CN116385397B - Road information identification method and system based on camera - Google Patents
Road information identification method and system based on camera Download PDFInfo
- Publication number
- CN116385397B CN116385397B CN202310355770.7A CN202310355770A CN116385397B CN 116385397 B CN116385397 B CN 116385397B CN 202310355770 A CN202310355770 A CN 202310355770A CN 116385397 B CN116385397 B CN 116385397B
- Authority
- CN
- China
- Prior art keywords
- area
- reflectivity
- target
- low
- boundary
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000002310 reflectometry Methods 0.000 claims abstract description 81
- 238000001514 detection method Methods 0.000 claims abstract description 62
- 239000000463 material Substances 0.000 claims abstract description 55
- 238000005192 partition Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 15
- 230000003287 optical effect Effects 0.000 claims description 15
- 238000013136 deep learning model Methods 0.000 claims description 10
- 239000010410 layer Substances 0.000 claims description 10
- 230000001681 protective effect Effects 0.000 claims description 9
- 238000005286 illumination Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 239000002344 surface layer Substances 0.000 claims description 7
- 238000005299 abrasion Methods 0.000 claims description 3
- 239000011248 coating agent Substances 0.000 claims description 3
- 238000000576 coating method Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 238000009826 distribution Methods 0.000 abstract description 15
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 108091026890 Coding region Proteins 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- 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
- G06T2207/30256—Lane; Road marking
Abstract
The invention relates to the technical field of lane information analysis, in particular to a camera-based road information identification method and system. Paving a pavement according to preset materials and preset coding information to form a target pavement lane line; carrying out partition detection on the target pavement lane line according to the radiance, and selecting detection areas, wherein the classification of the detection areas comprises a high reflection area and a low reflection area; performing area compensation, and selecting a target area of the maximum surrounding area; obtaining a boundary of a target area and extracting a central area; and carrying out lane line fitting to generate a lane accurate boundary. According to the scheme, the target object is made of high-reflectivity and low-reflectivity materials based on the special properties of the materials and preset paving coding information, and the high-low-reflectivity distribution similar to a chess-disk shape is realized by combining the setting distribution so as to improve the contrast ratio, and the mode of low reflectivity outside and high reflectivity inside is adopted, so that the target area can be conveniently and rapidly determined.
Description
Technical Field
The invention relates to the technical field of lane information analysis, in particular to a camera-based road information identification method and system.
Background
The camera is limited to be a passive optical device in most common cameras, the bit depth of the common cameras is 8 (the raw mode can reach 12 but the common cameras occupy a memory very often, one picture can reach tens of MB), the distinguishable intensity range is limited (0-255, 256 levels), and object information can not be obtained correctly in a strong light or weak light environment or the contrast ratio of different objects is very low, so that subsequent analysis can not be performed. The situation that the lane lines are lost or incomplete often occurs for driving, which is unfavorable for auxiliary or automatic driving and has potential safety hazard. In addition, the current deep learning model is highly dependent on the incoming data, and when the incoming data is special or worse in distribution, the accuracy of the model cannot be guaranteed.
Prior to the present invention, although the prior art can use multi-sensor data fusion to solve the problem, in consideration of possible safety requirements of various special scenes, certain constraint conditions such as equipment, equipment price, algorithm complexity and the like cannot be used, and related tasks sometimes need to be completed by means of a camera alone. The whole process of receiving the echo by the camera is carefully analyzed, the properties of the material are not known, the special optical properties of the material are not utilized, and the technological development of the road is relatively stagnant. After the reflection characteristics of special materials are researched and the wave band received by the camera is modeled and analyzed, the basic material selection and coding mode is determined, so that when the camera passively detects a target, higher contrast information can be obtained, and accurate information interpretation is realized.
Disclosure of Invention
In view of the above problems, the invention provides a road information identification method and system based on a camera, which make a target object consist of high-reflectivity and low-reflectivity materials based on the special properties of the materials and preset paving coding information, and combine with setting distribution to realize high-low reflectivity distribution similar to a checkerboard shape so as to improve contrast ratio, and the coding area is set in a mode of low reflectivity outside and high reflectivity inside, so that the target area can be quickly determined during detection.
According to a first aspect of the embodiment of the invention, a road information identification method based on a camera is provided.
Paving the pavement according to preset materials and preset coding information to form a target pavement lane line;
carrying out partition detection on the target pavement lane line according to the radiance, and selecting detection areas, wherein the classification of the detection areas comprises a high reflection area and a low reflection area;
searching the lowest reflection area or the high reflection area of the outermost layer according to the detection area, performing area compensation, and selecting the maximum surrounding area as a target area;
obtaining a target area boundary according to the high reflection area or the low reflection area inside the target area searching area;
extracting a central region according to the boundary of the target region;
and carrying out lane line fitting according to the central area to generate a lane accurate boundary.
Paving the road surface according to preset materials and preset coding information to form a target road surface lane line, wherein the method specifically comprises the following steps of:
selecting a lane, wherein the inner areas are alternately arranged in a square grid mode according to the low-reflectivity areas and the high-reflectivity areas, and the outermost layer of the lane is surrounded by the high-reflectivity areas and the low-reflectivity areas and is arranged in a mode of external low reflectivity and internal high reflectivity to serve as an initial arrangement scheme;
a low reflectivity material is used for the low reflectivity region;
a high reflectivity material is adopted for the high reflectivity region;
after the low-reflectivity region and the high-reflectivity region are arranged, coating a protective film on the surface layer, wherein the surface layer protective film is an antireflection film with a preset detection wave band, and the surface layer protective film is also used for protecting lower particles and reducing grain abrasion and carried loss;
the visible light wave band properties of the materials of the low-reflectivity region and the high-low-reflectivity region are uniform, wherein the uniformity of the properties particularly means that the intensity values of the cameras obtained by reflection generated under different illumination conditions are changed in equal proportion;
and distributing the low-reflectivity area and the high-reflectivity area on the surface of the pavement according to the initial arrangement scheme to form the target pavement lane line.
Preferably, the detecting area is selected according to the illumination intensity by performing the partition detection on the target pavement lane line, wherein the classification of the detecting area includes a high reflection area and a low reflection area, and specifically includes:
an auxiliary optical sensor is arranged on a running vehicle, and the current light intensity is obtained through the optical sensor;
according to the light intensity, a first command is sent out if a first calculation formula is met, a second command is sent out if a second calculation formula is met, and a third command is sent out if the first calculation formula is not met or the second calculation formula is not met;
after receiving the first command, deleting the data of the corresponding detection area;
after receiving the second command, the corresponding high-reflection area and the low-reflection area are reserved together as data of a detection area;
after receiving the third command, taking the low reflection area as a detection area;
the first calculation formula is as follows:
G>Y 1
wherein Y is 1 G is the light intensity for a first preset margin;
the second calculation formula is as follows:
G<Y 2
wherein Y is 2 Is a second preset margin.
Preferably, the searching the outermost low reflection area or the high reflection area according to the detection area, performing area compensation, and selecting the maximum surrounding area as the target area specifically includes:
after the detection area is obtained, the outermost low reflection area or the high reflection area is extracted, and the transverse longest distance and the longitudinal longest distance are obtained;
and setting a transverse boundary and a longitudinal boundary according to the transverse longest distance and the longitudinal longest distance, and complementing the detection area into a square shape as the target area of the maximum surrounding area.
Preferably, the obtaining the target area boundary according to the high reflection area or the low reflection area inside the target area searching area specifically includes:
searching an inner layer high reflection area or a low reflection area according to the target area;
setting a deep learning model according to equipment computing force requirements, task requirements, precision requirements and format requirements of a user, and acquiring boundaries in the target area by utilizing an original image according to the deep learning model.
Preferably, the extracting a central area according to the boundary of the target area specifically includes:
extracting a central region according to the boundary of the target region;
acquiring material coding information of a corresponding position according to the RGB information in the boundary of the target area;
and according to the material coding information, obtaining the block length according to curves under different preset light environments, and calculating boundary blocks, so that the central area of the whole lane line is determined.
Preferably, the lane line fitting is performed according to the central area, and the lane line fitting is generated as a lane accurate boundary, which specifically includes:
setting a scaling according to the central region;
and scaling the central area according to the scaling ratio to obtain a corresponding lane accurate boundary.
According to a second aspect of the embodiment of the invention, a road information identification system based on a camera is provided.
In one or more embodiments, preferably, the camera-based road information recognition system includes:
the grid setting module is used for paving the pavement according to the preset materials and the preset coding information to form a target pavement lane line;
the intensity analysis module is used for carrying out partition detection on the target pavement lane line according to the radiance and selecting detection areas, wherein the classification of the detection areas comprises a high-reflection area and a low-reflection area;
the outer boundary compensation module is used for searching the outermost low reflection area or the high reflection area according to the detection area, performing area compensation and selecting the maximum surrounding area as a target area;
the inner boundary operation module is used for searching a high-reflection area or a low-reflection area in the area according to the target area to obtain a target area boundary;
the central region analysis module is used for extracting a central region according to the boundary of the target region;
and the lane fitting module is used for performing lane line fitting according to the central area and generating a lane accurate boundary.
According to a third aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method according to any of the first aspect of embodiments of the present invention.
According to a fourth aspect of embodiments of the present invention there is provided an electronic device comprising a memory and a processor, the memory being for storing one or more computer program instructions, wherein the one or more computer program instructions are executable by the processor to implement the method of any of the first aspects of embodiments of the present invention.
The technical scheme provided by the embodiment of the invention can comprise the following beneficial effects:
according to the scheme, the target object is made of the high-reflectivity and low-reflectivity materials based on the special properties of the materials and preset paving coding information, and the high-low-reflectivity distribution similar to a chess-disk shape is realized by combining the set distribution, so that the contrast ratio is improved, and accurate information identification is realized.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for identifying road information based on a camera according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for identifying road information based on a camera according to an embodiment of the present invention, in which a road surface is paved according to a preset material and preset coding information, so as to form a lane line of a target road surface.
Fig. 3 is a flowchart illustrating a method for identifying road information based on a camera according to an embodiment of the present invention, in which a detection area is selected by performing a partition detection on the target road lane line according to a radiance, wherein the classification of the detection area includes a high reflection area and a low reflection area.
Fig. 4 is a flowchart of searching an outermost low reflection area or a high reflection area according to the detection area, performing area compensation, and selecting a maximum surrounding area as a target area in a camera-based road information identification method according to an embodiment of the present invention.
Fig. 5 is a flowchart of a method for identifying road information based on a camera according to an embodiment of the present invention, wherein the method searches for a high reflection area or a low reflection area inside an area according to the target area, and obtains a boundary of the target area.
Fig. 6 is a flowchart of extracting a center area according to a boundary of the target area in a camera-based road information recognition method according to an embodiment of the present invention.
Fig. 7 is a flowchart of a method for identifying road information based on a camera according to an embodiment of the present invention, in which lane line fitting is performed according to the center area, and a lane accurate boundary is generated.
Fig. 8 is a block diagram of a camera-based road information recognition system according to an embodiment of the present invention.
Fig. 9 is a block diagram of an electronic device in one embodiment of the invention.
Detailed Description
In some of the flows described in the specification and claims of the present invention and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as 101, 102, etc., being merely used to distinguish between the various operations, the order of the operations themselves not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
The camera is limited to be a passive optical device in most common cameras, the bit depth of the common cameras is 8 (the raw mode can reach 12 but the common cameras occupy a memory very often, one picture can reach tens of MB), the distinguishable intensity range is limited (0-255, 256 levels), and object information can not be obtained correctly in a strong light or weak light environment or the contrast ratio of different objects is very low, so that subsequent analysis can not be performed. The situation that the lane lines are lost or incomplete often occurs for driving, which is unfavorable for auxiliary or automatic driving and has potential safety hazard. In addition, the current deep learning model is highly dependent on the incoming data, and when the incoming data is special or worse in distribution, the accuracy of the model cannot be guaranteed.
Prior to the present invention, although the prior art can use multi-sensor data fusion to solve the problem, in consideration of possible safety requirements of various special scenes, certain constraint conditions such as equipment, equipment price, algorithm complexity and the like cannot be used, and related tasks sometimes need to be completed by means of a camera alone. The whole process of receiving the echo by the camera is carefully analyzed, the properties of the material are not known, the special optical properties of the material are not utilized, and the technological development of the road is relatively stagnant. After the reflection characteristics of special materials are researched and the wave band received by the camera is modeled and analyzed, the basic material selection and coding mode is determined, so that when the camera passively detects a target, higher contrast information can be obtained, and accurate information interpretation is realized.
The embodiment of the invention provides a method and a system for identifying road information based on a camera. According to the scheme, the target object is made of high-reflectivity and low-reflectivity materials based on the special properties of the materials and preset paving coding information, and the high-low-reflectivity distribution similar to a chess-disk shape is realized by combining the preset distribution so as to improve the contrast ratio, and the coding region is arranged in a mode of low reflectivity outside and high reflectivity inside, so that the target region can be conveniently and quickly determined during detection.
According to a first aspect of the embodiment of the invention, a road information identification method based on a camera is provided.
Fig. 1 is a flowchart of a method for identifying road information based on a camera according to an embodiment of the present invention.
In one or more embodiments, preferably, the method for identifying road information based on a camera includes:
s101, paving a pavement according to preset materials and preset coding information to form a target pavement lane line;
s102, carrying out partition detection on the lane line of the target pavement according to the radiance, and selecting detection areas, wherein the classification of the detection areas comprises a high-reflection area and a low-reflection area;
s103, searching an outermost layer low reflection area or a high reflection area according to the detection area, performing area compensation, and selecting a maximum surrounding area as a target area;
s104, searching a high reflection area or a low reflection area in the area according to the target area to obtain a target area boundary;
s105, extracting a central region according to the boundary of the target region;
s106, carrying out lane line fitting according to the central area, and generating a lane accurate boundary.
In the embodiment of the invention, based on special materials and artificial codes, the special optical properties of the materials are utilized to quickly determine the region of interest and improve the contrast of different areas so as to cope with extreme illumination environments, and the data is subjected to preset correction and then the boundary is determined through a deep learning model.
Fig. 2 is a flowchart of a method for identifying road information based on a camera according to an embodiment of the present invention, in which a road surface is paved according to a preset material and preset coding information, so as to form a lane line of a target road surface.
As shown in fig. 2, in one or more embodiments, preferably, the paving is laid according to a preset material and preset coding information to form a target pavement lane line, which specifically includes:
s201, selecting a lane, wherein the inner areas are alternately arranged in a square grid mode according to the low-reflectivity areas and the high-reflectivity areas, the outermost layer of the lane is surrounded by the high-reflectivity areas and the low-reflectivity areas, and the outer low-reflectivity inner high-reflectivity mode is adopted as an initial arrangement scheme;
s202, adopting a low-reflectivity material for the low-reflectivity area;
s203, adopting a high-reflectivity material for the high-reflectivity region;
s204, after the low-reflectivity region and the high-reflectivity region are arranged, coating a protective film on the surface layer, wherein the surface layer protective film is an antireflection film with a preset detection wave band, and the surface layer protective film is also used for protecting lower particles and reducing grain abrasion and carried loss;
s205, the visible light wave band properties of the materials of the low-reflectivity region and the high-low-reflectivity region are uniform, wherein the uniformity of the properties particularly means that the intensity values of the cameras obtained by reflection generated under different illumination conditions are changed in equal proportion;
s206, laying the low-reflectivity area and the high-reflectivity area on the surface of the road surface according to the initial arrangement scheme to form the target road surface lane line.
In the embodiment of the invention, the light wave reflected by the target object prepared and coded by the special material is detected based on the camera, the target object area is rapidly positioned according to the special optical property of the material, then the coded information of the target object is fitted through the deep learning algorithm, the obtained data is compared with the pre-stored data, and finally the physical information is processed into the road information which can be applied to the fields of intelligent automobiles, automatic driving, road coordination and the like.
Fig. 3 is a flowchart illustrating a method for identifying road information based on a camera according to an embodiment of the present invention, in which a detection area is selected by performing a partition detection on the target road lane line according to a radiance, wherein the classification of the detection area includes a high reflection area and a low reflection area.
As shown in fig. 3, in one or more embodiments, preferably, the detecting areas are selected according to the detection of the target pavement lane line in a partition manner, where the classification of the detecting areas includes a high reflection area and a low reflection area, and specifically includes:
s301, arranging an auxiliary optical sensor on a running vehicle, and acquiring the current light intensity through the optical sensor;
s302, according to the light intensity, a first command is sent out if a first calculation formula is met, a second command is sent out if a second calculation formula is met, and a third command is sent out if neither the first calculation formula nor the second calculation formula is met;
s303, deleting the data of the corresponding detection area after receiving the first command;
s304, after receiving the second command, reserving the corresponding high-reflection area and low-reflection area as data of a detection area;
s305, after receiving the third command, taking the low reflection area as a detection area;
the first calculation formula is as follows:
G>Y 1
wherein Y is 1 G is the light intensity for a first preset margin;
the second calculation formula is as follows:
G<Y 2
wherein Y is 2 Is a second preset margin.
In the embodiment of the invention, the coded target object is paved on the road in advance by using special preparation materials, when the vehicle passes through the area, the camera passively receives echoes of the target object and the surrounding environment, and a matching relationship is established by analyzing the optical characteristics of the object and echo information, so that the target object area is determined.
Fig. 4 is a flowchart of searching an outermost low reflection area or a high reflection area according to the detection area, performing area compensation, and selecting a maximum surrounding area as a target area in a camera-based road information identification method according to an embodiment of the present invention.
In one or more embodiments, as shown in fig. 4, preferably, the searching the outermost low reflection area or the high reflection area according to the detection area performs area compensation, and selecting the maximum surrounding area as the target area specifically includes:
s401, after the detection area is obtained, extracting the outermost low reflection area or the high reflection area in the detection area, and obtaining the horizontal longest distance and the longitudinal longest distance;
and S402, setting a transverse boundary and a longitudinal boundary according to the transverse longest distance and the longitudinal longest distance, and complementing the detection area into a square shape as the target area of the maximum surrounding area.
In the embodiment of the invention, the resolution of the original image is larger, so that after the region of interest is acquired, the target region is focused on, but the distribution of the target region may not meet the conditions of square, block missing, interruption and the like, so that the size set for model processing, such as 224×224 resolution and the like, needs to be complemented. Considering the background light influence problem possibly existing in the area determined based on the optical method, the situation that the boundary or part of the area is lost can also occur. Therefore, the distribution situation, coordinates, transverse-longitudinal proportion and the like of the acquired blocks are counted, a proper center point is selected, and then the target area is expanded to a specified resolution, so that the target area is fully included.
Fig. 5 is a flowchart of a method for identifying road information based on a camera according to an embodiment of the present invention, wherein the method searches for a high reflection area or a low reflection area inside an area according to the target area, and obtains a boundary of the target area.
As shown in fig. 5, in one or more embodiments, preferably, the searching for a high reflection area or a low reflection area inside the area according to the target area to obtain a target area boundary specifically includes:
s501, searching an inner layer high reflection area or a low reflection area according to the target area;
s502, setting a deep learning model according to equipment computing force requirements, task requirements, precision requirements and format requirements of a user, and acquiring boundaries in the target area by utilizing an original image according to the deep learning model.
In the embodiment of the invention, the boundary of the target area is obtained according to the high-reflection area or the low-reflection area inside the target area searching area, and a specific model is modified on some common frames, such as VGG, transformer, and the like, and on the basis of the model, some module replacement and modification and various super-parameter adjustment are performed. Specifically, the method is customized and modified according to the equipment computing power requirement, the task requirement, the precision requirement, the model format requirement and the like of the user (the large probability is that the proper model is required to be selected for retraining and is converted into the corresponding format, and some models are required to be subjected to operations such as quantization, clipping, graph optimization and the like). Meanwhile, the data of the model are optimized (related tasks such as data analysis, cleaning, distribution estimation and the like can be carried out, and the specific position of the camera can be also used.
Fig. 6 is a flowchart of extracting a center area according to a boundary of the target area in a camera-based road information recognition method according to an embodiment of the present invention.
As shown in fig. 6, in one or more embodiments, preferably, the extracting a central area according to a boundary of the target area specifically includes:
s601, extracting a central region according to the boundary of the target region;
s602, acquiring material coding information of a corresponding position according to the utilization RGB information in the boundary of the target area;
s603, according to the material coding information, obtaining block length according to curves under different preset light environments, and calculating boundary blocks, so that the central area of the whole lane line is determined.
In the embodiment of the invention, after the region is acquired, a deep learning model is used for fitting an optimal curve according to the RGB information of the echo and acquiring material coding information, support is provided for high-precision positioning and the like, a clearer block boundary and a non-center boundary marked on the outer side can be acquired after fitting, specific coordinate conditions, such as 1.5 pixels of an inner block length, can be acquired according to pre-stored data, the pixel length of a boundary block can be calculated according to the pre-set, thus the approximate center position of the whole lane line can be determined, and then the black-white block boundary of the searched clear boundary is searched at the position and sequentially used as the center (possibly even a plurality of blocks are arranged, the center is one, the center region can be selected), and the longitudinal uniformity is ensured.
Fig. 7 is a flowchart of a method for identifying road information based on a camera according to an embodiment of the present invention, in which lane line fitting is performed according to the center area, and a lane accurate boundary is generated.
As shown in fig. 7, in one or more embodiments, preferably, the generating a lane accurate boundary according to the lane line fitting performed by the central area specifically includes:
s701, setting a scaling ratio according to the central area;
s702, scaling the central area according to the scaling ratio to obtain a corresponding lane accurate boundary.
In the embodiment of the invention, after the center is acquired, the scaling is calculated, and the accurate boundary of the lane appears according to the set fitting. The problems of inaccurate scanning, loss and the like of the outer side can be avoided.
According to a second aspect of the embodiment of the invention, a road information identification system based on a camera is provided.
Fig. 8 is a block diagram of a camera-based road information recognition system according to an embodiment of the present invention.
In one or more embodiments, preferably, the camera-based road information recognition system includes:
the grid setting module 801 is configured to lay a pavement according to a preset material and preset coding information to form a target pavement lane line;
the intensity analysis module 802 is configured to perform a partition detection on the target pavement lane according to the radiance, and select a detection area, where the classification of the detection area includes a high reflection area and a low reflection area;
the outer boundary compensation module 803 is configured to search an outermost low reflection area or a high reflection area according to the detection area, perform area compensation, and select a maximum surrounding area as a target area;
the inner boundary operation module 804 is configured to obtain a target region boundary according to the target region searching region internal high reflection region or low reflection region;
a central region analysis module 805 configured to extract a central region according to a boundary of the target region;
and a lane fitting module 806, configured to perform lane line fitting according to the central area, and generate a lane accurate boundary.
In the embodiment of the invention, a system suitable for different structures is realized through a series of modularized designs, and the system can realize closed-loop, reliable and efficient execution through acquisition, analysis and control.
According to a third aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method according to any of the first aspect of embodiments of the present invention.
According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device. Fig. 9 is a block diagram of an electronic device in one embodiment of the invention. The electronic device shown in fig. 9 is a general camera-based road information recognition apparatus. Referring to fig. 9, the electronic device 900 includes one or more (only one shown) processors 902, memory 904, and a wireless module 906 coupled to one another. The memory 904 stores therein a program capable of executing the contents of the foregoing embodiments, and the processor 902 can execute the program stored in the memory 904.
Wherein the processor 902 may include one or more processing cores. The processor 902 utilizes various interfaces and lines to connect various portions of the overall electronic device 900, execute various functions of the electronic device 900, and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 904, and invoking data stored in the memory 904. Alternatively, the processor 902 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 902 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, a target application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 902 and may be implemented solely by a single communication chip.
The Memory 904 may include random access Memory (Random Access Memory, RAM) or Read-Only Memory (rom). The memory 904 may be used to store instructions, programs, code, sets of codes, or instruction sets. The memory 904 may include a stored program area that may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described below, and a stored data area. The storage data area may also store data created by the electronic device 900 in use (such as the text documents previously described), and so forth.
The wireless module 906 is configured to receive and transmit electromagnetic waves, and to implement mutual conversion between electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices, for example, to communicate with a base station based on a mobile communication protocol. The wireless module 906 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and the like. The wireless module 906 may communicate with various networks such as the internet, intranets, wireless networks, or other electronic devices via wireless networks. The wireless network may include a cellular telephone network, a wireless local area network, or a metropolitan area network. The wireless networks described above may use a variety of communication standards, protocols, and technologies, including but not limited to WLAN protocols and bluetooth protocols, and may even include those that have not yet been developed.
The technical scheme provided by the embodiment of the invention can comprise the following beneficial effects:
according to the scheme, the target object is made of the high-reflectivity and low-reflectivity materials based on the special properties of the materials and preset paving coding information, and the high-low-reflectivity distribution similar to a chess-disk shape is realized by combining the set distribution, so that the contrast ratio is improved, and accurate information identification is realized.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The method for identifying the road information based on the camera is characterized by comprising the following steps:
paving the pavement according to preset materials and preset coding information to form a target pavement lane line;
carrying out partition detection on the target pavement lane line according to the illumination intensity, and selecting detection areas, wherein the classification of the detection areas comprises a high-reflection area and a low-reflection area;
searching the lowest reflection area or the high reflection area of the outermost layer according to the detection area, performing area compensation, and selecting the maximum surrounding area as a target area;
obtaining a target area boundary according to the high reflection area or the low reflection area inside the target area searching area;
extracting a central region according to the boundary of the target region;
carrying out lane line fitting according to the central area to generate a lane accurate boundary;
the method for paving the road surface according to the preset materials and the preset coding information to form a target road surface lane line specifically comprises the following steps:
selecting a lane, wherein the inner areas are alternately arranged in a square grid mode according to the low-reflectivity areas and the high-reflectivity areas, and the outermost layer of the lane is surrounded by the high-reflectivity areas and the low-reflectivity areas and is arranged in a mode of external low reflectivity and internal high reflectivity to serve as an initial arrangement scheme;
a low reflectivity material is used for the low reflectivity region;
a high reflectivity material is adopted for the high reflectivity region;
and distributing the low-reflectivity area and the high-reflectivity area on the surface of the pavement according to the initial arrangement scheme to form the target pavement lane line.
2. The method for identifying road information based on camera as claimed in claim 1, wherein the paving of the road surface according to the preset material and the preset coding information forms a target road lane line, and specifically further comprises:
after the low-reflectivity region and the high-reflectivity region are arranged, coating a protective film on the surface layer, wherein the protective film is an antireflection film with a preset detection wave band, and the protective film is also used for protecting lower particles and reducing grain abrasion and carried loss;
the materials of the low-reflectivity region and the high-reflectivity region have uniform visible light wave band properties, wherein the property uniformity particularly means that the intensity values of the cameras obtained by reflection generated under different illumination conditions are changed in equal proportion.
3. The method for identifying road information based on camera as claimed in claim 1, wherein the detecting areas are selected by performing a partition detection on the target road lane according to the illumination intensity, wherein the classification of the detecting areas includes a high reflection area and a low reflection area, and specifically includes:
an auxiliary optical sensor is arranged on a running vehicle, and the current light intensity is obtained through the optical sensor;
according to the light intensity, a first command is sent out if a first calculation formula is met, a second command is sent out if a second calculation formula is met, and a third command is sent out if the first calculation formula is not met or the second calculation formula is not met;
after receiving the first command, deleting the data of the corresponding detection area;
after receiving the second command, the corresponding high-reflection area and the low-reflection area are reserved together as data of a detection area;
after receiving the third command, taking the low reflection area as a detection area;
the first calculation formula is as follows:
；
wherein Y is 1 G is the light intensity for a first preset margin;
the second calculation formula is as follows:
；
wherein Y is 2 Is a second preset margin.
4. The method for identifying road information based on camera as claimed in claim 1, wherein searching the outermost low reflection area or the high reflection area according to the detection area, performing area compensation, and selecting the maximum surrounding area as the target area comprises:
after the detection area is obtained, the outermost low reflection area or the high reflection area is extracted, and the transverse longest distance and the longitudinal longest distance are obtained;
and setting a transverse boundary and a longitudinal boundary according to the transverse longest distance and the longitudinal longest distance, and complementing the detection area into a square shape as the target area of the maximum surrounding area.
5. The method for identifying road information based on camera as claimed in claim 1, wherein the searching for the high reflection area or the low reflection area inside the area according to the target area to obtain the boundary of the target area comprises:
searching an inner layer high reflection area or a low reflection area according to the target area;
setting a deep learning model according to equipment computing force requirements, task requirements, precision requirements and format requirements of a user, and acquiring boundaries in the target area by utilizing an original image according to the deep learning model.
6. The method for identifying road information based on camera according to claim 1, wherein the extracting a central area according to the boundary of the target area comprises:
extracting a central region according to the boundary of the target region;
acquiring material coding information of a corresponding position according to the RGB information in the boundary of the target area;
and according to the material coding information, obtaining the block length according to curves under different preset light environments, and calculating boundary blocks, so that the central area of the whole lane line is determined.
7. The method for identifying road information based on camera as claimed in claim 1, wherein said performing lane line fitting according to said central area generates an accurate boundary of a lane, specifically comprising:
setting a scaling according to the central region;
and scaling the central area according to the scaling ratio to obtain a corresponding lane accurate boundary.
8. A camera-based road information identification system for implementing the method of any one of claims 1-7, the system comprising:
the grid setting module is used for paving the pavement according to the preset materials and the preset coding information to form a target pavement lane line;
the intensity analysis module is used for carrying out partition detection on the target pavement lane line according to the illumination intensity, and selecting detection areas, wherein the classification of the detection areas comprises a high-reflection area and a low-reflection area;
the outer boundary compensation module is used for searching the outermost low reflection area or the high reflection area according to the detection area, performing area compensation and selecting the maximum surrounding area as a target area;
the inner boundary operation module is used for searching a high-reflection area or a low-reflection area in the area according to the target area to obtain a target area boundary;
the central region analysis module is used for extracting a central region according to the boundary of the target region;
the lane fitting module is used for performing lane line fitting according to the central area to generate a lane accurate boundary;
the method for paving the road surface according to the preset materials and the preset coding information to form a target road surface lane line specifically comprises the following steps:
selecting a lane, wherein the inner areas are alternately arranged in a square grid mode according to the low-reflectivity areas and the high-reflectivity areas, and the outermost layer of the lane is surrounded by the high-reflectivity areas and the low-reflectivity areas and is arranged in a mode of external low reflectivity and internal high reflectivity to serve as an initial arrangement scheme;
a low reflectivity material is used for the low reflectivity region;
a high reflectivity material is adopted for the high reflectivity region;
and distributing the low-reflectivity area and the high-reflectivity area on the surface of the pavement according to the initial arrangement scheme to form the target pavement lane line.
9. A computer readable storage medium, on which computer program instructions are stored, which computer program instructions, when executed by a processor, implement the method of any of claims 1-7.
10. An electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310355770.7A CN116385397B (en) | 2023-04-04 | 2023-04-04 | Road information identification method and system based on camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310355770.7A CN116385397B (en) | 2023-04-04 | 2023-04-04 | Road information identification method and system based on camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116385397A CN116385397A (en) | 2023-07-04 |
| CN116385397B true CN116385397B (en) | 2023-10-03 |
Family
ID=86961126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310355770.7A Active CN116385397B (en) | 2023-04-04 | 2023-04-04 | Road information identification method and system based on camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116385397B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102789686A (en) * | 2012-07-10 | 2012-11-21 | 华南理工大学 | Road traffic flow detecting method based on road surface brightness composite mode recognition |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
| KR101868898B1 (en) * | 2017-02-06 | 2018-06-20 | 국방과학연구소 | Method and apparatus of identifying lane for self-driving car |
| DE102017101530A1 (en) * | 2017-01-26 | 2018-07-26 | Valeo Schalter Und Sensoren Gmbh | A lane-boundary detecting apparatus for a motor vehicle having a plurality of scanning areas arranged in a row |
| CN113885045A (en) * | 2020-07-03 | 2022-01-04 | 华为技术有限公司 | Method and device for detecting lane line |
| CN115755072A (en) * | 2022-11-24 | 2023-03-07 | 北京中科东信科技有限公司 | Special scene positioning method and system based on binocular structured light camera |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3748606A4 (en) * | 2018-01-31 | 2021-10-20 | Pioneer Corporation | Road surface information acquisition method |
| US11900695B2 (en) * | 2021-03-04 | 2024-02-13 | Nec Corporation Of America | Marking and detecting road marks |
-
2023
- 2023-04-04 CN CN202310355770.7A patent/CN116385397B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102789686A (en) * | 2012-07-10 | 2012-11-21 | 华南理工大学 | Road traffic flow detecting method based on road surface brightness composite mode recognition |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
| DE102017101530A1 (en) * | 2017-01-26 | 2018-07-26 | Valeo Schalter Und Sensoren Gmbh | A lane-boundary detecting apparatus for a motor vehicle having a plurality of scanning areas arranged in a row |
| KR101868898B1 (en) * | 2017-02-06 | 2018-06-20 | 국방과학연구소 | Method and apparatus of identifying lane for self-driving car |
| CN113885045A (en) * | 2020-07-03 | 2022-01-04 | 华为技术有限公司 | Method and device for detecting lane line |
| CN115755072A (en) * | 2022-11-24 | 2023-03-07 | 北京中科东信科技有限公司 | Special scene positioning method and system based on binocular structured light camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116385397A (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101880004B1 (en) | Method and apparatus for identifying television channel information | |
| JP6976270B2 (en) | Remote determination of the amount stored in a container in a geographic area | |
| US10580206B2 (en) | Method and apparatus for constructing three-dimensional map | |
| CN108701224B (en) | Visual vehicle parking occupancy sensor | |
| CN108052624B (en) | Point cloud data processing method and device and computer readable storage medium | |
| CN102844771B (en) | The method and apparatus followed the tracks of and identify is carried out with invariable rotary feature descriptor | |
| US10506128B1 (en) | Encoded signal systems and methods to ensure minimal robustness | |
| US20140133741A1 (en) | Device for generating three dimensional feature data, method for generating three-dimensional feature data, and recording medium on which program for generating three-dimensional feature data is recorded | |
| CN110502973B (en) | Automatic extraction and identification method for road marking based on vehicle-mounted laser point cloud | |
| CN108765584A (en) | Laser point cloud data collection augmentation method, apparatus and readable storage medium storing program for executing | |
| US6775396B2 (en) | Image processing device, plane detection method, and recording medium upon which plane detection program is recorded | |
| US20140125667A1 (en) | Roof Generation And Texturing Of 3D Models | |
| CN104835146A (en) | Salient object segmenting method in stereo image based on depth information and image cutting | |
| CN110866900A (en) | Water body color identification method and device | |
| CN108052869B (en) | Lane line recognition method, lane line recognition device and computer-readable storage medium | |
| CN114155497A (en) | Object identification method and device and storage medium | |
| WO2022206517A1 (en) | Target detection method and apparatus | |
| CN113947613B (en) | Target area detection method, device, equipment and storage medium | |
| CN110334751B (en) | Image processing method and device for binding nodes and terminal | |
| CN103942515B (en) | Correlation method and correlation device | |
| CN116385397B (en) | Road information identification method and system based on camera | |
| CN109815763A (en) | Detection method, device and the storage medium of two dimensional code | |
| CN106228553B (en) | High-resolution remote sensing image shadow Detection apparatus and method | |
| Zhang et al. | Lateral distance detection model based on convolutional neural network | |
| CN111881846A (en) | Image processing method and related device, equipment 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 |