[go: up one dir, main page]

CN114219796B - Intelligent highway maintenance marking quality detection method, system and electronic equipment - Google Patents

Intelligent highway maintenance marking quality detection method, system and electronic equipment Download PDF

Info

Publication number
CN114219796B
CN114219796B CN202111562375.3A CN202111562375A CN114219796B CN 114219796 B CN114219796 B CN 114219796B CN 202111562375 A CN202111562375 A CN 202111562375A CN 114219796 B CN114219796 B CN 114219796B
Authority
CN
China
Prior art keywords
image
marking
preset
road
information
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
Application number
CN202111562375.3A
Other languages
Chinese (zh)
Other versions
CN114219796A (en
Inventor
吴怡
孙毅
冯星
桂发民
谢一军
冯彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Urban Construction Engineering Consulting Co ltd
Original Assignee
Shanghai Urban Construction Engineering Consulting Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Urban Construction Engineering Consulting Co ltd filed Critical Shanghai Urban Construction Engineering Consulting Co ltd
Priority to CN202111562375.3A priority Critical patent/CN114219796B/en
Publication of CN114219796A publication Critical patent/CN114219796A/en
Application granted granted Critical
Publication of CN114219796B publication Critical patent/CN114219796B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51Indexing; Data structures therefor; Storage structures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/20Image enhancement or restoration using local operators
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/20Image enhancement or restoration using local operators
    • G06T5/30Erosion or dilatation, e.g. thinning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/70Denoising; Smoothing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • G06T7/73Determining position or orientation of objects or cameras using feature-based methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20024Filtering details
    • G06T2207/20032Median filtering
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30248Vehicle exterior or interior
    • G06T2207/30252Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256Lane; Road marking

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Library & Information Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Quality & Reliability (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The application relates to an intelligent road maintenance marking quality detection method, system and electronic equipment, which comprise the steps of acquiring image information at a preset ordinate position in a road marking frame flow picture according to a starting point trigger signal, recording the image information in a cache library, triggering the image information in a combined cache library according to a preset imaging rule to perform imaging to obtain a two-dimensional plane picture, generating a road section unique code mark for the two-dimensional plane picture, acquiring address information recorded in the frame flow picture through the road section unique code mark, extracting and calculating the two-dimensional plane picture to obtain a marking rectangular image, judging whether the marking rectangular image is qualified according to a preset judging rule, and if not, reserving the road section unique code mark in a database. The application has the effect of improving the working efficiency by automatically inspecting and identifying the quality condition of the marking.

Description

Intelligent highway maintenance marking quality detection method, system and electronic equipment
Technical Field
The application relates to the technical field of image recognition, in particular to an intelligent road maintenance marking quality detection method, system and electronic equipment.
Background
Traffic markings are marks for transmitting traffic information such as guidance, restriction, warning, etc. to traffic participants with lines on the road surface of a road. The traffic safety mark has the functions of controlling and guiding traffic, and the clearly and prominently marked mark can better ensure traffic safety and guide civilized driving.
Currently, in the process of inspecting road markings, the marking state is generally judged by visual inspection. When marking is re-applied, the current standard is specified in a non-quantitative way, and different patrol personnel have inconsistent understanding of 'good visibility', so that repeated application sometimes is caused, financial resource waste is caused, or no re-application is performed, and traffic accident hidden danger is easily formed. Therefore, the inventor considers that the existing inspection marking standard is not unified, and has low automation level, low efficiency and low intellectualization level, so that the inspection marking standard needs to be further improved.
Disclosure of Invention
In order to realize automatic inspection and identification of marking quality conditions and improve operation efficiency, the application provides an intelligent road maintenance marking quality detection method, an intelligent road maintenance marking quality detection system and electronic equipment.
In a first aspect, the application provides an intelligent highway maintenance marking quality detection method, which adopts the following technical scheme:
an intelligent highway maintenance marking quality detection method comprises the following steps:
Acquiring image information at a preset ordinate position in a road marking frame stream picture according to a starting point trigger signal, and recording the image information into a cache library;
Triggering image information in a combined cache library to image according to a preset imaging rule to obtain a two-dimensional plane image, generating a road section unique code mark for the two-dimensional plane image, and acquiring address information recorded by a frame stream picture through the road section unique code mark;
extracting and calculating the two-dimensional plan to obtain a marked line rectangular image;
Judging whether the marked line rectangular image is qualified according to a preset judging rule, and if the marked line rectangular image is not qualified, reserving a road section unique code mark into a database.
By adopting the technical scheme, the image information at the preset ordinate position of the frame flow picture of the road marking is acquired and recorded in the cache library, the image information in the cache library is subjected to combined imaging according to the preset imaging rule to obtain the two-dimensional plan, the two-dimensional plan is provided with the road section unique code mark, the address information of the recorded marking can be identified from the road section unique code mark, then the two-dimensional plan is subjected to calculation processing, the detection precision is increased, the rectangular image of the marking is obtained, whether the rectangular image of the marking is qualified or not is judged according to the preset judging rule, the automatic and intelligent acquisition and marking quality recognition are realized, the operation efficiency is improved, the inspection personnel are prevented from visually understanding inconsistency by comparing with the manual inspection through subjective observation, and the inspection objectivity and accuracy are improved.
Optionally, the preset imaging rule includes:
and recording the speed and time of the vehicle in real time after receiving the starting point trigger signal, calculating a current path numerical value, ending acquiring the image information at the preset ordinate position in the road marking frame flow picture when the current path numerical value reaches the preset path threshold value, and restarting acquiring the image information at the preset ordinate position in the next road marking frame flow picture until receiving the vehicle stop signal.
By adopting the technical scheme, compared with the dynamic identification path identification, the sectional type marking acquisition identification can timely release the memory, and the memory can be released as long as a certain section of marking is detected to be qualified, so that the continuous availability of a cache space is ensured, and the continuity of inspection operation is effectively enhanced.
Optionally, the step of imaging the image information in the combined repository to obtain a two-dimensional plan includes:
matching the pixel values recorded in two adjacent columns in the cache library to obtain similarity;
when the similarity is larger than a preset threshold value, deleting the similar content according to a preset deletion rule;
and combining the residual pixel values in the cache library according to the time sequence to obtain a two-dimensional plan.
Through adopting above-mentioned technical scheme, the similarity matching of setting and the rule of predetermining deletion can effectively compress the image, reduce the picture stretching deformation condition that many frame flows value frequency and too fast and lead to for the image is laminated normal visual marking two-dimensional plan more, thereby is favorable to discerning the marking quality.
Optionally, the step of matching the pixel values of two adjacent columns recorded in the cache library to obtain the similarity calculates the similarity of the two adjacent rows of pixel values in the cache library by using cosine similarity, and the cosine similarity algorithm is as follows:
Wherein, A and B respectively represent two adjacent rows of pixel values, A.B represents the inner product of the two rows of pixel values, and A represents the norm multiplication of the two rows of pixel values.
By adopting the technical scheme, the cosine similarity describes the similarity of two rows of pixel value changes, and the result is more accurate than a common pixel difference algorithm, thereby being beneficial to realizing two-dimensional plane image imaging.
Optionally, the step of extracting and calculating the two-dimensional plan to obtain the reticle image includes:
Preprocessing the two-dimensional plan to obtain an enhanced gray level image;
performing edge detection on the enhanced gray level image to obtain marking edge information;
Carrying out Hough transformation on the edge information of the marking to identify the shape of the marking, and extracting the shape of the marking to obtain a marking image;
and pasting the marked line image into a layer with a preset fixed size, and automatically filling preset pixel values into the blank of the layer to obtain a marked line rectangular image.
Through adopting above-mentioned technical scheme, preprocessing can effectively eliminate the influence such as two-dimensional plan view blurring or illumination difference, converts into enhancement gray level image, and the rethread carries out edge detection to enhancement gray level image to obtain marking edge information, and then rethread hough transform discernment marking shape obtains the marking image, and paste the marking image to the picture layer that pixel value is unified, and the preset pixel value that sets up has contrast with marking department pixel value, reduces whether the highway face except marking is qualified to cause the influence to discernment, has improved the precision of quality discernment.
Optionally, the step of preprocessing the two-dimensional plan to obtain an enhanced gray-scale image includes:
performing a first corrosion and then expansion opening operation on the two-dimensional plan to obtain a primary treatment image;
Graying treatment is carried out on the primary treatment image by a weighted average method, so that a gray image is obtained;
and carrying out median filtering treatment on the gray level image to obtain an enhanced gray level image.
By adopting the technical scheme, the opening operation has the effects of eliminating fine objects, separating the objects at the fine and smoothing the boundaries of larger objects. The median filtering has remarkable effects on salt and pepper noise and speckle noise, has good edge maintaining characteristics, and can further enhance and distinguish the situation of incomplete line edges.
Optionally, the preset judging rule includes:
And counting the number of pixels in the standard rectangular image, wherein the number of pixels is smaller than a preset threshold value, judging whether the ratio is larger than a preset ratio or not according to the ratio of the number to the total number, and judging that the standard rectangular image is unqualified if the ratio is larger than the preset ratio.
Because the marked line pattern in the standard rectangular image is in a rectangular shape without excessive complicated patterns, the processing speed of the whole calculation can be effectively improved by counting the number to ratio, the buffer memory can be timely released, and the sustainable time of the quality identification operation is enhanced.
In a second aspect, the application provides an intelligent highway maintenance marking quality detection system, which adopts the following technical scheme:
an intelligent highway maintenance marking quality detection system, comprising:
the information recording module is used for acquiring image information at a preset ordinate position in the road marking frame stream picture according to the starting point trigger signal and recording the image information into the cache library;
The information imaging module is used for triggering the image information in the combined cache library to image according to a preset imaging rule, obtaining a two-dimensional plane image, generating a road section unique code mark for the two-dimensional plane image, and acquiring address information recorded by a frame stream picture through the road section unique code mark;
The image processing module is used for extracting, calculating and processing the two-dimensional plan to obtain a marked line rectangular image;
and the image judging module is used for judging whether the marked line rectangular image is qualified according to a preset judging rule, and if the marked line rectangular image is unqualified, reserving the unique code mark of the road section into the database.
In a third aspect, the present application provides an electronic device, which adopts the following technical scheme:
An electronic device comprising a memory and a processor, the memory storing a computer program capable of being loaded by the processor and executing an intelligent road maintenance marking quality detection method as described above.
In a fourth aspect, the present application provides a computer storage medium, which adopts the following technical scheme:
a computer readable storage medium storing a computer program loadable by a processor and adapted to perform an intelligent road maintenance marking quality detection method as described above.
In summary, the application has the following beneficial technical effects:
The method comprises the steps of obtaining image information at a preset ordinate position of a road marking frame flow picture, recording the image information in a cache library, carrying out combined imaging on the image information in the cache library according to a preset imaging rule to obtain a two-dimensional plan, wherein the two-dimensional plan is provided with a road section unique code mark, address information of recorded markings can be identified from the road section unique code mark, then the two-dimensional plan is subjected to calculation processing, the detection accuracy is improved, a marking rectangular image is obtained, whether the marking rectangular image is qualified or not is judged according to the preset judging rule, automatic acquisition and marking quality identification are realized, the identification qualification standard is unified, and meanwhile, the operation efficiency is improved.
Drawings
FIG. 1 is a flow chart of an intelligent road maintenance marking quality detection method according to one embodiment of the application.
FIG. 2 is a flowchart showing the steps for imaging the image information in the combined repository in step S2 according to another embodiment of the present application.
Fig. 3 is a flowchart showing the specific steps of step S3 in another embodiment of the present application.
Fig. 4 is a flowchart showing the specific steps of step S30 in another embodiment of the present application.
FIG. 5 is a block diagram of an intelligent highway maintenance marking quality inspection system according to one embodiment of the present application.
In the figure, 1, an information recording module, 2, an information imaging module, 3, an image processing module and 4, an image judging module.
Detailed Description
The application is described in further detail below with reference to fig. 1-5.
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings 1 to 5 and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Referring to fig. 1, the embodiment of the application discloses an intelligent highway maintenance marking quality detection method, which comprises the following steps:
S1, acquiring image information at a preset ordinate position in a road marking frame stream picture according to a starting point trigger signal, and recording the image information into a buffer library.
Specifically, by additionally arranging a data acquisition camera on the vehicle, the camera is fixedly arranged in the front of the vehicle and is vertical to the road surface, so that the ground can be clearly focused and shot, wherein the camera can be selected as a fisheye camera or a common lens, and the method is not limited by the type of the camera. When the road marking is required to be patrolled, the vehicle navigation system is connected, the starting point address is recorded, a starting point trigger signal is generated through a preset button or a voice command and is sent to the server, after the server acquires the starting point trigger signal, the server starts to acquire image information at a preset ordinate position in a road marking frame flow picture through the camera, in the embodiment, the pixel value in the horizontal direction of the most middle area of the ordinate position of the frame flow picture is preferentially acquired, and because the most middle position of the frame flow picture shot by the camera is perpendicular to the road marking, the imaging quality is good, and the influence of the reflection of a road surface at a distance on the frame flow picture when sunlight is violent can be effectively avoided.
In addition, the buffer memory can be of a fixed length, so that the buffer memory can not overflow in the long-term recording process, and particularly, the buffer memory is responsible for recording the fed ordinate scanning results according to the shooting sequence, and when the recorded content exceeds the maximum capacity of the buffer memory, the early data is deleted from the buffer memory by adopting a first-in first-out method, and new data is recorded.
S2, triggering image information in the combined cache library to image according to a preset imaging rule, obtaining a two-dimensional plane image, generating a road section unique code mark for the two-dimensional plane image, and acquiring address information recorded by a frame stream picture through the road section unique code mark.
Specifically, the preset imaging rule is that the vehicle speed and time are recorded in real time after the starting point trigger signal is received, the current distance value is calculated, when the current distance value reaches the preset distance threshold value, the acquisition of the image information at the preset ordinate position in the road marking frame flow picture is ended, and meanwhile, the acquisition of the image information at the preset ordinate position in the next section of road marking frame flow picture is restarted until the vehicle stop signal is received.
In this embodiment, the preset distance threshold may be set to 1 km. When the vehicle walks for 1 km to finish the image information acquisition, the image information in the combined cache library is triggered to image at the same time, specifically, the pixel values in the cache library which are arranged according to the time sequence are combined together to obtain a two-dimensional plane diagram, which is equivalent to converting time sequence information in the center of a picture into plane information.
In addition, fig. 2 is a flowchart of an alternative implementation of imaging the image information in the combined repository in step S2 in the present disclosure, and referring to fig. 2, step S2 specifically includes the following steps S20, S21, and S22:
And S20, matching pixel values recorded in two adjacent columns in the cache library to obtain the similarity.
S21, deleting the similar content according to a preset deletion rule when the similarity is larger than a preset threshold value.
S22, combining the residual pixel values in the cache library according to the time sequence, and obtaining a two-dimensional plan.
Specifically, since the frame rate of the frame stream picture is often faster than the running speed of the vehicle, frames are easily taken at the same position for multiple times, and if the pixel values in the buffer library are directly combined, the actual marking line is stretched too long, which causes data redundancy to affect the overall processing speed, so that similar contents need to be deleted, and in this embodiment, the similarity of two adjacent columns of pixel values in the calculation buffer is preferably calculated by using a cosine similarity algorithm. The cosine similarity describes the similarity of two columns of pixel changes, and the result is accurate but the calculated amount is large, so that the cosine similarity algorithm is very suitable for being applied to similarity vector calculation with high precision requirements but limited quantity, and the fixed length of the cache can be known according to a preset imaging rule, and is very suitable for similarity calculation of the application. The cosine similarity calculation formula is as follows, wherein A and B respectively represent two adjacent rows of pixel values, a·b represents the inner product of two adjacent rows of pixel values, and iia iib iirepresents the norm multiplication of two adjacent rows of pixel values:
when the cosine similarity exceeds 95%, judging that the similarity exists between two adjacent rows of pixel values, wherein only one row of pixel values with the later time is reserved in the two adjacent rows of pixel values, otherwise, judging that the similarity does not exist between the two adjacent rows of pixel values, and reserving the two adjacent rows of pixel values. The above process is iterated until the entire cache iterates one time.
In another embodiment, the similarity between two adjacent rows of pixel values in the calculation buffer may be obtained by comparing the differences between the two adjacent rows of pixel values.
And S3, extracting and calculating the two-dimensional plan to obtain a marked line rectangular image.
Specifically, after the pixel values in the buffer library are combined, the combined size of each path is different, so that errors are easily caused to subsequent qualification judgment, and therefore, relevant feature extraction, calculation and other processes are required to be carried out on the two-dimensional plan, so that a marked line rectangular image with uniform size is obtained.
Fig. 3 is a flowchart of an alternative implementation of step S3 in the present disclosure, and referring to fig. 3, step S3 specifically includes the following steps S30, S31, S32, and S33:
s30, preprocessing the two-dimensional plan to obtain an enhanced gray level image.
S31, performing edge detection on the enhanced gray level image to obtain the marking edge information.
S32, carrying out Hough transformation on the marking edge information to identify the marking shape, and extracting the marking shape to obtain a marking image.
And S33, pasting the marked line image into a layer with a preset fixed size, and automatically filling preset pixel values into the blank of the layer to obtain a marked line rectangular image.
Specifically, due to the influence of illumination, errors easily exist between two-dimensional plane diagrams of each path, so that enhancement preprocessing is required to be performed on the two-dimensional plane diagrams to obtain an enhanced gray level image. And edge detection is carried out on the enhanced gray level image to obtain marking edge information, namely a plurality of marking edge point coordinates, wherein the edge detection can be Canny detection, the Canny detection can identify as many actual edges as possible, and meanwhile false alarms generated by noise are reduced as much as possible, so that the method has the characteristics of high positioning performance, minimum response and the like. Then carrying out Hough transformation according to the edge information of the marking so as to identify the marking shape, matting out the marking shape to obtain a marking image, pasting the marking image into a layer with a preset fixed size, and automatically filling preset pixel values into the blank of the layer to obtain a marking rectangular image, wherein the preset pixel values are set to 0, and the maximum variance is formed between the preset pixel values and the marking, so that influence on marking quality identification caused by road paths except the marking in an original image is eliminated.
Fig. 4 is a flowchart of an alternative implementation of step S30 in the present disclosure, referring to fig. 4, step S30 specifically includes the following steps S300, S301, and S302:
s300, performing an opening operation of etching and then expanding on the two-dimensional plan to obtain a primary processing image.
S301, carrying out graying treatment on the primary treatment image by a weighted average method to obtain a gray image.
S302, carrying out median filtering processing on the gray level image to obtain an enhanced gray level image.
Specifically, the two-dimensional plan is subjected to an opening operation of etching and then expanding to obtain a primary processed image, which has the effects of eliminating fine objects, separating the objects at the fine and smoothing the boundary of a larger object. Then, the primary processed image is subjected to graying processing, and in this embodiment, a weighted average method is used for the graying processing. And then, carrying out median filtering treatment on the gray image to obtain an enhanced gray image, wherein the median filtering has obvious effects on salt and pepper noise and spot noise, has good edge retention characteristic, and can further strengthen and distinguish the situation of incomplete line edges.
And S4, judging whether the marked line rectangular image is qualified according to a preset judging rule, and if the marked line rectangular image is unqualified, reserving a road section unique code mark into a database.
Specifically, the preset judging rule is to count the number of pixels in the standard rectangular image, the number of pixels is smaller than a preset threshold value, judge whether the ratio is larger than a preset ratio or not according to the ratio of the calculated number to the total number, and judge that the marked rectangular image is unqualified if the ratio is larger than the preset ratio. After the road section unique code identification is unqualified, the data in the cache bank is subjected to emptying treatment, the memory is released timely, the sustainability of the identification operation is enhanced, and meanwhile, the equipment cache capacity is not required to be too large, so that the equipment purchase cost is greatly reduced.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
The embodiment of the application also provides an intelligent road maintenance marking quality detection system which corresponds to the intelligent road maintenance marking quality detection method in the embodiment one by one. Referring to fig. 5, the intelligent road maintenance marking quality detection system comprises an information recording module 1, an information imaging module 2, an image processing module 3 and an image judging module 4. The functional modules are described in detail as follows:
The information recording module 1 is used for acquiring image information at a preset ordinate position in the road marking frame stream picture according to the starting point trigger signal and recording the image information into the buffer library.
The information imaging module 2 is used for triggering the image information in the combined cache library to image according to a preset imaging rule, obtaining a two-dimensional plane image, generating a road section unique code mark on the two-dimensional plane image, and acquiring address information recorded by the frame stream picture through the road section unique code mark.
And the image processing module 3 is used for extracting and calculating the two-dimensional plan view to obtain a marked line rectangular image.
And the image judging module 4 is used for judging whether the marked line rectangular image is qualified according to a preset judging rule, and if the marked line rectangular image is not qualified, reserving the unique code mark of the road section into the database.
The intelligent road maintenance marking quality detection system utilizes an information recording module 1 to acquire image information at a preset ordinate position in a road marking frame stream picture from a camera according to a starting point trigger signal, records the image information into a cache library, then utilizes an information imaging module 2 to trigger image information in a combined cache library according to a preset imaging rule to acquire a two-dimensional plane picture, generates a road section unique code mark on the two-dimensional plane picture, can acquire address information recorded by the frame stream picture through the road section unique code mark, utilizes an image processing module 3 to extract and calculate the two-dimensional plane picture to acquire a marking rectangular image, and finally utilizes an image judging module 4 to judge whether the marking rectangular image is qualified according to a preset judging rule, and if not, reserves the road section unique code mark into a database.
The specific limitation of the intelligent road maintenance marking quality detection system can be referred to the limitation of the intelligent road maintenance marking quality detection method in the context, and the detailed description is omitted here. All or part of each module in the intelligent highway maintenance marking quality detection system can be realized by software, hardware and combination thereof. The above modules may be embedded in hardware or independent of a processor in the electronic device, or may be stored in software in a memory of the electronic device, so that the processor may call and execute operations corresponding to the above modules.
The embodiment of the application discloses electronic equipment. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed by the processor performs the steps of:
S1, acquiring image information at a preset ordinate position in a road marking frame stream picture according to a starting point trigger signal, and recording the image information into a buffer library.
S2, triggering image information in the combined cache library to image according to a preset imaging rule, obtaining a two-dimensional plane image, generating a road section unique code mark for the two-dimensional plane image, and acquiring address information recorded by a frame stream picture through the road section unique code mark.
And S3, extracting and calculating the two-dimensional plan to obtain a marked line rectangular image.
And S4, judging whether the marked line rectangular image is qualified according to a preset judging rule, and if the marked line rectangular image is unqualified, reserving a road section unique code mark into a database.
The step of imaging the image information in the combined repository in step S2 includes:
And S20, matching pixel values recorded in two adjacent columns in the cache library to obtain the similarity.
S21, deleting the similar content according to a preset deletion rule when the similarity is larger than a preset threshold value.
S22, combining the residual pixel values in the cache library according to the time sequence, and obtaining a two-dimensional plan.
The step S3 comprises the following steps:
s30, preprocessing the two-dimensional plan to obtain an enhanced gray level image.
S31, performing edge detection on the enhanced gray level image to obtain the marking edge information.
S32, carrying out Hough transformation on the marking edge information to identify the marking shape, and extracting the marking shape to obtain a marking image.
And S33, pasting the marked line image into a layer with a preset fixed size, and automatically filling preset pixel values into the blank of the layer to obtain a marked line rectangular image.
Step S30 includes:
s300, performing an opening operation of etching and then expanding on the two-dimensional plan to obtain a primary processing image.
S301, carrying out graying treatment on the primary treatment image by a weighted average method to obtain a gray image.
S302, carrying out median filtering processing on the gray level image to obtain an enhanced gray level image.
The embodiment of the application also discloses a computer readable storage medium which stores a computer program capable of being loaded and executed by a processor, wherein the computer program realizes the steps of any one of the intelligent road maintenance marking quality detection methods when being executed by the processor, and can achieve the same effect.
The computer readable storage medium includes, for example, a U disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
The foregoing description of the preferred embodiments of the application is not intended to limit the scope of the application in any way, including the abstract and drawings, in which case any feature disclosed in this specification (including abstract and drawings) may be replaced by alternative features serving the same, equivalent purpose, unless expressly stated otherwise. That is, each feature is one example only of a generic series of equivalent or similar features, unless expressly stated otherwise.

Claims (9)

1. An intelligent highway maintenance marking quality detection method is characterized by comprising the following steps:
acquiring image information at a preset ordinate position in a road marking frame flow picture according to a starting point trigger signal, namely acquiring a pixel value positioned in the horizontal direction of the most middle area of the ordinate position of the frame flow picture, and recording the image information into a cache library;
Triggering image information in a combined cache library to image according to a preset imaging rule to obtain a two-dimensional plane image, wherein the two-dimensional plane image comprises pixel values recorded in two adjacent columns in the cache library, matching to obtain similarity, deleting similar contents according to a preset deleting rule when the similarity is larger than a preset threshold value, combining the residual pixel values in the cache library according to time sequence to obtain the two-dimensional plane image, generating a road section unique code identifier for the two-dimensional plane image, and acquiring address information recorded by a frame stream picture through the road section unique code identifier;
extracting and calculating the two-dimensional plan to obtain a marked line rectangular image;
Judging whether the marked line rectangular image is qualified according to a preset judging rule, and if the marked line rectangular image is not qualified, reserving a road section unique code mark into a database.
2. The method for detecting the quality of an intelligent road maintenance marking according to claim 1, wherein the preset imaging rules comprise:
and recording the speed and time of the vehicle in real time after receiving the starting point trigger signal, calculating a current path numerical value, ending acquiring the image information at the preset ordinate position in the road marking frame flow picture when the current path numerical value reaches the preset path threshold value, and restarting acquiring the image information at the preset ordinate position in the next road marking frame flow picture until receiving the vehicle stop signal.
3. The method for detecting the quality of the intelligent road maintenance marking according to claim 2, wherein the step of matching the pixel values recorded in two adjacent rows in the cache library to obtain the similarity uses cosine similarity to calculate the similarity of the two adjacent rows in the cache library, and the cosine similarity algorithm is as follows:
Wherein A and B respectively represent two adjacent rows of pixel values, A.B represents the inner product of the two rows of pixel values,
II A II B II represents multiplication of norms of pixel values of two rows.
4. The method for detecting the quality of an intelligent road maintenance marking according to claim 1, wherein the step of extracting and calculating the two-dimensional plan to obtain the marking image comprises the following steps:
Preprocessing the two-dimensional plan to obtain an enhanced gray level image;
performing edge detection on the enhanced gray level image to obtain marking edge information;
Carrying out Hough transformation on the edge information of the marking to identify the shape of the marking, and extracting the shape of the marking to obtain a marking image;
and pasting the marked line image into a layer with a preset fixed size, and automatically filling preset pixel values into the blank of the layer to obtain a marked line rectangular image.
5. The method for detecting the quality of an intelligent road maintenance marking according to claim 4, wherein the step of preprocessing the two-dimensional plan to obtain the enhanced gray-scale image comprises the steps of:
the method comprises the steps of performing a first erosion and then expansion on a two-dimensional plane graph to obtain a primary processing image, performing graying treatment on the primary processing image by a weighted average method to obtain a gray image, and performing median filtering treatment on the gray image to obtain an enhanced gray image.
6. The method for detecting the quality of an intelligent road maintenance marking according to claim 1, wherein the preset judging rule comprises:
And counting the number of pixels in the standard rectangular image, wherein the number of pixels is smaller than a preset threshold value, judging whether the ratio is larger than a preset ratio or not according to the ratio of the number to the total number, and judging that the standard rectangular image is unqualified if the ratio is larger than the preset ratio.
7. An intelligent highway maintenance marking quality detection system, which is characterized by comprising:
The information recording module (1) is used for acquiring image information at a preset ordinate position in the road marking frame flow picture according to the starting point trigger signal, namely acquiring a pixel value positioned in the horizontal direction of the most middle area of the ordinate position of the frame flow picture, and recording the image information into the cache library;
The information imaging module (2) is used for triggering the image information in the combined cache library to image according to a preset imaging rule to obtain a two-dimensional plane image, and comprises the steps of matching pixel values of two adjacent columns recorded in the cache library to obtain similarity, deleting similar contents according to a preset deleting rule when the similarity is larger than a preset threshold value, combining the residual pixel values in the cache library according to time sequence to obtain the two-dimensional plane image, generating a road section unique code identifier for the two-dimensional plane image, and acquiring address information recorded by a frame stream picture through the road section unique code identifier;
The image processing module (3) is used for extracting, calculating and processing the two-dimensional plan to obtain a marked line rectangular image;
and the image judging module (4) is used for judging whether the marked line rectangular image is qualified according to a preset judging rule, and if the marked line rectangular image is unqualified, reserving the unique code mark of the road section into the database.
8. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program capable of being loaded by the processor and performing the intelligent road maintenance marking quality inspection method of any one of claims 1 to 6.
9. A computer readable storage medium storing a computer program loadable by a processor and performing the intelligent road maintenance marking quality detection method of any one of claims 1 to 6.
CN202111562375.3A 2021-12-20 2021-12-20 Intelligent highway maintenance marking quality detection method, system and electronic equipment Active CN114219796B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111562375.3A CN114219796B (en) 2021-12-20 2021-12-20 Intelligent highway maintenance marking quality detection method, system and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111562375.3A CN114219796B (en) 2021-12-20 2021-12-20 Intelligent highway maintenance marking quality detection method, system and electronic equipment

Publications (2)

Publication Number Publication Date
CN114219796A CN114219796A (en) 2022-03-22
CN114219796B true CN114219796B (en) 2025-03-18

Family

ID=80704325

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111562375.3A Active CN114219796B (en) 2021-12-20 2021-12-20 Intelligent highway maintenance marking quality detection method, system and electronic equipment

Country Status (1)

Country Link
CN (1) CN114219796B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104021574A (en) * 2014-07-04 2014-09-03 武汉武大卓越科技有限责任公司 Method for automatically identifying pavement diseases
CN110021167A (en) * 2019-04-09 2019-07-16 杭州路灵信息技术有限公司 A kind of highway cloud inspection system and data processing method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103778786B (en) * 2013-12-17 2016-04-27 东莞中国科学院云计算产业技术创新与育成中心 A kind of break in traffic rules and regulations detection method based on remarkable vehicle part model
CN110373979B (en) * 2019-07-09 2021-08-20 中铁大桥科学研究院有限公司 Road quality detection device and detection method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104021574A (en) * 2014-07-04 2014-09-03 武汉武大卓越科技有限责任公司 Method for automatically identifying pavement diseases
CN110021167A (en) * 2019-04-09 2019-07-16 杭州路灵信息技术有限公司 A kind of highway cloud inspection system and data processing method

Also Published As

Publication number Publication date
CN114219796A (en) 2022-03-22

Similar Documents

Publication Publication Date Title
US20210319561A1 (en) Image segmentation method and system for pavement disease based on deep learning
JP6259928B2 (en) Lane data processing method, apparatus, storage medium and equipment
US10212397B2 (en) Abandoned object detection apparatus and method and system
CN114677554A (en) Statistical filtering infrared small target detection tracking method based on YOLOv5 and Deepsort
CN110298300B (en) Method for detecting vehicle illegal line pressing
CN103093201B (en) Vehicle-logo location recognition methods and system
CN101770583B (en) Template matching method based on global features of scene
CN105678213B (en) Dual-mode mask person event automatic detection method based on video feature statistics
CN109871792B (en) Pedestrian detection method and device
CN101114337A (en) A method for identifying and locating buildings on the ground
CN111191482B (en) Brake lamp identification method and device and electronic equipment
CN116152219B (en) Concrete component damage detection and assessment method and system
JP2025511271A (en) IMAGE PROCESSING METHOD, APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
CN114998317A (en) Lens occlusion detection method and device, camera device and storage medium
CN115410174B (en) A two-stage auto insurance anti-fraud image acquisition quality inspection method, device and system
JP7264428B2 (en) Road sign recognition device and its program
CN109101874B (en) Library robot obstacle identification method based on depth image
CN111062415B (en) Object image extraction method, system and storage medium based on contrast difference
CN113256683B (en) Target tracking method and related equipment
CN114219796B (en) Intelligent highway maintenance marking quality detection method, system and electronic equipment
CN113469179B (en) Image recognition method, device, electronic device and storage medium
CN113657264A (en) Forest fire smoke root node detection method based on fusion of dark channel and KNN algorithm
CN109784229B (en) A Composite Recognition Method of Ground Building Data Fusion
Michael et al. Fast change detection for camera-based surveillance systems
Balcilar et al. Extracting vehicle density from background estimation using Kalman filter

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