, so as to obtain the comparison sequence of the monitoring points on the concentric circles.
The invention aims to improve the determination efficiency of the corrected driving position by comparing the concentric circles and the monitoring points which are obtained by dividing the positioning monitoring area, wherein the analysis basis is that the driving position of the unmanned automobile at the abnormal monitoring moment is very likely to be concentrated on the circumference of the positioning monitoring area because the unmanned automobile moves between the normal monitoring moment and the abnormal monitoring moment, therefore, the concentric circles farthest from the circle center are compared firstly, the determination efficiency of the corrected driving position can be improved, in addition, the sorting of the monitoring points can lead the monitoring points with a plurality of successfully matched environmental elements to be compared preferentially, and the determination efficiency of the corrected driving position can be improved to the greatest extent.
When the coincidence rate of the reference areas corresponding to all monitoring points on all concentric circles is smaller than the effective coincidence rate, the method is executed according to a special correction driving position determining algorithm, and specifically comprises the following steps: the first step, screening key monitoring points from all monitoring points distributed on all concentric circles, wherein the specific screening mode is as follows: and sequencing the monitoring points on each concentric circle according to the reference region coincidence rate in a descending order, extracting the monitoring point corresponding to the maximum reference region coincidence rate from the sequencing result, marking the monitoring point as a key monitoring point, and acquiring the adjacent monitoring point corresponding to the key monitoring point according to the position of the key monitoring point, and marking the adjacent monitoring point as an auxiliary monitoring point.
Extracting an effective monitoring area from a reference area corresponding to a key monitoring point in a specific extraction mode, namely extracting an uncombined area from the reference area corresponding to the key monitoring point, removing the uncombined area to obtain the effective monitoring area corresponding to the key monitoring point, further intercepting a live-action image of the effective monitoring area from a live-action image of the reference area corresponding to the key monitoring point, and performing superposition comparison between the live-action image and a surrounding environment panoramic image of a driving position corresponding to an abnormal monitoring moment of the unmanned vehicle, and intercepting an uncombined part image from the live-action image;
and thirdly, matching the real images of the reference areas corresponding to the auxiliary monitoring points with the non-coincident part images, screening out the auxiliary monitoring points successfully matched from the real images, marking the auxiliary monitoring points as specific monitoring points, and further outlining the areas corresponding to the non-coincident part images in the reference areas corresponding to the monitoring points, and marking the areas as important monitoring areas.
And fourthly, fusing the effective monitoring areas corresponding to the key monitoring points with the key monitoring areas to obtain a complete monitoring area, further taking the central point corresponding to the complete monitoring area, extracting the position of the central point from the electronic map, and taking the position as the corrected driving position of the unmanned automobile at the abnormal monitoring moment.
According to the invention, when the positioning abnormality is identified, the real-scene image of the positioning monitoring area of the unmanned automobile at the abnormality monitoring moment is intercepted, and meanwhile, the panoramic camera is started to acquire the surrounding environment panoramic image of the running position of the unmanned automobile, so that the abnormality positioning correction is carried out based on the matching result of the real-scene image and the surrounding environment panoramic image, the coincidence comparison mode adopted by the correction mode belongs to comprehensive comparison, and instead of taking traffic environment information as a comparison object, the implemented running scene is more comprehensive and is close to the actual situation, thereby avoiding the application limitation caused by taking a road as an implementation scene to the greatest extent in the prior art, being beneficial to improving the reliability of the abnormality positioning correction and having higher practical value.
The initial navigation route changing module is used for re-planning the navigation route based on the corrected driving position of the unmanned automobile at the abnormal monitoring moment, so that the change of the initial navigation route is realized.
According to the method, whether the positioning abnormality exists or not is judged in real time in the running process of the unmanned automobile according to the navigation route, and then the targeted positioning abnormality correction is carried out when the positioning abnormality exists is judged, so that the dynamic change of the navigation route is carried out, the running positioning accuracy of the unmanned automobile can be ensured to the greatest extent, meanwhile, the invalid utilization rate of the positioning auxiliary equipment can be reduced, the use time of the positioning auxiliary equipment is further prolonged, and the method has a great practical advantage.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art can be made to the described embodiments without departing from the scope of the invention or from the scope of the invention as defined in the accompanying claims.
Claims (7)
1. An intelligent positioning management system for automobile running, which is characterized by comprising:
the positioning equipment setting module is used for setting a GPS (global positioning system) positioning instrument and positioning auxiliary equipment on the unmanned automobile; the positioning auxiliary equipment comprises a GPS detector, a panoramic camera and a vehicle speed detector;
the positioning equipment setting module further comprises a step of obtaining setting parameters corresponding to all panoramic cameras, wherein the setting parameters comprise a visual angle range, a setting azimuth and a setting focal length;
the initial navigation route planning module is used for inputting a driving starting point and a driving end point on a navigation terminal of the unmanned automobile, and planning an initial navigation route of the unmanned automobile according to the driving starting point and the driving end point;
the positioning information acquisition module is used for acquiring the driving position and positioning auxiliary information of the unmanned automobile according to the defined monitoring moments by the GPS positioning instrument and the positioning auxiliary equipment respectively in the driving process of the unmanned automobile according to the planned initial navigation route;
the positioning abnormality judging module is used for judging whether the positioning of the unmanned automobile at each monitoring moment is abnormal or not;
the normal monitoring time identification module is used for marking the monitoring time as abnormal monitoring time when the positioning abnormality of the unmanned automobile at a certain monitoring time is judged, and reversely pushing the abnormal monitoring time forward to obtain the normal monitoring time;
the normal monitoring moment positioning and extracting module is used for extracting the driving position of the unmanned automobile positioned at the normal monitoring moment;
the positioning monitoring area demarcation module is used for demarcating a positioning monitoring area of the unmanned vehicle at an abnormal monitoring moment on the electronic map according to the running position of the unmanned vehicle at the normal monitoring moment;
the positioning correction module is used for determining the corrected driving position of the unmanned automobile at the abnormal monitoring moment according to the positioning monitoring area of the unmanned automobile at the abnormal monitoring moment;
the method for determining the corrected driving position of the unmanned automobile at the abnormal monitoring moment comprises the following steps:
(1) Recognizing a surrounding environment acquisition area corresponding to a panoramic camera in the unmanned automobile, extracting the outline of the surrounding environment acquisition area, and starting the panoramic camera in the positioning auxiliary equipment at the abnormal monitoring moment to acquire a surrounding environment panoramic image of the running position of the unmanned automobile;
(2) Dividing the locating monitoring area of the unmanned automobile at the abnormal monitoring moment into equidistant concentric circles;
(3) Determining the arrangement intervals of the monitoring points from the outline of the surrounding environment acquisition area, arranging the monitoring points on each concentric circle according to the arrangement intervals to obtain a plurality of monitoring points, and further demarcating a reference area according to the outline of the surrounding environment acquisition area by taking the positions of the monitoring points arranged on each concentric circle as the center to obtain the reference area corresponding to each monitoring point on each concentric circle;
(4) Extracting a live-action image corresponding to a positioning monitoring area of the unmanned automobile at an abnormal monitoring moment from the live-action map, and intercepting a reference area live-action image corresponding to each monitoring point on each concentric circle from the live-action image;
(5) Respectively carrying out superposition comparison on the real images of the reference areas corresponding to the monitoring points on each concentric circle and the surrounding environment panoramic images of the running positions of the unmanned vehicles to obtain the superposition rates of the reference areas corresponding to the monitoring points on each concentric circle, comparing the superposition rates with the effective superposition rates, extracting the positions of the monitoring points from the electronic map if the superposition rates of the reference areas are larger than or equal to the effective superposition rates of the monitoring points, taking the positions of the monitoring points as corrected running positions of the unmanned vehicles at abnormal monitoring moments, and executing according to a special correction running position determining algorithm if the superposition rates of the reference areas corresponding to all the monitoring points on all the concentric circles are smaller than the effective superposition rates;
and the initial navigation route changing module is used for changing the initial navigation route based on the corrected driving position of the unmanned automobile at the abnormal monitoring moment.
2. The intelligent positioning management system for automobile running according to claim 1, wherein: the positioning assistance information includes GPS signal strength and travel speed.
3. The intelligent positioning management system for automobile running according to claim 2, wherein: the method comprises the following steps of judging whether the positioning of the unmanned automobile at each monitoring moment is abnormal or not:
s1, extracting GPS signal intensity from positioning auxiliary information of the unmanned automobile at each monitoring moment, and enabling the GPS signal intensity to pass through a formula
Calculating the positioning accuracy of the unmanned automobile at each monitoring moment>
T is denoted as monitoring time number, +.>
，/>
Number expressed as monitoring time, +.>
GPS signal strength, expressed as unmanned car at time t monitoring time,/for>
Expressed as standard GPS signal strength, e expressed as a natural constant;
s2, comparing the positioning accuracy of the unmanned automobile at each monitoring moment with a set threshold value, and judging that the positioning of the unmanned automobile at a certain monitoring moment is abnormal if the positioning accuracy of the unmanned automobile at the certain monitoring moment is smaller than the set threshold value.
4. A vehicle travel intelligent positioning management system according to claim 3, wherein: the abnormal monitoring time is pushed forward and backward to obtain a specific operation mode of the normal monitoring time: and sequentially extracting the last monitoring time corresponding to the abnormal monitoring time, judging whether the positioning of the unmanned automobile at the monitoring time is abnormal according to S1-S2, and further taking the monitoring time which is the normal judgment result and is closest to the abnormal monitoring time as the normal monitoring time.
5. The intelligent positioning management system for automobile running according to claim 2, wherein: the method comprises the following steps of:
marking a travel position point on the electronic map according to the travel position of the unmanned automobile positioned at the normal monitoring moment;
the driving speeds of the unmanned automobile at the normal monitoring moment and the abnormal monitoring moment are respectively extracted from the positioning auxiliary information of the unmanned automobile at each monitoring moment, and a formula is utilized
Calculating the corresponding driving speed fluctuation degree of the unmanned automobile>
，/>
、/>
The driving speed of the unmanned automobile at the normal monitoring moment and the abnormal monitoring moment is respectively expressed;
comparing the driving speed fluctuation degree corresponding to the unmanned automobile with a set critical value, and if the driving speed fluctuation degree corresponding to the unmanned automobile is smaller than or equal to the set critical value, then
The result obtained is the effective driving speed of the unmanned vehicle, whereas +.>
As the effective running speed corresponding to the unmanned automobile;
acquiring the running time between the normal monitoring time and the abnormal monitoring time;
calculating the driving distance from the normal monitoring moment to the abnormal monitoring moment of the unmanned automobile according to the effective driving speed and the driving duration corresponding to the unmanned automobile;
and taking a running position point marked on the electronic map as a circle center, taking a running distance from a normal monitoring moment to an abnormal monitoring moment of the unmanned automobile as a radius to make a circle, wherein an area in the circle is a positioning monitoring area of the unmanned automobile at the abnormal monitoring moment.
6. The intelligent positioning management system for automobile running according to claim 1, wherein: the algorithm for determining the special corrected driving position performs the following steps:
screening key monitoring points from all monitoring points distributed on all concentric circles, and acquiring adjacent monitoring points corresponding to the key monitoring points according to the positions of the key monitoring points to be recorded as auxiliary monitoring points;
extracting an effective monitoring area from a reference area corresponding to a key monitoring point, further intercepting a live-action image corresponding to the effective monitoring area from a live-action image of the reference area corresponding to the key monitoring point, performing superposition comparison between the live-action image and a surrounding environment panoramic image of a running position of the unmanned automobile, and intercepting an uncombined part image from the non-superposed part image;
the third step, matching the real images of the reference areas corresponding to the auxiliary monitoring points with the images of the non-overlapping parts, identifying specific monitoring points from the real images, and outlining the areas corresponding to the images of the non-overlapping parts in the reference areas corresponding to the monitoring points, and recording the areas as key monitoring areas;
and fourthly, fusing the effective monitoring areas corresponding to the key monitoring points with the key monitoring areas to obtain a complete monitoring area, further taking the central point corresponding to the complete monitoring area, extracting the position of the central point from the electronic map, and taking the position as the corrected driving position of the unmanned automobile at the abnormal monitoring moment.
7. The intelligent positioning management system for automobile running according to claim 1, wherein: the method comprises the following steps of determining surrounding environment acquisition areas corresponding to panoramic cameras in an unmanned automobile:
(11) Extracting a visual angle range and a setting azimuth from setting parameters corresponding to all panoramic cameras on the unmanned automobile so as to obtain a shooting angle interval of each panoramic camera on the unmanned automobile on one circumference;
(12) Extracting a set focal length from set parameters corresponding to all panoramic cameras on the unmanned automobile, so as to match the adaptive visual distance corresponding to all the panoramic cameras;
(13) And outlining a surrounding environment acquisition area corresponding to the panoramic cameras in the unmanned automobile according to the shooting angle interval and the adaptive visual distance of each panoramic camera on one circumference of the unmanned automobile.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310148003.9A CN115824231B (en) | 2023-02-22 | 2023-02-22 | Intelligent positioning management system for automobile running |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310148003.9A CN115824231B (en) | 2023-02-22 | 2023-02-22 | Intelligent positioning management system for automobile running |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115824231A CN115824231A (en) | 2023-03-21 |
| CN115824231B true CN115824231B (en) | 2023-04-28 |
Family
ID=85522088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310148003.9A Active CN115824231B (en) | 2023-02-22 | 2023-02-22 | Intelligent positioning management system for automobile running |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115824231B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116878572B (en) * | 2023-07-11 | 2024-03-15 | 中国人民解放军国防大学联合勤务学院 | Multisource geographic information data analysis method based on armored car test environment |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101209062B1 (en) * | 2012-07-24 | 2012-12-06 | 주식회사 피엘케이 테크놀로지 | Gps correction system using image recognition information and its method |
| KR102263185B1 (en) * | 2013-11-05 | 2021-06-10 | 현대모비스 주식회사 | Method for determining location of vehicle |
| CN109655075B (en) * | 2019-01-16 | 2021-09-14 | 北京百度网讯科技有限公司 | Unmanned vehicle positioning method and device |
| CN111272165B (en) * | 2020-02-27 | 2020-10-30 | 清华大学 | Intelligent vehicle positioning method based on characteristic point calibration |
| CN112712558A (en) * | 2020-12-25 | 2021-04-27 | 北京三快在线科技有限公司 | Positioning method and device of unmanned equipment |
| CN114019540A (en) * | 2021-11-12 | 2022-02-08 | 深圳市乐福衡器有限公司 | Vehicle-mounted GPS correction system and correction method |
| CN114397685A (en) * | 2021-12-27 | 2022-04-26 | 无锡行米科技有限公司 | Vehicle navigation method, device, equipment and storage medium for weak GNSS signal area |
| CN114217333A (en) * | 2022-02-21 | 2022-03-22 | 北京交研智慧科技有限公司 | Road network topological abnormal position positioning method and device and related equipment |
| CN114754778A (en) * | 2022-04-02 | 2022-07-15 | 智道网联科技(北京)有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
-
2023
- 2023-02-22 CN CN202310148003.9A patent/CN115824231B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115824231A (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108388641B (en) | Traffic facility map generation method and system based on deep learning | |
| WO2020042348A1 (en) | Method for generating autonomous driving navigation map, system, vehicle-mounted terminal, and server | |
| CN109815300B (en) | Vehicle positioning method | |
| CN111508260A (en) | Vehicle parking space detection method, device and system | |
| JP6280409B2 (en) | Self-vehicle position correction method, landmark data update method, in-vehicle device, server, and self-vehicle position data correction system | |
| CN111695546A (en) | Traffic signal lamp identification method and device for unmanned vehicle | |
| CN110658539B (en) | Vehicle positioning method, device, vehicle and computer readable storage medium | |
| US11703344B2 (en) | Landmark location estimation apparatus and method, and computer-readable recording medium storing computer program programmed to perform method | |
| JP2009014574A (en) | Road information generator, road information generation method, and road information generation program | |
| CN115824231B (en) | Intelligent positioning management system for automobile running | |
| CN104422426B (en) | The method and apparatus that vehicle navigation information is provided in overpass region | |
| CN110008891B (en) | Pedestrian detection positioning method and device, vehicle-mounted computing equipment and storage medium | |
| CN111815742A (en) | Lane line generation method and system | |
| CN109515439A (en) | Automatic Pilot control method, device, system and storage medium | |
| CN113029187A (en) | Lane-level navigation method and system fusing ADAS fine perception data | |
| CN113850237B (en) | Internet vehicle target detection and evaluation method and system based on video and track data | |
| CN111144467A (en) | Method and system for realizing scene factor acquisition | |
| CN111325187A (en) | Lane position identification method and device | |
| US11443131B2 (en) | Systems and methods for creating a parking map | |
| CN114252859A (en) | Target area determination method and device, computer equipment and storage medium | |
| CN114252883A (en) | Target detection method, apparatus, computer device and medium | |
| CN115083203B (en) | Method and system for inspecting parking in road based on image recognition berth | |
| CN114252884A (en) | Method and device for positioning and monitoring roadside radar, computer equipment and storage medium | |
| CN113465608B (en) | Road side sensor calibration method and system | |
| JP2011214961A (en) | Reference pattern information generating device, method, program and general vehicle position specifying device |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An Intelligent Positioning Management System for Automobile Driving Effective date of registration: 20230629 Granted publication date: 20230428 Pledgee: Hefei high tech Company limited by guarantee Pledgor: ANHUI ART AUTOMOBILE ELECTRONIC TECHNOLOGY CO.,LTD. Registration number: Y2023980046561 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |