CN113392762B - Intersection detection method, system, terminal and computer readable storage medium - Google Patents
Intersection detection method, system, terminal and computer readable storage medium Download PDFInfo
- Publication number
- CN113392762B CN113392762B CN202110660972.3A CN202110660972A CN113392762B CN 113392762 B CN113392762 B CN 113392762B CN 202110660972 A CN202110660972 A CN 202110660972A CN 113392762 B CN113392762 B CN 113392762B
- Authority
- CN
- China
- Prior art keywords
- road
- arrow
- ground
- intersection
- detecting
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 claims abstract description 39
- 239000003550 marker Substances 0.000 claims abstract description 38
- 230000000149 penetrating effect Effects 0.000 claims description 29
- 238000010586 diagram Methods 0.000 claims description 21
- 230000000750 progressive effect Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 7
- 238000009825 accumulation Methods 0.000 claims description 6
- 230000001131 transforming effect Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 description 10
- 230000009466 transformation Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 238000003491 array Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a method, a system, a terminal and a computer readable storage medium for detecting an intersection, wherein the method for detecting the intersection comprises the following steps: acquiring a road surface annular view, and extracting a ground marker from the road surface annular view; the ground identifier comprises a road indication straight line and/or a ground arrow; when the ground marker only comprises a road indication straight line, detecting an intersection appearing in the road surface ring view according to the road indication straight line; detecting an intersection appearing in the road surface ring view according to a ground arrow when the ground marker includes only the ground arrow; or detecting an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow when the ground marker comprises the road indication straight line and the ground arrow. The intersection detection method, the system, the terminal and the computer readable storage medium can enable the intersection detection to be simpler, more efficient, faster and more accurate.
Description
Technical Field
The invention belongs to the technical field of image processing, relates to a detection method and a detection system, and in particular relates to a detection method, a detection system, a terminal and a computer readable storage medium for an intersection.
Background
The automatic parking system is an important part of an advanced intelligent driving auxiliary system, acquires the environmental information of parking through an on-vehicle sensor, and helps a driver to control a vehicle to complete parking after detecting a proper parking space. In the existing underground garage, a parking space management system with unified control is not provided, the parking spaces cannot be directly locked in the underground garage, and a reasonable path is planned in the background, so that a vehicle needs to autonomously find a proper parking space at a low speed in the complex garage. When a vehicle autonomously searches for a proper parking space at a low speed in the underground parking garage, the vehicle needs to identify an intersection besides the empty parking space, judge the intersection to turn, and further drive to a correct lane to continue to search for the parking space. The existing intersection detection algorithm is used for judging the intersection and the direction according to the air marks such as traffic lights and the like aiming at the intersection on the ground road, or providing intersection information for the automatic driving automobile under the assistance of a positioning system. However, for the automatic parking system of the underground parking garage, no obvious air sign exists, the positioning system can provide less road information and even fails, at the moment, the intersection is judged by the traditional picture detection method,
Therefore, how to provide a method, a system, a terminal and a computer readable storage medium for detecting an intersection, so as to solve the defects that the prior art cannot fully utilize various ground marks and the accuracy of detecting the intersection is low, and the like, is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, an object of the present invention is to provide a method, a system, a terminal and a computer readable storage medium for detecting an intersection, which are used for solving the problem that the accuracy of detecting intersections by fully utilizing various ground signs in the prior art is low.
To achieve the above and other related objects, an aspect of the present invention provides a method for detecting an intersection, including: acquisition path
A surface ring view, and extracting a ground marker from the surface ring view; the ground identifier comprises a road indication straight line and/or a ground arrow; when the ground marker only comprises a road indication straight line, detecting an intersection appearing in the road surface ring view according to the road indication straight line; detecting an intersection appearing in the road surface ring view according to a ground arrow when the ground marker includes only the ground arrow; or detecting an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow when the ground marker comprises the road indication straight line and the ground arrow.
In an embodiment of the present invention, the step of detecting the intersection appearing in the road surface ring view according to the road indication straight line includes: performing pixel-level progressive scanning on the extracted picture of the road indication straight line to detect whether the road indication straight line penetrating through the extracted picture exists or not; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether mutually perpendicular road indication straight lines exist; wherein the road indication straight line comprises a lane line and/or a center line.
In an embodiment of the present invention, the step of performing pixel-level progressive scanning on the extracted picture of the road indication line to detect whether the road indication line passing through the extracted picture exists includes: dividing an extracted picture of a road indication straight line into two road side pictures aiming at the extracted lane line; respectively carrying out pixel-level row-by-row/column scanning on the two road side pictures to detect whether lane lines penetrating through the pictures appear on the two road side pictures; if yes, the road junction is not detected in the road surface ring view; if not, the step of detecting whether the mutually perpendicular road indication straight lines exist or not is carried out; the standard of detecting whether the lane lines penetrating through the pictures appear in the two road side pictures is whether the continuous scanning width/row degree of the row/column scanning is larger than an accumulated threshold value or not; the step of detecting whether the mutually perpendicular road indication straight lines exist or not comprises the step of detecting whether mutually perpendicular lane lines/central lines appear in an extracted picture of the road indication straight lines or not.
In an embodiment of the present invention, the step of detecting whether the lane lines/centerlines perpendicular to each other appear in the extracted picture of the road indication straight line includes: detecting a straight line existing in the extracted picture of the road indication straight line by adopting the straight line; calculating an included angle between every two straight lines, and judging whether lane lines/central lines which are perpendicular to each other appear in the extracted picture according to the included angle; if yes, the road junction is detected in the road surface ring view; if not, the process is ended.
In an embodiment of the present invention, when the ground marker includes only a ground arrow, the step of detecting the intersection appearing in the road surface ring view according to the ground arrow includes: detecting in the extracted pictures of the ground arrows to judge whether straight arrows appear in the pictures; if yes, indicating that the intersection does not appear in the road surface ring view; if not, the intersection appears in the road surface ring view.
In an embodiment of the present invention, the step of detecting in the extracted pictures of the ground arrow to determine whether the straight arrow appears includes: acquiring a ground arrow from an extracted picture of the ground arrow; the outline of the ground arrow is a characteristic point, and the non-outline in the extracted picture of the ground arrow is a non-characteristic point; transforming the outline of the ground arrow to generate a feature map to be matched for matching with a pre-stored arrow template; superposing the feature points on the pre-stored arrow templates on the feature images to be matched, and calculating the distance between the feature points on the pre-stored arrow templates and the pixel points on the feature images to be matched; comparing the calculated distance with a distance conversion threshold value to judge whether the matching with the template is successful or not; if the method is successful, the arrow type in the template is considered as the arrow type of the ground arrow in the extracted picture, and whether the arrow type of the ground arrow is a non-straight arrow is judged; if yes, indicating that an intersection appears in the road surface ring view; if not, indicating that the intersection does not appear in the road surface ring view; if not, replacing another pre-stored arrow template, and returning to the step of superposing the characteristic points on the pre-stored arrow template on the characteristic diagram to be matched, and calculating the distance between the characteristic points on the pre-stored arrow template and the pixel points on the characteristic diagram to be matched until all pre-stored arrow templates are traversed.
In an embodiment of the present invention, the non-straight arrow includes a left turn flag arrow, a right turn flag arrow, a straight left turn flag arrow, a straight right turn flag arrow, a right and left turn flag arrow, and/or a straight right and left turn flag arrow.
In an embodiment of the present invention, when the ground marker includes a road indication line and a ground arrow, the step of detecting the intersection appearing in the road surface ring view according to the road indication line and the ground arrow includes: performing pixel-level progressive scanning on the extracted picture of the road indication straight line to detect whether the road indication straight line penetrating through the extracted picture exists or not; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether mutually perpendicular road indication straight lines exist; wherein the road indication straight line comprises a lane line and/or a central line; detecting in the extracted pictures of the ground arrows to judge whether straight arrows appear in the pictures; if yes, indicating that the intersection does not appear in the road surface ring view; if not, the intersection appears in the road surface ring view.
In an embodiment of the present invention, the step of performing pixel-level progressive scanning on the extracted picture of the road indication line to detect whether the road indication line passing through the extracted picture exists includes: dividing an extracted picture of a road indication straight line into two road side pictures aiming at the extracted lane line; respectively carrying out pixel-level row-by-row/column scanning on the two road side pictures to detect whether lane lines penetrating through the pictures appear on the two road side pictures; if yes, the road junction is not detected in the road surface ring view; if not, the step of detecting whether the mutually perpendicular road indication straight lines exist or not is carried out; the standard of detecting whether the lane lines penetrating through the pictures appear in the two road side pictures is whether the continuous scanning width/row degree of the row/column scanning is larger than an accumulated threshold value or not; the method comprises the steps of detecting whether mutually perpendicular road indication straight lines exist or not, wherein the step of detecting whether mutually perpendicular lane lines/central lines exist in an extracted picture of the road indication straight lines or not;
In an embodiment of the present invention, the step of detecting whether the lane lines/centerlines perpendicular to each other appear in the extracted picture of the road indication straight line includes: detecting a straight line existing in the extracted picture of the road indication straight line by adopting the straight line; calculating an included angle between every two straight lines, and judging whether lane lines/central lines which are perpendicular to each other appear in the extracted picture according to the included angle; if yes, the road junction is detected in the road surface ring view; if not, the step of detecting the intersection not detected in the road surface annular view, and transferring to the extracted picture of the ground arrow for detection to judge whether the straight arrow appears.
Another aspect of the present invention provides a system for detecting an intersection, including: the acquisition module is used for acquiring the road surface ring view; the extraction module is used for extracting the ground identifier from the road surface annular view; the ground identifier comprises a road indication straight line and/or a ground arrow; the detection module is used for detecting the intersection appearing in the road surface annular view; when the ground marker only comprises a road indication straight line, detecting an intersection appearing in the road surface annular view according to the road indication straight line; detecting an intersection appearing in the road surface ring view according to a ground arrow when the ground marker includes only the ground arrow; or detecting an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow when the ground marker comprises the road indication straight line and the ground arrow.
Still another aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of detecting an intersection.
In a final aspect of the present invention, a detection terminal for a road junction is provided, including: a processor and a memory; the memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory so that the detection terminal can execute the intersection detection method.
In an embodiment of the invention, the detection terminal of the road junction includes a vehicle-mounted terminal.
As described above, the intersection detection method, system, terminal and computer-readable storage medium of the present invention have the following beneficial effects:
The intersection detection method, the intersection detection system, the intersection detection terminal and the computer readable storage medium acquire the semantic segmentation results of the ground marks such as the lane lines, the central lines and the arrows on the look-around splice graph by means of the deep learning network, and the intersection detection method, the intersection detection system and the intersection detection terminal are more than the marks acquired by traditional picture detection, are more beneficial to mark distinction, and therefore have the advantages that different marks are different and different detection algorithms are adopted; and based on semantic segmentation results, the attribute values of different ground marks can be obtained, so that the ground marks can be easily obtained, the means for detecting the intersections are increased, the situation that whether lane lines are continuous or not and whether the lane lines or the central lines are vertical or not is used, and the ground arrows are detected, so that the detection of the intersections is simpler, more efficient, faster and more accurate.
Drawings
Fig. 1 shows a schematic diagram of a pre-stored arrow template for a ground arrow according to the present invention.
Fig. 2 is a schematic flow chart of an implementation of the crossing detection method of the present invention.
Fig. 2A is a schematic flow chart of S22 in the crossing detection method of the present invention.
Fig. 3A is a schematic diagram showing that lane lines penetrating through the picture are detected in each of the road side pictures according to the present invention.
Fig. 3B is a schematic diagram showing that lane lines penetrating through the picture are detected in the road side pictures according to the present invention.
Fig. 4A is a schematic view showing that the intersection of the present invention causes a lane line to be interrupted.
Fig. 4B is a schematic view showing that the intersection of the present invention causes a lane line to be interrupted.
Fig. 5A shows a schematic diagram of an intersection detected in the case of the present invention where a vertical lane line appears.
Fig. 5B shows a schematic diagram of the present invention in which an intersection is detected in the case where a vertical lane line appears.
Fig. 6A shows a schematic view of an intersection detected in the presence of mutually perpendicular centerlines of the present invention.
Fig. 6B shows a schematic view of an intersection detected with the occurrence of mutually perpendicular centerlines of the present invention.
Fig. 7 is a schematic flow chart of another implementation of the crossing detection method of the present invention.
Fig. 7A is a schematic flow chart of S72 in the method for detecting an intersection according to the present invention.
Fig. 8 shows a chamfer distance map of the present invention.
Fig. 9 is a schematic diagram showing the arrow matching result of the present invention.
Fig. 10 is a schematic flow chart of another implementation of the crossing detection method of the present invention.
Fig. 11 is a schematic structural diagram of an intersection detection system according to an embodiment of the invention.
Description of element reference numerals
| 1 | Intersection detection system |
| 11 | Acquisition module |
| 12 | Extraction module |
| 113 | Detection module |
| S21～S22 | Step (a) |
| S221～S223 | Step (a) |
| S71～S72 | Step (a) |
| S721～S726 | Step (a) |
| S91～S92 | Step (a) |
| S921～S246 | Step (a) |
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
Example 1
The intersection detection method provided by the embodiment comprises the following steps:
acquiring a road surface annular view, and extracting a ground marker from the road surface annular view; the ground identifier comprises a road indication straight line and/or a ground arrow;
when the ground marker only comprises a road indication straight line, detecting an intersection appearing in the road surface ring view according to the road indication straight line;
Detecting an intersection appearing in the road surface ring view according to a ground arrow when the ground marker includes only the ground arrow; or (b)
And when the ground marker comprises a road indication straight line and a ground arrow, detecting an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow. The method for detecting an intersection provided in this embodiment will be described in detail with reference to the drawings. The intersection detection method is applied to scenes such as traffic roads and parking lots, and the road surfaces of the scenes are provided with ground identifiers. The ground marker comprises a road indicating straight line and/or a ground arrow. The road indication straight line comprises a lane line and/or a center line. The ground arrow comprises a straight mark arrow, a left turning mark arrow, a right turning mark arrow, a straight left turning mark arrow, a straight right turning mark arrow, a right and left turning mark arrow, a straight left and right turning mark arrow, a turning mark arrow and the like as shown in fig. 1.
Referring to fig. 2, a schematic flow chart of an implementation of the method for detecting an intersection is shown. The intersection detection method is applied to the case that the ground marker only comprises a road indication straight line. As shown in fig. 2, the intersection detection method specifically includes the following steps:
s21, obtaining a road surface annular view, and extracting a ground identifier from the road surface annular view; the road surface annular view is produced based on splicing in an application scene. The ground marker comprises a road indicating straight line.
In this embodiment, the deep learning network model performs semantic segmentation on the road surface ring view, so that more marks can be obtained, and the mark distinction can be facilitated, so that the road surface ring view has the advantages that different marks are adopted and different detection algorithms are adopted, for example, a large number of lane lines and parking space lines exist in the road surface ring view, and the road surface ring view has parallel and vertical parts, and if the road surface ring view is distinguished after the road surface ring view is not subjected to semantic segmentation, the road surface ring view cannot be applied to subsequent road junction detection, and only the road junction can be judged by means of ground arrows. In the semantic segmentation result, the attribute values of different ground marks can be obtained, the ground marks can be easily obtained, and the means for detecting the intersections of the parking lot are increased.
S22, detecting the intersection appearing in the road surface annular view according to the road indication straight line.
Specifically, performing pixel-level progressive scanning on an extracted picture of a road indication straight line to detect whether the road indication straight line penetrating through the extracted picture exists or not; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether mutually perpendicular road indication straight lines exist
Referring to fig. 2A, a flow chart of S22 is shown. As shown in fig. 2A, the step S22 includes the following steps:
S221, dividing the extracted picture of the road indication line into two road side pictures for the extracted lane line.
S222, respectively carrying out pixel-level row-by-row/column scanning on the two road side pictures to detect whether lane lines penetrating through the pictures appear on the two road side pictures; if so, indicating that an intersection (specifically, an intersection) is not detected in the road surface annular view; if not, the process proceeds to S233, where it is detected whether or not there are mutually perpendicular road instruction lines. In this embodiment, since the intersection has the intersection and the t-shaped intersection, in order to accurately detect the intersection, it is necessary to detect the lane line penetrating through the image in both the road side images, as shown in fig. 3A and 3B, to determine that the road is a straight lane, and to determine that the intersection is not detected.
In this embodiment, if one of the two road side pictures recognizes that a lane line passing through the picture appears, it means that a t-junction is detected in the road surface annular view.
In this embodiment, the criterion for detecting whether the lane lines penetrating the pictures appear in both road side pictures is whether the continuous scanning width/line width of the line/column scanning is greater than the accumulation threshold.
S223, detecting whether mutually perpendicular road indication straight lines exist.
Specifically, whether lane lines/central lines which are perpendicular to each other appear in the extracted picture of the road indication straight line is detected. For example, in fig. 4A and 4B, in order to show a schematic view of a lane line break caused by an intersection, further judgment needs to be made by detecting lane lines perpendicular to each other or a perpendicular center line.
In this embodiment, the step S223 includes:
Detecting a straight line (for example, hough straight line detection) existing in the extracted picture of the road indication straight line;
calculating an included angle between every two straight lines, and judging whether lane lines/central lines which are perpendicular to each other appear in the extracted picture according to the included angle; if so, indicating that a road opening (crossroad) is detected in the road surface annular view; if not, it indicates that an intersection (crossroad) is not detected in the road surface annular view.
For example, if a vertical lane line occurs, it may be concluded that an intersection is detected, as in fig. 5A and 5B, and thus a conclusion is drawn that an intersection is detected. Similarly, as shown in fig. 6A and 6B, the detection of the center lines perpendicular to each other may also draw a conclusion that the intersection is detected.
Referring to fig. 7, a flow chart of another implementation of the method for detecting an intersection is shown. Another embodiment of the intersection detection method is applied to the ground marker only including ground arrows. As shown in fig. 7, the method for detecting the intersection specifically includes the following steps:
S71, obtaining a road surface annular view, and extracting a ground identifier from the road surface annular view; the road surface annular view is produced based on splicing in an application scene. The ground marker comprises a ground arrow. The outline of the ground arrow is a characteristic point, and the non-outline in the extracted picture of the ground arrow is a non-characteristic point.
S72, detecting the intersection appearing in the road surface annular view according to the ground arrow.
Specifically, detecting in the extracted picture of the ground arrow to judge whether a straight arrow appears in the extracted picture; if yes, indicating that the intersection does not appear in the road surface ring view; if not, the intersection appears in the road surface ring view.
Referring to fig. 7A, a flow chart of S72 is shown. As shown in fig. 7A, the step S72 includes the steps of:
S721, acquiring a ground arrow from an extracted picture of the ground arrow; the outline of the ground arrow is a characteristic point, and the non-outline in the extracted picture of the ground arrow is a non-characteristic point;
s722, transforming the outline of the ground arrow so as to generate a feature map to be matched for matching with a pre-stored arrow template.
In this embodiment, the feature map to be matched is a chamfer distance transformation map, which is a binary image with feature points and non-feature points, and the distance between each point in the map and the nearest feature point is solved to form a map, such as a chamfer distance transformation map shown in fig. 8.
S723, superposing the feature points on the pre-stored arrow templates on the feature map to be matched, and calculating the distance between the feature points on the pre-stored arrow templates and the pixel points on the feature map to be matched. In this embodiment, the distance between the feature point on the pre-stored arrow template and the pixel point on the feature map to be matched is represented by the average value of the distance transformation values corresponding to the feature point superimposed on the chamfer distance transformation map. The matched images may be translated, rotated, and scaled to match to find an optimal location. Referring to fig. 9, a schematic diagram of the arrow matching result is shown. As shown in fig. 9, several look-around views are spliced into a single picture, and then template matching is performed, and the detected results are all correctly identified.
S724, comparing the calculated distance with a distance conversion threshold value to judge whether the matching with the template is successful or not; if successful, executing S725; if not, S726 is performed.
S725, recognizing the arrow type in the template as the arrow type of the ground arrow in the extracted picture, and judging whether the arrow type of the ground arrow is a non-straight arrow; if yes, indicating that an intersection appears in the road surface ring view; if not, the road surface ring view indicates that the intersection does not appear.
The non-straight arrow includes a left turn flag arrow, a right turn flag arrow, a straight left turn flag arrow, a straight right turn flag arrow, a left-right turn flag arrow, and/or a straight left-right turn flag arrow.
S726, replacing another pre-stored arrow template, and returning to the step of superposing the characteristic points on the pre-stored arrow template on the characteristic diagram to be matched, and calculating the distance between the characteristic points on the pre-stored arrow template and the pixel points on the characteristic diagram to be matched until all pre-stored arrow templates are traversed.
Referring to fig. 10, a schematic flow chart of another implementation of the method for detecting an intersection is shown. As shown in fig. 10, the method for detecting the intersection comprises the following steps:
S91, obtaining a road surface ring view, and extracting a ground identifier from the road surface ring view; the ground identifier comprises a road indication straight line and a ground arrow;
And S92, detecting the intersection appearing in the road surface annular view according to the road indication straight line and the ground arrow.
Specifically, performing pixel-level progressive scanning on an extracted picture of the road indication line to detect whether the road indication line penetrating through the extracted picture exists or not; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether mutually perpendicular road indication straight lines exist; wherein the road indication straight line comprises a lane line and/or a central line;
Detecting in the extracted pictures of the ground arrows to judge whether straight arrows appear in the pictures; if yes, indicating that the intersection does not appear in the road surface ring view; if not, the intersection appears in the road surface ring view.
The step S92 specifically includes the following steps:
s921, the extracted picture of the road indication line is divided into two road side pictures for the extracted lane line.
S922, pixel-level row-by-row/column scanning is performed on the two road side pictures respectively to detect whether lane lines penetrating through the pictures appear on the two road side pictures; if so, indicating that an intersection (specifically, an intersection) is not detected in the road surface annular view; if not, the process proceeds to S923, where it is detected whether or not there are mutually perpendicular road instruction lines. In this embodiment, since the intersection has the intersection and the t-shaped intersection, in order to accurately detect the intersection, it is necessary to detect the lane line penetrating through the picture in both of the road side pictures, and it is determined that the road is a straight lane, and the conclusion of the intersection is not detected.
In this embodiment, if one of the two road side pictures recognizes that a lane line passing through the picture appears, it means that a t-junction is detected in the road surface annular view.
In this embodiment, the criterion for detecting whether the lane lines penetrating the pictures appear in both road side pictures is whether the continuous scanning width/line width of the line/column scanning is greater than the accumulation threshold.
S923, whether the mutually perpendicular road indication straight lines exist or not is detected.
Specifically, whether lane lines/central lines which are perpendicular to each other appear in the extracted picture of the road indication straight line is detected.
In this embodiment, the S923 includes:
Detecting a straight line (for example, hough straight line detection) existing in the extracted picture of the road indication straight line;
Calculating an included angle between every two straight lines, and judging whether lane lines/central lines which are perpendicular to each other appear in the extracted picture according to the included angle; if so, indicating that a road opening (crossroad) is detected in the road surface annular view; if not, the road surface ring view indicates that an intersection (crossroad) is not detected, and the process proceeds to S924.
For example, if a vertical lane line occurs, a conclusion may be drawn that an intersection was detected, and thus a conclusion may be drawn that an intersection was detected. Similarly, the center lines perpendicular to each other are detected, and the conclusion that the intersection is detected can be also obtained.
S924, acquiring the ground arrow from the extracted picture of the ground arrow; the outline of the ground arrow is a characteristic point, and the non-outline in the extracted picture of the ground arrow is a non-characteristic point;
S925, transforming the outline of the ground arrow so as to generate a feature map to be matched for matching with a pre-stored arrow template.
In this embodiment, the feature map to be matched is a chamfer distance transformation map, which is a binary image with feature points and non-feature points, and the distance between each point in the map and the nearest feature point is solved to form a map.
S927, the feature points on the pre-stored arrow templates are overlapped on the feature map to be matched, and the distance between the feature points on the pre-stored arrow templates and the pixel points on the feature map to be matched is calculated. In this embodiment, the distance between the feature point on the pre-stored arrow template and the pixel point on the feature map to be matched is represented by the average value of the distance transformation values corresponding to the feature point superimposed on the chamfer distance transformation map. The matched images may be translated, rotated, and scaled to match to find an optimal location. S928, comparing the calculated distance with a distance transformation threshold to judge whether the matching with the template is successful; if successful, then execution S929; if not, S920 is performed.
S929, the arrow type in the template is determined as the arrow type of the ground arrow in the extracted picture, and whether the arrow type of the ground arrow is a non-straight arrow is judged; if yes, indicating that an intersection appears in the road surface ring view; if not, the road surface ring view indicates that the intersection does not appear.
The non-straight arrow includes a left turn flag arrow, a right turn flag arrow, a straight left turn flag arrow, a straight right turn flag arrow, a left-right turn flag arrow, and/or a straight left-right turn flag arrow.
S920, replacing another pre-stored arrow template, and returning to the step of superposing the characteristic points on the pre-stored arrow template on the characteristic diagram to be matched, and calculating the distance between the characteristic points on the pre-stored arrow template and the pixel points on the characteristic diagram to be matched until all pre-stored arrow templates are traversed.
The intersection detection method of the embodiment obtains semantic segmentation results of the ground marks such as lane lines, center lines, arrows and the like on the looking-around spliced graph by means of the deep learning network, and the semantic segmentation results are more than the marks obtained by traditional image detection, and are more beneficial to mark distinction, so that the intersection detection method has the advantages that the marks are different and different detection algorithms are adopted; and based on semantic segmentation results, the attribute values of different ground marks can be obtained, so that the ground marks can be easily obtained, the means for detecting the intersections are increased, the situation that whether lane lines are continuous or not and whether the lane lines or the central lines are vertical or not is used, and the ground arrows are detected, so that the detection of the intersections is simpler, more efficient, faster and more accurate.
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the intersection detection method as described in fig. 2a,7a and 10.
The present application may be a system, method and/or computer program product at any possible level of technical details. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present application.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device. Computer program instructions for carrying out operations of the present application may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as SMALLTALK, C ++ or the like and a procedural programming language such as the "C" language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present application are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information for computer readable program instructions, which can execute the computer readable program instructions.
Example two
The present embodiment provides a detection system for an intersection, including:
the acquisition module is used for acquiring the road surface ring view;
the extraction module is used for extracting the road indication straight line and the ground arrow;
The detection module is used for detecting the intersection appearing in the road surface annular view; when the ground marker only comprises a road indication straight line, detecting an intersection appearing in the road surface annular view according to the road indication straight line; detecting an intersection appearing in the road surface ring view according to a ground arrow when the ground marker includes only the ground arrow; or detecting an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow when the ground marker comprises the road indication straight line and the ground arrow. .
The crossing detection system provided by the embodiment will be described in detail with reference to the drawings. Referring to fig. 11, a schematic structural diagram of an intersection detection system in an embodiment is shown. As shown in fig. 11, the intersection detection system 11 specifically includes: an acquisition module 111, an extraction module 112 and a detection module 113.
The acquisition module 111 is configured to acquire a road surface ring view.
The extracting module 112 is configured to extract a ground identifier from the road surface annular view; the ground identifier comprises a road indication straight line and/or a ground arrow; the road indication straight line comprises a lane line and/or a center line.
The detection module 113 is used for detecting intersections appearing in the road surface annular view.
Wherein, when the ground marker includes only a road indication straight line, the detection module 113 detects an intersection appearing in the road surface ring view according to the road indication straight line;
Specifically, the detection module 113 performs pixel-level progressive scanning on the extracted picture of the road indication line to detect whether the road indication line passing through the extracted picture exists; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether the mutually perpendicular road indication straight lines exist.
Preferably, the extracted picture of the road indication straight line is divided into two road side pictures for the extracted lane line; respectively carrying out pixel-level row-by-row/column scanning on the two road side pictures to detect whether lane lines penetrating through the pictures appear on the two road side pictures; if yes, the road junction is not detected in the road surface ring view; if not, the step of detecting whether the mutually perpendicular road indication straight lines exist or not is carried out; the criterion for detecting whether the lane lines penetrating through the pictures appear in the two road side pictures is whether the continuous scanning width/row degree of the row/column scanning is larger than an accumulation threshold value. The step of detecting whether the mutually perpendicular road indication straight lines exist or not comprises the step of detecting whether mutually perpendicular lane lines/central lines appear in an extracted picture of the road indication straight lines or not.
The process of detecting whether the lane lines/central lines perpendicular to each other appear in the extracted picture of the road indication straight line by the detection module 113 includes: detecting a straight line existing in the extracted picture of the road indication straight line by adopting the straight line; calculating an included angle between every two straight lines, and judging whether lane lines/central lines which are perpendicular to each other appear in the extracted picture according to the included angle; if yes, the road junction is detected in the road surface ring view; if not, the detection is ended.
When the ground marker includes only a ground arrow, the detection module 113 detects an intersection appearing in the road surface ring view according to the ground arrow.
Specifically, the detection module 113 detects in the extracted picture of the ground arrow to determine whether a straight arrow appears therein; if yes, indicating that the intersection does not appear in the road surface ring view; if not, the intersection appears in the road surface ring view.
Preferably, the detection module 113 acquires the ground arrow from an extracted picture of the ground arrow; the outline of the ground arrow is a characteristic point, and the non-outline in the extracted picture of the ground arrow is a non-characteristic point; transforming the outline of the ground arrow to generate a feature map to be matched for matching with a pre-stored arrow template; superposing the feature points on the pre-stored arrow templates on the feature images to be matched, and calculating the distance between the feature points on the pre-stored arrow templates and the pixel points on the feature images to be matched; comparing the calculated distance with a distance conversion threshold value to judge whether the matching with the template is successful or not; if the method is successful, the arrow type in the template is considered as the arrow type of the ground arrow in the extracted picture, and whether the arrow type of the ground arrow is a non-straight arrow is judged; if yes, indicating that an intersection appears in the road surface ring view; if not, indicating that the intersection does not appear in the road surface ring view; if not, replacing another pre-stored arrow template, and returning to the step of superposing the characteristic points on the pre-stored arrow template on the characteristic diagram to be matched, and calculating the distance between the characteristic points on the pre-stored arrow template and the pixel points on the characteristic diagram to be matched until all pre-stored arrow templates are traversed.
When the ground marker includes a road indication straight line and a ground arrow, the detection module 113 detects an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow.
Specifically, the detection module 113 is configured to perform pixel-level progressive scanning on an extracted picture of a road indication line, so as to detect whether a road indication line penetrating through the extracted picture exists; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether mutually perpendicular road indication straight lines exist; wherein the road indication straight line comprises a lane line and/or a central line; detecting in the extracted pictures of the ground arrows to judge whether straight arrows appear in the pictures; if yes, indicating that the intersection does not appear in the road surface ring view; if not, the intersection appears in the road surface ring view.
When the ground marker includes a road indication straight line and a ground arrow, the detection module 113 is configured to detect an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow.
Specifically, the detection module 113 performs pixel-level progressive scanning on the extracted picture of the road indication line to detect whether the road indication line passing through the extracted picture exists; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether mutually perpendicular road indication straight lines exist; detecting in the extracted pictures of the ground arrows to judge whether straight arrows appear in the pictures; if yes, indicating that the intersection does not appear in the road surface ring view; if not, the intersection appears in the road surface ring view. Wherein the road indication straight line comprises a lane line and/or a center line.
Preferably, the detection module 113 divides the extracted picture of the road indication line into two road side pictures for the extracted lane line; respectively carrying out pixel-level row-by-row/column scanning on the two road side pictures to detect whether lane lines penetrating through the pictures appear on the two road side pictures; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether lane lines/central lines which are perpendicular to each other appear in the extracted pictures of the road indication straight lines. The criterion for detecting whether the lane lines penetrating through the pictures appear in the two road side pictures is whether the continuous scanning width/row degree of the row/column scanning is larger than an accumulation threshold value.
Specifically, the detecting module 113 detects whether there are mutually perpendicular road indication lines, which means that the process of detecting whether mutually perpendicular lane lines/centerlines appear in the extracted picture of the road indication lines includes: detecting a straight line existing in the extracted picture of the road indication straight line by adopting the straight line; calculating an included angle between every two straight lines, and judging whether lane lines/central lines which are perpendicular to each other appear in the extracted picture according to the included angle; if yes, the road junction is detected in the road surface ring view; if not, the intersection is not detected in the road surface annular view, and the intersection is detected in the extracted picture of the ground arrow so as to judge whether a straight arrow appears in the extracted picture.
The detection module 113 acquires the outline of the ground arrow from the extracted picture of the ground arrow; the outline of the ground arrow is a characteristic point, and the non-outline in the extracted picture of the ground arrow is a non-characteristic point; transforming the outline of the ground arrow to generate a feature map to be matched for matching with a pre-stored arrow template; superposing the feature points on the pre-stored arrow templates on the feature images to be matched, and calculating the distance between the feature points on the pre-stored arrow templates and the pixel points on the feature images to be matched; comparing the calculated distance with a distance conversion threshold value to judge whether the modulus is successfully matched; if the method is successful, the arrow type in the template is considered as the arrow type of the ground arrow in the extracted picture, and whether the arrow type of the ground arrow is a non-straight arrow is judged; if yes, indicating that an intersection appears in the road surface ring view; if not, indicating that the intersection does not appear in the road surface ring view; if not, replacing another pre-stored arrow template, and returning to the step of superposing the characteristic points on the pre-stored arrow template on the characteristic diagram to be matched, and calculating the distance between the characteristic points on the pre-stored arrow template and the pixel points on the characteristic diagram to be matched until all pre-stored arrow templates are traversed.
It should be noted that, it should be understood that the division of the modules of the above system is merely a division of a logic function, and may be fully or partially integrated into a physical entity or may be physically separated. The modules can be realized in a form of calling the processing element through software, can be realized in a form of hardware, can be realized in a form of calling the processing element through part of the modules, and can be realized in a form of hardware. For example: the x module may be a processing element which is independently set up, or may be implemented in a chip integrated in the system. The x module may be stored in the memory of the system in the form of program codes, and the functions of the x module may be called and executed by a certain processing element of the system. The implementation of the other modules is similar. All or part of the modules can be integrated together or can be implemented independently. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in a software form. The above modules may be one or more integrated circuits configured to implement the above methods, for example: one or more Application SPECIFIC INTEGRATED Circuits (ASIC), one or more microprocessors (DIGITAL SINGNAL Processor DSP), one or more field programmable gate arrays (Field Programmable GATE ARRAY FPGA), etc. When the above module is implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a central processing unit (Central Processing Unit, CPU) or other processor that may invoke the program code. These modules may be integrated together and implemented in the form of a System-on-a-chip (SOC) for short.
Example III
The embodiment provides a detection terminal for a road junction, which comprises: a processor, memory, transceiver, communication interface, or/and system bus; the memory and the communication interface are connected with the processor and the transceiver through the system bus and complete the communication among each other, the memory is used for storing a computer program, the communication interface is used for communicating with other devices, and the processor and the transceiver are used for running the computer program to enable the road junction detection terminal to execute the steps of the road junction detection method. In practical application, the detection terminal comprises a vehicle-mounted terminal.
The system bus mentioned above may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, or the like. The system bus may be classified into an address bus, a data bus, a control bus, and the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other devices (such as a client, a read-write library and a read-only library). The memory may include random access memory (Random Access Memory, RAM) and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, abbreviated as CPU), a network processor (Network Processor, abbreviated as NP), etc.; but may also be a digital signal processor (DIGITAL SIGNAL Processing, DSP), application SPECIFIC INTEGRATED Circuit, ASIC, field programmable gate array (Field Programmable GATE ARRAY, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
The protection scope of the road junction detection method of the present invention is not limited to the execution sequence of the steps listed in the present embodiment, and all the schemes implemented by the steps of increasing or decreasing and step replacing in the prior art according to the principles of the present invention are included in the protection scope of the present invention.
The invention also provides a road crossing detection system, which can realize the road crossing detection method, but the device for realizing the road crossing detection method comprises but is not limited to the structure of the road crossing detection system listed in the embodiment, and all the structural modifications and substitutions of the prior art according to the principles of the invention are included in the protection scope of the invention.
In summary, the method, the system, the terminal and the computer readable storage medium for detecting the intersection acquire the semantic segmentation results of the lane lines, the central lines, the arrows and other ground marks on the looking-around splice graph by means of the deep learning network, are more than marks acquired by traditional image detection, and are more beneficial to mark distinction, so that the method and the system have the advantages that different marks adopt different detection algorithms; and based on semantic segmentation results, the attribute values of different ground marks can be obtained, so that the ground marks can be easily obtained, the means for detecting the intersections are increased, the situation that whether lane lines are continuous or not and whether the lane lines or the central lines are vertical or not is used, and the ground arrows are detected, so that the detection of the intersections is simpler, more efficient, faster and more accurate. The invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims, which are within the ordinary skill of the art, be within the spirit and scope of the present disclosure.
Claims (13)
1. A method for detecting an intersection, comprising:
acquiring a road surface annular view, and extracting a ground marker from the road surface annular view; the ground identifier comprises a road indication straight line and/or a ground arrow;
when the ground marker only comprises a road indication straight line, detecting an intersection appearing in the road surface ring view according to the road indication straight line;
Detecting an intersection appearing in the road surface ring view according to a ground arrow when the ground marker includes only the ground arrow; or (b)
When the ground marker comprises a road indication straight line and a ground arrow, detecting an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow;
wherein, according to the road indication straight line, the step of detecting the crossing appearing in the road surface ring view comprises: performing pixel-level progressive scanning on the extracted picture of the road indication straight line to detect whether the road indication straight line penetrating through the extracted picture exists or not; wherein the road indication straight line comprises a lane line and/or a central line; dividing an extracted picture of a road indication straight line into two road side pictures aiming at the extracted lane line; respectively carrying out pixel-level row-by-row/column scanning on the two road side pictures to detect whether lane lines penetrating through the pictures appear on the two road side pictures; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether lane lines/central lines which are perpendicular to each other appear in the extracted pictures of the road indication straight lines.
2. The method for detecting an intersection according to claim 1, wherein,
The criterion for detecting whether the lane lines penetrating through the pictures appear in the two road side pictures is whether the continuous scanning width/row degree of the row/column scanning is larger than an accumulation threshold value.
3. The intersection detection method according to claim 1, wherein the step of detecting whether or not lane lines/center lines perpendicular to each other appear in the extracted picture of the road indication straight line comprises:
Detecting a straight line existing in the extracted picture of the road indication straight line by adopting the straight line;
Calculating an included angle between every two straight lines, and judging whether lane lines/central lines which are perpendicular to each other appear in the extracted picture according to the included angle; if yes, the road junction is detected in the road surface ring view; if not, the process is ended.
4. The method according to claim 1, wherein when the ground marker includes only a ground arrow, the step of detecting the intersection appearing in the road surface ring view according to the ground arrow includes:
Detecting in the extracted pictures of the ground arrows to judge whether straight arrows appear in the pictures; if yes, indicating that the intersection does not appear in the road surface ring view; if not, the intersection appears in the road surface ring view.
5. The method of detecting an intersection according to claim 4, wherein the step of detecting in the extracted picture of the ground arrow to determine whether a straight arrow appears therein comprises:
Acquiring a ground arrow from an extracted picture of the ground arrow; the outline of the ground arrow is a characteristic point, and the non-outline in the extracted picture of the ground arrow is a non-characteristic point;
transforming the outline of the ground arrow to generate a feature map to be matched for matching with a pre-stored arrow template;
Superposing the feature points on the pre-stored arrow templates on the feature images to be matched, and calculating the distance between the feature points on the pre-stored arrow templates and the pixel points on the feature images to be matched;
comparing the calculated distance with a distance conversion threshold value to judge whether the matching with the template is successful or not; if the method is successful, the arrow type in the template is considered as the arrow type of the ground arrow in the extracted picture, and whether the arrow type of the ground arrow is a non-straight arrow is judged; if yes, indicating that an intersection appears in the road surface ring view; if not, indicating that the intersection does not appear in the road surface ring view; if not, replacing another pre-stored arrow template, and returning to the step of superposing the characteristic points on the pre-stored arrow template on the characteristic diagram to be matched, and calculating the distance between the characteristic points on the pre-stored arrow template and the pixel points on the characteristic diagram to be matched until all pre-stored arrow templates are traversed.
6. The method for detecting an intersection according to claim 5, wherein,
The non-straight arrow includes a left turn flag arrow, a right turn flag arrow, a straight left turn flag arrow, a straight right turn flag arrow, a left-right turn flag arrow, and/or a straight left-right turn flag arrow.
7. The method of detecting an intersection according to claim 1, wherein when the ground marker includes a road indication straight line and a ground arrow, the step of detecting an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow includes:
Performing pixel-level progressive scanning on the extracted picture of the road indication straight line to detect whether the road indication straight line penetrating through the extracted picture exists or not; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether mutually perpendicular road indication straight lines exist; wherein the road indication straight line comprises a lane line and/or a central line;
Detecting in the extracted pictures of the ground arrows to judge whether straight arrows appear in the pictures; if yes, indicating that the intersection does not appear in the road surface ring view; if not, the intersection appears in the road surface ring view.
8. The method of claim 7, wherein the step of performing pixel-level progressive scanning on the extracted picture of the road indication line to detect whether the road indication line passing through the extracted picture exists comprises:
dividing an extracted picture of a road indication straight line into two road side pictures aiming at the extracted lane line;
Respectively carrying out pixel-level row-by-row/column scanning on the two road side pictures to detect whether lane lines penetrating through the pictures appear on the two road side pictures; if yes, the road junction is not detected in the road surface ring view; if not, the step of detecting whether the mutually perpendicular road indication straight lines exist or not is carried out; the method comprises the steps of detecting whether two road side pictures are provided with lane lines penetrating through the pictures or not according to whether the continuous scanning width/line degree of line/column scanning is larger than an accumulation threshold value or not, wherein the step of detecting whether the road indication straight lines perpendicular to each other or not comprises the step of detecting whether the lane lines/central lines perpendicular to each other are provided in the extracted pictures of the road indication straight lines or not.
9. The intersection detection method according to claim 8, wherein the step of detecting whether or not lane lines/center lines perpendicular to each other appear in the extracted picture of the road indication straight line includes:
Detecting a straight line existing in the extracted picture of the road indication straight line by adopting the straight line;
calculating an included angle between every two straight lines, and judging whether lane lines/central lines which are perpendicular to each other appear in the extracted picture according to the included angle; if yes, the road junction is detected in the road surface ring view; if not, the step of detecting the intersection not detected in the road surface annular view, and transferring to the extracted picture of the ground arrow for detection to judge whether the straight arrow appears.
10. A system for detecting an intersection, comprising:
the acquisition module is used for acquiring the road surface ring view;
the extraction module is used for extracting the ground identifier from the road surface annular view; the ground identifier comprises a road indication straight line and/or a ground arrow;
The detection module is used for detecting the intersection appearing in the road surface annular view; when the ground marker only comprises a road indication straight line, detecting an intersection appearing in the road surface annular view according to the road indication straight line; detecting an intersection appearing in the road surface ring view according to a ground arrow when the ground marker includes only the ground arrow; or when the ground marker comprises a road indication straight line and a ground arrow, detecting an intersection appearing in the road surface ring view according to the road indication straight line and the ground arrow;
wherein, according to the road indication straight line, the step of detecting the crossing appearing in the road surface ring view comprises: performing pixel-level progressive scanning on the extracted picture of the road indication straight line to detect whether the road indication straight line penetrating through the extracted picture exists or not; wherein the road indication straight line comprises a lane line and/or a central line; dividing an extracted picture of a road indication straight line into two road side pictures aiming at the extracted lane line; respectively carrying out pixel-level row-by-row/column scanning on the two road side pictures to detect whether lane lines penetrating through the pictures appear on the two road side pictures; if yes, the road junction is not detected in the road surface ring view; if not, detecting whether lane lines/central lines which are perpendicular to each other appear in the extracted pictures of the road indication straight lines.
11. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the method for detecting an intersection as claimed in any one of claims 1 to 9.
12. The utility model provides a detection terminal of road crossing which characterized in that includes: a processor and a memory;
The memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory, so that the detection terminal executes the intersection detection method according to any one of claims 1 to 9.
13. The crossing detection terminal of claim 12, wherein the road crossing detection terminal comprises a vehicle-mounted terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110660972.3A CN113392762B (en) | 2021-06-15 | 2021-06-15 | Intersection detection method, system, terminal and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110660972.3A CN113392762B (en) | 2021-06-15 | 2021-06-15 | Intersection detection method, system, terminal and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113392762A CN113392762A (en) | 2021-09-14 |
| CN113392762B true CN113392762B (en) | 2024-04-26 |
Family
ID=77621048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110660972.3A Active CN113392762B (en) | 2021-06-15 | 2021-06-15 | Intersection detection method, system, terminal and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392762B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246010A (en) * | 2007-02-13 | 2008-08-20 | 爱信艾达株式会社 | Lane determining device, method, and program |
| EP3171292A1 (en) * | 2015-09-10 | 2017-05-24 | Baidu Online Network Technology (Beijing) Co., Ltd. | Driving lane data processing method, device, storage medium and apparatus |
| CN106778593A (en) * | 2016-12-11 | 2017-05-31 | 北京联合大学 | A kind of track level localization method based on the fusion of many surface marks |
| CN107346611A (en) * | 2017-07-20 | 2017-11-14 | 北京纵目安驰智能科技有限公司 | A kind of barrier-avoiding method and obstacle avoidance system of the vehicle of autonomous driving |
| CN108189838A (en) * | 2017-12-30 | 2018-06-22 | 吉利汽车研究院（宁波）有限公司 | A kind of pattern of fusion adaptive cruise curve control method and device |
| CN110197589A (en) * | 2019-05-29 | 2019-09-03 | 杭州诚道科技股份有限公司 | A kind of illegal detection method of making a dash across the red light based on deep learning |
| CN110502982A (en) * | 2019-07-11 | 2019-11-26 | 平安科技（深圳）有限公司 | The method, apparatus and computer equipment of barrier in a kind of detection highway |
| CN110781816A (en) * | 2019-10-25 | 2020-02-11 | 北京行易道科技有限公司 | Method, device, equipment and storage medium for transverse positioning of vehicle in lane |
| CN111414826A (en) * | 2020-03-13 | 2020-07-14 | 腾讯科技（深圳）有限公司 | Method, device and storage medium for identifying landmark arrow |
| CN111985373A (en) * | 2020-08-12 | 2020-11-24 | 杭州鸿泉物联网技术股份有限公司 | Safety early warning method and device based on traffic intersection identification and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5188452B2 (en) * | 2009-05-22 | 2013-04-24 | 富士重工業株式会社 | Road shape recognition device |
-
2021
- 2021-06-15 CN CN202110660972.3A patent/CN113392762B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246010A (en) * | 2007-02-13 | 2008-08-20 | 爱信艾达株式会社 | Lane determining device, method, and program |
| EP3171292A1 (en) * | 2015-09-10 | 2017-05-24 | Baidu Online Network Technology (Beijing) Co., Ltd. | Driving lane data processing method, device, storage medium and apparatus |
| CN106778593A (en) * | 2016-12-11 | 2017-05-31 | 北京联合大学 | A kind of track level localization method based on the fusion of many surface marks |
| CN107346611A (en) * | 2017-07-20 | 2017-11-14 | 北京纵目安驰智能科技有限公司 | A kind of barrier-avoiding method and obstacle avoidance system of the vehicle of autonomous driving |
| CN108189838A (en) * | 2017-12-30 | 2018-06-22 | 吉利汽车研究院（宁波）有限公司 | A kind of pattern of fusion adaptive cruise curve control method and device |
| CN110197589A (en) * | 2019-05-29 | 2019-09-03 | 杭州诚道科技股份有限公司 | A kind of illegal detection method of making a dash across the red light based on deep learning |
| CN110502982A (en) * | 2019-07-11 | 2019-11-26 | 平安科技（深圳）有限公司 | The method, apparatus and computer equipment of barrier in a kind of detection highway |
| CN110781816A (en) * | 2019-10-25 | 2020-02-11 | 北京行易道科技有限公司 | Method, device, equipment and storage medium for transverse positioning of vehicle in lane |
| CN111414826A (en) * | 2020-03-13 | 2020-07-14 | 腾讯科技（深圳）有限公司 | Method, device and storage medium for identifying landmark arrow |
| CN111985373A (en) * | 2020-08-12 | 2020-11-24 | 杭州鸿泉物联网技术股份有限公司 | Safety early warning method and device based on traffic intersection identification and electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| Robust Traffic Light and Arrow Detection Using Digital Map with Spatial Prior Information for Automated Driving;Keisuke Yoneda等;《Sensors》;第20卷(第4期);第1-24页 * |
| 多尺度窗口的自适应透射率修复交通图像去雾方法;黄鹤 等;《中国光学》;第12卷(第6期);第1311-1320页 * |
| 引入辅助损失的多场景车道线检测;陈立潮;《中国图象图形学报》;第25卷(第9期);第1882-1893页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113392762A (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106446769B (en) | System and method for marker-based positioning | |
| CN111582189B (en) | Traffic signal lamp identification method and device, vehicle-mounted control terminal and motor vehicle | |
| Yuan et al. | Robust lane detection for complicated road environment based on normal map | |
| CN110163176B (en) | Lane line change position identification method, device, equipment and medium | |
| CN112967283B (en) | Target identification method, system, equipment and storage medium based on binocular camera | |
| CN111508258B (en) | Positioning method and device | |
| CN104517111A (en) | Lane line detection method and system, and lane deviation early warning method and system | |
| CN112307978B (en) | Target detection method and device, electronic equipment and readable storage medium | |
| JP2017130155A (en) | Object recognition device and object recognition method | |
| CN111967384A (en) | Vehicle information processing method, device, equipment and computer readable storage medium | |
| CN112669615B (en) | Parking space detection method and system based on camera | |
| CN113392762B (en) | Intersection detection method, system, terminal and computer readable storage medium | |
| CN113569812A (en) | Unknown obstacle identification method and device and electronic equipment | |
| CN112464914A (en) | Guardrail segmentation method based on convolutional neural network | |
| Priambada et al. | Levensthein distance as a post-process to improve the performance of ocr in written road signs | |
| CN111414903B (en) | Method, device and equipment for identifying content of indication board | |
| Puthon et al. | A complete system to determine the speed limit by fusing a GIS and a camera | |
| CN113591543B (en) | Traffic sign recognition method, device, electronic equipment and computer storage medium | |
| CN114202689A (en) | Point location marking method and device, electronic equipment and storage medium | |
| CN113158976B (en) | Ground arrow identification method, system, terminal and computer readable storage medium | |
| CN109284665B (en) | Method and apparatus for reducing number of detection candidates for object recognition method | |
| CN113807293B (en) | Deceleration strip detection method, deceleration strip detection system, deceleration strip detection equipment and computer readable storage medium | |
| WO2023130263A1 (en) | Pavement marker recognition method and apparatus, device, storage medium, and vehicle | |
| Panda et al. | RECENT DEVELOPMENTS IN LANE DEPARTURE WARNING SYSTEM: AN ANALYSIS | |
| CN114782927B (en) | Obstacle detection method, obstacle detection device, electronic device, and storage medium |
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 |