CN113221701A - Lane line and track line identification method and system based on direction prediction - Google Patents
Lane line and track line identification method and system based on direction prediction Download PDFInfo
- Publication number
- CN113221701A CN113221701A CN202110481095.3A CN202110481095A CN113221701A CN 113221701 A CN113221701 A CN 113221701A CN 202110481095 A CN202110481095 A CN 202110481095A CN 113221701 A CN113221701 A CN 113221701A
- Authority
- CN
- China
- Prior art keywords
- line
- slope
- track
- line segment
- lane
- 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.)
- Granted
Links
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
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- 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
Abstract
The invention discloses a lane line and track line identification method and system based on direction prediction, and relates to the field of intelligent network connection design of transportation, wherein the method comprises the steps of obtaining a lane line or a track line of which the head of a vehicle extends forwards for a preset distance as an edge line segment; acquiring image characteristics of the edge line segment as reference image characteristics, and determining a starting point and an end point of the edge line segment according to the vehicle driving direction; calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and taking the calculated slope as a reference slope; and identifying the lane line or the track line in the preset radius range in front of the edge line segment end point based on the reference image characteristic and the reference slope. The method has high identification precision, and the identification of the lane line or the track line is stable, thereby effectively reducing the identification cost of the lane line or the track line.
Description
Technical Field
The invention relates to the field of intelligent network connection design of traffic transportation, in particular to a lane line and track line identification method and system based on direction prediction.
Background
Currently, for automatic identification of a lane line or a track line, the automatic identification is generally performed based on a machine learning identification algorithm, and the position of the lane line or the track line is identified from a background of an original image through a machine learning identification algorithm such as a convolutional neural network.
However, the following problems occur when the machine learning recognition algorithm is used to automatically recognize the lane line or the track line: 1. because background images of road images are complex (including grassland, stone road, forest, snow and the like), backgrounds are variable and have large interference, and a machine learning identification algorithm is difficult to obtain enough scene data for training, the identification rate is low; 2. parameters of a machine learning model cannot be explained, and the machine learning model cannot be checked when a fault occurs, so that the stability is poor; 3. the calculation amount is huge, the method is complex, the requirements on software and hardware equipment are high, and the identification cost is high.
Disclosure of Invention
In view of the defects in the prior art, the present invention aims to provide a method and a system for recognizing a lane line or a track line based on direction prediction, which have high recognition accuracy, stable recognition of the lane line or the track line, and effectively reduce the recognition cost of the lane line or the track line.
In order to achieve the above object, the present invention provides a method for identifying a lane line and a track line based on direction prediction, which specifically comprises the following steps:
acquiring a lane line or a track line extending forwards by a preset distance from the head of the vehicle as an edge line segment;
acquiring image characteristics of the edge line segment as reference image characteristics, and determining a starting point and an end point of the edge line segment according to the vehicle driving direction;
calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and taking the calculated slope as a reference slope;
and identifying the lane line or the track line in the preset radius range in front of the edge line segment end point based on the reference image characteristic and the reference slope.
On the basis of the technical scheme, the image features comprise colors and textures.
On the basis of the technical scheme, the specific process of obtaining the image characteristics of the edge line segment is as follows:
and for the obtained edge line segment, intercepting the edge line segment with a preset length, and taking the image feature of the intercepted edge line segment as a reference image feature.
On the basis of the technical scheme, based on the reference image characteristics and the reference slope, the method for recognizing the lane line or the track line in the preset radius range in front of the edge line segment terminal point specifically comprises the following steps:
based on the reference image characteristics, acquiring an area which is the same as the reference image characteristics in the image within a preset radius range in front of the edge line segment end point, and taking the acquired area as an area to be identified;
and calculating the slope of each region to be recognized based on the end points of the regions to be recognized, comparing the calculated slope with the reference slope, wherein the region to be recognized with the slope closest to the reference slope is the lane line or the track line obtained by recognition.
On the basis of the technical scheme, the step of comparing the calculated slope with the reference slope, wherein the region to be identified, the slope of which is closest to the reference slope, is a lane line or a track line obtained by identification, and the specific steps are as follows:
judging whether an area to be identified in front of the edge line segment exists in the acquired area to be identified:
if so, the area to be identified, which is positioned in front of the edge line segment, is the identified lane line or track line;
if not, comparing the calculated slope with the reference slope, wherein the region to be identified, the slope of which is closest to the reference slope, is the identified lane line or track line.
On the basis of the technical scheme, when the area which is the same as the reference image feature in the image in the preset radius range in front of the edge line segment end point is obtained based on the reference image feature, if the area which is the same as the reference image feature is not obtained, the preset radius range in front of the edge line segment end point is enlarged, and the area which is the same as the reference image feature is obtained in the newly determined radius range.
On the basis of the technical scheme, after the lane line or the track line in the preset radius range in front of the end point of the edge line segment is obtained through recognition, the lane line or the track line obtained through recognition is used as a new edge line segment, the image feature of the new edge line segment is obtained and used as a new image feature, the reference slope of the new edge line segment is calculated and used as a new reference slope, then the lane line or the track line in the preset radius range in front of the end point of the new edge line segment is recognized based on the new reference image feature and the new reference slope, and the process is repeated until the lane line or the track line with the preset length is obtained through recognition.
On the basis of the technical scheme, the lane line or the track line in the preset radius range in front of the edge line segment end point is identified, wherein when the number of the lane lines or the track lines is multiple, each lane line or each track line is identified according to the lane line and track line identification method based on direction prediction.
The invention provides a lane line and track line identification system based on direction prediction, which comprises:
the vehicle head control device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring a lane line or a track line extending forwards for a preset distance from the head of a vehicle as an edge line segment;
the determining module is used for acquiring the image characteristics of the edge line segment as the reference image characteristics and determining the starting point and the end point of the edge line segment according to the vehicle running direction;
the calculation module is used for calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and taking the calculated slope as a reference slope;
and the identification module is used for identifying the lane line or the track line in the preset radius range in front of the edge line segment terminal point based on the reference image characteristic and the reference slope.
On the basis of the technical scheme, the image features comprise colors and textures.
Compared with the prior art, the invention has the advantages that: the method comprises the steps of obtaining image characteristics of edge line segments as reference image characteristics, determining a starting point and an end point of the edge line segments according to the vehicle driving direction, calculating the slope of the edge line segments based on the determined starting point and the end point of the edge line segments, using the calculated slope as a reference slope, and recognizing the lane or the track line in a preset radius range in front of the end point of the edge line segments based on the reference image characteristics and the reference slope.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a lane line and track line identification method based on direction prediction according to an embodiment of the present invention;
fig. 2 is a schematic distribution diagram of regions to be identified in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a lane line and track line identification method based on direction prediction, which comprises the steps of obtaining the image characteristics of edge line segments as the reference image characteristics, determining the starting point and the end point of the edge line segment according to the driving direction of the vehicle, calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and the calculated slope is used as a reference slope, the identification of the lane line or the track line in the preset radius range in front of the edge line segment terminal point is carried out based on the reference image characteristic and the reference slope, namely, by selecting a lane line or a track line with a preset distance as an edge line segment, based on the image characteristics and the slope of the edge line segment, the lane line or the track line is identified in sequence in the preset radius range in front of the edge line segment terminal point, the identification precision is high, and the identification of the lane line or the track line is stable, and the identification cost of the lane line or the track line is effectively reduced. The embodiment of the invention correspondingly provides a lane line and track line identification system based on direction prediction.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In automatic driving, a non-rail vehicle that travels along a track line or a rail vehicle that runs on a rail needs to recognize a track line or a track line of a certain length in front of the vehicle, and the recognition information of the track line or the track line in front is prestored in a vehicle information system for modeling, and is used for vehicle control, front obstacle recognition, and the like.
Any artificial lane or track, mathematically speaking, has the following two characteristics: the path has continuity and the direction of the curve of the path changes continuously, since any abrupt change or break would cause an accident. The invention relates to a lane line and track line identification method, which utilizes the continuity of the change of the bending direction to extract the image characteristics (color, reflection degree and the like, mainly color) of the initial direction and the lane (track) line from a small section of known lane line (track line) in front of a vehicle head, conjectures and detects the initial direction of the edge lines on two sides and the surface image characteristics of the edge lines in a step forward manner, determines the specific position of the next section of edge line, and iterates forward until the lane (track) line with enough length is mapped.
Referring to fig. 1, a method for identifying a lane line and a track line based on direction prediction according to an embodiment of the present invention specifically includes the following steps:
s1: and acquiring a lane line or a track line extending forwards by a preset distance from the head of the vehicle as an edge line segment. The lane line or the track line with a preset distance is obtained in the shot image as the edge line segment by shooting the image in front of the head of the vehicle, and the shot image is relatively short in shooting distance and small in interference, so that the lane line or the track line with a distance from the head of the vehicle can be easily identified and obtained.
S2: acquiring image characteristics of the edge line segment as reference image characteristics, and determining a starting point and an end point of the edge line segment according to the vehicle driving direction; image features include color and texture.
In the embodiment of the invention, the image characteristics of the edge line segment are obtained by the following specific processes:
and for the obtained edge line segment, intercepting the edge line segment with a preset length, and taking the image feature of the intercepted edge line segment as a reference image feature.
S3: calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and taking the calculated slope as a reference slope;
s4: and identifying the lane line or the track line in the preset radius range in front of the edge line segment end point based on the reference image characteristic and the reference slope.
In the embodiment of the present invention, based on the reference image feature and the reference slope, the method for identifying a lane line or a track line within a preset radius range in front of the edge line segment end point specifically includes:
s401: based on the reference image characteristics, acquiring an area which is the same as the reference image characteristics in the image within a preset radius range in front of the edge line segment end point, and taking the acquired area as an area to be identified; in an actual application process, image features of a plurality of identified regions may be the same as the reference image features, and the identified regions are all to-be-identified regions.
S402: and calculating the slope of each region to be recognized based on the end points of the regions to be recognized, comparing the calculated slope with the reference slope, wherein the region to be recognized with the slope closest to the reference slope is the lane line or the track line obtained by recognition. Comparing each calculated slope with a reference slope, and for the slope with the minimum difference value with the reference slope, the region to be identified corresponding to the slope is the lane line or the track line obtained by identification.
In the embodiment of the invention, the calculated slope is compared with the reference slope, and the area to be identified, the slope of which is closest to the reference slope, is the lane line or the track line obtained by identification, and the specific steps are as follows:
judging whether an area to be identified in front of the edge line segment exists in the acquired area to be identified:
if so, the area to be identified, which is positioned in front of the edge line segment, is the identified lane line or track line;
if not, comparing the calculated slope with the reference slope, wherein the region to be identified, the slope of which is closest to the reference slope, is the identified lane line or track line.
As shown in fig. 2, since the direction of the next lane or track line to be determined and the direction of the currently determined lane or track line do not change abruptly, the possible direction of the next lane or track line to be determined is a probability distribution, and with the direction of the currently determined lane or track line as a center, the probability that the next lane or track line to be determined is located at the center is the largest, and the probability is smaller toward the direction away from the center on both sides, and the probability is in accordance with a normal distribution. Therefore, when the area to be recognized in front of the edge line segment exists in the acquired area to be recognized, the area to be recognized in front of the edge line segment is the recognized lane line or track line, and the comparison of other areas to be recognized is not performed at this time; and when the area to be recognized does not exist in the acquired area to be recognized, comparing the slope, and comparing the calculated slope with the reference slope, wherein the area to be recognized with the slope closest to the reference slope is the lane line or the track line obtained by recognition.
In the embodiment of the invention, when the area which is the same as the reference image feature in the image in the preset radius range in front of the edge line segment end point is obtained based on the reference image feature, if the area which is the same as the reference image feature is not obtained, the preset radius range in front of the edge line segment end point is increased, and the area which is the same as the reference image feature is obtained in the newly determined radius range. And according to the rule, until an area to be identified is found, if the area to be identified still cannot be found after the preset radius range in front of the edge line segment end point is increased for multiple times, the interruption of the lane line or the track line is reported.
In the embodiment of the invention, after the lane line or the track line in the preset radius range in front of the end point of the edge line segment is obtained through recognition, the lane line or the track line obtained through recognition is used as a new edge line segment, the image feature of the new edge line segment is obtained and used as a new image feature, the reference slope of the new edge line segment is calculated and used as a new reference slope, then the lane line or the track line in the preset radius range in front of the end point of the new edge line segment is recognized based on the new reference image feature and the new reference slope, and the analogy is carried out until the lane line or the track line with the preset length is obtained through recognition.
After the lane line or the track line in the preset radius range in front of the edge line segment terminal point is obtained through recognition, the lane line or the track line obtained through recognition is used as a new edge line segment, the image feature of the new edge line segment is obtained and used as a new image feature, the new reference slope of the new edge line segment is calculated and used as a new reference slope, then the lane line or the track line in the preset radius range in front of the new edge line segment terminal point is recognized based on the new reference image feature and the reference slope, the lane line or the track line obtained through recognition is used as a new edge line segment, the image feature and the slope of the new edge line segment are obtained and used as the new reference slope of the new edge line segment, recognition is carried out again, and the like is carried out until the lane line or the track line with the preset length is obtained through recognition.
In the embodiment of the invention, the lane lines or the track lines in the preset radius range in front of the edge line segment end point are identified, wherein when the number of the lane lines or the track lines is multiple, each lane line or each track line is identified according to the lane line and track line identification method based on direction prediction. For example, there are generally two track lines, and for each track line, the track line and track line identification method based on direction prediction according to the present invention is used for identification; for the lane lines on the road, there are usually a plurality of lane lines, and for each lane line, the lane line track line identification method based on the direction prediction of the invention is used for identification.
The invention relates to a lane line and track line identification method based on direction prediction, which takes a block from a known track (lane) line in an image as a reference for comparing with other blocks in the image to determine whether a front area to be identified also belongs to a part of the track (lane) line; selecting a preset radius range from the tail end of a known track line or lane line segment as a circle center, taking the front of the edge line segment end point as a potential to-be-identified area belonging to the track line or lane line as a comparison target, and greatly reducing the comparison range; based on the principle that the direction of a lane (track) line does not change steeply, the probability distribution of the direction of the next track line or the lane line is set, the direction with the highest probability is searched preferentially, once the next track line or the lane line is found in the direction with the highest probability, the search is quitted, the calculated amount is reduced, and the calculating speed is accelerated.
The method for recognizing the track line of the lane based on the direction prediction of the embodiment of the invention obtains the image characteristics of the edge line segment as the reference image characteristics, determining the starting point and the end point of the edge line segment according to the driving direction of the vehicle, calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and the calculated slope is used as a reference slope, the identification of the lane line or the track line in the preset radius range in front of the edge line segment terminal point is carried out based on the reference image characteristic and the reference slope, namely, by selecting a lane line or a track line with a preset distance as an edge line segment, based on the image characteristics and the slope of the edge line segment, the lane line or the track line is identified in sequence in the preset radius range in front of the edge line segment terminal point, the identification precision is high, and the identification of the lane line or the track line is stable, and the identification cost of the lane line or the track line is effectively reduced.
Embodiments of the present invention also provide a readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the above-described convenient storage method. The method specifically comprises the following steps:
acquiring a lane line or a track line extending forwards by a preset distance from the head of the vehicle as an edge line segment;
acquiring image characteristics of the edge line segment as reference image characteristics, and determining a starting point and an end point of the edge line segment according to the vehicle driving direction;
calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and taking the calculated slope as a reference slope;
and identifying the lane line or the track line in the preset radius range in front of the edge line segment end point based on the reference image characteristic and the reference slope.
In an embodiment of the present invention, the image features include color and texture. Acquiring the image characteristics of the edge line segment, and the specific process is as follows: and for the obtained edge line segment, intercepting the edge line segment with a preset length, and taking the image feature of the intercepted edge line segment as a reference image feature.
In the embodiment of the present invention, based on the reference image feature and the reference slope, the method for identifying a lane line or a track line within a preset radius range in front of the edge line segment end point specifically includes:
based on the reference image characteristics, acquiring an area which is the same as the reference image characteristics in the image within a preset radius range in front of the edge line segment end point, and taking the acquired area as an area to be identified;
and calculating the slope of each region to be recognized based on the end points of the regions to be recognized, comparing the calculated slope with the reference slope, wherein the region to be recognized with the slope closest to the reference slope is the lane line or the track line obtained by recognition.
In the embodiment of the invention, the calculated slope is compared with the reference slope, and the area to be identified, the slope of which is closest to the reference slope, is the lane line or the track line obtained by identification, and the specific steps are as follows:
judging whether an area to be identified in front of the edge line segment exists in the acquired area to be identified:
if so, the area to be identified, which is positioned in front of the edge line segment, is the identified lane line or track line;
if not, comparing the calculated slope with the reference slope, wherein the region to be identified, the slope of which is closest to the reference slope, is the identified lane line or track line.
In the embodiment of the invention, when the area which is the same as the reference image feature in the image in the preset radius range in front of the edge line segment end point is obtained based on the reference image feature, if the area which is the same as the reference image feature is not obtained, the preset radius range in front of the edge line segment end point is increased, and the area which is the same as the reference image feature is obtained in the newly determined radius range.
In the embodiment of the invention, after the lane line or the track line in the preset radius range in front of the end point of the edge line segment is obtained through recognition, the lane line or the track line obtained through recognition is used as a new edge line segment, the image characteristic of the new edge line segment is obtained and used as a new image characteristic, the reference slope of the new edge line segment is calculated and used as a new reference slope, then the lane line or the track line in the preset radius range in front of the end point of the new edge line segment is recognized based on the new reference image characteristic and the type reference slope, and the analogy is carried out until the lane line or the track line with the preset length is obtained through recognition.
In embodiments of the present invention, a storage medium may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-readable storage medium may be, for example but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The lane line and track line identification system based on direction prediction comprises an acquisition module, a determination module, a calculation module and an identification module.
In an embodiment of the present invention, the image features include color and texture. Acquiring the image characteristics of the edge line segment, and the specific process is as follows: and for the obtained edge line segment, intercepting the edge line segment with a preset length, and taking the image feature of the intercepted edge line segment as a reference image feature.
In the embodiment of the present invention, based on the reference image feature and the reference slope, the method for identifying a lane line or a track line within a preset radius range in front of the edge line segment end point specifically includes:
based on the reference image characteristics, acquiring an area which is the same as the reference image characteristics in the image within a preset radius range in front of the edge line segment end point, and taking the acquired area as an area to be identified;
and calculating the slope of each region to be recognized based on the end points of the regions to be recognized, comparing the calculated slope with the reference slope, wherein the region to be recognized with the slope closest to the reference slope is the lane line or the track line obtained by recognition.
In the embodiment of the invention, the calculated slope is compared with the reference slope, and the area to be identified, the slope of which is closest to the reference slope, is the lane line or the track line obtained by identification, and the specific steps are as follows:
judging whether an area to be identified in front of the edge line segment exists in the acquired area to be identified:
if so, the area to be identified, which is positioned in front of the edge line segment, is the identified lane line or track line;
if not, comparing the calculated slope with the reference slope, wherein the region to be identified, the slope of which is closest to the reference slope, is the identified lane line or track line.
In the embodiment of the invention, when the area which is the same as the reference image feature in the image in the preset radius range in front of the edge line segment end point is obtained based on the reference image feature, if the area which is the same as the reference image feature is not obtained, the preset radius range in front of the edge line segment end point is increased, and the area which is the same as the reference image feature is obtained in the newly determined radius range.
In the embodiment of the invention, after the lane line or the track line in the preset radius range in front of the end point of the edge line segment is obtained through recognition, the lane line or the track line obtained through recognition is used as a new edge line segment, the image characteristic of the new edge line segment is obtained and used as a new image characteristic, the reference slope of the new edge line segment is calculated and used as a new reference slope, then the lane line or the track line in the preset radius range in front of the end point of the new edge line segment is recognized based on the new reference image characteristic and the type reference slope, and the analogy is carried out until the lane line or the track line with the preset length is obtained through recognition.
The lane line and track line identification system based on direction prediction of the embodiment of the invention obtains the image characteristics of the edge line segment as the reference image characteristics, determining the starting point and the end point of the edge line segment according to the driving direction of the vehicle, calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and the calculated slope is used as a reference slope, the identification of the lane line or the track line in the preset radius range in front of the edge line segment terminal point is carried out based on the reference image characteristic and the reference slope, namely, by selecting a lane line or a track line with a preset distance as an edge line segment, based on the image characteristics and the slope of the edge line segment, the lane line or the track line is identified in sequence in the preset radius range in front of the edge line segment terminal point, the identification precision is high, and the identification of the lane line or the track line is stable, and the identification cost of the lane line or the track line is effectively reduced.
The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
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 flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
Claims (10)
1. A lane line track line identification method based on direction prediction is characterized by comprising the following steps:
acquiring a lane line or a track line extending forwards by a preset distance from the head of the vehicle as an edge line segment;
acquiring image characteristics of the edge line segment as reference image characteristics, and determining a starting point and an end point of the edge line segment according to the vehicle driving direction;
calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and taking the calculated slope as a reference slope;
and identifying the lane line or the track line in the preset radius range in front of the edge line segment end point based on the reference image characteristic and the reference slope.
2. The lane line track line identification method based on direction prediction according to claim 1, characterized in that: the image features include color and texture.
3. The method for identifying a lane line and a track line based on direction prediction according to claim 1, wherein the obtaining of the image features of the edge line segments comprises the following specific processes:
and for the obtained edge line segment, intercepting the edge line segment with a preset length, and taking the image feature of the intercepted edge line segment as a reference image feature.
4. The method for recognizing the lane line or the track line based on the direction prediction as claimed in claim 1, wherein the recognizing of the lane line or the track line within a preset radius range in front of the end point of the edge line segment is performed based on the reference image feature and the reference slope, and specifically comprises:
based on the reference image characteristics, acquiring an area which is the same as the reference image characteristics in the image within a preset radius range in front of the edge line segment end point, and taking the acquired area as an area to be identified;
and calculating the slope of each region to be recognized based on the end points of the regions to be recognized, comparing the calculated slope with the reference slope, wherein the region to be recognized with the slope closest to the reference slope is the lane line or the track line obtained by recognition.
5. The method for recognizing the lane line and the track line based on the direction prediction as claimed in claim 4, wherein the step of comparing the calculated slope with a reference slope, wherein the region to be recognized, in which the slope is closest to the reference slope, is a recognized lane line or a track line, and comprises the following specific steps:
judging whether an area to be identified in front of the edge line segment exists in the acquired area to be identified:
if so, the area to be identified, which is positioned in front of the edge line segment, is the identified lane line or track line;
if not, comparing the calculated slope with the reference slope, wherein the region to be identified, the slope of which is closest to the reference slope, is the identified lane line or track line.
6. The lane line track line identification method based on direction prediction according to claim 4, wherein: when the area which is the same as the reference image feature in the image in the preset radius range in front of the edge line segment end point is obtained based on the reference image feature, if the area which is the same as the reference image feature is not obtained, the preset radius range in front of the edge line segment end point is increased, and the area which is the same as the reference image feature is obtained in the newly determined radius range.
7. The lane line track line identification method based on direction prediction according to claim 1, characterized in that: and when the lane line or the track line in the preset radius range in front of the edge line segment end point is obtained through recognition, taking the lane line or the track line obtained through recognition as a new edge line segment, obtaining the image characteristics of the new edge line segment as new image characteristics, calculating the reference slope of the new edge line segment as a new reference slope, then recognizing the lane line or the track line in the preset radius range in front of the new edge line segment end point based on the new reference image characteristics and the new reference slope, and repeating the steps until the lane line or the track line with the preset length is obtained through recognition.
8. The lane line track line identification method based on direction prediction according to claim 1, characterized in that: and recognizing the lane lines or the track lines in the preset radius range in front of the edge line segment end point, wherein when the number of the lane lines or the track lines is multiple, each lane line or each track line is recognized according to the lane line and track line recognition method based on direction prediction.
9. A lane line track line identification system based on direction prediction, comprising:
the vehicle head control device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring a lane line or a track line extending forwards for a preset distance from the head of a vehicle as an edge line segment;
the determining module is used for acquiring the image characteristics of the edge line segment as the reference image characteristics and determining the starting point and the end point of the edge line segment according to the vehicle running direction;
the calculation module is used for calculating the slope of the edge line segment based on the determined starting point and the determined end point of the edge line segment, and taking the calculated slope as a reference slope;
and the identification module is used for identifying the lane line or the track line in the preset radius range in front of the edge line segment terminal point based on the reference image characteristic and the reference slope.
10. A direction prediction based lane line track line identification system as claimed in claim 9 wherein: the image features include color and texture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110481095.3A CN113221701B (en) | 2021-04-30 | 2021-04-30 | Lane line and track line identification method and device based on direction prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110481095.3A CN113221701B (en) | 2021-04-30 | 2021-04-30 | Lane line and track line identification method and device based on direction prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113221701A true CN113221701A (en) | 2021-08-06 |
| CN113221701B CN113221701B (en) | 2022-06-10 |
Family
ID=77090483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110481095.3A Active CN113221701B (en) | 2021-04-30 | 2021-04-30 | Lane line and track line identification method and device based on direction prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113221701B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150279017A1 (en) * | 2014-03-28 | 2015-10-01 | Fuji Jukogyo Kabushiki Kaisha | Stereo image processing device for vehicle |
| CN108171225A (en) * | 2018-03-14 | 2018-06-15 | 海信集团有限公司 | Lane detection method, device, terminal and storage medium |
| CN109241929A (en) * | 2018-09-20 | 2019-01-18 | 北京海纳川汽车部件股份有限公司 | Method for detecting lane lines, device and the automatic driving vehicle of automatic driving vehicle |
| EP3525132A1 (en) * | 2018-02-13 | 2019-08-14 | KPIT Technologies Ltd. | System and method for lane detection |
| CN112507852A (en) * | 2020-12-02 | 2021-03-16 | 上海眼控科技股份有限公司 | Lane line identification method, device, equipment and storage medium |
-
2021
- 2021-04-30 CN CN202110481095.3A patent/CN113221701B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150279017A1 (en) * | 2014-03-28 | 2015-10-01 | Fuji Jukogyo Kabushiki Kaisha | Stereo image processing device for vehicle |
| EP3525132A1 (en) * | 2018-02-13 | 2019-08-14 | KPIT Technologies Ltd. | System and method for lane detection |
| CN108171225A (en) * | 2018-03-14 | 2018-06-15 | 海信集团有限公司 | Lane detection method, device, terminal and storage medium |
| CN109241929A (en) * | 2018-09-20 | 2019-01-18 | 北京海纳川汽车部件股份有限公司 | Method for detecting lane lines, device and the automatic driving vehicle of automatic driving vehicle |
| CN112507852A (en) * | 2020-12-02 | 2021-03-16 | 上海眼控科技股份有限公司 | Lane line identification method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| DING YONG 等: "Fast lane detection based on bird"s eye view and improved random sample consensus algorithm", 《SPRINGLINK》, 31 December 2017 (2017-12-31), pages 22979 - 22998 * |
| 袁望方 等: "基于机器视觉的车道偏离预警技术研究", 《中国安全生产科学技术》, 31 December 2019 (2019-12-31), pages 73 - 78 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113221701B (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2012160165A (en) | Baseline band video monitoring system and method | |
| CN113835102B (en) | Lane line generation method and device | |
| CN112528807B (en) | Method and device for predicting running track, electronic equipment and storage medium | |
| CN115273039B (en) | Small obstacle detection method based on camera | |
| CN114648654A (en) | Clustering method for fusing point cloud semantic categories and distances | |
| CN116071729A (en) | Method and device for detecting drivable area and road edge and related equipment | |
| CN114092909A (en) | Lane line extraction method and device, vehicle and storage medium | |
| CN113221701B (en) | Lane line and track line identification method and device based on direction prediction | |
| CN110543818B (en) | Traffic light tracking method, device, medium and equipment based on weight graph matching | |
| CN111192216A (en) | Lane line smoothing method and system | |
| CN114179805B (en) | Driving direction determining method, device, equipment and storage medium | |
| CN115782919A (en) | Information sensing method and device and electronic equipment | |
| CN115761702A (en) | Vehicle track generation method and device, electronic equipment and computer readable medium | |
| CN110363834B (en) | Point cloud data segmentation method and device | |
| CN115439484B (en) | Detection method and device based on 4D point cloud, storage medium and processor | |
| CN115965927B (en) | Pavement information extraction method and device, electronic equipment and readable storage medium | |
| CN116434166A (en) | Target area identification method, device, equipment and storage medium | |
| CN117740014A (en) | Navigation finger line generating method, device and computer readable storage medium | |
| CN116992348A (en) | Track classification method, model training method, device, equipment and medium | |
| CN114863148A (en) | Target identification method based on millimeter wave radar and terminal equipment | |
| CN117635987A (en) | Track matching method, track matching device, computer readable storage medium and terminal equipment | |
| CN115376088A (en) | Lane line generation method and device, readable storage medium and electronic equipment | |
| CN115586772A (en) | Hierarchical control system and method for automatic driving vehicle | |
| CN116311961A (en) | Traffic jam detection method and device, electronic equipment and storage medium | |
| CN117113281A (en) | Multi-mode data processing method, device, agent and 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 |