CN109389013B - Parking space combination algorithm and medium based on parking space main direction and template response points - Google Patents
Parking space combination algorithm and medium based on parking space main direction and template response points Download PDFInfo
- Publication number
- CN109389013B CN109389013B CN201710679402.2A CN201710679402A CN109389013B CN 109389013 B CN109389013 B CN 109389013B CN 201710679402 A CN201710679402 A CN 201710679402A CN 109389013 B CN109389013 B CN 109389013B
- Authority
- CN
- China
- Prior art keywords
- parking space
- pixel
- pixel point
- line
- point
- 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
- 230000004044 response Effects 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000005259 measurement Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
Abstract
The invention provides a parking space combination algorithm and a medium based on a parking space main direction and response points, which are used for acquiring a captured image and preprocessing elements of each pixel point on the captured image; the brightness contrast response value X is arranged according to the priority of each pixel point in sequence; traversing the pixels one by one according to the priority of the pixels, and searching the pixels matched with the pixels according to the parking space width threshold and the main direction to obtain parking space corner points so as to obtain the parking space. Compared with the traditional method for identifying the parking space, the method reduces the calculated amount of the combination of the parking space lines and the parking space corner points and improves the accuracy of identifying the parking space lines and the parking space corner points.
Description
Technical Field
The invention relates to the technical field of vehicle-mounted electronics, in particular to a parking space combination algorithm and medium based on a parking space main direction and a response point.
Background
The increase of the automobile storage quantity promotes the development of large-scale parking lots, and in twenty-first century, the large-scale parking lots are more and more, and the increasing of the scale of the parking lots brings a series of problems of parking and taking vehicles, so that the large-scale parking lots become the social problems generally faced by each large-scale and medium-scale city worldwide.
In the autonomous parking process, how to quickly and accurately identify the corner points of the parking space becomes the current urgent problem to be solved according to the environment sensing information, the accurate parking space is detected, and the calculated amount of equipment is reduced in the detection process.
The existing method for identifying the parking space is that line segments are identified on a captured image according to pixel brightness differences, horizontal bright lines and vertical bright lines which meet the conditions are found out through the line segments, intersection points of central lines of two sides of the horizontal bright lines and central lines of two sides of the vertical bright lines are found out, and the corner points of the parking space lines are determined. And finding out all the bright lines and the corner points of the bright lines which accord with the width and the height of the parking space lines, and then matching the bright lines and the corner points one by one to find out the bright lines and the corner point combination information which accord with the parking space lines, thereby forming the combined parking space. However, the combination rule of the parking space lines has a large calculation amount, wherein a plurality of unnecessary combination calculation of the bright lines and the corner points exist.
Disclosure of Invention
In order to solve the above and other potential technical problems, the invention provides a parking space combination algorithm and medium based on a parking space main direction and response points, which comprises the steps of firstly obtaining brightness contrast response values X of all pixel points in a captured image, then arranging the priority of each pixel point according to the magnitude sequence of the brightness contrast response values X, and finding out a suspected parking space by pairing pixel points one by one according to the priority.
A parking space combination algorithm based on a parking space main direction and response points comprises the following steps:
s01: acquiring a captured image, and preprocessing to obtain elements of each pixel point on the captured image; extracting the captured image has
Brightness contrast response value X of pixel point with L or T-shaped corner feature, and the brightness contrast response value X is determined according to the size
Sequentially arranged; the brightness contrast response value X is prioritized for each pixel in order of magnitude,
s02: for pixel points P with the brightness contrast response value X larger than a certain threshold value, traversing the pixel points one by one according to the priority of the pixel points, and searching the pixel points matched with the pixel points according to the parking space width threshold value and the main direction to obtain P1 (X1, y 1) and P2 (X2, y 2) as two corner points of a suspicious parking space;
s03: judging whether a pixel point P3 exists in the opposite direction of the pixel points P1 (x 1, y 1) and P2 (x 2, y 2), and if the pixel point P3 exists, judging whether the pixel points P1, P2 and P3 meet the following conditions of a and b:
a:Min(e(p1),e(p2),e(p3))≥1；
b:Max(e(p1),e(p2),e(p3))≥2；
the number of the directions of the corresponding line segments of the pixel points p is marked as e (p), and the value range of the e (p) is 0,1 and 2;
if so, P1, P2 and P3 are determined as two parking spaces.
Further, in the step S02, when the pixel point P having the luminance-contrast response value X larger than the predetermined threshold value is taken, the threshold value of the luminance-contrast response value X is 20.
Further, step S04 is included, if the pixel P3 is not present in the opposite direction of the pixel P1 (x 1, y 1) and P2 (x 2, y 2) or if the pixel P3 is present in step S03 but the conditions a and b are not satisfied and two parking spaces are not formed, determining whether P1 and P2 form one parking space is as follows:
whether or not it is a clear image:
judging whether P1 and P2 meet Min (e (P1), e (P2)) ∈2, if so, P1 and P2 form a parking space, and if not, returning to S02;
the number of the directions of the corresponding line segments of the pixel points p is marked as e (p), and the value range of the e (p) is 0,1 and 2;
if not a sharp image:
judging whether the non-zero values of c and d in the elements of P1 and P2 are consistent or not, and if so, judging that P1 and P2 form a parking space; if not, returning to step S02.
I.e., C (p 1) =c (p 2) =1 or D (p 1) =d (p 2) =1;
if the corresponding transverse line at the pixel point p is marked as C (p), if the corresponding transverse line is marked as C (p), the value of C (p) is 1, and if the corresponding transverse line is not marked as C (p), the value of C (p) is 0;
if the pixel point p has a corresponding vertical line marked as D (p), the value of D (p) is 1 if there is a vertical line, and the value of D (p) is 0 if there is no vertical line.
Further, in the step S03, if the image is not clear, it is determined whether the non-zero values of c and d in the elements of P1, P2 and P3 are consistent, and if so, it is determined that P1, P2 and P3 constitute a parking space; if not, returning to step S02.
I.e., C (p 1) =c (p 2) =c (p 3) =1 or D (p 1) =d (p 2) =d (p 3) =1.
Further, in the step S03, the distance between the pixel point P3 and the pixel point P2 is equal to or approximately equal to the distance between the pixel point P1 and the pixel point P2.
Further, the elements of preprocessing in step S01 to obtain each pixel point p on the captured image include:
a, acquiring position coordinates (x, y) of a pixel point;
b, acquiring a brightness contrast response value X of the pixel point;
c, judging whether a corresponding transverse line exists at the pixel point, marking the corresponding transverse line as C (p), if the corresponding transverse line exists, the value of C (p) is 1, and if the corresponding transverse line does not exist, the value of C (p) is 0;
d, if the pixel point has a corresponding longitudinal line, marking as D (p), if the pixel point has a longitudinal line D (p) value of 1, if the pixel point has no longitudinal line D (p) value of 0;
the number of the directions of the corresponding line segments exists in the e pixel points, the number is marked as e (p), and the value range of the e (p) is 0,1 and 2.
Further, in the step S01, when the elements of each pixel point on the captured image are obtained, the method further includes calling a line segment measurement set detected from the captured image, extracting a line segment of which the line segment measurement set is consistent with the main direction of the parking space or the main direction of the parking space and the extension line thereof passes through the pixel point P1 to form a first suspicious parking space line segment set, extracting a line segment of which the line segment measurement set is consistent with the main direction of the parking space or the main direction of the parking space and the extension line thereof passes through the pixel point P2 (x 2, y 2) to form a second suspicious parking space line segment set, and determining whether the credibility of the pixel points P1 (x 1, y 1) and P2 (x 2, y 2) exceeds a credibility threshold according to the numbers of the line segments of the first suspicious parking space line segment set and the second suspicious parking space line segment set along the main direction of the parking space and the line segments along the main direction of the parking space, and if yes, determining that the suspicious parking space is the pixel points P1 (x 1, y 1) and P2 (x 2, y 2).
Further, in the step S02, the method for obtaining the suspicious parking space through the pixel points P1 (x 1, y 1) and P2 (x 2, y 2) includes:
connecting the corner points P1 (x 1, y 1) and P2 (x 2, y 2), and taking the connecting line and vertical lines on two sides of the connecting line as three sides of the suspicious parking space; when determining the extending direction of the connecting line vertical line, the extending direction of the vertical line is determined along the relative positions of the cameras and the vehicle body, which obtain the pixel points P1 (x 1, y 1) and P2 (x 2, y 2).
Further, in the step S02, when traversing the pixels one by one according to the priorities of the pixels, at least one traversal is included, and the first traversal, the second traversal, the third traversal, and the like are recorded;
the first traversal process is:
the pixel P with the maximum brightness contrast response value X is selected as a pixel P1, the pixel P2 with the brightness contrast response value X arranged behind the pixel P1 is found in the residual arrangement according to the brightness contrast response value X, if the pairing is unsuccessful, the pixel P2 is marked as failed in pairing, the pixel P3 with the brightness contrast response value X arranged behind the pixel P2 is found in the residual arrangement according to the brightness contrast response value X, the pixel P3 and the pixel P1 are paired, if the pairing is unsuccessful, the P3 pixel is marked as failed in pairing until the pixel P1 is successfully paired, and if the pixel P1 is failed in pairing, the second traversal is entered;
the second traversal process is:
if the pixel P1 traverses the pixel points one by one and can not be successfully paired, selecting a second pixel P2 of the brightness contrast response value X, based on P2, finding out a remaining pixel P3 arranged behind P2 according to the brightness contrast response value X in order arrangement, and pairing the pixel P2 and the pixel P3, if the pairing is unsuccessful, marking that the P2 pixel point pairing fails until the pixel point P2 pairing is successful, and if the pixel point P2 pairing fails, entering a third traversal;
and so on until the pixel point P of which the luminance contrast response value X is within the threshold value range is traversed.
Further, in the step S02, when traversing pixels one by one according to the priority of the pixels, the method further includes removing the pixels to be paired according to the traversing rule within the range near the position identified as the parking space corner point in the previous traversal.
For example: after P1, P2 and P3 are identified as parking space corner points, when the corner points outside P2 and P3 need to be extended:
when expanding the corner points outside the P2 pixel points, only searching the pixel point P4 in a double area range taking the P1 as an origin point to extend in the P2 direction, wherein the distance between the pixel point P1 and the pixel point P1 is equal to or approximately equal to the distance between the pixel points P1 and P2;
when expanding the corner point outside the P3 pixel point, only the pixel point P5 is searched in the range of the double area which takes the P1 as the origin point and extends towards the P3 direction and has the distance from the pixel point P1 equal to or approximately equal to the distance between the pixel points P1 and P3.
As described above, the present invention has the following advantageous effects:
in practical scene application, the line segments formed by detecting environmental interference such as light in the captured image are divergent and have no regularity. The line segments formed by the fixed environments such as vehicles, pillars, walls, car barriers and the like in the captured images are detected to be consistent with the main direction, so that the following effects exist when the main direction of the parking space is judged based on the method:
the method comprises the steps of acquiring brightness contrast response values X of all pixel points in a captured image, arranging the priority of each pixel point according to the size sequence of the brightness contrast response values X, and finding out suspected parking spaces by matching the pixel points one by one according to the priority.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a schematic diagram of two corner points P1 (x 1, y 1) and P2 (x 2, y 2) obtained in step S02.
Fig. 2 shows a schematic diagram of three corner points P1 (x 1, y 1) P2 (x 2, y 2) and P3 (x 3, y 3) obtained in step S03.
Fig. 3 shows a schematic view of the outward expansion of corner point P2 and corner point P3 in the preferred embodiment.
Fig. 4 shows an effect diagram of the lateral and longitudinal lines and the corner points and parking spaces obtained from the captured image using the method of the invention.
Fig. 5 shows an effect diagram of obtaining a left parking space for a left camera.
Fig. 6 shows an effect diagram of obtaining a right parking space for a right camera.
Fig. 7 shows an effect diagram of obtaining a right parking space by the right camera in another embodiment.
Fig. 8 shows an effect diagram of the left camera obtaining a left single parking space in another embodiment.
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 understood that the structures, proportions, sizes, etc. shown in the drawings are for illustration purposes only and should not be construed as limiting the invention to the extent that it can be practiced, since modifications, changes in the proportions, or otherwise, used in the practice of the invention, are not intended to be critical to the essential characteristics of the invention, but are intended to fall within the spirit and scope of the invention. Also, the terms such as "upper," "lower," "left," "right," "middle," and "a" and the like recited in the present specification are merely for descriptive purposes and are not intended to limit the scope of the invention, but are intended to provide relative positional changes or modifications without materially altering the technical context in which the invention may be practiced.
With reference to figures 1 to 8 of the drawings,
a parking space combination algorithm based on a parking space main direction and response points comprises the following steps:
s01: acquiring a captured image, and preprocessing to obtain elements of each pixel point on the captured image; extracting brightness contrast response values X of pixel points with L-shaped or T-shaped corner features in the captured image, and arranging the brightness contrast response values X according to the size sequence; the brightness contrast response value X is arranged according to the priority of each pixel point in sequence;
s02: for pixel points P with the brightness contrast response value X larger than a certain threshold value, traversing the pixel points one by one according to the priority of the pixel points, and searching the pixel points matched with the pixel points according to the parking space width threshold value and the main direction to obtain P1 (X1, y 1) and P2 (X2, y 2) as two corner points of a suspicious parking space;
s03: judging whether a pixel point P3 exists in the opposite direction of the pixel points P1 (x 1, y 1) and P2 (x 2, y 2), and if the pixel point P3 exists, judging whether the pixel points P1, P2 and P3 meet the following conditions of a and b:
a:Min(e(p1),e(p2),e(p3))≥1；
b:Max(e(p1),e(p2),e(p3))≥2；
the number of the directions of the corresponding line segments of the pixel points p is marked as e (p), and the value range of the e (p) is 0,1 and 2;
if so, P1, P2 and P3 are determined as two parking spaces.
Further, in the step S02, when the pixel point P having the luminance-contrast response value X larger than the predetermined threshold value is taken, the threshold value of the luminance-contrast response value X is 20.
Further, step S04 is included, if the pixel P3 is not present in the opposite direction of the pixel P1 (x 1, y 1) and P2 (x 2, y 2) or if the pixel P3 is present in step S03 but the conditions a and b are not satisfied and two parking spaces are not formed, determining whether P1 and P2 form one parking space is as follows:
whether or not it is a clear image:
judging whether P1 and P2 meet Min (e (P1), e (P2)) ∈2, if so, P1 and P2 form a parking space, and if not, returning to S02;
the number of the directions of the corresponding line segments of the pixel points p is marked as e (p), and the value range of the e (p) is 0,1 and 2;
if not a sharp image:
judging whether the non-zero values of c and d in the elements of P1 and P2 are consistent or not, and if so, judging that P1 and P2 form a parking space; if not, returning to step S02.
I.e., C (p 1) =c (p 2) =1 or D (p 1) =d (p 2) =1;
if the corresponding transverse line at the pixel point p is marked as C (p), if the corresponding transverse line is marked as C (p), the value of C (p) is 1, and if the corresponding transverse line is not marked as C (p), the value of C (p) is 0;
if the pixel point p has a corresponding vertical line marked as D (p), the value of D (p) is 1 if there is a vertical line, and the value of D (p) is 0 if there is no vertical line.
Further, in the step S03, if the image is not clear, it is determined whether the non-zero values of c and d in the elements of P1, P2 and P3 are consistent, and if so, it is determined that P1, P2 and P3 constitute a parking space; if not, returning to step S02.
I.e., C (p 1) =c (p 2) =c (p 3) =1 or D (p 1) =d (p 2) =d (p 3) =1.
Further, in the step S03, the distance between the pixel point P3 and the pixel point P2 is equal to or approximately equal to the distance between the pixel point P1 and the pixel point P2.
Further, the elements of preprocessing in step S01 to obtain each pixel point p on the captured image include:
a, acquiring position coordinates (x, y) of a pixel point;
b, acquiring a brightness contrast response value X of the pixel point;
c, judging whether a corresponding transverse line exists at the pixel point, marking the corresponding transverse line as C (p), if the corresponding transverse line exists, the value of C (p) is 1, and if the corresponding transverse line does not exist, the value of C (p) is 0;
d, if the pixel point has a corresponding longitudinal line, marking as D (p), if the pixel point has a longitudinal line D (p) value of 1, if the pixel point has no longitudinal line D (p) value of 0;
the number of the directions of the corresponding line segments exists in the e pixel points, the number is marked as e (p), and the value range of the e (p) is 0,1 and 2.
Further, in the step S01, when the elements of each pixel point on the captured image are obtained, the method further includes calling a line segment measurement set detected from the captured image, extracting a line segment of which the line segment measurement set is consistent with the main direction of the parking space or the main direction of the parking space and the extension line thereof passes through the pixel point P1 to form a first suspicious parking space line segment set, extracting a line segment of which the line segment measurement set is consistent with the main direction of the parking space or the main direction of the parking space and the extension line thereof passes through the pixel point P2 (x 2, y 2) to form a second suspicious parking space line segment set, and determining whether the credibility of the pixel points P1 (x 1, y 1) and P2 (x 2, y 2) exceeds a credibility threshold according to the numbers of the line segments of the first suspicious parking space line segment set and the second suspicious parking space line segment set along the main direction of the parking space and the line segments along the main direction of the parking space, and if yes, determining that the suspicious parking space is the pixel points P1 (x 1, y 1) and P2 (x 2, y 2).
Further, in the step S02, the method for obtaining the suspicious parking space through the pixel points P1 (x 1, y 1) and P2 (x 2, y 2) includes:
connecting the corner points P1 (x 1, y 1) and P2 (x 2, y 2), and taking the connecting line and vertical lines on two sides of the connecting line as three sides of the suspicious parking space; when determining the extending direction of the connecting line vertical line, the extending direction of the vertical line is determined along the relative positions of the cameras and the vehicle body, which obtain the pixel points P1 (x 1, y 1) and P2 (x 2, y 2).
Further, in the step S02, when traversing the pixels one by one according to the priorities of the pixels, at least one traversal is included, and the first traversal, the second traversal, the third traversal, and the like are recorded;
the first traversal process is:
the pixel P with the maximum brightness contrast response value X is selected as a pixel P1, the pixel P2 with the brightness contrast response value X arranged behind the pixel P1 is found in the residual arrangement according to the brightness contrast response value X, if the pairing is unsuccessful, the pixel P2 is marked as failed in pairing, the pixel P3 with the brightness contrast response value X arranged behind the pixel P2 is found in the residual arrangement according to the brightness contrast response value X, the pixel P3 and the pixel P1 are paired, if the pairing is unsuccessful, the P3 pixel is marked as failed in pairing until the pixel P1 is successfully paired, and if the pixel P1 is failed in pairing, the second traversal is entered;
the second traversal process is:
if the pixel P1 traverses the pixel points one by one and can not be successfully paired, selecting a second pixel P2 of the brightness contrast response value X, based on P2, finding out a remaining pixel P3 arranged behind P2 according to the brightness contrast response value X in order arrangement, and pairing the pixel P2 and the pixel P3, if the pairing is unsuccessful, marking that the P2 pixel point pairing fails until the pixel point P2 pairing is successful, and if the pixel point P2 pairing fails, entering a third traversal;
and so on until the pixel point P of which the luminance contrast response value X is within the threshold value range is traversed.
Further, in the step S02, when traversing pixels one by one according to the priority of the pixels, the method further includes removing the pixels to be paired according to the traversing rule within the range near the position identified as the parking space corner point in the previous traversal.
For example: after P1, P2 and P3 are identified as parking space corner points, when the corner points outside P2 and P3 need to be extended:
when expanding the corner points outside the P2 pixel points, only searching the pixel point P4 in a double area range taking the P1 as an origin point to extend in the P2 direction, wherein the distance between the pixel point P1 and the pixel point P1 is equal to or approximately equal to the distance between the pixel points P1 and P2;
when expanding the corner point outside the P3 pixel point, only the pixel point P5 is searched in the range of the double area which takes the P1 as the origin point and extends towards the P3 direction and has the distance from the pixel point P1 equal to or approximately equal to the distance between the pixel points P1 and P3.
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 of this invention, which are within the skill of those skilled in the art, be included within the spirit and scope of this invention.
Claims (8)
1. The parking space combination method based on the main direction and the response point of the parking space is characterized by comprising the following steps of:
s01: acquiring a captured image, and preprocessing to obtain elements of each pixel point on the captured image; extracting brightness contrast response values X of pixel points with L-shaped or T-shaped corner features in the captured image, and arranging the brightness contrast response values X according to the size sequence; the brightness contrast response value X is arranged according to the priority of each pixel point in sequence;
s02: for pixel points P with the brightness contrast response value X larger than a certain threshold value, traversing the pixel points one by one according to the priority of the pixel points, and searching the pixel points matched with the pixel points according to the parking space width threshold value and the main direction to obtain P1 (X1, y 1) and P2 (X2, y 2) as two corner points of a suspicious parking space;
s03: judging whether a pixel point P3 exists in the opposite direction of the pixel points P1 (x 1, y 1) and P2 (x 2, y 2), and if the pixel point P3 exists, judging whether the pixel points P1, P2 and P3 meet the following conditions of a and b:
a:Min(e(p1),e(p2),e(p3))≥1；
b:Max(e(p1),e(p2),e(p3))≥2；
the number of the directions of the corresponding line segments of the pixel points p is marked as e (p), and the value range of the e (p) is 0,1 and 2;
if yes, judging that the parking spaces P1, P2 and P3 are two parking spaces;
in the step S01, when the element of each pixel point P on the captured image is obtained, the method further includes calling a line segment measurement set detected from the captured image, extracting a line segment of which the line segment measurement set is consistent with the main direction of the parking space or the main direction of the parking space and which is itself or an extension line thereof passes through a pixel point P1 to form a first suspicious parking space line segment set, extracting a line segment of which the line segment measurement set is consistent with the main direction of the parking space or the main direction of the parking space and which is itself or an extension line thereof passes through a pixel point P2 (x 2, y 2) to form a second suspicious parking space line segment set, and determining whether the credibility of the pixel points P1 (x 1, y 1) and P2 (x 2, y 2) exceeds a credibility threshold according to the numbers of the line segments of the first suspicious parking space line segment set and the second suspicious parking space line segment set along the main direction of the parking space and the line segments along the main direction of the parking space, if the credibility of the line segments exceeds the credibility threshold, determining that the suspicious parking space points are the pixel points P1 (x 1, y 1) and P2 (x 2, y 2);
in the step S02, when traversing the pixel points one by one according to the priority of the pixel points, at least one traversal is included, and the traversal is marked as a first traversal, a second traversal, a third traversal and the like;
the first traversal process is:
the pixel P with the maximum brightness contrast response value X is selected as a pixel P1, the pixel P2 with the brightness contrast response value X arranged behind the pixel P1 is found in the residual arrangement according to the brightness contrast response value X, if the pairing is unsuccessful, the pixel P1 and the pixel P2 are marked as failed in pairing, the pixel P3 with the brightness contrast response value X arranged behind the pixel P2 is found in the residual arrangement according to the brightness contrast response value X, the pixel P3 and the pixel P1 are paired, if the pairing is unsuccessful, the P3 pixel is marked as failed in pairing until the pixel P1 is successfully paired, and if the pixel P1 is failed in pairing, the second traversal is entered;
the second traversal process is:
if the pixel P1 traverses the pixel points one by one, the next pixel point P2 of the brightness contrast response value X is selected, the pixel point P3 of which the brightness contrast response value X is arranged behind the pixel point P2 is found in the rest of the sequence arrangement according to the brightness contrast response value X based on the P2, the pixel points P2 and P3 are paired, if the pairing is unsuccessful, the P2 pixel point pairing failure is marked until the pixel point P2 pairing is successful, and if the pixel point P2 pairing failure, the third traversal is entered;
and so on until the pixel point P of which the luminance contrast response value X is within the threshold value range is traversed.
2. The parking space combination method based on the main parking space direction and the response point according to claim 1, further comprising step S04, if the opposite directions of the pixel points P1 (x 1, y 1) and P2 (x 2, y 2) do not have the pixel point P3 or if the pixel point P3 is present in step S03 but the conditions a and b are not satisfied, and no two parking spaces are formed, judging whether P1 and P2 form one parking space, wherein the judging conditions are as follows:
whether or not it is a clear image:
judging whether P1 and P2 meet Min (e (P1), e (P2)) ∈2, if so, P1 and P2 form a parking space, and if not, returning to S02;
the number of the directions of the corresponding line segments of the pixel points p is marked as e (p), and the value range of the e (p) is 0,1 and 2;
if not a sharp image:
judging whether the non-zero values of c and d in the elements of P1 and P2 are consistent or not, and if so, judging that P1 and P2 form a parking space; if not, returning to the step S02; i.e., C (p 1) =c (p 2) =1 or D (p 1) =d (p 2) =1;
if the corresponding transverse line at the pixel point p is marked as C (p), if the corresponding transverse line is marked as C (p), the value of C (p) is 1, and if the corresponding transverse line is not marked as C (p), the value of C (p) is 0;
if the pixel point p has a corresponding vertical line marked as D (p), the value of D (p) is 1 if there is a vertical line, and the value of D (p) is 0 if there is no vertical line.
3. The parking space combination method based on the main direction and the response point of the parking space according to claim 1, wherein in the step S03, if not the clear image, according to whether the non-zero values of c and d in the elements of P1, P2 and P3 are consistent, if so, it is determined that P1, P2 and P3 constitute the parking space; if not, returning to the step S02;
i.e., C (p 1) =c (p 2) =c (p 3) =1 or D (p 1) =d (p 2) =d (p 3) =1.
4. The parking space combination method based on the main parking space direction and the response point according to claim 1, wherein the distance between the pixel point P3 and the pixel point P2 in the step S03 is equal to or approximately equal to the distance between the pixel point P1 and the pixel point P2.
5. The parking space combination method based on the main parking space direction and the response point according to claim 1, wherein the preprocessing in step S01 to obtain the elements of each pixel point p on the captured image includes:
a, acquiring position coordinates (x, y) of a pixel point;
b, acquiring a brightness contrast response value X of the pixel point;
c, judging whether a corresponding transverse line exists at the pixel point, marking the corresponding transverse line as C (p), if the corresponding transverse line exists, the value of C (p) is 1, and if the corresponding transverse line does not exist, the value of C (p) is 0;
d, if the pixel point has a corresponding longitudinal line, marking as D (p), if the pixel point has a longitudinal line D (p) value of 1, if the pixel point has no longitudinal line D (p) value of 0;
the number of the directions of the corresponding line segments exists in the e pixel points, the number is marked as e (p), and the value range of the e (p) is 0,1 and 2.
6. The parking space combination method based on the main parking space direction and the response point according to claim 1, wherein the method for obtaining the suspicious parking space through the pixel points P1 (x 1, y 1) and P2 (x 2, y 2) in the step S02 is as follows:
connecting the corner points P1 (x 1, y 1) and P2 (x 2, y 2), and taking the connecting line and vertical lines on two sides of the connecting line as three sides of the suspicious parking space; when determining the extending direction of the connecting line vertical line, the extending direction of the vertical line is determined along the relative positions of the cameras and the vehicle body, which obtain the pixel points P1 (x 1, y 1) and P2 (x 2, y 2).
7. The parking space combination method based on the main direction and the response point of the parking space according to claim 1, wherein in the step S02, when the pixel points are traversed one by one according to the priority of the pixel points, further comprising removing the pixel points which are determined to be in the previous traversal and are in the position vicinity of the parking space corner point and need to be paired according to the traversal rule.
8. A computer-readable storage medium having stored thereon a computer program, characterized by: the program, when executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710679402.2A CN109389013B (en) | 2017-08-10 | 2017-08-10 | Parking space combination algorithm and medium based on parking space main direction and template response points |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710679402.2A CN109389013B (en) | 2017-08-10 | 2017-08-10 | Parking space combination algorithm and medium based on parking space main direction and template response points |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109389013A CN109389013A (en) | 2019-02-26 |
| CN109389013B true CN109389013B (en) | 2024-02-09 |
Family
ID=65414337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710679402.2A Active CN109389013B (en) | 2017-08-10 | 2017-08-10 | Parking space combination algorithm and medium based on parking space main direction and template response points |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109389013B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110132278B (en) * | 2019-05-14 | 2021-07-02 | 驭势科技（北京）有限公司 | Method and device for instant positioning and mapping |
| JP7367375B2 (en) * | 2019-08-07 | 2023-10-24 | 株式会社アイシン | Specific area detection device |
| CN110544386A (en) * | 2019-09-18 | 2019-12-06 | 奇瑞汽车股份有限公司 | parking space identification method and device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002170103A (en) * | 2000-12-01 | 2002-06-14 | Nissan Motor Co Ltd | Parking space map creating device and display device |
| CN102306274A (en) * | 2011-06-17 | 2012-01-04 | 东北大学 | Device for identifying parking space state and method |
| CN104933409A (en) * | 2015-06-12 | 2015-09-23 | 北京理工大学 | Parking space identification method based on point and line features of panoramic image |
| CN106845495A (en) * | 2016-12-30 | 2017-06-13 | 浙江工业大学 | Broken curve method of closing in a kind of image |
| CN106997688A (en) * | 2017-06-08 | 2017-08-01 | 重庆大学 | Parking position detecting method based on multi-sensor information fusion |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI419081B (en) * | 2009-12-29 | 2013-12-11 | Univ Nat Taiwan Science Tech | Method and system for providing augmented reality based on marker tracing, and computer program product thereof |
| KR101947826B1 (en) * | 2012-04-10 | 2019-02-13 | 현대자동차주식회사 | Method for recognizimg parking mark for vehicle |
-
2017
- 2017-08-10 CN CN201710679402.2A patent/CN109389013B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002170103A (en) * | 2000-12-01 | 2002-06-14 | Nissan Motor Co Ltd | Parking space map creating device and display device |
| CN102306274A (en) * | 2011-06-17 | 2012-01-04 | 东北大学 | Device for identifying parking space state and method |
| CN104933409A (en) * | 2015-06-12 | 2015-09-23 | 北京理工大学 | Parking space identification method based on point and line features of panoramic image |
| CN106845495A (en) * | 2016-12-30 | 2017-06-13 | 浙江工业大学 | Broken curve method of closing in a kind of image |
| CN106997688A (en) * | 2017-06-08 | 2017-08-01 | 重庆大学 | Parking position detecting method based on multi-sensor information fusion |
Non-Patent Citations (2)
| Title |
|---|
| 倒车辅助系统车位线识别方法研究;吴晓刚;;测绘通报(07);全文 * |
| 基于Harris与SVM角点判断的车位状态检测算法;杨英杰;胡义轩;张文龙;徐亮;;计算机光盘软件与应用(21);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109389013A (en) | 2019-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9771080B2 (en) | Road surface gradient detection device | |
| JP5293815B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| JP5754470B2 (en) | Road surface shape estimation device | |
| JP5267596B2 (en) | Moving body detection device | |
| US9846823B2 (en) | Traffic lane boundary line extraction apparatus and method of extracting traffic lane boundary line | |
| US10509971B2 (en) | Landmark recognition device and landmark recognition method using a database storing landmark extraction information | |
| CN109389013B (en) | Parking space combination algorithm and medium based on parking space main direction and template response points | |
| CN107817246B (en) | Medium storing image processing program, image processing method and image processing apparatus | |
| CN110287779A (en) | Detection method, device and the equipment of lane line | |
| US10339396B2 (en) | Vehicle accessibility determination device | |
| JP6156400B2 (en) | Traveling road surface detection device and traveling road surface detection method | |
| CN112598922B (en) | Parking space detection method, device, equipment and storage medium | |
| US20150156471A1 (en) | Method and device for processing stereoscopic data | |
| EP3082068A1 (en) | Traveling road surface detection device and traveling road surface detection method | |
| CN107748882B (en) | Lane line detection method and device | |
| JP2012168884A (en) | Traffic lane boundary detection device and traffic lane boundary detection method | |
| JP2013186663A (en) | Crosswalk recognition device and crosswalk recognition method | |
| JP2019067159A (en) | Dividing line recognition device | |
| JP2013186664A (en) | Crosswalk recognition device and crosswalk recognition method | |
| JP4762026B2 (en) | Road sign database construction device | |
| CN109389644B (en) | Direction gradient enhancement-based parking space line detection method | |
| JP5997962B2 (en) | In-vehicle lane marker recognition device | |
| US20160307055A1 (en) | Stereoscopic object detection device and stereoscopic object detection method | |
| CN109753840B (en) | Method, system and storage medium for determining parking space line corner points based on response values | |
| JP2010107435A (en) | Feature position recognition 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 |