CN115457504A - Parking space line detection optimization method and system based on fish eye pattern - Google Patents
Parking space line detection optimization method and system based on fish eye pattern Download PDFInfo
- Publication number
- CN115457504A CN115457504A CN202211042832.0A CN202211042832A CN115457504A CN 115457504 A CN115457504 A CN 115457504A CN 202211042832 A CN202211042832 A CN 202211042832A CN 115457504 A CN115457504 A CN 115457504A
- Authority
- CN
- China
- Prior art keywords
- line
- inner edge
- edge line
- point
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 32
- 238000005457 optimization Methods 0.000 title claims abstract description 28
- 238000010586 diagram Methods 0.000 claims abstract description 56
- 238000012937 correction Methods 0.000 claims abstract description 20
- 238000005070 sampling Methods 0.000 claims description 131
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims description 25
- 240000004050 Pentaglottis sempervirens Species 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 11
- 238000004422 calculation algorithm Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241001300198 Caperonia palustris Species 0.000 description 1
- 235000000384 Veronica chamaedrys Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
- G06T3/047—Fisheye or wide-angle transformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30264—Parking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a fisheye diagram-based parking space line detection optimization method and a fisheye diagram-based parking space line detection optimization system. The parking space line detection optimization method based on the fish eye diagram only depends on a camera and a traditional algorithm, the recognition cost is low, the correction process is simplified, meanwhile, only inner edge points are adopted for straight line fitting, interference of outer points formed by line stain shadow and other reasons on the straight line fitting of the inner edge lines is eliminated, and the recognition accuracy is improved.
Description
Technical Field
The invention relates to a parking space automatic identification technology, in particular to a parking space line detection optimization method and system based on a fish eye diagram.
Background
In the automatic parking, a vehicle to be parked uses a vehicle-mounted sensor to collect information around the vehicle, the collected information is transmitted to a sensing module to be analyzed to obtain a target point, a planning module calculates a parking track according to the target point analyzed by the sensing module, and finally a control module controls the vehicle to be parked in a parking space.
Because the cost of the camera is lower and the acquired information around the vehicle is richer, most perception recognition algorithm methods at present rely on vision. The fisheye lens is a lens with a large visual field range in a fixed-focus lens, and the visual angle is usually larger than 180 degrees, so that the imaging distortion is large. Therefore, most parking space detection algorithms perform parking space detection by performing distortion removal on the fisheye image and then converting the fisheye image into the bird's-eye view image, and consider that the distortion coefficient calculation has errors when the fisheye image is re-distorted and an object far away from the center of the camera when the fisheye image is converted into the bird's-eye view image has a stretching phenomenon. Therefore, part of the parking space detection schemes can convert the bird's eye view into a fish eye diagram, and parking space correction is carried out in the fish eye diagram.
In the fisheye image correction process, a general algorithm can identify an inner frame and an outer frame of a vehicle position line, then the inner frame is used as a correction starting point to perform correction in the direction from the inner frame to the outer frame, the correction method is to calculate the difference of adjacent pixels, the pixel coordinate with large pixel difference is set as an edge point of parking space correction because the pixel difference between the vehicle position line and the ground is the largest, then the corrected parking space point is converted into a bird's-eye view image to perform straight line fitting, and the fitted straight line is the corrected vehicle position line. However, except for the large difference of the pixel values of the edge of the parking space line, the difference of the pixel values calculated by the shadow and the spot inside the parking space line is also large, and the spot and the shadow point are referred to in the process of straight line fitting, so that the fitted parking space line point has a large error.
Disclosure of Invention
The invention aims to overcome the technical defects, provides a parking space line detection optimization method and system based on a fish eye diagram, and solves the problem that spot and shadow points are referred to in the existing straight line fitting process, and the fitted parking space line points have large errors.
In order to achieve the above technical object, a first aspect of the technical solution of the present invention provides a parking space line detection optimization method based on a fish eye diagram, which includes the following steps:
distortion correction is carried out on the fisheye diagram of the vehicle location line, the fisheye diagram is converted into a bird's-eye view, and the inner edge line of the vehicle location line is extracted from the bird's-eye view;
determining an undistorted inner edge line sampling point and an outer edge line preset sampling point in the aerial view, and projecting the inner edge line sampling point and the outer edge line preset sampling point into the fisheye diagram;
searching in the range between the sampling point of the inner edge line of the fisheye pattern and the preset sampling point of the outer edge line, and extracting to obtain a distortion-removed sampling point of the inner edge line based on the pixel difference between adjacent searching points;
and projecting the inner edge distortion removal sampling points to the aerial view, distinguishing the inner point from the outer point of the inner edge distortion removal sampling points by adopting a method of straight line fitting based on ransac, and performing straight line fitting by using the inner points to obtain the actual inner edge of the vehicle-side line.
The invention provides a parking space line detection optimization system based on a fish eye diagram, which comprises the following functional modules:
the inner edge line extraction module is used for carrying out distortion correction on the fish eye diagram of the parking space line and converting the fish eye diagram into a bird's-eye view diagram, and extracting the inner edge line of the parking space line from the bird's-eye view diagram;
the outer edge line determining module is used for determining undistorted inner edge line sampling points and outer edge line preset sampling points in the bird's-eye view image and projecting the inner edge line sampling points and the outer edge line preset sampling points into the fish-eye image;
the sampling point extraction module is used for searching in a range between an inner edge line sampling point of the fisheye pattern and an outer edge line preset sampling point, and extracting to obtain an inner edge line distortion removal sampling point based on a pixel difference between adjacent searching points;
and the inner point straight line fitting module is used for projecting the inner edge line distortion removal sampling points to the aerial view, distinguishing the inner point from the outer point of the inner edge line distortion removal sampling points by adopting a method of straight line fitting based on ransac, and performing straight line fitting by using the inner points to obtain the actual inner edge line of the vehicle position line.
The third aspect of the present invention provides a server, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the above-mentioned method for optimizing the detection of the lane based on the fish eye diagram.
A fourth aspect of the present invention provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method for optimizing parking stall line detection based on a fish eye diagram is implemented.
Compared with the prior art, the fisheye-diagram-based parking space line detection optimization method has the advantages that distortion correction is carried out on the inner edge line of the parking space line through the fisheye camera, the inner edge line distortion removal sampling points are obtained through searching according to the corrected inner edge line and the search range of the width of the parking space line, the inner edge line distortion removal sampling points are divided into the inner edge points and the outer edge points through fitting correction, and the inner edge points are used for carrying out straight line fitting to obtain the actual inner edge line of the parking space line. The parking space line detection optimization method based on the fish eye diagram only depends on a camera and a traditional algorithm, the recognition cost is low, the correction process is simplified, meanwhile, only the inner edge points are adopted for straight line fitting, interference of outer points formed by line stain shadow and other reasons on the straight line fitting of the inner edge lines is eliminated, and the recognition accuracy is improved.
Drawings
Fig. 1 is a block flow diagram of a parking space line detection optimization method based on a fish eye diagram according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a substep of step S2 in a parking space line detection optimization method based on a fish eye diagram according to an embodiment of the present invention;
fig. 3 is a flow chart of steps of step S3 in the parking space line detection optimization method based on the fish eye diagram according to the embodiment of the present invention;
fig. 4 is a flowchart illustrating a substep of step S4 in the parking space line detection optimization method based on the fish eye diagram according to the embodiment of the present invention;
fig. 5 is a block diagram of a parking space line detection optimization system based on a fish eye diagram according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1 to 4, an embodiment of the present invention provides a method for optimizing parking space line detection based on a fish eye pattern, which includes the following steps:
s1, distortion correction is carried out on the fish-eye image of the vehicle location line, the fish-eye image is converted into a bird 'S-eye view image, and the inner edge line of the vehicle location line is extracted and obtained from the bird' S-eye view image.
Because the imaging distortion of the fisheye lens is large, the fisheye image needs to be subjected to distortion removal, then the fisheye image is converted into a bird's-eye view image to be subjected to parking space detection, and the inner edge line of the parking space line is extracted and obtained and is shown in fig. 1.
S2, determining undistorted inner edge line sampling points and outer edge line preset sampling points in the aerial view, and projecting the inner edge line sampling points and the outer edge line preset sampling points into the fisheye diagram.
The inner edge line sampling point is extracted from the inner edge line, the outer edge line preset sampling point is obtained based on the width search of the inner edge line sampling point and the stop line, and the inner edge line sampling point and the outer edge line preset sampling point are projected into the fisheye diagram.
Specifically, as shown in fig. 2, the step S2 includes the following sub-steps:
s21, equally dividing the inner edge of the vehicle line to obtain inner edge sampling points;
s22, setting the sampling point of the inner edge line as an edge searching initial point, and searching outwards according to the width of the stop line to obtain an edge searching end point which is the preset sampling point of the outer edge line;
and S23, projecting the inner edge line sampling points and the outer edge line preset sampling points into the fisheye diagram according to the camera internal parameters and the distortion coefficient of the camera.
And S3, searching within the range between the inner edge line sampling point of the fisheye pattern and the preset sampling point of the outer edge line, and extracting to obtain an inner edge line distortion-removing sampling point based on the pixel difference between adjacent searching points.
As shown in fig. 3, the step S3 includes the following sub-steps:
s31, searching outwards from the inner edge line sampling point in the range between the inner edge line sampling point of the fisheye pattern and the preset sampling point of the outer edge line;
and S32, calculating pixel difference between adjacent search points, wherein the line pixel difference is larger than a set threshold and is set as an inner-edge line distortion removal sampling point which is negative.
And S4, projecting the inner edge line distortion removal sampling points to the aerial view, distinguishing inner points from outer points of the inner edge line distortion removal sampling points by adopting a method of straight line fitting based on ransac, and performing straight line fitting by using the inner points to obtain the actual inner edge line of the vehicle position line.
The method for performing linear fitting based on ransac distinguishes the inner and outer points of the distortion-removed sampling points of the inner line, and specifically comprises the following steps:
and taking any two inner edge line distortion removal sampling points to calculate a straight line, calculating the distance between the residual inner edge line distortion removal sampling points and the straight line, if the distance is greater than the preset threshold distance, summarizing the distance into an outer point, and if the distance is less than the preset threshold distance, summarizing the distance into an inner point.
As shown in fig. 4, the step S4 includes the following sub-steps:
s41, projecting the inner edge distortion removal sampling points to a bird-eye view, taking any two inner edge distortion removal sampling points to calculate a straight line, and calculating the distance between the remaining inner edge distortion removal sampling points and the straight line, wherein if the distance is greater than a preset threshold distance, the distance is summarized as an outer point, and if the distance is less than the preset threshold distance, the distance is summarized as an inner point;
s42, arranging the inner point sets obtained by distinguishing each straight line, and selecting the point set with the largest number of inner points to perform straight line fitting to obtain a vertical line of the corrected inner edge line;
and S43, setting a new parking space according to the intersection point of the horizontal line of the inner edge line of the original parking space line and the vertical line of the corrected inner edge line.
The number of the interior points of the interior point set for linear fitting is selected to be more than 2.
The embodiment of the invention provides a fisheye diagram-based parking space line detection optimization method, which comprises the steps of carrying out distortion correction on an inner edge line of a parking space line, deriving an outer edge line preset sampling point according to a distortion-removed inner edge line sampling point, and searching in a range between the inner edge line sampling point and the outer edge line preset sampling point to obtain an inner edge line distortion-removed sampling point; and distinguishing the inner edge point and the outer edge point of the distortion-removing sampling point of the inner edge in the aerial view, and performing straight line fitting by using the inner points to obtain the actual inner edge line of the vehicle position line.
The parking space line detection optimization method based on the fisheye diagram comprises the steps of carrying out distortion correction on an inner edge line of a parking space line through a fisheye camera, searching according to the corrected inner edge line and the search range of the width of the parking space line to obtain an inner edge line distortion removal sampling point, dividing the inner edge line distortion removal sampling point into an inner edge point and an outer edge point through fitting correction, and carrying out straight line fitting through the inner edge point to obtain an actual inner edge line of the parking space line. The parking space line detection optimization method based on the fish eye diagram only depends on a camera and a traditional algorithm, the recognition cost is low, the correction process is simplified, meanwhile, only the inner edge points are adopted for straight line fitting, interference of outer points formed by line stain shadow and other reasons on the straight line fitting of the inner edge lines is eliminated, and the recognition accuracy is improved.
As shown in fig. 5, the embodiment of the present invention further discloses a parking space line detection optimization system based on a fish eye diagram, which includes the following functional modules:
the inner edge line extraction module 10 is configured to perform distortion correction on the fisheye diagram of the vehicle location line, convert the fisheye diagram into a bird's-eye view diagram, and extract the inner edge line of the vehicle location line from the bird's-eye view diagram;
the outer edge line determining module 20 is used for determining an undistorted inner edge line sampling point and an outer edge line preset sampling point in the bird's eye view, and projecting the inner edge line sampling point and the outer edge line preset sampling point into the fish eye diagram;
the sampling point extraction module 30 is used for searching in a range between an inner edge line sampling point of the fisheye pattern and an outer edge line preset sampling point, and extracting to obtain an inner edge line distortion removal sampling point based on a pixel difference between adjacent searching points;
and the inner point straight line fitting module 40 is used for projecting the inner edge line distortion removal sampling points to the aerial view, distinguishing the inner point from the outer point of the inner edge line distortion removal sampling points by adopting a method of straight line fitting based on ransac, and performing straight line fitting by using the inner points to obtain the actual inner edge line of the vehicle position line.
The execution mode of the parking space line detection optimization system based on the fish-eye pattern in this embodiment is basically the same as that of the parking space line detection optimization method based on the fish-eye pattern, and therefore detailed description is omitted.
The server in this embodiment is a device for providing computing services, and generally refers to a computer with high computing power, which is provided to a plurality of consumers via a network. The server of this embodiment includes: a memory including an executable program stored thereon, a processor, and a system bus, it will be understood by those skilled in the art that the terminal device structure of the present embodiment does not constitute a limitation of the terminal device, and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
The memory may be used to store software programs and modules, and the processor may execute various functional applications of the terminal and data processing by operating the software programs and modules stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the terminal, etc. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The memory contains an executable program of the method for optimizing the detection of the lane based on the fish eye diagram, the executable program can be divided into one or more modules/units, the one or more modules/units are stored in the memory and executed by the processor to complete the acquisition and implementation process of the information, and the one or more modules/units can be a series of instruction segments of a computer program capable of completing specific functions, and the instruction segments are used for describing the execution process of the computer program in the server. For example, the computer program may be divided into an inner edge line extraction module 10, an outer edge line determination module 20, a sampling point extraction module 30, and an inner point straight line fitting module 40.
The processor is a control center of the server, connects various parts of the whole terminal equipment by various interfaces and lines, and executes various functions of the terminal and processes data by running or executing software programs and/or modules stored in the memory and calling data stored in the memory, thereby performing overall monitoring of the terminal. Alternatively, the processor may include one or more processing units; preferably, the processor may integrate an application processor, which mainly handles operating systems, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor.
The system bus is used to connect functional units in the computer, and can transmit data information, address information and control information, and the types of the functional units can be PCI bus, ISA bus, VESA bus, etc. The system bus is responsible for data and instruction interaction between the processor and the memory. Of course, the system bus may also access other devices such as network interfaces, display devices, etc.
The server at least includes a CPU, a chipset, a memory, a disk system, and the like, and other components are not described herein again.
In the embodiment of the present invention, the executable program executed by the processor included in the terminal specifically includes: a parking space line detection optimization method based on a fish eye diagram comprises the following steps:
distortion correction is carried out on the fisheye diagram of the vehicle location line, the fisheye diagram is converted into a bird's-eye view, and the inner edge line of the vehicle location line is extracted from the bird's-eye view;
determining undistorted inner edge line sampling points and preset sampling points of the outer edge line in the bird's-eye view, and projecting the inner edge line sampling points and the preset sampling points of the outer edge line into the fish eye view;
searching in the range between the sampling point of the inner edge line of the fisheye pattern and the preset sampling point of the outer edge line, and extracting to obtain a distortion-removed sampling point of the inner edge line based on the pixel difference between adjacent searching points;
and projecting the inner edge distortion removal sampling points to the aerial view, distinguishing the inner point from the outer point of the inner edge distortion removal sampling points by adopting a method of straight line fitting based on ransac, and performing straight line fitting by using the inner points to obtain the actual inner edge of the vehicle-side line.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art would appreciate that the modules, elements, and/or method steps of the various embodiments described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. The parking space line detection optimization method based on the fish eye diagram is characterized by comprising the following steps of:
distortion correction is carried out on the fisheye diagram of the vehicle location line, the fisheye diagram is converted into a bird's-eye view, and the inner edge line of the vehicle location line is extracted from the bird's-eye view;
determining an undistorted inner edge line sampling point and an outer edge line preset sampling point in the aerial view, and projecting the inner edge line sampling point and the outer edge line preset sampling point into the fisheye diagram;
searching in the range between the inner edge line sampling point of the fisheye pattern and the preset sampling point of the outer edge line, and extracting to obtain an inner edge line distortion removal sampling point based on the pixel difference between adjacent searching points;
and projecting the inner edge distortion removal sampling points to the aerial view, distinguishing the inner point from the outer point of the inner edge distortion removal sampling points by adopting a method of straight line fitting based on ransac, and performing straight line fitting by using the inner points to obtain the actual inner edge of the vehicle-side line.
2. The method for optimizing the detection of the parking space line based on the fish-eye diagram according to claim 1, wherein the step of determining the undistorted sampling points of the inner edge line and the predetermined sampling points of the outer edge line in the bird's eye view and projecting the sampling points of the inner edge line and the predetermined sampling points of the outer edge line into the fish-eye diagram comprises the steps of:
interior limit line sampling point is drawed on the interior limit line, and the width search based on interior limit line sampling point and parking line obtains the preset sampling point of outer sideline, with interior limit line sampling point and with the preset sampling point projection of outer sideline to the fish-eye pattern in.
3. The parking space line detection optimization method based on the fish eye pattern according to claim 2, wherein the inner edge line sampling points are extracted from the inner edge lines, the outer edge line preset sampling points are obtained based on the inner edge line sampling points and the width search of the stop line, and the inner edge line sampling points and the outer edge line preset sampling points are projected into the fish eye pattern, and the method specifically comprises the following steps:
equally dividing the inner edge of the vehicle line to obtain inner edge sampling points;
setting an inner edge line sampling point as an edge search starting point, and searching outwards according to the width of the stop line to obtain an edge search end point which is an outer edge line preset sampling point;
and projecting the inner edge line sampling point and the outer edge line preset sampling point into the fisheye diagram according to the camera internal parameter and the distortion coefficient of the camera.
4. The method according to claim 1, wherein the fish-eye diagram based parking space line detection optimization method is characterized in that the method searches within a range between an inner edge line sampling point of the fish-eye diagram and an outer edge line preset sampling point, and extracts an inner edge line distortion removing sampling point based on a pixel difference between adjacent searching points, and specifically comprises the following steps:
searching outwards from the inner edge line sampling point in the range between the inner edge line sampling point of the fisheye pattern and the preset sampling point of the outer edge line;
and calculating pixel difference between adjacent search points, wherein the line pixel difference is greater than a set threshold and is set as an inner-edge line distortion removal sampling point which is negative.
5. The method according to claim 1, wherein the method for performing inner and outer point distinguishing on the sampling points for inner edge distortion removal by using a line fitting method based on ransac specifically comprises:
and taking any two inner edge line distortion removal sampling points to calculate a straight line, calculating the distance between the residual inner edge line distortion removal sampling points and the straight line, if the distance is greater than the preset threshold distance, summarizing the distance into an outer point, and if the distance is less than the preset threshold distance, summarizing the distance into an inner point.
6. The method according to claim 5, wherein the inner edge distortion removal sampling points are projected to the bird's-eye view, the inner edge distortion removal sampling points are distinguished by inner and outer points by a method based on ransac line fitting, and the inner points are used for line fitting to obtain the actual inner edge of the parking space line, and the method specifically comprises the following steps:
projecting the inner edge line distortion removal sampling points to the aerial view, taking any two inner edge line distortion removal sampling points to calculate a straight line, and calculating the distance between the remaining inner edge line distortion removal sampling points and the straight line, wherein if the distance is greater than a preset threshold distance, the distance is summarized as an outer point, and if the distance is less than the preset threshold distance, the distance is summarized as an inner point;
sorting the inner point sets obtained by distinguishing each straight line, and selecting the point set with the largest number of inner points to perform straight line fitting to obtain a vertical line of the corrected inner edge line;
and setting the intersection point of the horizontal line of the inner edge line of the original parking space line and the vertical line of the corrected inner edge line as a new parking space.
7. The method of claim 6, wherein the number of interior points of the interior point set selected for straight line fitting is greater than 2.
8. The utility model provides a parking stall line detection optimizing system based on fish eye, its characterized in that includes following functional module:
the inner edge line extraction module is used for carrying out distortion correction on the fish eye diagram of the parking space line and converting the fish eye diagram into a bird's-eye view diagram, and extracting the inner edge line of the parking space line from the bird's-eye view diagram;
the outer edge line determining module is used for determining undistorted inner edge line sampling points and outer edge line preset sampling points in the bird's-eye view image and projecting the inner edge line sampling points and the outer edge line preset sampling points into the fish-eye image;
the sampling point extraction module is used for searching in a range between an inner edge line sampling point of the fisheye pattern and an outer edge line preset sampling point, and extracting to obtain an inner edge line distortion removal sampling point based on a pixel difference between adjacent searching points;
and the inner point straight line fitting module is used for projecting the inner edge line distortion removal sampling points to the aerial view, distinguishing the inner point from the outer point of the inner edge line distortion removal sampling points by adopting a method of straight line fitting based on ransac, and performing straight line fitting by using the inner points to obtain the actual inner edge line of the vehicle position line.
9. A server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the fisheye-based lane detection optimization method of any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the fisheye-based lane detection optimization method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211042832.0A CN115457504A (en) | 2022-08-29 | 2022-08-29 | Parking space line detection optimization method and system based on fish eye pattern |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211042832.0A CN115457504A (en) | 2022-08-29 | 2022-08-29 | Parking space line detection optimization method and system based on fish eye pattern |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115457504A true CN115457504A (en) | 2022-12-09 |
Family
ID=84301575
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211042832.0A Pending CN115457504A (en) | 2022-08-29 | 2022-08-29 | Parking space line detection optimization method and system based on fish eye pattern |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115457504A (en) |
-
2022
- 2022-08-29 CN CN202211042832.0A patent/CN115457504A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6336117B2 (en) | Building height calculation method, apparatus and storage medium | |
CN105718872B (en) | Auxiliary method and system for rapidly positioning lanes on two sides and detecting vehicle deflection angle | |
CN112348921B (en) | Drawing construction method and system based on visual semantic point cloud | |
CN111376895A (en) | Around-looking parking sensing method and device, automatic parking system and vehicle | |
CN108748184B (en) | Robot patrol method based on regional map identification and robot equipment | |
CN111027381A (en) | Method, device, equipment and storage medium for recognizing obstacle by monocular camera | |
CN104535047A (en) | Multi-agent target tracking global positioning system and method based on video stitching | |
WO2021017211A1 (en) | Vehicle positioning method and device employing visual sensing, and vehicle-mounted terminal | |
CN108961276B (en) | Distribution line inspection data automatic acquisition method and system based on visual servo | |
CN111046809B (en) | Obstacle detection method, device, equipment and computer readable storage medium | |
CN113469201A (en) | Image acquisition equipment offset detection method, image matching method, system and equipment | |
CN110718068A (en) | Road monitoring camera installation angle estimation method | |
CN105389812A (en) | Computer vision-based vehicle-mounted information terminal function automatic test method | |
CN113190564A (en) | Map updating system, method and device | |
CN115457504A (en) | Parking space line detection optimization method and system based on fish eye pattern | |
CN116912517A (en) | Method and device for detecting camera view field boundary | |
CN115223135B (en) | Parking space tracking method and device, vehicle and storage medium | |
CN111639662A (en) | Remote sensing image bidirectional matching method and device, electronic equipment and storage medium | |
CN111046831A (en) | Poultry identification method and device and server | |
CN110986916A (en) | Indoor positioning method and device, electronic equipment and storage medium | |
CN114463717A (en) | Obstacle position judgment method and system, electronic device and storage medium | |
CN114750746A (en) | Parking space tracking method based on domain controller, electronic device and storage medium | |
CN111860084B (en) | Image feature matching and positioning method and device and positioning system | |
CN114025089A (en) | Video image acquisition jitter processing method and system | |
CN113643374A (en) | Multi-view camera calibration method, device, equipment and medium based on road characteristics |
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 |