CN114037875A - Ground marking classification extraction method and device based on contour features - Google Patents
Ground marking classification extraction method and device based on contour features Download PDFInfo
- Publication number
- CN114037875A CN114037875A CN202111354504.XA CN202111354504A CN114037875A CN 114037875 A CN114037875 A CN 114037875A CN 202111354504 A CN202111354504 A CN 202111354504A CN 114037875 A CN114037875 A CN 114037875A
- Authority
- CN
- China
- Prior art keywords
- ground marking
- ground
- marking
- training
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 20
- 238000012706 support-vector machine Methods 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims description 48
- 238000000034 method Methods 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 17
- 239000000284 extract Substances 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 11
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- PUZPDOWCWNUUKD-UHFFFAOYSA-M sodium fluoride Chemical compound [F-].[Na+] PUZPDOWCWNUUKD-UHFFFAOYSA-M 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a ground marking classification extraction method and a device based on contour features, which comprises the following steps: extracting the characteristics of the ground marking; inputting the characteristics of the ground marking into a trained support vector machine to obtain the type of the ground marking; and adding the type of the ground marking into the ground marking data for outputting. The support vector machine is trained by extracting the features of the ground marking, and the trained support vector machine is utilized to accurately classify the ground marking and extract the physical information of the ground marking, so that the accuracy of a high-precision map is improved, and the safety and the comfort of automatic driving are further improved.
Description
Technical Field
The invention relates to the technical field of high-precision map making, in particular to a ground marking classification extraction method and device based on contour features.
Background
In the field of automatic driving, in order to accurately control the driving of a vehicle, drawing of a high-precision map is often involved. The ground marking data of high-precision map drawing, the graph of each ground marking represents different physical meanings, and the ground marking data directly participate in the driving decision of the automatic driving vehicle. When the sensor of the automatic driving vehicle fails under the influence of severe weather such as heavy fog, hail, heavy rain and the like, the vehicle can decide the driving behavior through the ground marking data in the known high-precision map. Because the ground marking is gathered because of factors such as equipment in the collection process and the like causes the figure of the ground marking to have great change, if the physical information of the ground marking can not be accurately extracted, the automatic driving vehicle can enter a wrong lane when driving, and the driving safety and the comfort are greatly reduced. Therefore, it is necessary to accurately classify the ground reticle and extract the physical information thereof, thereby improving safety and comfort.
Disclosure of Invention
The invention provides a ground marking classification extraction method and device based on contour features, aiming at the technical problems in the prior art. The support vector machine is trained by extracting the features of the ground marking, and the trained support vector machine is utilized to accurately classify the ground marking and extract the physical information of the ground marking, so that the accuracy of a high-precision map is improved, and the safety and the comfort of automatic driving are further improved.
The technical scheme for solving the technical problems is as follows:
in a first aspect, the present invention provides a method for classifying and extracting a ground reticle based on contour features, comprising:
extracting the characteristics of the ground marking; inputting the characteristics of the ground marking into a trained support vector machine to obtain the type of the ground marking; adding the type of the ground marking into ground marking data and outputting the ground marking data;
the method for extracting the characteristics of the ground reticle comprises the following steps:
obtaining two points A and A with the farthest distance in the ground marking line pointsB, recording the length of AB as dAB；
Making a straight line l1 vertical AB passing through the point B, making a vertical line l1 passing through all shape points of the ground marking line, and obtaining two points G and H with the farthest distances in the drop foot, wherein the shape points corresponding to the points G and H are respectively C and D; c and D are crossed to form a perpendicular line of the line segment AB, and the vertical feet are respectively points E and F; making a connection line of the points C and D, and marking the intersection point of the line segment CD and the line segment AB as O;
if the length d of AOAOLength d less than BOBOThen, the point A and the point B are exchanged and calculated
According to the right-hand rule, if the cross multiplication result is negative, exchanging the point C and the point D;
calculating the characteristic value of the ground mark
Further, the training method of the support vector machine comprises the following steps:
acquiring a ground marking data set, and marking the type of each ground marking in the data set;
extracting the characteristics of each ground marking in the data set to obtain the characteristic value f of each ground marking in the data seti；
Dividing a data set into a training set and a testing set, training a support vector machine by using the characteristic values of the ground marking in the training set, testing by using the characteristic values of the ground marking in the testing set after each training for a specified number of times, calculating the accuracy R and storing the accuracy R in a queue R; and if the number of the values in the queue R is smaller than a preset threshold value, continuing the training, otherwise, comparing whether the head data R0 of the queue R is larger than the rest data of the queue R, stopping the model training if the head data R0 of the queue R is larger than the rest data of the queue R, and otherwise, deleting the head data R0 and continuing the model training.
In a second aspect, the present invention provides a contour feature-based ground reticle classification and extraction apparatus, comprising:
the characteristic extraction module is used for extracting the characteristics of the ground marking;
the classification module is used for inputting the characteristics of the ground marking into a trained support vector machine to obtain the type of the ground marking;
an output module: the device is used for adding the type of the ground marking into the ground marking data and outputting the data;
the feature extraction module is specifically configured to:
obtaining two points A and B with the farthest distance in the ground marking line points, and recording the length of AB as dAB；
Making a straight line l1 vertical AB passing through the point B, making a vertical line l1 passing through all shape points of the ground marking line, and obtaining two points G and H with the farthest distances in the drop foot, wherein the shape points corresponding to the points G and H are respectively C and D; c and D are crossed to form a perpendicular line of the line segment AB, and the vertical feet are respectively points E and F; making a connection line of the points C and D, and marking the intersection point of the line segment CD and the line segment AB as O;
if the length d of AOAOLength d less than BOBOThen, the point A and the point B are exchanged and calculated
According to the right-hand rule, if the cross multiplication result is negative, exchanging the point C and the point D;
calculating the characteristic value of the ground mark
Further, the device also comprises a training module used for training the support vector machine;
the training method of the support vector machine comprises the following steps:
acquiring a ground marking data set, and marking the type of each ground marking in the data set;
extracting the characteristics of each ground marking in the data set to obtain the characteristic value f of each ground marking in the data seti；
Dividing a data set into a training set and a testing set, training a support vector machine by using the characteristic values of the ground marking in the training set, testing by using the characteristic values of the ground marking in the testing set after each training for a specified number of times, calculating the accuracy R and storing the accuracy R in a queue R; and if the number of the values in the queue R is smaller than a preset threshold value, continuing the training, otherwise, comparing whether the head data R0 of the queue R is larger than the rest data of the queue R, stopping the model training if the head data R0 of the queue R is larger than the rest data of the queue R, and otherwise, deleting the head data R0 and continuing the model training.
In a third aspect, the present invention provides an electronic device comprising:
a memory for storing a computer software program;
and the processor is used for reading and executing the computer software program so as to realize the contour feature-based ground marking classification and extraction method in the first aspect of the invention.
In a fourth aspect, the present invention provides a non-transitory computer readable storage medium, wherein a computer software program for implementing the contour feature-based ground mark classification and extraction method according to the first aspect of the present invention is stored in the storage medium.
The invention has the beneficial effects that: the collected ground mark lines may have larger deviation in shape, so that the extraction of physical information of the collected ground mark lines is influenced, if the physical information of the collected ground mark lines cannot be accurately extracted, the driving decision of the automatic driving vehicle is wrong, and the safety and the comfort in the driving of the vehicle are reduced. The method mainly extracts the physical information of the ground marking accurately, and provides help for vehicle driving decision better.
Drawings
Fig. 1 is a schematic flow chart of a method for classifying and extracting a ground reticle based on contour features according to an embodiment of the present invention;
FIGS. 2-5 are schematic diagrams of the extraction method for four types of ground reticle during the extraction of the features of the ground reticle;
fig. 6 is a schematic structural diagram of a device for classifying and extracting a ground reticle based on contour features according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to the present invention;
fig. 8 is a schematic structural diagram of a computer-readable storage medium according to the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a schematic flow chart of a method for classifying and extracting a ground reticle based on contour features according to an embodiment of the present invention. As shown in fig. 1, the method includes:
and S1, extracting the characteristics of the ground marking.
Obtaining two points A and B with the farthest distance in the ground marking line points, and recording the length of AB as dAB。
Making a straight line l1 vertical AB passing through the point B, making a vertical line l1 passing through all shape points of the ground marking line, and obtaining two points G and H with the farthest distances in the drop foot, wherein the shape points corresponding to the points G and H are respectively C and D; c and D are crossed to form a perpendicular line of the line segment AB, and the vertical feet are respectively points E and F; and (5) making a connection line of the points C and D, and marking the intersection point of the line segment CD and the line segment AB as O. Fig. 2-5, wherein fig. 2 is a schematic view of a straight-going ground reticle, fig. 3 is a schematic view of a right-turn ground reticle, fig. 4 is a schematic view of a left-turn ground reticle, and fig. 5 is a schematic view of a straight-going right-turn ground reticle.
If the length d of AOAOLength d less than BOBOThen, the point A and the point B are exchanged and calculated
According to the right-hand rule, if the cross multiplication result is negative, exchanging the point C and the point D;
calculating the characteristic value of the ground mark
S2, inputting the characteristics of the ground marking into a trained support vector machine to obtain the type of the ground marking;
and S3, adding the type of the ground marking into the ground marking data and outputting the ground marking data.
The training method of the support vector machine comprises the following steps:
s201, acquiring a ground marking data set, selecting 400 pieces of ground marking data from all ground marking data to form a data set omega, and marking the type of each ground marking in the data set omega;
s202, extracting the features of each ground marking in the data set omega to obtain the feature value f of each ground marking in the data seti(ii) a The feature extraction method employed here is the same as that employed in step S1.
S203, dividing the data set into a training set and a testing set, wherein the quantity ratio of data contained in the training set to the testing set is 7: 3. and training the support vector machine by using the characteristic values of the ground marked lines in the training set, testing by using the characteristic values of the ground marked lines in the testing set after each training specified time, calculating the accuracy R and storing the accuracy R into a queue R. In this example, the test was performed every 50 times of training. The queue R follows a first-in first-out principle. The preset length of the queue R is 3, that is, only 3 data can be stored at most. And if the number of the values in the queue R is less than 3, namely the queue is not full, continuing the training, otherwise, comparing whether the head data R0 of the queue R is greater than the rest data of the queue R, if so, stopping the model training, otherwise, deleting the head data R0 and continuing the model training.
Fig. 6 is a schematic structural diagram of a device for classifying and extracting a ground reticle based on contour features according to an embodiment of the present invention. As shown in fig. 6, the apparatus includes:
the characteristic extraction module is used for extracting the characteristics of the ground marking;
the classification module is used for inputting the characteristics of the ground marking into a trained support vector machine to obtain the type of the ground marking;
the output module is used for adding the type of the ground marking into the ground marking data and outputting the ground marking data;
and the training module is used for training the support vector machine.
The feature extraction module is specifically configured to:
obtaining the farthest distance in the ground marking pointTwo points A and B of (A) and (B) are marked that the length of AB is dAB；
Making a straight line l1 vertical AB passing through the point B, making a vertical line l1 passing through all shape points of the ground marking line, and obtaining two points G and H with the farthest distances in the drop foot, wherein the shape points corresponding to the points G and H are respectively C and D; c and D are crossed to form a perpendicular line of the line segment AB, and the vertical feet are respectively points E and F; making a connection line of the points C and D, and marking the intersection point of the line segment CD and the line segment AB as O;
if the length d of AOAOLength d less than BOBOThen, the point A and the point B are exchanged and calculated
According to the right-hand rule, if the cross multiplication result is negative, exchanging the point C and the point D;
calculating the characteristic value of the ground mark
Referring to fig. 7, fig. 7 is a schematic view of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 7, an embodiment of the present invention provides an electronic device, which includes a memory 510, a processor 520, and a computer program 511 stored in the memory 520 and executable on the processor 520, wherein the processor 520 executes the computer program 511 to implement the following steps:
extracting the characteristics of the ground marking; inputting the characteristics of the ground marking into a trained support vector machine to obtain the type of the ground marking; and adding the type of the ground marking into the ground marking data for outputting.
Referring to fig. 8, fig. 8 is a schematic diagram illustrating an embodiment of a computer-readable storage medium according to the present invention. As shown in fig. 8, the present embodiment provides a computer-readable storage medium 600 having a computer program 611 stored thereon, the computer program 611, when executed by a processor, implementing the steps of:
extracting the characteristics of the ground marking; inputting the characteristics of the ground marking into a trained support vector machine to obtain the type of the ground marking; and adding the type of the ground marking into the ground marking data for outputting.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, 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, disk storage, CD-ROM, 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 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 computer, 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.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (6)
1. A ground marking classifying and extracting method based on contour features is characterized by comprising the following steps:
extracting the characteristics of the ground marking; inputting the characteristics of the ground marking into a trained support vector machine to obtain the type of the ground marking; adding the type of the ground marking into ground marking data and outputting the ground marking data;
the method for extracting the characteristics of the ground reticle comprises the following steps:
obtaining two points A and B with the farthest distance in the ground marking line points, and recording the length of AB as dAB；
Making a straight line l1 vertical AB passing through the point B, making a vertical line l1 passing through all shape points of the ground marking line, and obtaining two points G and H with the farthest distances in the drop foot, wherein the shape points corresponding to the points G and H are respectively C and D; c and D are crossed to form a perpendicular line of the line segment AB, and the vertical feet are respectively points E and F; making a connection line of the points C and D, and marking the intersection point of the line segment CD and the line segment AB as O;
if the length d of AOAOLength d less than BOBOThen, the point A and the point B are exchanged and calculated
According to the right-hand rule, if the cross multiplication result is negative, exchanging the point C and the point D;
calculating the characteristic value of the ground mark
2. The method of claim 1, wherein the training method of the support vector machine comprises:
acquiring a ground marking data set, and marking the type of each ground marking in the data set;
extracting the characteristics of each ground marking in the data set to obtain the characteristic value f of each ground marking in the data seti；
Dividing a data set into a training set and a testing set, training a support vector machine by using the characteristic values of the ground marking in the training set, testing by using the characteristic values of the ground marking in the testing set after each training for a specified number of times, calculating the accuracy R and storing the accuracy R in a queue R; and if the number of the values in the queue R is smaller than a preset threshold value, continuing the training, otherwise, comparing whether the head data R0 of the queue R is larger than the rest data of the queue R, stopping the model training if the head data R0 of the queue R is larger than the rest data of the queue R, and otherwise, deleting the head data R0 and continuing the model training.
3. The utility model provides a ground marking classification extraction element based on profile feature which characterized in that includes:
the characteristic extraction module is used for extracting the characteristics of the ground marking;
the classification module is used for inputting the characteristics of the ground marking into a trained support vector machine to obtain the type of the ground marking;
an output module: the device is used for adding the type of the ground marking into the ground marking data and outputting the data;
the feature extraction module is specifically configured to:
obtaining two points A and B with the farthest distance in the ground marking line points, and recording the length of AB as dAB；
Making a straight line l1 vertical AB passing through the point B, making a vertical line l1 passing through all shape points of the ground marking line, and obtaining two points G and H with the farthest distances in the drop foot, wherein the shape points corresponding to the points G and H are respectively C and D; c and D are crossed to form a perpendicular line of the line segment AB, and the vertical feet are respectively points E and F; making a connection line of the points C and D, and marking the intersection point of the line segment CD and the line segment AB as O;
if the length d of AOAOLength d less than BOBOThen, the point A and the point B are exchanged and calculated
According to the right-hand rule, if the cross multiplication result is negative, exchanging the point C and the point D;
calculating the characteristic value of the ground mark
4. The apparatus of claim 2, further comprising a training module for training a support vector machine;
the training method of the support vector machine comprises the following steps:
acquiring a ground marking data set, and marking the type of each ground marking in the data set;
extracting the characteristics of each ground marking in the data set to obtain the characteristic value f of each ground marking in the data seti；
Dividing a data set into a training set and a testing set, training a support vector machine by using the characteristic values of the ground marking in the training set, testing by using the characteristic values of the ground marking in the testing set after each training for a specified number of times, calculating the accuracy R and storing the accuracy R in a queue R; and if the number of the values in the queue R is smaller than a preset threshold value, continuing the training, otherwise, comparing whether the head data R0 of the queue R is larger than the rest data of the queue R, stopping the model training if the head data R0 of the queue R is larger than the rest data of the queue R, and otherwise, deleting the head data R0 and continuing the model training.
5. An electronic device, comprising:
a memory for storing a computer software program;
a processor for reading and executing the computer software program to realize a contour feature-based ground reticle classification and extraction method according to any one of claims 1-2.
6. A non-transitory computer readable storage medium, wherein the storage medium stores a computer software program for implementing the contour feature based ground reticle classification extracting method according to any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111354504.XA CN114037875A (en) | 2021-11-16 | 2021-11-16 | Ground marking classification extraction method and device based on contour features |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111354504.XA CN114037875A (en) | 2021-11-16 | 2021-11-16 | Ground marking classification extraction method and device based on contour features |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114037875A true CN114037875A (en) | 2022-02-11 |
Family
ID=80144491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111354504.XA Pending CN114037875A (en) | 2021-11-16 | 2021-11-16 | Ground marking classification extraction method and device based on contour features |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114037875A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102697508A (en) * | 2012-04-23 | 2012-10-03 | 中国人民解放军国防科学技术大学 | Method for performing gait recognition by adopting three-dimensional reconstruction of monocular vision |
| CN103697883A (en) * | 2014-01-07 | 2014-04-02 | 中国人民解放军国防科学技术大学 | Aircraft horizontal attitude determination method based on skyline imaging |
| US20200380272A1 (en) * | 2018-05-07 | 2020-12-03 | Tencent Technology (Shenzhen) Company Limited | Ground mark extraction method, model training method, device and storage medium |
| CN112287894A (en) * | 2020-11-25 | 2021-01-29 | 深圳力维智联技术有限公司 | Water area feature extraction method and system based on deep learning |
-
2021
- 2021-11-16 CN CN202111354504.XA patent/CN114037875A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102697508A (en) * | 2012-04-23 | 2012-10-03 | 中国人民解放军国防科学技术大学 | Method for performing gait recognition by adopting three-dimensional reconstruction of monocular vision |
| CN103697883A (en) * | 2014-01-07 | 2014-04-02 | 中国人民解放军国防科学技术大学 | Aircraft horizontal attitude determination method based on skyline imaging |
| US20200380272A1 (en) * | 2018-05-07 | 2020-12-03 | Tencent Technology (Shenzhen) Company Limited | Ground mark extraction method, model training method, device and storage medium |
| CN112287894A (en) * | 2020-11-25 | 2021-01-29 | 深圳力维智联技术有限公司 | Water area feature extraction method and system based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 王军;李璐;代佳敏: "高速公路快速养护标线***探索与实施", 中国公路学会养护与管理分会第十届学术年会, 31 December 2020 (2020-12-31) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3792901B1 (en) | Ground mark extraction method, model training method, device and storage medium | |
| CN109165549B (en) | Road identification obtaining method based on three-dimensional point cloud data, terminal equipment and device | |
| CN109858476B (en) | Tag expansion method and electronic equipment | |
| CN111310835B (en) | Target object detection method and device | |
| CN110532250B (en) | Method and device for processing traffic data | |
| CN112513927A (en) | Wind turbine blade defect inspection based on convolutional neural networks | |
| CN110889399A (en) | High-resolution remote sensing image weak and small target detection method based on deep learning | |
| CN107909068A (en) | A kind of big data image curve reverse resolution method and system | |
| CN116052094A (en) | Ship detection method, system and computer storage medium | |
| CN116342525A (en) | SOP chip pin defect detection method and system based on Lenet-5 model | |
| CN112418193B (en) | Lane line identification method and system | |
| CN111460861B (en) | Road traffic sign recognition method, device and recognition equipment | |
| CN117083621A (en) | Detector training method, device and storage medium | |
| CN112434582A (en) | Lane line color identification method and system, electronic device and storage medium | |
| CN112434585A (en) | Method, system, electronic device and storage medium for identifying virtual reality of lane line | |
| CN114037875A (en) | Ground marking classification extraction method and device based on contour features | |
| CN111414903A (en) | Method, device and equipment for identifying content of indicator | |
| CN114037854B (en) | Method and device for clustering and fusing ground elements in crowdsourcing high-precision map | |
| CN108090401A (en) | Line detecting method and line detection device | |
| CN112949358A (en) | Road description file generation method and equipment | |
| CN111159998B (en) | Method and system for analyzing hierarchical structure of font outline | |
| CN110705479A (en) | Model training method, target recognition method, device, equipment and medium | |
| CN112163471A (en) | Congestion detection method and device | |
| CN114022501B (en) | Automatic detection method and system for arrow corner points, electronic equipment and storage medium | |
| CN104282016B (en) | Embedded image data processing method |
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 |