CN112597829A - Method, device and equipment for detecting faults of traffic guidance screen - Google Patents
Method, device and equipment for detecting faults of traffic guidance screen Download PDFInfo
- Publication number
- CN112597829A CN112597829A CN202011447753.9A CN202011447753A CN112597829A CN 112597829 A CN112597829 A CN 112597829A CN 202011447753 A CN202011447753 A CN 202011447753A CN 112597829 A CN112597829 A CN 112597829A
- Authority
- CN
- China
- Prior art keywords
- image
- display
- detection
- guidance screen
- traffic guidance
- 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
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000001514 detection method Methods 0.000 claims abstract description 215
- 238000004458 analytical method Methods 0.000 claims abstract description 30
- 238000009826 distribution Methods 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 39
- 238000012423 maintenance Methods 0.000 claims description 28
- 238000012937 correction Methods 0.000 claims description 22
- 238000013135 deep learning Methods 0.000 claims description 22
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 11
- 230000003068 static effect Effects 0.000 claims description 10
- 230000001939 inductive effect Effects 0.000 claims description 8
- 239000007787 solid Substances 0.000 claims description 3
- 230000006698 induction Effects 0.000 abstract description 16
- 238000010586 diagram Methods 0.000 description 21
- 238000012544 monitoring process Methods 0.000 description 12
- 238000000605 extraction Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000003860 storage Methods 0.000 description 7
- 239000003086 colorant Substances 0.000 description 6
- 230000007547 defect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004020 luminiscence type Methods 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 125000001475 halogen functional group Chemical group 0.000 description 2
- 230000036244 malformation Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- ORFSSYGWXNGVFB-UHFFFAOYSA-N sodium 4-amino-6-[[4-[4-[(8-amino-1-hydroxy-5,7-disulfonaphthalen-2-yl)diazenyl]-3-methoxyphenyl]-2-methoxyphenyl]diazenyl]-5-hydroxynaphthalene-1,3-disulfonic acid Chemical compound COC1=C(C=CC(=C1)C2=CC(=C(C=C2)N=NC3=C(C4=C(C=C3)C(=CC(=C4N)S(=O)(=O)O)S(=O)(=O)O)O)OC)N=NC5=C(C6=C(C=C5)C(=CC(=C6N)S(=O)(=O)O)S(=O)(=O)O)O.[Na+] ORFSSYGWXNGVFB-UHFFFAOYSA-N 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000011418 maintenance treatment Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention provides a method, a device and equipment for detecting faults of a traffic guidance screen, wherein the method comprises the following steps: acquiring predefined image detection data and sending the predefined image detection data to a traffic guidance screen for displaying; sending an image intercepting instruction to a camera device, and acquiring a display image intercepted by the camera device in the process of displaying the image detection data on the traffic guidance screen; extracting a first image characteristic of the display image and a second image characteristic of the detection image at the same display moment as the display image; and analyzing and comparing the first image characteristic and the second image characteristic, and determining whether the traffic guidance screen has a fault according to an analysis result. By utilizing the method disclosed by the invention, the consistency of the display image and the detection image is contrastively analyzed, so that the detection of various common faults of the induction screen can be realized.
Description
Technical Field
The invention relates to the field of video analysis, in particular to a method, a device and equipment for detecting a traffic guidance screen fault.
Background
The traffic guidance screen provides the road trend ahead for the driver in a graphic mode of presenting the overall road route outline, and has the function of a guidepost; the LED variable light band is embedded in the road section identification area of the static figure, the real-time road condition of the road section is visually identified by the light emission of different colors of the LED, for example, the road section is unblocked by green identification, the road section is blocked by red identification and crowded by orange identification, so that a driver can judge and select a proper driving route, and the traffic guidance effect is achieved. At present, a large number of traffic guidance screens are built in traffic projects, efficient travel of citizens is guided, and an important role is played in building a good traffic order.
However, since the traffic guidance screen device is disposed outdoors, various failures are liable to occur, and the following are common failures: (1) inducing abnormal screen luminescence; (2) inducing a screen to be patterned; (3) the induction screen is attacked by external illegal attacks, and illegal characters or video contents are displayed. The fault of the traffic guidance screen brings inconvenience to the trip and produces adverse social influence.
The current traffic guidance screen fault detection method comprises the following steps: (1) the voltage and current of the module are detected by using the external equipment, and whether the module is normal or not is judged. The method can quickly realize the monitoring of the module state, but only can monitor whether the display of the equipment is normal or not, and has the defect of single detection item. (2) And identifying the content of the induction screen by using the snapshot video. However, the method can only identify text content, cannot identify images, has the defects of high requirements on detection technology, low accuracy and the like, and cannot effectively land on actual projects.
Disclosure of Invention
The invention provides a method, a device and equipment for detecting faults of a traffic guidance screen, and solves the problems of single detection item and low accuracy in the existing fault detection scheme of the traffic guidance screen.
In a first aspect, the present invention provides a method for detecting a failure of a traffic guidance screen, the method comprising:
acquiring predefined image detection data and sending the predefined image detection data to a traffic guidance screen for displaying;
sending an image intercepting instruction to a camera device, and acquiring a display image intercepted by the camera device in the process of displaying the image detection data on the traffic guidance screen;
extracting a first image characteristic of the display image and a second image characteristic of the detection image at the same display moment as the display image;
and analyzing and comparing the first image characteristic and the second image characteristic, and determining whether the traffic guidance screen has a fault according to an analysis result.
Optionally, extracting a second image feature of the detected image at the same display time as the display image specifically includes:
and displaying the image detection data, intercepting a detection image at the same display time as the display image in the display process, and extracting a second image feature of the detection image.
Optionally, the method further comprises:
and determining that the traffic guidance screen has a fault, and sending fault information to an operation and maintenance platform for maintenance, wherein the fault information comprises the detection image, the display image and a fault detection result.
Optionally, determining that the predefined image detection data is a pure color image of a single color, extracting a first image feature of the display image and a second image feature of the detection image at the same display time as the display image, includes:
processing the display image to obtain a first color distribution histogram;
and processing the pure color image of the single color to obtain a second color distribution histogram.
Optionally, analyzing and comparing the first image feature and the second image feature, and determining whether the traffic guidance screen is faulty according to an analysis result, including:
determining that the similarity of the first color distribution histogram and the second color distribution histogram is greater than a first preset threshold value, and determining that the traffic guidance screen normally emits light;
otherwise, determining that the traffic guidance screen has a fault of abnormal light emission.
Optionally, analyzing and comparing the first image feature and the second image feature, and determining whether the traffic guidance screen is faulty according to an analysis result, including:
comparing first image features of each frame of the display image with second image features of a corresponding frame of the detection image, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that the similarity of the detected image and one frame of the detected image is greater than a second preset threshold value, and determining that the display content of the traffic guidance screen is legal, otherwise, determining that the traffic guidance screen has a fault that the display content is illegal.
Optionally, analyzing and comparing the first image feature and the second image feature, and determining whether the traffic guidance screen is faulty according to an analysis result, including:
respectively carrying out gridding processing on the display image and the detection image;
comparing first image features of the grid images in each frame of display image with second image features of corresponding grid images in the detection image of the corresponding frame respectively, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that at least one frame of grid image exceeding a set proportion exists in the display image, the similarity of the grid image and the grid image of one frame of detection image is greater than a third preset threshold value, determining that the traffic guidance screen has no screen-splash fault, and otherwise, determining that the traffic guidance screen has the screen-splash fault.
Optionally, before extracting the first image feature of the display image, the method further includes:
performing deformity correction on the display image according to the set size of the corrected image and the pre-established image coordinate corresponding relation between the display image and the corrected image; and/or
And identifying and filtering a blurred image with the definition smaller than a set threshold value and a shielding image with a shielding area in the display image through an AI deep learning algorithm, removing noise in the filtered display image, and adjusting the brightness and the contrast of the display image.
Optionally, intercepting a detection image at the same display time as the display image in the display process includes:
when the image detection data is determined to be a static image, intercepting a detection image in the display process;
and when the image detection data is determined to be the dynamic video, intercepting a plurality of detection images according to frames in the display process.
In a second aspect, the present invention provides an apparatus for traffic-inducing screen fault detection, comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor is used for reading the program in the memory and executing the following steps:
acquiring predefined image detection data and sending the predefined image detection data to a traffic guidance screen for displaying;
sending an image intercepting instruction to a camera device, and acquiring a display image intercepted by the camera device in the process of displaying the image detection data on the traffic guidance screen;
extracting a first image characteristic of the display image and a second image characteristic of the detection image at the same display moment as the display image;
and analyzing and comparing the first image characteristic and the second image characteristic, and determining whether the traffic guidance screen has a fault according to an analysis result.
Optionally, the extracting, by the processor, a second image feature of the detected image at the same display time as the display image specifically includes:
and displaying the image detection data, intercepting a detection image at the same display time as the display image in the display process, and extracting a second image feature of the detection image.
Optionally, the processor is further configured to:
and determining that the traffic guidance screen has a fault, and sending fault information to an operation and maintenance platform for maintenance, wherein the fault information comprises the detection image, the display image and a fault detection result.
Optionally, the determining, by the processor, that the predefined image detection data is a pure color image of a single color, extracting a first image feature of the display image and a second image feature of the detection image at the same display time as the display image, includes:
processing the display image to obtain a first color distribution histogram;
and processing the pure color image of the single color to obtain a second color distribution histogram.
Optionally, the analyzing and comparing the first image feature and the second image feature by the processor, and determining whether the traffic guidance screen is faulty according to the analysis result, including:
determining that the similarity of the first color distribution histogram and the second color distribution histogram is greater than a first preset threshold value, and determining that the traffic guidance screen normally emits light;
otherwise, determining that the traffic guidance screen has a fault of abnormal light emission.
Optionally, the analyzing and comparing the first image feature and the second image feature by the processor, and determining whether the traffic guidance screen is faulty according to the analysis result, including:
comparing first image features of each frame of the display image with second image features of a corresponding frame of the detection image, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that the similarity of the detected image and one frame of the detected image is greater than a second preset threshold value, and determining that the display content of the traffic guidance screen is legal, otherwise, determining that the traffic guidance screen has a fault that the display content is illegal.
Optionally, the analyzing and comparing the first image feature and the second image feature by the processor, and determining whether the traffic guidance screen is faulty according to the analysis result, including:
respectively carrying out gridding processing on the display image and the detection image;
comparing first image features of the grid images in each frame of display image with second image features of corresponding grid images in the detection image of the corresponding frame respectively, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that at least one frame of grid image exceeding a set proportion exists in the display image, the similarity of the grid image and the grid image of one frame of detection image is greater than a third preset threshold value, determining that the traffic guidance screen has no screen-splash fault, and otherwise, determining that the traffic guidance screen has the screen-splash fault.
Optionally, before extracting the first image feature of the display image, the processor is further configured to:
performing deformity correction on the display image according to the set size of the corrected image and the pre-established image coordinate corresponding relation between the display image and the corrected image; and/or
And identifying and filtering a blurred image with the definition smaller than a set threshold value and a shielding image with a shielding area in the display image through an AI deep learning algorithm, removing noise in the filtered display image, and adjusting the brightness and the contrast of the display image.
Optionally, the intercepting, by the processor, a detection image at the same display time as the display image in a display process includes:
when the image detection data is determined to be a static image, intercepting a detection image in the display process;
and when the image detection data is determined to be the dynamic video, intercepting a plurality of detection images according to frames in the display process.
In a third aspect, the present invention provides a device of a method for detecting a fault of a traffic guidance screen, including:
the data acquisition unit is used for acquiring predefined image detection data and sending the predefined image detection data to the traffic guidance screen for displaying;
the image intercepting unit is used for sending an image intercepting instruction to the camera equipment and acquiring a display image intercepted by the camera equipment in the process of displaying the image detection data on the traffic guidance screen;
the characteristic extraction unit is used for extracting a first image characteristic of the display image and a second image characteristic of the detection image at the same display moment as the display image;
and the fault detection unit is used for analyzing and comparing the first image characteristic and the second image characteristic and determining whether the traffic guidance screen has a fault according to an analysis result.
Optionally, the extracting the second image feature of the detection image at the same display time as the display image by the feature extracting unit specifically includes:
and displaying the image detection data, intercepting a detection image at the same display time as the display image in the display process, and extracting a second image feature of the detection image.
Optionally, the fault detection unit is further configured to:
and determining that the traffic guidance screen has a fault, and sending fault information to an operation and maintenance platform for maintenance, wherein the fault information comprises the detection image, the display image and a fault detection result.
Optionally, the determining, by the feature extraction unit, that the predefined image detection data is a pure-color image of a single color, extracting a first image feature of the display image and a second image feature of the detection image at the same display time as the display image, includes:
processing the display image to obtain a first color distribution histogram;
and processing the pure color image of the single color to obtain a second color distribution histogram.
Optionally, the analyzing and comparing the first image feature and the second image feature by the fault detecting unit, and determining whether the traffic guidance screen is faulty according to an analysis result, including:
determining that the similarity of the first color distribution histogram and the second color distribution histogram is greater than a first preset threshold value, and determining that the traffic guidance screen normally emits light;
otherwise, determining that the traffic guidance screen has a fault of abnormal light emission.
Optionally, the analyzing and comparing the first image feature and the second image feature by the fault detecting unit, and determining whether the traffic guidance screen is faulty according to an analysis result, including:
comparing first image features of each frame of the display image with second image features of a corresponding frame of the detection image, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that the similarity of the detected image and one frame of the detected image is greater than a second preset threshold value, and determining that the display content of the traffic guidance screen is legal, otherwise, determining that the traffic guidance screen has a fault that the display content is illegal.
Optionally, the analyzing and comparing the first image feature and the second image feature by the fault detecting unit, and determining whether the traffic guidance screen is faulty according to an analysis result, including:
respectively carrying out gridding processing on the display image and the detection image;
comparing first image features of the grid images in each frame of display image with second image features of corresponding grid images in the detection image of the corresponding frame respectively, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that at least one frame of grid image exceeding a set proportion exists in the display image, the similarity of the grid image and the grid image of one frame of detection image is greater than a third preset threshold value, determining that the traffic guidance screen has no screen-splash fault, and otherwise, determining that the traffic guidance screen has the screen-splash fault.
Optionally, before the feature extraction unit extracts the first image feature of the display image, the feature extraction unit is further configured to:
performing deformity correction on the display image according to the set size of the corrected image and the pre-established image coordinate corresponding relation between the display image and the corrected image; and/or
And identifying and filtering a blurred image with the definition smaller than a set threshold value and a shielding image with a shielding area in the display image through an AI deep learning algorithm, removing noise in the filtered display image, and adjusting the brightness and the contrast of the display image.
Optionally, the image capturing unit captures a detection image at the same display time as the display image in the display process, and includes:
when the image detection data is determined to be a static image, intercepting a detection image in the display process;
and when the image detection data is determined to be the dynamic video, intercepting a plurality of detection images according to frames in the display process.
In a fourth aspect, the present invention provides a computer program medium having a computer program stored thereon, which when executed by a processor, performs the steps of a method of traffic-inducing screen fault detection as provided in the first aspect above.
The method, the device and the equipment for detecting the faults of the traffic guidance screen have the following beneficial effects that:
through the similarity of the display image and the detection image of contrast traffic guidance screen display, need not discern the concrete content that traffic guidance screen displayed, just can realize the detection to the multiple trouble of traffic guidance screen, above-mentioned multiple trouble includes: abnormal lighting of the induction screen, screen splash, illegal display content and the like.
Drawings
Fig. 1 is a schematic view of a display content of a traffic guidance screen according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a system for detecting a failure of a traffic guidance screen according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for detecting a failure of a traffic guidance screen according to an embodiment of the present invention;
FIG. 4 is a schematic view of a deformity correction provided by an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating the principles of deformity correction according to embodiments of the present invention;
fig. 6 is a schematic diagram illustrating a method for determining whether a traffic guidance screen has a fault that the displayed content is illegal according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a method for determining whether a traffic guidance screen has a screen-splash fault according to an embodiment of the present invention;
fig. 8 is a flowchart of detecting abnormal light emitting faults of a traffic guidance screen according to an embodiment of the present invention;
fig. 9 is a flowchart of detecting an illegal failure of the display content of the traffic guidance screen according to an embodiment of the present invention;
fig. 10 is a device for detecting a failure of a traffic guidance screen according to an embodiment of the present invention;
fig. 11 is a schematic diagram of a device for detecting a failure of a traffic guidance screen according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The traffic guidance screen provides the road trend ahead for the driver in a graphic mode of presenting the overall road route outline, and has the function of a guidepost; the LED variable light band is embedded in the road section identification area of the static figure, the real-time road condition of the road section is visually identified by the light emission of different colors of the LED, for example, the road section is unblocked by green identification, the road section is blocked by red identification and crowded by orange identification, so that a driver can judge and select a proper driving route, and the traffic guidance effect is achieved.
At present, a large number of traffic guidance screens are built in traffic projects, efficient travel of citizens is guided, and an important role is played in building a good traffic order.
However, since the traffic guidance screen device is disposed outdoors, various failures are liable to occur, and the following are common failures:
(1) inducing screen lighting anomalies, wherein the lighting anomalies comprise: incomplete displayed characters and contents caused by non-luminescence of the induction screen, partial luminescence of the induction screen and insufficient luminosity of the induction screen;
(3) inducing a screen to be patterned;
(4) the induction screen is attacked by external illegal attacks, and illegal characters or video contents are displayed.
The fault of the traffic guidance screen brings inconvenience to the trip and produces adverse social influence.
The current common traffic guidance screen fault detection method comprises the following steps:
(1) and detecting the voltage and current of the module of the traffic guidance screen by using the external equipment to judge whether the module is normal or not.
The method can quickly realize the monitoring of the module state of the traffic guidance screen, but only can monitor whether the equipment display is normal, and has the defect of single detection item.
(2) And identifying the content of the induction screen by using the snapshot video.
The method can only identify the text content, cannot identify the image, has the defects of high detection technical requirement, low accuracy and the like, and cannot effectively land on the ground in actual projects.
As shown in fig. 1, an embodiment of the invention provides a schematic view of a display content of a traffic guidance screen. Fig. 1 is a schematic diagram of a display content of a pure text and a schematic diagram of a display content of a combination of a text and a pattern from top to bottom. The scheme for identifying the content of the guidance screen by snapping the video can only detect the traffic guidance screen displaying the pure text content and cannot detect the traffic guidance screen displaying the content containing the image.
In view of the above problems, embodiments of the present application provide a method, an apparatus, and a device for detecting a traffic guidance screen fault, which can detect multiple common faults of a guidance screen by comparing and analyzing similarities between a display image and a detection image.
Embodiments of a method, an apparatus, and a device for detecting a traffic guidance screen fault according to embodiments of the present invention are given below.
Example 1
The embodiment of the present invention provides a schematic diagram of a system for detecting a fault of a traffic guidance screen, as shown in fig. 2, including:
the server 201 is used for acquiring predefined image detection data and sending the predefined image detection data to the traffic guidance screen for displaying; sending an image intercepting instruction to a camera device, and acquiring a display image intercepted by the camera device in the process of displaying the image detection data on the traffic guidance screen; extracting a first image characteristic of the display image and a second image characteristic of the detection image at the same display moment as the display image; analyzing and comparing the first image characteristic and the second image characteristic, and determining whether the traffic guidance screen has a fault according to an analysis result; determining that the traffic guidance screen has a fault, and sending fault information to an operation and maintenance platform for maintenance, wherein the fault information comprises the detection image, the display image and a fault detection result;
a traffic guidance screen 202, configured to receive image detection data sent by the server and display the image detection data;
the camera device 203 is configured to receive an image capturing instruction sent by the server, and capture a display image in the process of displaying the image detection data on the traffic guidance screen according to the image capturing instruction;
the camera equipment is the existing traffic monitoring equipment; and/or
And the simple camera equipment is arranged on the front surface or the side surface of the traffic guidance screen.
The existing traffic monitoring equipment comprises intersection monitoring, high point monitoring and the like.
In fig. 2, 203-a is a schematic diagram of a simple camera device installed on the front surface of the traffic guidance screen, and 203-b is a schematic diagram of a simple camera device installed on the side surface of the traffic guidance screen.
In specific implementation, the camera device can be selected according to the actual situation of the traffic guidance screen needing to be detected.
For example, the traffic guidance screen to be detected is in the camera shooting range of the existing traffic monitoring equipment, and the requirements of the captured image meet the standard, then the existing traffic monitoring equipment can be directly utilized; if the existing traffic monitoring equipment does not exist around the traffic guidance screen needing to be detected, or the image intercepted by the existing traffic monitoring equipment does not meet the requirement, or in order to ensure the accuracy, under the condition that the existing traffic equipment is available, the simple camera equipment is installed on the front side or the side surface of the traffic guidance screen.
The camera equipment is selected according to specific implementation conditions, the existing traffic monitoring equipment can be fully utilized, the detection cost is reduced, and the modification cost is greatly reduced.
It should be noted that, no matter the existing traffic monitoring equipment or the simple camera equipment installed on the front or side of the traffic guidance screen, the standard of the display image intercepted by the simple camera equipment is required to be consistent, specifically: the display image is an image with a shooting angle smaller than a preset angle and resolution reaching a preset standard.
In practical implementation, the preset angle and the preset standard may be set according to specific situations, for example, the preset angle is set to 30 degrees, and the preset standard is 640 times 480.
The operation and maintenance platform 204 is used for receiving the fault information sent by the server and performing maintenance processing according to the fault information;
it should be noted that the operation and maintenance platform may be deployed at a cloud, a server, a PC, or a mobile terminal, and related users may log in the operation and maintenance platform through a web page, PC software, or mobile software, check the fault information, and perform subsequent maintenance processing.
Or the server notifies the fault information to the operation and maintenance platform through telephone, short message, mail, notification message and other modes.
The following describes a method for detecting a traffic guidance screen fault by the server with reference to a flowchart.
The embodiment of the invention provides a flow chart of a method for detecting a fault of a traffic guidance screen, which comprises the following steps as shown in fig. 3:
step S301, obtaining predefined image detection data and sending the predefined image detection data to a traffic guidance screen for displaying;
it should be noted that the image detection data is defined in advance according to the type of the specific detection failure:
(1) when the fault type is the abnormal light emission of the induction screen, determining that the image detection data is a pure-color image with a single color;
the solid image includes at least one of: a pure white image; a pure black image; a pure red image; a pure yellow image; a pure blue image.
Common faults of the traffic induction screen include that the traffic induction screen cannot emit light, only can display white light, and cannot display colored light. Wherein, the pure white image has the best effect for detecting the fault condition that the light cannot be emitted, the pure black image has the best effect for detecting the fault condition that the light can only be displayed, and the pure red image; a pure yellow image; the three primary colors of the pure blue image can comprehensively detect the fault condition that the colored light cannot be displayed.
In specific implementation, any one or more of the pure color images can be selected for detection according to specific functions of the traffic guidance screen, and other colors such as orange color can also be selected for detection.
(2) And when the fault type is screen splash or the display content is illegal, determining that the image detection data is a static picture or a dynamic video.
It should be noted that, in the embodiment of the present invention, the still picture is a still picture, and any changed picture, such as a moving picture or multiple still pictures displayed by switching, belongs to the scope of a dynamic video.
The still picture and the moving video may be still pictures and moving videos containing only text or images, or still pictures and moving videos containing text and images.
In the specific implementation, the specific setting of the above type can be performed according to the specific implementation.
It should be noted that, when detecting a fault of the traffic guidance screen, only one fault type may be detected, and multiple fault types may also be detected. When detecting various fault types, for example, detecting abnormal lighting of the induction screen, illegal screen splash and display content, acquiring various predefined image detection data, and sending the data to the traffic induction screen so as to display the traffic induction screen in sequence.
Step S302, sending an image intercepting instruction to a camera device, and acquiring a display image intercepted by the camera device in the process of displaying the image detection data on the traffic guidance screen;
in specific implementation, the image capturing instruction includes a capturing time requirement, which may be set according to specific situations, where the capturing time is immediately captured when the image capturing instruction is received, or is set to be captured after a certain time interval after the image capturing instruction is received, or is set to be captured at a specific time, for example, the beijing time 10-point capturing.
Considering the influence of the surrounding environment of the traffic guidance screen, such as factors of sunlight reflection, object shielding, air quality and the like, when the displayed image is intercepted, a plurality of images are intercepted so as to be subsequently subjected to optimized screening, and the accuracy of fault detection is ensured.
Step S303, extracting a first image characteristic of the display image and a second image characteristic of the detection image at the same display time as the display image;
embodiment 1: determining whether the traffic guidance screen has a fault of abnormal light emission;
processing the display image to obtain a first color distribution histogram;
and processing the pure color image of the single color to obtain a second color distribution histogram.
The color distribution histogram describes the number characteristics of colors in the image, can reflect the statistical distribution and basic tone of the image colors, and can intuitively acquire the lighting condition of the traffic guidance screen by comparing the first color distribution histogram with the second color distribution histogram.
Embodiment 2: determining whether the traffic guidance screen has a fault that the displayed content is illegal or the screen is blurred;
and extracting the first image characteristic and the second image characteristic through a convolution algorithm of deep learning.
The convolution algorithm of the deep learning is obtained by training a training sample set in advance, and the extraction of image features can be realized.
Extracting a second image feature of the detection image at the same display time as the display image, specifically comprising:
and displaying the image detection data, intercepting a detection image at the same display time as the display image in the display process, and extracting a second image feature of the detection image.
It should be noted that, when the image detection data is determined to be a static image, a detection image is captured in the display process;
and when the image detection data is determined to be the dynamic video, intercepting a plurality of detection images according to frames in the display process.
The tag of the image detection data is actually a still picture or a moving picture.
The same display time as the display image can be realized in various ways, for example:
(1) intercepting the image immediately when the image intercepting instruction comprises intercepting time requirements, wherein the intercepting time requirements are that the image intercepting instruction is received, and intercepting one or more detection images in real time according to frames when the instruction is sent;
(2) intercepting the image at a certain time interval after the image interception instruction is received or at a specific moment, and intercepting one or more detection images at the appointed moment according to frames, wherein the time requirement of interception included in the image interception instruction is that the interception is carried out after the certain time interval after the image interception instruction is received;
(3) and intercepting the detection images of the whole frame number or the set proportion frame number or the set frame number, and including the detection images with the same display time as the display images in the intercepted images.
In order to reduce the influence of the ambient environment on the fault detection result, before extracting the first image feature of the display image, the method further includes:
performing deformity correction on the display image according to the set size of the corrected image and the pre-established image coordinate corresponding relation between the display image and the corrected image; and/or
And identifying and filtering a blurred image with the definition smaller than a set threshold value and a shielding image with a shielding area in the display image through an AI deep learning algorithm, removing noise in the filtered display image, and adjusting the brightness and the contrast of the display image.
It should be noted that, because the installation position of the image pickup apparatus is difficult to ensure to be directly opposite to the induction screen, the photographed image inevitably has a malformation phenomenon, and a malformation correction is required.
As shown in fig. 4, the present embodiment provides a schematic view of deformity correction.
According to the camera mounted position difference, common deformity is corrected and is from last to down in proper order: upper and lower deformity correction, left and right deformity correction, irregular deformity correction. The left side of the arrow is a deformed image before correction, and the right side of the arrow is a corrected image.
As shown in fig. 5, the embodiment of the present invention provides a schematic view of the principle of deformity correction.
As shown in fig. 5, any point in the image has a corresponding area in the image imaged by the camera, and the specific position (x, y) in the corrected image after correction can find the corresponding point (x ', y') in the display image, and after finding the corresponding point according to the pre-established image coordinate correspondence between the display image and the corrected image after correction, the corresponding point pixel in the display image is assigned to (x, y) in the corrected image after correction, so as to obtain the image after distortion correction.
Wherein, the image coordinate corresponding relation between the pre-established display image and the corrected image after correction is as follows:
where, (x1, y1) is the coordinate of the upper left corner of the display image, (x2, y2) is the coordinate of the upper right corner of the display image, (x3, y3) is the coordinate of the lower left corner of the display image, (x4, y4) is the coordinate of the lower right corner of the display image, (x ', y') is the coordinate of any point in the display image, and (x, y) is the coordinate of the point corresponding to (x ', y') in the corrected image.
Due to the influence of light and time periods, the display image has some noises, including strong light, backlight, image blurring caused by halo influence, and the like, and the display image needs to be filtered and subjected to noise processing.
(1) Image filtering:
and identifying and filtering a blurred image with the definition smaller than a set threshold value and an occlusion image with an occlusion area in the display image through an AI deep learning algorithm.
The blurred image comprises an image with the definition smaller than a set threshold value due to strong light, backlight, large halo at night and the like, and the set threshold value can be set according to specific implementation conditions; the sheltered image comprises an image sheltered by weather factors such as birds, floating objects, rain, snow, frost, haze and the like to appear in a sheltered area.
(2) Noise processing:
and removing noise in the filtered display image, and adjusting the brightness and contrast of the display image.
The method comprises the steps of processing image noise based on common methods such as median filtering, a nonlinear filter, transform domain filtering and the like of a spatial domain, and then adjusting brightness, contrast and the like to remove obvious noise influence.
And step S304, analyzing and comparing the first image characteristic and the second image characteristic, and determining whether the traffic guidance screen has a fault according to an analysis result.
The core of the invention is that whether the traffic guidance screen display is abnormal or not is judged by comparing the display image of the traffic guidance screen with the detection image, and the abnormality is represented as long as the contents of the front end and the rear end are inconsistent on the premise of accurate detection.
The specific embodiment of comparing the display image and the detection image of the traffic guidance screen includes:
embodiment 1: determining whether the traffic guidance screen has a fault of abnormal light emission;
determining that the similarity of the first color distribution histogram and the second color distribution histogram is greater than a first preset threshold value, and determining that the traffic guidance screen normally emits light;
otherwise, determining that the traffic guidance screen has a fault of abnormal light emission.
Since different scenes and different time periods can affect the detection result, the first preset threshold, the second preset threshold and the third preset threshold may be specifically defined according to specific implementation conditions, and are not described in detail.
Embodiment 2: determining whether a fault that display content is illegal occurs in the traffic guidance screen;
comparing the first image characteristics of each frame of the display image with the second image characteristics of the detection image of the corresponding frame;
determining that the similarity between the detected image and one frame of the detected image is greater than a second preset threshold value, and determining that the display content of the traffic guidance screen is legal;
otherwise, determining that the traffic guidance screen has a fault that the displayed content is illegal.
As shown in fig. 6, an embodiment of the present invention provides a schematic diagram for determining whether a traffic guidance screen has a fault that the displayed content is illegal.
Where a' k (k ═ 1, 2, 3.. n) is a first image feature of each frame of the display image, and Bm (m ═ 1, 2, 3.. n) is a second image feature of each frame of the detection image.
And comparing the A' k (k is 1, 2, 3.. n) with the Bm (m is 1, 2, 3.. n), and if the similarity of one group is greater than a second preset threshold value, the comparison is considered to be passed.
Embodiment 3: determining whether the traffic guidance screen has a screen-splash fault;
respectively carrying out gridding processing on the display image and the detection image;
comparing the first image characteristics of the grid images in each frame of display image with the second image characteristics of the corresponding grid images in the detection images of the corresponding frames respectively;
determining that at least one frame of grid image exceeding a set proportion exists in the display image, the similarity of the grid image and the grid image of one frame of detection image is greater than a third preset threshold value, and determining that the traffic guidance screen does not have the screen-blooming fault;
otherwise, determining that the traffic guidance screen has the screen-splash fault.
As shown in fig. 7, the embodiment of the present invention provides a schematic diagram for determining whether a traffic guidance screen has a screen-splash fault.
The black and white stripe area in the right image is the schematic area of the screen area.
And meshing the images, comparing each mesh image, and if the individual mesh images are not consistent, indicating that the screen is not displayed.
When any one or any more of the three embodiments is used, when the traffic guidance screen is determined to have a fault, fault information is sent to an operation and maintenance platform for maintenance, and the fault information comprises the detection image, the display image and a fault detection result.
And after receiving the fault information, the operation and maintenance platform confirms and arranges maintenance workers according to the fault information, performs maintenance treatment and completes one cycle of traffic guidance screen fault detection.
As shown in fig. 8, an embodiment of the present invention provides a flow chart of detecting a light-emitting abnormal fault of a traffic guidance screen.
In the embodiment shown in fig. 8, a pure white image and a pure black image are selected for detecting the abnormal light emitting fault of the traffic guidance screen, the above embodiment is only a specific example of the solution of the present invention, and does not specifically limit the embodiment of the present invention, and in the specific implementation, the image detection data may be predefined according to the specific implementation situation.
Step S801, acquiring predefined image detection data, and sending the predefined image detection data to a traffic guidance screen for displaying, wherein the image detection data is a pure white image;
step S802, sending an image intercepting instruction to a camera device, and acquiring a first display image intercepted by the camera device in the process of displaying the image detection data on the traffic guidance screen;
step S803, acquiring predefined image detection data, and sending the predefined image detection data to a traffic guidance screen for displaying, wherein the image detection data are pure black images;
step S804, sending an image intercepting instruction to the camera equipment, and acquiring a second display image intercepted by the camera equipment in the process of displaying the image detection data on the traffic guidance screen;
step S805, extracting a first image feature of the first display image and a second image feature of the first detection image at the same display time as the first display image; extracting a third image feature of the second display image and a fourth image feature of a second detection image at the same display time as the second display image;
processing the first display image to obtain a first color distribution histogram;
processing the pure white image to obtain a second color distribution histogram;
processing the second display image to obtain a third color distribution histogram;
processing the pure black image to obtain a fourth color distribution histogram;
step S806, analyzing and comparing the first image characteristic and the second image characteristic, analyzing and comparing the third image characteristic and the fourth image characteristic, and determining whether the traffic guidance screen has a fault according to an analysis result.
And judging whether the fault of abnormal light emission exists or not by comparing and analyzing the first color distribution histogram and the second color distribution histogram and comparing and analyzing the third color distribution histogram and the fourth color distribution histogram.
Step S807, when the traffic guidance screen is determined to have a fault, sending fault information to an operation and maintenance platform for maintenance.
As shown in fig. 9, an embodiment of the present invention provides a flow chart of detecting an illegal failure of a display content of a traffic guidance screen.
Step S901, acquiring predefined image detection data and sending the predefined image detection data to a traffic guidance screen for displaying;
step S902, sending an image capturing instruction to a camera device, and acquiring a display image captured by the camera device in the process of displaying the image detection data on the traffic guidance screen;
step S903, displaying the image detection data, and intercepting a detection image with the same display time as the display image in the display process;
and intercepting the detection image while sending the image interception instruction.
Step S904, performing a deformity correction on the display image to obtain a corrected display image;
step S905, carrying out noise processing on the corrected display image to obtain a display image after the noise processing;
step S906, extracting a first image characteristic of the display image after the noise processing and a second image characteristic of a detection image at the same display time as the display image after the noise processing;
and step S907, analyzing and comparing the first image characteristics and the second image characteristics, and determining whether the traffic guidance screen has a fault according to an analysis result.
Step S908, when it is determined that the traffic guidance screen has a fault, sending fault information to an operation and maintenance platform for maintenance.
Example 2
The embodiment of the present invention provides a device 1000 for detecting a traffic guidance screen fault, which includes a memory 1001 and a processor 1002, as shown in fig. 10, where:
the memory is used for storing a computer program;
the processor is used for reading the program in the memory and executing the following steps:
acquiring predefined image detection data and sending the predefined image detection data to a traffic guidance screen for displaying;
sending an image intercepting instruction to a camera device, and acquiring a display image intercepted by the camera device in the process of displaying the image detection data on the traffic guidance screen;
extracting a first image characteristic of the display image and a second image characteristic of the detection image at the same display moment as the display image;
and analyzing and comparing the first image characteristic and the second image characteristic, and determining whether the traffic guidance screen has a fault according to an analysis result.
Optionally, the extracting, by the processor, a second image feature of the detected image at the same display time as the display image specifically includes:
and displaying the image detection data, intercepting a detection image at the same display time as the display image in the display process, and extracting a second image feature of the detection image.
Optionally, the processor is further configured to:
and determining that the traffic guidance screen has a fault, and sending fault information to an operation and maintenance platform for maintenance, wherein the fault information comprises the detection image, the display image and a fault detection result.
Optionally, the determining, by the processor, that the predefined image detection data is a pure color image of a single color, extracting a first image feature of the display image and a second image feature of the detection image at the same display time as the display image, includes:
processing the display image to obtain a first color distribution histogram;
and processing the pure color image of the single color to obtain a second color distribution histogram.
Optionally, the analyzing and comparing the first image feature and the second image feature by the processor, and determining whether the traffic guidance screen is faulty according to the analysis result, including:
determining that the similarity of the first color distribution histogram and the second color distribution histogram is greater than a first preset threshold value, and determining that the traffic guidance screen normally emits light;
otherwise, determining that the traffic guidance screen has a fault of abnormal light emission.
Optionally, the analyzing and comparing the first image feature and the second image feature by the processor, and determining whether the traffic guidance screen is faulty according to the analysis result, including:
comparing first image features of each frame of the display image with second image features of a corresponding frame of the detection image, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that the similarity of the detected image and one frame of the detected image is greater than a second preset threshold value, and determining that the display content of the traffic guidance screen is legal, otherwise, determining that the traffic guidance screen has a fault that the display content is illegal.
Optionally, the analyzing and comparing the first image feature and the second image feature by the processor, and determining whether the traffic guidance screen is faulty according to the analysis result, including:
respectively carrying out gridding processing on the display image and the detection image;
comparing first image features of the grid images in each frame of display image with second image features of corresponding grid images in the detection image of the corresponding frame respectively, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that at least one frame of grid image exceeding a set proportion exists in the display image, the similarity of the grid image and the grid image of one frame of detection image is greater than a third preset threshold value, determining that the traffic guidance screen has no screen-splash fault, and otherwise, determining that the traffic guidance screen has the screen-splash fault.
Optionally, before extracting the first image feature of the display image, the processor is further configured to:
performing deformity correction on the display image according to the set size of the corrected image and the pre-established image coordinate corresponding relation between the display image and the corrected image; and/or
And identifying and filtering a blurred image with the definition smaller than a set threshold value and a shielding image with a shielding area in the display image through an AI deep learning algorithm, removing noise in the filtered display image, and adjusting the brightness and the contrast of the display image.
Optionally, the intercepting, by the processor, a detection image at the same display time as the display image in a display process includes:
when the image detection data is determined to be a static image, intercepting a detection image in the display process;
and when the image detection data is determined to be the dynamic video, intercepting a plurality of detection images according to frames in the display process.
The embodiment of the present invention provides a schematic diagram of a traffic guidance screen fault detection device, as shown in fig. 11, including:
the data acquisition unit 1101 is used for acquiring predefined image detection data and sending the predefined image detection data to the traffic guidance screen for displaying;
an image capturing unit 1102, configured to send an image capturing instruction to a camera device, and obtain a display image captured by the camera device in a process of displaying the image detection data on the traffic guidance screen;
a feature extraction unit 1103 configured to extract a first image feature of the display image and a second image feature of the detection image at the same display time as the display image;
and the fault detection unit 1104 is used for analyzing and comparing the first image characteristic and the second image characteristic, and determining whether the traffic guidance screen has a fault according to an analysis result.
Optionally, the extracting the second image feature of the detection image at the same display time as the display image by the feature extracting unit specifically includes:
and displaying the image detection data, intercepting a detection image at the same display time as the display image in the display process, and extracting a second image feature of the detection image.
Optionally, the fault detection unit is further configured to:
and determining that the traffic guidance screen has a fault, and sending fault information to an operation and maintenance platform for maintenance, wherein the fault information comprises the detection image, the display image and a fault detection result.
Optionally, the determining, by the feature extraction unit, that the predefined image detection data is a pure-color image of a single color, extracting a first image feature of the display image and a second image feature of the detection image at the same display time as the display image, includes:
processing the display image to obtain a first color distribution histogram;
and processing the pure color image of the single color to obtain a second color distribution histogram.
Optionally, the analyzing and comparing the first image feature and the second image feature by the fault detecting unit, and determining whether the traffic guidance screen is faulty according to an analysis result, including:
determining that the similarity of the first color distribution histogram and the second color distribution histogram is greater than a first preset threshold value, and determining that the traffic guidance screen normally emits light;
otherwise, determining that the traffic guidance screen has a fault of abnormal light emission.
Optionally, the analyzing and comparing the first image feature and the second image feature by the fault detecting unit, and determining whether the traffic guidance screen is faulty according to an analysis result, including:
comparing first image features of each frame of the display image with second image features of a corresponding frame of the detection image, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that the similarity of the detected image and one frame of the detected image is greater than a second preset threshold value, and determining that the display content of the traffic guidance screen is legal, otherwise, determining that the traffic guidance screen has a fault that the display content is illegal.
Optionally, the analyzing and comparing the first image feature and the second image feature by the fault detecting unit, and determining whether the traffic guidance screen is faulty according to an analysis result, including:
respectively carrying out gridding processing on the display image and the detection image;
comparing first image features of the grid images in each frame of display image with second image features of corresponding grid images in the detection image of the corresponding frame respectively, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that at least one frame of grid image exceeding a set proportion exists in the display image, the similarity of the grid image and the grid image of one frame of detection image is greater than a third preset threshold value, determining that the traffic guidance screen has no screen-splash fault, and otherwise, determining that the traffic guidance screen has the screen-splash fault.
Optionally, before the feature extraction unit extracts the first image feature of the display image, the feature extraction unit is further configured to:
performing deformity correction on the display image according to the set size of the corrected image and the pre-established image coordinate corresponding relation between the display image and the corrected image; and/or
And identifying and filtering a blurred image with the definition smaller than a set threshold value and a shielding image with a shielding area in the display image through an AI deep learning algorithm, removing noise in the filtered display image, and adjusting the brightness and the contrast of the display image.
Optionally, the image capturing unit captures a detection image at the same display time as the display image in the display process, and includes:
when the image detection data is determined to be a static image, intercepting a detection image in the display process;
and when the image detection data is determined to be the dynamic video, intercepting a plurality of detection images according to frames in the display process.
The present invention also provides a computer program medium having a computer program stored thereon, which when executed by a processor, implements the steps of a method of traffic guidance screen fault detection provided in embodiment 2 above.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may be stored in a computer readable storage medium.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.
The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store or a data storage device, such as a server, a data center, etc., that is integrated with one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The technical solutions provided by the present application are introduced in detail, and the present application applies specific examples to explain the principles and embodiments of the present application, and the descriptions of the above examples are only used to help understand the method and the core ideas of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (11)
1. A method of traffic-inducing screen fault detection, comprising:
acquiring predefined image detection data and sending the predefined image detection data to a traffic guidance screen for displaying;
sending an image intercepting instruction to a camera device, and acquiring a display image intercepted by the camera device in the process of displaying the image detection data on the traffic guidance screen;
extracting a first image characteristic of the display image and a second image characteristic of the detection image at the same display moment as the display image;
and analyzing and comparing the first image characteristic and the second image characteristic, and determining whether the traffic guidance screen has a fault according to an analysis result.
2. The method according to claim 1, wherein extracting a second image feature of the detected image at the same display time as the display image specifically comprises:
and displaying the image detection data, intercepting a detection image at the same display time as the display image in the display process, and extracting a second image feature of the detection image.
3. The method of claim 1, further comprising:
and determining that the traffic guidance screen has a fault, and sending fault information to an operation and maintenance platform for maintenance, wherein the fault information comprises the detection image, the display image and a fault detection result.
4. The method of claim 1, wherein determining the predefined image detection data as a solid color image of a single color, extracting a first image feature of the display image and a second image feature of a detection image at a same display time as the display image comprises:
processing the display image to obtain a first color distribution histogram;
and processing the pure color image of the single color to obtain a second color distribution histogram.
5. The method of claim 4, wherein analyzing and comparing the first image feature and the second image feature and determining whether the traffic guidance screen is faulty according to the analysis result comprises:
determining that the similarity of the first color distribution histogram and the second color distribution histogram is greater than a first preset threshold value, and determining that the traffic guidance screen normally emits light;
otherwise, determining that the traffic guidance screen has a fault of abnormal light emission.
6. The method according to any one of claims 1 to 3, wherein the analyzing and comparing the first image characteristic and the second image characteristic and determining whether the traffic guidance screen has a fault according to the analysis result comprise:
comparing first image features of each frame of the display image with second image features of a corresponding frame of the detection image, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that the similarity of the detected image and one frame of the detected image is greater than a second preset threshold value, and determining that the display content of the traffic guidance screen is legal, otherwise, determining that the traffic guidance screen has a fault that the display content is illegal.
7. The method according to any one of claims 1 to 3, wherein the analyzing and comparing the first image characteristic and the second image characteristic and determining whether the traffic guidance screen has a fault according to the analysis result comprise:
respectively carrying out gridding processing on the display image and the detection image;
comparing first image features of the grid images in each frame of display image with second image features of corresponding grid images in the detection image of the corresponding frame respectively, wherein the first image features and the second image features are extracted through a convolution algorithm of deep learning;
and determining that at least one frame of grid image exceeding a set proportion exists in the display image, the similarity of the grid image and the grid image of one frame of detection image is greater than a third preset threshold value, determining that the traffic guidance screen has no screen-splash fault, and otherwise, determining that the traffic guidance screen has the screen-splash fault.
8. The method of claim 1, wherein prior to extracting the first image feature of the display image, further comprising:
performing deformity correction on the display image according to the set size of the corrected image and the pre-established image coordinate corresponding relation between the display image and the corrected image; and/or
And identifying and filtering a blurred image with the definition smaller than a set threshold value and a shielding image with a shielding area in the display image through an AI deep learning algorithm, removing noise in the filtered display image, and adjusting the brightness and the contrast of the display image.
9. The method of claim 2, wherein intercepting the detection image during display at the same display time as the display image comprises:
when the image detection data is determined to be a static image, intercepting a detection image in the display process;
and when the image detection data is determined to be the dynamic video, intercepting a plurality of detection images according to frames in the display process.
10. An apparatus for traffic-inducing screen fault detection, comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor is used for reading the program in the memory and executing the method for detecting the fault of the traffic guidance screen as claimed in any one of claims 1 to 9.
11. A computer program medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of traffic guidance screen fault detection according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011447753.9A CN112597829A (en) | 2020-12-09 | 2020-12-09 | Method, device and equipment for detecting faults of traffic guidance screen |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011447753.9A CN112597829A (en) | 2020-12-09 | 2020-12-09 | Method, device and equipment for detecting faults of traffic guidance screen |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112597829A true CN112597829A (en) | 2021-04-02 |
Family
ID=75191900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011447753.9A Pending CN112597829A (en) | 2020-12-09 | 2020-12-09 | Method, device and equipment for detecting faults of traffic guidance screen |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112597829A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203644221U (en) * | 2013-11-06 | 2014-06-11 | 深圳市凯达尔科技实业有限公司 | Parking guidance management system with monitoring camera shooting |
| CN105424710A (en) * | 2015-11-20 | 2016-03-23 | 上海斐讯数据通信技术有限公司 | Method and device for detecting screen of electronic equipment |
| CN107749055A (en) * | 2017-09-20 | 2018-03-02 | 广东方纬科技有限公司 | A kind of fault detection method, system and the device of LED traffic guidances screen |
| CN108831179A (en) * | 2018-06-27 | 2018-11-16 | 深圳市凯达尔科技实业有限公司 | Traffic guidance screen monitoring method, system |
| CN110046592A (en) * | 2019-04-22 | 2019-07-23 | 北京志远鸿通科技有限公司 | A kind of traffic guidance screen monitoring method |
| CN111353419A (en) * | 2020-02-26 | 2020-06-30 | 北京百度网讯科技有限公司 | Image comparison method and device, electronic equipment and storage medium |
-
2020
- 2020-12-09 CN CN202011447753.9A patent/CN112597829A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203644221U (en) * | 2013-11-06 | 2014-06-11 | 深圳市凯达尔科技实业有限公司 | Parking guidance management system with monitoring camera shooting |
| CN105424710A (en) * | 2015-11-20 | 2016-03-23 | 上海斐讯数据通信技术有限公司 | Method and device for detecting screen of electronic equipment |
| CN107749055A (en) * | 2017-09-20 | 2018-03-02 | 广东方纬科技有限公司 | A kind of fault detection method, system and the device of LED traffic guidances screen |
| CN108831179A (en) * | 2018-06-27 | 2018-11-16 | 深圳市凯达尔科技实业有限公司 | Traffic guidance screen monitoring method, system |
| CN110046592A (en) * | 2019-04-22 | 2019-07-23 | 北京志远鸿通科技有限公司 | A kind of traffic guidance screen monitoring method |
| CN111353419A (en) * | 2020-02-26 | 2020-06-30 | 北京百度网讯科技有限公司 | Image comparison method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102348128B (en) | Surveillance camera system having camera malfunction detection function | |
| US7742650B2 (en) | Object detection in images | |
| CN108683907A (en) | Optics module picture element flaw detection method, device and equipment | |
| CN112396999B (en) | Abnormal display block detection method, display screen fault detection method and equipment thereof | |
| CN104749184A (en) | Automatic optical detection method and automatic optical detection system | |
| US20060221181A1 (en) | Video ghost detection by outline | |
| CN110781853B (en) | Crowd abnormality detection method and related device | |
| CN109166111B (en) | Electronic ink screen defect detection method and system | |
| JP2005331929A5 (en) | ||
| CN113781396B (en) | Screen defect detection method, device, equipment and storage medium | |
| CN112291551A (en) | Video quality detection method based on image processing, storage device and mobile terminal | |
| CN110399831A (en) | A kind of method for inspecting and device | |
| CN110659546A (en) | Illegal booth detection method and device | |
| CN111931726A (en) | Traffic light detection method and device, computer storage medium and road side equipment | |
| CN111127358B (en) | Image processing method, device and storage medium | |
| US8547430B2 (en) | System and method for marking discrepancies in image of object | |
| CN112364884A (en) | Method for detecting moving object | |
| CN111695374B (en) | Segmentation method, system, medium and device for zebra stripes in monitoring view angles | |
| CN112597829A (en) | Method, device and equipment for detecting faults of traffic guidance screen | |
| CN115278217A (en) | Image picture detection method and device, electronic equipment and storage medium | |
| KR100860358B1 (en) | Apparatus and method for detecting pixel error of variable message sign board | |
| CN117095389B (en) | Image data processing method and system based on liquid crystal visual recognition unit | |
| CN118115944A (en) | Smoke detection method, device, electronic equipment and computer readable storage medium | |
| CN116416238A (en) | Abnormal screen shielding detection method, device, equipment and storage medium | |
| CN117676122A (en) | Detection method and device of image acquisition device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210402 |
|
| RJ01 | Rejection of invention patent application after publication |