CN112257723B - Confidence evaluation method and system for guardrail extraction - Google Patents
Confidence evaluation method and system for guardrail extraction Download PDFInfo
- Publication number
- CN112257723B CN112257723B CN202011158443.5A CN202011158443A CN112257723B CN 112257723 B CN112257723 B CN 112257723B CN 202011158443 A CN202011158443 A CN 202011158443A CN 112257723 B CN112257723 B CN 112257723B
- Authority
- CN
- China
- Prior art keywords
- guardrail
- data
- sampling
- confidence
- extraction
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 title claims description 29
- 238000005070 sampling Methods 0.000 claims abstract description 83
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 15
- 230000035772 mutation Effects 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 18
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 238000013507 mapping Methods 0.000 abstract description 6
- 238000005259 measurement Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000002360 preparation method Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a method and a system for evaluating confidence coefficient of guardrail extraction, which comprises the steps of firstly discretizing a guardrail outline in extracted guardrail data, and then sampling the discretized guardrail outline; and finally, processing the sampling points, and evaluating the confidence coefficient of the guardrail contour sampling points. And evaluating whether the automatically extracted guardrail data meets the high-precision mapping standard by using the confidence coefficient. Compared with the quality inspection method adopting manual measurement in the prior art, which consumes manpower and has low quality inspection efficiency, the method provided by the invention reduces the time for quality inspection after extraction of the guardrail in the high-precision map, and improves the manufacturing efficiency of the high-precision map.
Description
Technical Field
The invention relates to the field of automatic driving high-precision map making, in particular to a method and a system for evaluating confidence coefficient of guardrail extraction.
Background
The guardrail is one of the elements for manufacturing the high-precision map, and at present, the quality of the guardrail extracted automatically needs to be manually detected aiming at the quality inspection of guardrail data in the high-precision map manufacturing process. Need measure the guardrail of automatic extraction just can confirm whether accord with the preparation standard in the manual detection process, this process cost a large amount of time, and there is the problem of false retrieval moreover, this efficiency of high accuracy map preparation has just so great influence.
Therefore, a method and a system for evaluating confidence of guardrail extraction are needed to solve the above problem.
Disclosure of Invention
The invention provides a confidence evaluation method and a confidence evaluation system for guardrail extraction, which are used for solving the problems that the quality inspection of guardrail data in the existing high-precision map data is carried out by adopting a manual measurement method, the labor is consumed, and the quality inspection efficiency is low.
In a first aspect, an embodiment of the present invention provides a method for evaluating confidence of guardrail extraction, including:
step 1, discretizing a guardrail outline in the extracted guardrail data;
step 2, sampling the discretized guardrail profile;
and 3, processing the sampling points, and evaluating the confidence coefficient of the guardrail contour sampling points.
Further, before step 1, the method further comprises:
and automatically extracting guardrail data from the high-precision map data.
Further, after automatically extracting the guardrail data from the high-precision map data, the method further comprises the following steps:
and if the automatically extracted guardrail data is laser point cloud data, projecting the laser point cloud data into two-dimensional image data.
Further, the step 3 specifically includes:
and processing the sampling points according to the gray features of the guardrail area in the two-dimensional projection drawing of the guardrail, and judging the confidence coefficient of the guardrail contour sampling points.
Further, according to the gray scale characteristics of the guardrail region in the two-dimensional projection drawing of the guardrail, the sampling points are processed, and the confidence of the guardrail contour sampling points is judged, which specifically comprises the following steps:
taking a sampling point as a center, and respectively taking two rectangular frames at the upper side and the lower side of the sampling point; wherein, the two rectangular frames comprise the rows where the sampling points are located;
calculating the maximum gray value of each row of pixels on the two rectangular frames, obtaining a row of maximum gray pixel points from each rectangular frame, and respectively smoothing the two rows of maximum gray pixel points to remove gray abnormal pixel points;
and acquiring mutation positions of two rows of maximum gray pixel points, and if the mutation position distance of one row of maximum gray pixel points is far from the sampling point by the preset distance and the mutation position distance of the other row of maximum gray pixel points is far more than the sampling point by the preset distance, judging that the confidence of the sampling point is in a credible state.
In a second aspect, an embodiment of the present invention further provides a system for evaluating confidence of guardrail extraction, including:
the discretization module is used for discretizing the guardrail outline in the extracted guardrail data;
the sampling module is used for sampling the discretized guardrail outline;
and the confidence evaluation module is used for processing the sampling points and evaluating the confidence of the guardrail contour sampling points.
Further, the confidence evaluation system for guardrail extraction further comprises:
and the guardrail data extraction module is used for automatically extracting guardrail data from the high-precision map data.
In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a memory, a communication interface, and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the memory stores program instructions executable by the processor, which invokes a confidence assessment method that enables the guard bar extraction described above to be performed.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the above-described method for confidence evaluation of guardrail extraction.
The confidence evaluation method and the system for guardrail extraction provided by the embodiment of the invention have the advantages that firstly, the guardrail outline in the extracted guardrail data is discretized, and then the discretized guardrail outline is sampled; and finally, processing the sampling points, and evaluating the confidence coefficient of the guardrail contour sampling points. And evaluating whether the automatically extracted guardrail data meets the high-precision mapping standard by using the confidence coefficient. Compared with the quality inspection method adopting manual measurement in the prior art, which consumes manpower and has low quality inspection efficiency, the method provided by the invention reduces the time for quality inspection after extraction of the guardrail in the high-precision map, and improves the manufacturing efficiency of the high-precision map.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the embodiments or technical solutions in the prior art are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a confidence evaluation method for guardrail extraction according to an embodiment of the present invention;
fig. 2 is a two-dimensional projection diagram of laser point cloud data of a guardrail provided by an embodiment of the invention;
fig. 3 is a block diagram of a confidence evaluation system for guardrail extraction according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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 invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The guardrail is one of the elements for manufacturing the high-precision map, and at present, the quality of the guardrail extracted automatically needs to be manually detected aiming at the quality inspection of guardrail data in the high-precision map manufacturing process. Need measure the guardrail of automatic extraction just can confirm whether accord with the preparation standard in the manual detection process, this process cost a large amount of time, and there is the problem of false retrieval moreover, this efficiency of high accuracy map preparation has just so great influence.
Therefore, the embodiment of the invention provides a confidence evaluation method for guardrail extraction, which comprises the steps of firstly discretizing a guardrail profile in extracted guardrail data, and then sampling the discretized guardrail profile; and finally, processing the sampling points, and evaluating the confidence coefficient of the guardrail contour sampling points. And evaluating whether the automatically extracted guardrail data meets the high-precision mapping standard by using the confidence coefficient. The method reduces the quality inspection time of the extracted guardrails in the high-precision map, and improves the manufacturing efficiency of the high-precision map. The method solves the defects that the manual measurement is adopted for quality inspection, the labor is consumed, and the quality inspection efficiency is low in the conventional guardrail data quality inspection method. The following description and description of various embodiments are presented in conjunction with the following drawings.
As shown in fig. 1, in order to reduce the time for automatically extracting the manual quality inspection of the guard bar in the high-precision map making process, the embodiment of the invention provides a confidence evaluation method for guard bar extraction. First, the overall principle of the method provided by the embodiment of the present invention is briefly described, and the method includes the following steps:
and step 1, discretizing the guardrail outline in the extracted guardrail data.
Specifically, before step 1 is performed, first, guardrail data is automatically extracted from high-precision map data. The data used by the high-precision map is generally laser point cloud data, and if the guardrail data extracted automatically is laser point cloud data, the guardrail data needs to be projected into two-dimensional image data. If the automatically extracted guardrail data is two-dimensional image data, projection is not needed. Fig. 2 is a two-dimensional projection diagram of laser point cloud data of the guardrail provided by the embodiment of the invention.
After the guardrail data is automatically extracted from the high-precision map data, step 1 is executed to discretize the automatically extracted guardrail profile: the guardrail profile is discretized in preparation for further processing.
And 2, sampling the discretized guardrail outline.
In this embodiment, each discretized guardrail profile is sampled to obtain a plurality of sampling points. On one side of the guardrail contour, basically no difference exists between adjacent pixels, therefore, the invention samples the discretized guardrail contour to reduce the calculation amount.
And 3, processing the sampling points, and evaluating the confidence coefficient of the sampling points of the guardrail contour.
Specifically, according to the gray scale characteristics of the guardrail area in the two-dimensional projection image of the guardrail, the sampling points are processed, and the confidence coefficient of the guardrail outline sampling points is judged. The confidence coefficient comprises a credible state and an incredible state, and the confidence coefficient extracted by the guardrail represents the credibility of the guardrail for accurate extraction and identification. Because the gray value of the guardrail area is larger than the gray value of the surrounding area in the two-dimensional projection image of the guardrail, the invention judges whether the confidence of the guardrail outline sampling point is credible according to the gray value of the guardrail area corresponding to the sampling point, and can evaluate whether the automatically extracted guardrail data conforms to the high-precision map making standard or not through the confidence.
The confidence evaluation method for guardrail extraction provided by the embodiment of the invention comprises the steps of firstly discretizing a guardrail outline in extracted guardrail data, and then sampling the discretized guardrail outline; and finally, processing the sampling points, and evaluating the confidence coefficient of the guardrail contour sampling points. And evaluating whether the automatically extracted guardrail data meets the high-precision map making standard or not by using the confidence coefficient of each sampling point. The method reduces the quality inspection time of the extracted guardrails in the high-precision map, and improves the manufacturing efficiency of the high-precision map.
In one embodiment, in step 3, processing the sample points, and evaluating the confidence of the guardrail contour sample points specifically includes:
step 10, taking a sampling point as a center, and respectively taking two rectangular frames at the upper side and the lower side of the sampling point; wherein both rectangular frames include the row where the sample point is located.
The two-dimensional projection drawing of the guardrail is characterized in that the gray value of the guardrail area is larger than the gray value of the surrounding area, so that whether the guardrail contour sampling points meet the high-precision mapping standard or not is judged according to the gray values of the sampling points corresponding to the guardrail area.
In this embodiment, a high-precision map making standard of 5cm is taken as an example for explanation, that is, a difference between an extracted edge of a guardrail and a real edge of the guardrail is less than 5cm, and 1 pixel is 1 cm. Taking a sampling point as a center, and respectively taking two rectangular frames at the upper side and the lower side of the sampling point. Since the gray-scale value of the projected guardrail image has a fault in both the row direction and the column direction, the size of the rectangular frame needs to be larger, and preferably, the rectangular frames on the upper and lower sides are 40 × 40cm respectively, which is not specifically limited in the embodiment of the present invention. The upper and lower rectangular frames include the row where the sampling point is located.
Step 20, calculating the maximum gray value of each row of pixels on two rectangular frames, obtaining a row of maximum gray pixel points from each rectangular frame, and respectively smoothing the two rows of maximum gray pixel points to remove gray abnormal pixel points;
specifically, first, the maximum gray level of each row of pixels is calculated on two rectangular frames, and a column of maximum gray level pixel points is obtained from each rectangular frame.
And then, respectively carrying out smoothing treatment on the two columns of maximum gray pixel points, and removing gray abnormal pixel points. For example: the gray value of the point A is 3, the gray values of the two maximum gray pixel points before and after the point A are 102 and 104 respectively, the gray value of the point A is an abnormal value, the gray values of the two points before and after the point A are averaged to obtain an average gray value 103 to replace the gray value 3 of the point A, and other abnormal conditions are similarly processed.
And step 30, acquiring mutation positions of two columns of maximum gray-scale pixel points, and if the mutation position distance of one column of the maximum gray-scale pixel points is far greater than the preset distance of the sampling point, and the mutation position distance of the other column of the maximum gray-scale pixel points is far greater than the preset distance, judging that the confidence of the sampling point is in a credible state.
Since the gray value of the guardrail is larger than that of the surrounding area, the edge area of the guardrail has abrupt gray change. The method comprises the steps of obtaining mutation positions of two rows of maximum gray pixel points, and if the mutation position of one row of maximum gray pixel points is far away from the sampling point by a preset distance and the mutation position of the other row of maximum gray pixel points is far greater than the sampling point by the preset distance, judging the confidence of the sampling point to be a credible state, wherein the sampling point accords with the high-precision map manufacturing standard. In this embodiment, the high-precision map is made by 5cm (i.e. the difference between the extracted edge of the guardrail and the real edge of the guardrail is less than 5cm), and therefore, the preset distance is 5 cm.
According to the confidence evaluation method for guardrail extraction provided by the embodiment of the invention, the sampling points are processed according to the gray features of the guardrail area in the two-dimensional projection graph of the guardrail, so as to evaluate whether the automatically extracted guardrail data meet the high-precision mapping standard. The method reduces the quality inspection time of the extracted guardrails in the high-precision map, and improves the manufacturing efficiency of the high-precision map.
In one embodiment, fig. 3 is a block diagram of a confidence evaluation system for guardrail extraction according to an embodiment of the present invention, and referring to fig. 3, the system includes:
the discretization module 301 is used for discretizing the guardrail outline in the extracted guardrail data;
a sampling module 302, configured to sample the discretized guardrail profile;
and the confidence evaluation module 303 is configured to process the sampling points and evaluate the confidence of the guardrail contour sampling points.
Specifically, how to utilize the discretization module 301, the sampling module 302 and the confidence evaluation module 303 to perform confidence evaluation of guardrail extraction can refer to the above method embodiment, and the embodiment of the present invention is not described herein again.
According to the confidence evaluation system for guardrail extraction provided by the embodiment of the invention, firstly, the guardrail outline in the extracted guardrail data is discretized, and then the discretized guardrail outline is sampled; and finally, processing the sampling points, and evaluating the confidence coefficient of the guardrail contour sampling points. And evaluating whether the automatically extracted guardrail data meets the high-precision mapping standard or not by using the confidence of each sampling point. The method reduces the quality inspection time of the extracted guardrails in the high-precision map, and improves the manufacturing efficiency of the high-precision map.
In an embodiment, based on the same concept, an embodiment of the present invention provides an electronic device, which may include, as shown in fig. 4: a processor (processor)401, a communication Interface (communication Interface)402, a memory (memory)403 and a communication bus 404, wherein the processor 401, the communication Interface 402 and the memory 403 complete communication with each other through the communication bus 404. The processor 401 may call logic instructions in the memory 403 to execute the steps of the confidence evaluation method for guardrail extraction provided by the above embodiments, for example, including: step 1, discretizing a guardrail outline in the extracted guardrail data; step 2, sampling the discretized guardrail outline; and 3, processing the sampling points, and evaluating the confidence coefficient of the guardrail contour sampling points.
In one embodiment, based on the same concept, the embodiment of the present invention further provides a non-transitory computer readable storage medium, on which a computer program is stored, and the computer program is implemented by a processor to execute the steps of the confidence evaluation method for guardrail extraction provided by the above embodiments, for example, the method includes: step 1, discretizing a guardrail outline in the extracted guardrail data; step 2, sampling the discretized guardrail outline; and 3, processing the sampling points, and evaluating the confidence coefficient of the sampling points of the guardrail contour.
The embodiments of the present invention can be arbitrarily combined to achieve different technical effects.
The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A confidence evaluation method for guardrail extraction is characterized by comprising the following steps:
step 1, discretizing a guardrail outline in the extracted guardrail data;
step 2, sampling the discretized guardrail profile;
step 3, processing the sampling points according to the gray features of the guardrail data, and evaluating the confidence coefficient of the guardrail outline sampling points; taking a sampling point as a center, and respectively taking two rectangular frames at the upper side and the lower side of the sampling point; wherein, the two rectangular frames comprise the rows where the sampling points are located; calculating the maximum gray value of each row of pixels on the two rectangular frames, obtaining a row of maximum gray pixel points from each rectangular frame, and respectively smoothing the two rows of maximum gray pixel points to remove gray abnormal pixel points; and acquiring mutation positions of two rows of maximum gray pixel points, and if the mutation position distance of one row of maximum gray pixel points is far from the sampling point by the preset distance and the mutation position distance of the other row of maximum gray pixel points is far more than the sampling point by the preset distance, judging that the confidence of the sampling point is in a credible state.
2. The confidence evaluation method for guardrail extraction of claim 1, wherein before step 1, the method further comprises:
and automatically extracting guardrail data from the high-precision map data.
3. The confidence evaluation method for guardrail extraction according to claim 2, further comprising, after automatically extracting guardrail data from the high-precision map data:
and if the automatically extracted guardrail data is laser point cloud data, projecting the laser point cloud data into two-dimensional image data.
4. A confidence evaluation system for guardrail extraction is characterized by comprising:
the discretization module is used for discretizing the guardrail outline in the extracted guardrail data;
the sampling module is used for sampling the discretized guardrail outline;
the confidence evaluation module is used for processing the sampling points according to the gray features of the guardrail data and evaluating the confidence of the guardrail outline sampling points; taking a sampling point as a center, and respectively taking two rectangular frames at the upper side and the lower side of the sampling point; wherein, the two rectangular frames comprise the rows where the sampling points are located; calculating the maximum gray value of each row of pixels on the two rectangular frames, obtaining a row of maximum gray pixel points from each rectangular frame, and respectively smoothing the two rows of maximum gray pixel points to remove gray abnormal pixel points; and acquiring mutation positions of two rows of maximum gray pixel points, and if the mutation position distance of one row of maximum gray pixel points is far from the sampling point by the preset distance and the mutation position distance of the other row of maximum gray pixel points is far more than the sampling point by the preset distance, judging that the confidence of the sampling point is in a credible state.
5. The guardrail extraction confidence evaluation system of claim 4, further comprising:
and the guardrail data extraction module is used for automatically extracting guardrail data from the high-precision map data.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the confidence evaluation method of guardrail extraction according to any of claims 1 to 3.
7. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the confidence evaluation method of guardrail extraction according to any of claims 1 to 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011158443.5A CN112257723B (en) | 2020-10-26 | 2020-10-26 | Confidence evaluation method and system for guardrail extraction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011158443.5A CN112257723B (en) | 2020-10-26 | 2020-10-26 | Confidence evaluation method and system for guardrail extraction |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112257723A CN112257723A (en) | 2021-01-22 |
CN112257723B true CN112257723B (en) | 2022-09-27 |
Family
ID=74262410
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011158443.5A Active CN112257723B (en) | 2020-10-26 | 2020-10-26 | Confidence evaluation method and system for guardrail extraction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112257723B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017104574A1 (en) * | 2015-12-14 | 2017-06-22 | 株式会社リコー | Image processing device, object recognition device, apparatus control system, image processing method and program |
CN111797803A (en) * | 2020-07-15 | 2020-10-20 | 郑州昂达信息科技有限公司 | Road guardrail abnormity detection method based on artificial intelligence and image processing |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102445453B (en) * | 2011-11-30 | 2013-10-23 | 北京交通大学 | Automatic detection device and identification method for integrality of guardrail of high-speed railway line |
CN109035759B (en) * | 2018-06-13 | 2021-02-02 | 重庆邮电大学 | Guardrail detection and evaluation method |
CN110363771B (en) * | 2019-07-15 | 2021-08-17 | 武汉中海庭数据技术有限公司 | Isolation guardrail shape point extraction method and device based on three-dimensional point cloud data |
CN111709322B (en) * | 2020-05-28 | 2022-09-06 | 武汉中海庭数据技术有限公司 | Method and device for calculating lane line confidence |
-
2020
- 2020-10-26 CN CN202011158443.5A patent/CN112257723B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017104574A1 (en) * | 2015-12-14 | 2017-06-22 | 株式会社リコー | Image processing device, object recognition device, apparatus control system, image processing method and program |
CN111797803A (en) * | 2020-07-15 | 2020-10-20 | 郑州昂达信息科技有限公司 | Road guardrail abnormity detection method based on artificial intelligence and image processing |
Also Published As
Publication number | Publication date |
---|---|
CN112257723A (en) | 2021-01-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111709322B (en) | Method and device for calculating lane line confidence | |
CN108961316B (en) | Image processing method and device and server | |
CN110705759B (en) | Water level early warning monitoring method and device, storage medium and electronic equipment | |
CN111768450A (en) | Automatic detection method and device for line deviation of structured light camera based on speckle pattern | |
CN116168351B (en) | Inspection method and device for power equipment | |
CN112529014A (en) | Straight line detection method, information extraction method, device, equipment and storage medium | |
CN112257723B (en) | Confidence evaluation method and system for guardrail extraction | |
CN107578001B (en) | Method and device for testing resolution of fingerprint acquisition equipment | |
CN114332487A (en) | Image-based accumulated water early warning method, device, equipment, storage medium and product | |
CN116091503B (en) | Method, device, equipment and medium for discriminating panel foreign matter defects | |
CN115083008A (en) | Moving object detection method, device, equipment and storage medium | |
CN116091405B (en) | Image processing method and device, computer equipment and storage medium | |
CN115639578A (en) | Beidou navigation positioning monitoring processing method and system | |
CN112257725B (en) | Kerb extraction confidence evaluation method and system | |
CN112258595A (en) | Method and system for evaluating confidence of transverse deceleration marked line | |
CN112257724B (en) | Road outside line confidence evaluation method and system | |
CN111932621B (en) | Method and device for evaluating arrow extraction confidence | |
CN117522855B (en) | Image-based device fault diagnosis method and device, electronic device and storage medium | |
CN113139454B (en) | Road width extraction method and device based on single image | |
CN111047550A (en) | Product abnormity detection method, device and equipment based on machine vision | |
CN114862856B (en) | Panel defect area identification method and device, electronic equipment and medium | |
CN118096767B (en) | Wafer cutting defect detection method, system, equipment and storage medium | |
CN115359359A (en) | Oil storage tank detection method and device based on remote sensing image | |
CN118334644A (en) | Wheat cob phenotype parameter determination method, device, equipment and medium based on deep learning | |
CN118279607A (en) | Method and device for determining object type, storage medium and electronic device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |