CN117475269A - Abnormal signal identification method and system based on video monitoring system equipment - Google Patents
Abnormal signal identification method and system based on video monitoring system equipment Download PDFInfo
- Publication number
- CN117475269A CN117475269A CN202311534109.9A CN202311534109A CN117475269A CN 117475269 A CN117475269 A CN 117475269A CN 202311534109 A CN202311534109 A CN 202311534109A CN 117475269 A CN117475269 A CN 117475269A
- Authority
- CN
- China
- Prior art keywords
- signal
- abnormal
- identification
- network
- image set
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 155
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 title claims abstract description 20
- 230000005856 abnormality Effects 0.000 claims abstract description 82
- 230000004044 response Effects 0.000 claims abstract description 35
- 238000012806 monitoring device Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 230000008859 change Effects 0.000 claims description 26
- 238000011156 evaluation Methods 0.000 claims description 23
- 238000000605 extraction Methods 0.000 claims description 21
- 230000003068 static effect Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- 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
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an abnormal signal identification method and system based on video monitoring system equipment, and relates to the technical field of data processing, wherein the method comprises the following steps: acquiring light control information of each signal device in a target area, acquiring standard signal control parameters, and constructing an abnormal signal identification network; the method comprises the steps of using a video monitoring device to acquire signal images of target signal equipment, acquiring a basic signal image set, and preprocessing to obtain an initial signal image set; and extracting features based on the initial signal image set, acquiring target signal features, carrying out abnormal signal recognition by combining an abnormal signal recognition network, acquiring an abnormal signal recognition result, and carrying out fault early warning. The signal lamp abnormality intelligent recognition method and device solve the technical problems of low signal lamp abnormality recognition accuracy and low abnormal signal response speed in the prior art, and achieve the technical effects of intelligent signal lamp abnormality recognition based on a video monitoring system and improvement of abnormal signal response speed and recognition accuracy.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an abnormal signal identification method and system based on video monitoring system equipment.
Background
The traffic signal lamp plays a vital role in daily operation of urban traffic, if the traffic signal lamp fails, the traffic signal lamp can seriously affect the fluency of road traffic, and the traffic order of intersections is destroyed, so that traffic jam is caused, even traffic accidents are caused, and therefore, the traffic signal lamp needs to be monitored and maintained in real time to ensure the normal operation of the traffic signal lamp. However, the current traffic signal abnormality identification method is low in intelligent level, so that abnormal signals are not early-warned timely, the accuracy is low, and the fault processing efficiency is affected.
Disclosure of Invention
The application provides an abnormal signal identification method and system based on video monitoring system equipment, which are used for solving the technical problems of low signal lamp abnormal identification accuracy and low abnormal signal response speed in the prior art.
In a first aspect of the present application, there is provided a method for identifying abnormal signals based on a video monitoring system device, the method comprising: collecting light control information of each signal device in a target area, wherein the light control information comprises a light color sequence and a corresponding control duration, and the light control information is provided with a time mark; collecting standard signal control parameters according to the light control information, and constructing an abnormal signal identification network by combining an abnormal signal judgment rule; acquiring signal images of target signal equipment by using a video monitoring device to acquire a basic signal image set; preprocessing the basic signal image set to obtain an initial signal image set; extracting features based on the initial signal image set to obtain target signal features; based on the target signal characteristics, combining an abnormal signal recognition network to perform abnormal signal recognition, acquiring an abnormal signal recognition result, and performing fault early warning according to the abnormal signal recognition result.
In a second aspect of the present application, there is provided an abnormal signal identification system based on a video monitoring system apparatus, the system comprising: the light control information acquisition module is used for acquiring light control information of each signal device in the target area, wherein the light control information comprises a light color sequence and a corresponding control duration, and the light control information is provided with a time mark; the abnormal signal identification network construction module is used for acquiring standard signal control parameters according to the lamplight control information and combining an abnormal signal judgment rule to construct an abnormal signal identification network; the base signal image set acquisition module is used for acquiring signal images of target signal equipment by using the video monitoring device to acquire a base signal image set; the initial signal image set acquisition module is used for preprocessing the basic signal image set to obtain an initial signal image set; the target signal feature extraction module is used for carrying out feature extraction based on the initial signal image set to obtain target signal features; the abnormal signal identification module is used for carrying out abnormal signal identification based on the target signal characteristics and combining an abnormal signal identification network, obtaining an abnormal signal identification result and carrying out fault early warning according to the abnormal signal identification result.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the abnormal signal identification method based on the video monitoring system equipment comprises the steps of acquiring light control information of each signal equipment in a target area, acquiring standard signal control parameters, constructing an abnormal signal identification network, acquiring a basic signal image set by using a video monitoring device, preprocessing to obtain an initial signal image set, acquiring target signal characteristics through characteristic extraction, carrying out abnormal signal identification by combining the abnormal signal identification network, carrying out fault early warning according to an abnormal signal identification result, solving the technical problems of low signal lamp abnormal identification accuracy and low abnormal signal response speed in the prior art, carrying out signal lamp abnormal intelligent identification by using a video monitoring system, and realizing the technical effects of improving the abnormal signal response speed and the identification accuracy.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an abnormal signal identification method based on video monitoring system equipment according to an embodiment of the present application;
fig. 2 is a schematic flow chart of obtaining an initial signal image set in an abnormal signal identification method based on video monitoring system equipment according to an embodiment of the present application;
fig. 3 is a schematic flow chart of obtaining a signal control abnormal result in an abnormal signal identification method based on video monitoring system equipment according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an abnormal signal identification system based on video monitoring system equipment according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a light control information acquisition module 11, an abnormal signal identification network construction module 12, a basic signal image set acquisition module 13, an initial signal image set acquisition module 14, a target signal characteristic extraction module 15 and an abnormal signal identification module 16.
Detailed Description
The application provides an abnormal signal identification method based on video monitoring system equipment, which is used for solving the technical problems of low signal lamp abnormal identification accuracy and low abnormal signal response speed in the prior art.
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. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides an abnormal signal identification method based on a video monitoring system device, where the method includes:
p10: collecting light control information of each signal device in a target area, wherein the light control information comprises a light color sequence and a corresponding control duration, and the light control information is provided with a time mark;
optionally, light control information of each signal device of each traffic road section in a target area is collected, the target area refers to an area to be monitored by signal lamp abnormality and can refer to any traffic jurisdiction area, the light control information comprises a light color sequence and corresponding control duration, the light color sequence comprises signal lamp color control instructions of a plurality of time nodes in preset control time, the signal lamp color control instructions are arranged according to time sequence and correspond to the control duration, the light control information is provided with a time mark, and standard control data of signal lamps of each intersection in the preset control time can be reflected.
P20: collecting standard signal control parameters according to the light control information, and constructing an abnormal signal identification network by combining an abnormal signal judgment rule;
further, step P20 in the embodiment of the present application further includes:
p21: the abnormal signal identification network comprises a control abnormal identification sub-network and a display abnormal identification sub-network;
p22: acquiring standard signal control parameters including a plurality of standard signal change parameters based on time nodes, a plurality of standard signal duration and a plurality of corresponding standard image features through the light control information;
p23: constructing a control anomaly identification sub-network based on a plurality of standard signal change parameters and a plurality of standard signal duration;
p24: constructing a display anomaly identification sub-network by combining a twin neural network through a plurality of standard image features;
p25: and connecting the control abnormality identification sub-network with the display abnormality identification sub-network to obtain the abnormality signal identification network.
It should be understood that extracting the standard signal control parameters from the light control information includes collecting a plurality of standard signal change parameters based on a time node, a plurality of standard signal duration, and a corresponding plurality of standard image features, that is, extracting the change parameters of each signal device according to time sequence, for example, the signal change parameters of a certain signal device at the time node are red light and yellow light, and continuously flashing for 3 seconds, where the standard image features include standard color, brightness, shape, and the like of the signal lamp.
Further, the multiple standard signal change parameters and the multiple standard signal duration are used as identification standards, and the control anomaly identification sub-network is built according to a preset anomaly signal judgment rule, wherein the preset anomaly signal judgment rule comprises judgment of the signal change parameters and judgment of the signal duration and can be used for evaluating whether the response speed of a signal change instruction and the accuracy of the signal duration are abnormal or not.
Further, a plurality of standard image features are used as training data, a twin neural network principle is combined, the display anomaly identification sub-network is constructed and trained, the twin neural network takes two samples as input data, and the characterization of the two samples embedded into a high-dimensional space is output to compare the similarity degree of the two samples, and the two neural networks are shared in weight. The standard image features and the real-time signal features can be respectively input into the twin neural network to perform image feature recognition, so that a standard feature recognition result and a real-time feature recognition result are obtained, and similarity between the real-time signal features and the standard image features is obtained by performing similarity calculation on the standard feature recognition result and the real-time feature recognition result, and the smaller the similarity is, the more likely that abnormality exists in the real-time signal display result is indicated. And connecting the control abnormality recognition sub-network and the display abnormality recognition sub-network to form the abnormality signal recognition network.
P30: acquiring signal images of target signal equipment by using a video monitoring device to acquire a basic signal image set;
specifically, video monitoring devices are distributed around each target signal device, and the video monitoring devices can be CCD image sensors, high-definition cameras and the like, are in communication connection with an abnormal signal monitoring center, and simulate the visual angle of a driver to adjust the angle and the height of the video monitoring devices. And acquiring the screen display images of the target signal devices in real time by adopting the video monitoring device according to a preset signal abnormality identification period, for example, 3 minutes, so as to obtain a basic signal image set.
P40: preprocessing the basic signal image set to obtain an initial signal image set;
further, as shown in fig. 2, step P40 in the embodiment of the present application further includes:
p41: reading basic information of the basic signal image set, and setting a first operator;
p42: acquiring a first central pixel point based on the basic signal image set, and combining the first operator to perform pixel mean value calculation to acquire a denoising pixel value of the first central pixel point;
p43: and by analogy, traversing the basic signal image set to perform pixel mean value calculation to obtain a plurality of denoising pixel points, and obtaining the initial signal image set.
Illustratively, the base signal image set is preprocessed, that is, noise reduction enhancement processing is performed, first, the base information of the base signal image set, including the definition of the base image, the image size, and the like, is read, and a first operator is set according to the base information, where the first operator refers to a pixel area range of single filtering, for example, a pixel grid of 5*5.
Further, for any basic signal image in the basic signal image set, selecting any pixel point from the image as a first central pixel point, carrying out mean value calculation on gray values of all pixel points in the range according to the pixel area range of the first operator to obtain a mean value calculation result, and replacing the original gray value of the first central pixel point with the mean value calculation result to serve as a denoising pixel value of the first central pixel point.
And similarly, based on the basic signal image set, traversing all pixel points of all basic signal images respectively, determining a plurality of central pixel points, calculating pixel mean values according to the first operators respectively, replacing original central pixel point gray values with obtained mean value calculation results to obtain a plurality of denoising pixel points, and further forming a plurality of low-interference signal images by the plurality of denoising pixel points to form the initial signal image set, so that the number of noise lines in the basic signal images can be reduced, and noise interference is reduced.
P50: extracting features based on the initial signal image set to obtain target signal features;
further, step P50 of the embodiment of the present application further includes:
p51: constructing a feature extraction model, wherein the feature extraction model comprises a dynamic capturing channel and a detail identifying channel;
p52: based on the initial signal image set, combining the dynamic capturing channel to obtain dynamic signal characteristics, wherein the dynamic signal characteristics comprise display duration characteristics and display color characteristics;
p53: based on the initial signal image set, combining the detail recognition channel to obtain static signal characteristics, wherein the static signal characteristics comprise brightness characteristics, color characteristics and shape characteristics;
p54: and combining the dynamic signal characteristics and the static signal characteristics to obtain the target signal characteristics.
In a possible embodiment of the present application, the target signal features are obtained by performing real-time feature extraction through the initial signal image set. Specifically, a feature extraction model is constructed according to the dynamic feature and static feature extraction requirements, the feature extraction model comprises a dynamic capturing channel and a detail identification channel, the dynamic capturing channel is used for capturing dynamic change features of signals, such as duration of a signal lamp, flicker frequency and the like, and the detail identification channel is used for identifying detail features of signal display, such as color of the signal lamp, brightness features and the like.
Further, the initial signal image sets are respectively input into the dynamic capture channel for image downsampling, dynamic signal characteristics are obtained, the dynamic signal characteristics comprise display duration characteristics and display color characteristics of the target signal equipment at all time points in a preset abnormal signal identification period, and the signal duration conditions and the signal color conditions of the target signal equipment in the preset abnormal signal identification period can be reflected. Further, the initial signal image sets are respectively input into the detail recognition channel, key frames in the initial signal images are screened by the detail recognition channel, static signal features including brightness features, color features, shape features and the like are extracted, and the image display condition of the signal lamp can be reflected.
P60: based on the target signal characteristics, combining an abnormal signal recognition network to perform abnormal signal recognition, acquiring an abnormal signal recognition result, and performing fault early warning according to the abnormal signal recognition result.
Further, step P60 of the embodiment of the present application further includes:
p61: the abnormal signal identification result comprises a signal control abnormal result and a signal display abnormal result;
p62: based on the dynamic signal characteristics, carrying out control abnormality identification through the control abnormality identification sub-network to obtain a signal control abnormality result;
p63: based on the dynamic signal characteristics and the static signal characteristics, carrying out display abnormality identification through the display abnormality identification sub-network to obtain a signal display abnormality result;
p64: and carrying out signal lamp fault early warning based on the signal control abnormal result and the signal display abnormal result.
Optionally, the target signal features are input into the abnormal signal recognition network to perform abnormal signal recognition, and an abnormal signal recognition result is obtained, where the abnormal signal recognition result includes a signal control abnormal result and a signal display abnormal result, the signal control abnormal result is that a signal lamp responds to a control instruction in an abnormal manner, for example, the signal lamp has overlong single-color display time, insufficient brightness and disordered light sequence, and the signal display abnormal result is that a screen of the signal device is damaged or a signal is abnormal due to shielding of environments, trees, billboards, stains and the like. Both signal control anomalies and signal display anomalies can affect driver perception, constituting potential traffic safety risks.
Further, the dynamic signal characteristics are input into the control abnormality recognition sub-network to perform control abnormality recognition, for example, control instruction response speed judgment and control instruction execution result judgment are performed, and signal control abnormality results are obtained. And respectively inputting the dynamic signal characteristics and the static signal characteristics into the display abnormality recognition sub-network to perform display abnormality recognition, including abnormal flicker recognition, abnormal shape recognition and the like, and obtaining a signal display abnormality result. And according to the signal control abnormal result and the signal display abnormal result, performing signal lamp fault early warning, and timely performing corresponding signal equipment maintenance so as to improve traffic running efficiency and safety.
Further, as shown in fig. 3, step P62 in the embodiment of the present application further includes:
p62-1: the control anomaly identification comprises node response anomaly evaluation and signal duration anomaly evaluation;
p62-2: extracting signal change node information based on the dynamic signal characteristics through the control anomaly identification sub-network, wherein the signal change node information comprises color conversion information and response time information;
p62-3: based on the color conversion information and the response time information, carrying out node response evaluation and signal duration evaluation by combining a plurality of standard signal change parameters and a plurality of standard signal duration to obtain node response efficiency and signal duration deviation;
p62-4: and carrying out abnormality judgment by responding to the efficiency threshold and the signal duration deviation threshold to obtain a signal control abnormal result.
The control anomaly identification comprises node response anomaly evaluation and signal duration anomaly evaluation, wherein the node response anomaly evaluation is to evaluate the response speed of each signal conversion node, for example, the duration for converting to a green light at a specified red light-to-green light node, and the signal duration anomaly evaluation is to evaluate the accuracy of a specified traffic light maintaining duration. Specifically, the control anomaly identification sub-network extracts signal change node information from the dynamic signal characteristics, wherein the signal change node information comprises color conversion information and response time information of each conversion node of the signal.
Further, with the time of the conversion node as a reference, calculating a time difference by using the color conversion information and the response time information and corresponding standard signal change parameters and standard signal duration, obtaining a node response time difference and a signal holding time difference, taking the node response time difference and the signal holding time difference as node response efficiency and signal duration deviation, respectively comparing the node response efficiency and signal duration deviation with a response efficiency threshold and a signal duration deviation threshold, and if any item exceeds the threshold, indicating that the problem of too slow signal lamp response speed or inaccurate duration exists, marking that signal control is abnormal, and obtaining a signal control abnormal result.
Further, step P60 of the embodiment of the present application further includes:
p63-1: the display abnormality identification comprises flicker abnormality assessment and image abnormality assessment;
p63-2: extracting image flicker frequency information based on the dynamic signal characteristics through the display abnormality identification sub-network;
p63-3: performing scintillation abnormality assessment based on the scintillation frequency information to obtain a signal scintillation abnormality result;
p63-4: extracting image color features, brightness features and shape features based on the static signal features through the display abnormality identification sub-network, and carrying out image abnormality assessment by combining a plurality of standard image features to obtain an image abnormality assessment result;
p63-5: and adding the signal flicker abnormal result and the image abnormality evaluation result to the signal display abnormal result.
It should be understood that the display abnormality recognition includes a flicker abnormality evaluation for a signal lamp abnormality flicker problem caused by a circuit contact abnormality and an image abnormality evaluation for an image abnormality problem caused by a display screen malfunction or an environmental shielding. Specifically, through the display anomaly identification sub-network, image brightness change data is extracted from the dynamic signal characteristics, image flicker frequency information is obtained through calculation, the flicker frequency information is compared with a flicker frequency threshold value, a signal flicker anomaly result is obtained, and if the flicker frequency information exceeds the flicker frequency threshold value, the existence of abnormal flicker is determined.
Further, through the display anomaly identification sub-network, extracting image color features, brightness features and shape features from the static signal features, carrying out similarity calculation by combining a plurality of standard image features, judging whether the static signal features are anomaly according to the similarity, wherein the closer the similarity is, the smaller the possibility of anomaly is, the greater the possibility of anomaly is, and the image anomaly evaluation result is obtained through similarity judgment. The signal flicker abnormal result and the image abnormal evaluation result are used as the signal display abnormal result together, so that abnormal problems such as abnormal flicker, insufficient brightness, incomplete display and the like of the signal lamp can be reflected.
In summary, the embodiments of the present application have at least the following technical effects:
according to the method, the standard signal control parameters are acquired through collecting the light control information of each signal device in the target area, the abnormal signal recognition network is constructed, the video monitoring device is used for acquiring the basic signal image set, the initial signal image set is obtained through preprocessing, the target signal characteristics are acquired through characteristic extraction, the abnormal signal recognition is carried out by combining the abnormal signal recognition network, and the fault early warning is carried out according to the abnormal signal recognition result.
The technical effects of improving the response speed and the recognition accuracy of the abnormal signals are achieved.
Example two
Based on the same inventive concept as the method for identifying abnormal signals based on the video monitoring system device in the foregoing embodiments, as shown in fig. 4, the present application provides an abnormal signal identifying system based on the video monitoring system device, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
the light control information acquisition module 11 is used for acquiring light control information of each signal device in the target area, wherein the light control information comprises a light color sequence and a corresponding control duration, and the light control information is provided with a time mark;
the abnormal signal identification network construction module 12 is used for acquiring standard signal control parameters according to the lamplight control information and combining an abnormal signal judgment rule to construct an abnormal signal identification network;
the base signal image set acquisition module 13 is used for acquiring signal images of target signal equipment by using a video monitoring device to acquire a base signal image set;
the initial signal image set acquisition module 14, wherein the initial signal image set acquisition module 14 is used for preprocessing the basic signal image set to obtain an initial signal image set;
the target signal feature extraction module 15, wherein the target signal feature extraction module 15 is configured to perform feature extraction based on the initial signal image set, so as to obtain a target signal feature;
the abnormal signal identification module 16, wherein the abnormal signal identification module 16 is configured to perform abnormal signal identification in combination with an abnormal signal identification network based on the target signal characteristics, obtain an abnormal signal identification result, and perform fault early warning according to the abnormal signal identification result.
Further, the abnormal signal identifying network construction module 12 is further configured to perform the following steps:
the abnormal signal identification network comprises a control abnormal identification sub-network and a display abnormal identification sub-network;
acquiring standard signal control parameters including a plurality of standard signal change parameters based on time nodes, a plurality of standard signal duration and a plurality of corresponding standard image features through the light control information;
constructing a control anomaly identification sub-network based on a plurality of standard signal change parameters and a plurality of standard signal duration;
constructing a display anomaly identification sub-network by combining a twin neural network through a plurality of standard image features;
and connecting the control abnormality identification sub-network with the display abnormality identification sub-network to obtain the abnormality signal identification network.
Further, the initial signal image set acquisition module 14 is further configured to perform the following steps:
reading basic information of the basic signal image set, and setting a first operator;
acquiring a first central pixel point based on the basic signal image set, and combining the first operator to perform pixel mean value calculation to acquire a denoising pixel value of the first central pixel point;
and by analogy, traversing the basic signal image set to perform pixel mean value calculation to obtain a plurality of denoising pixel points, and obtaining the initial signal image set.
Further, the target signal feature extraction module 15 is further configured to perform the following steps:
constructing a feature extraction model, wherein the feature extraction model comprises a dynamic capturing channel and a detail identifying channel;
based on the initial signal image set, combining the dynamic capturing channel to obtain dynamic signal characteristics, wherein the dynamic signal characteristics comprise display duration characteristics and display color characteristics;
based on the initial signal image set, combining the detail recognition channel to obtain static signal characteristics, wherein the static signal characteristics comprise brightness characteristics, color characteristics and shape characteristics;
and combining the dynamic signal characteristics and the static signal characteristics to obtain the target signal characteristics.
Further, the abnormal signal identification module 16 is further configured to perform the following steps:
the abnormal signal identification result comprises a signal control abnormal result and a signal display abnormal result;
based on the dynamic signal characteristics, carrying out control abnormality identification through the control abnormality identification sub-network to obtain a signal control abnormality result;
based on the dynamic signal characteristics and the static signal characteristics, carrying out display abnormality identification through the display abnormality identification sub-network to obtain a signal display abnormality result;
and carrying out signal lamp fault early warning based on the signal control abnormal result and the signal display abnormal result.
Further, the abnormal signal identification module 16 is further configured to perform the following steps:
the control anomaly identification comprises node response anomaly evaluation and signal duration anomaly evaluation;
extracting signal change node information based on the dynamic signal characteristics through the control anomaly identification sub-network, wherein the signal change node information comprises color conversion information and response time information;
based on the color conversion information and the response time information, carrying out node response evaluation and signal duration evaluation by combining a plurality of standard signal change parameters and a plurality of standard signal duration to obtain node response efficiency and signal duration deviation;
and carrying out abnormality judgment by responding to the efficiency threshold and the signal duration deviation threshold to obtain a signal control abnormal result.
Further, the abnormal signal identification module 16 is further configured to perform the following steps:
the display abnormality identification comprises flicker abnormality assessment and image abnormality assessment;
extracting image flicker frequency information based on the dynamic signal characteristics through the display abnormality identification sub-network;
performing scintillation abnormality assessment based on the scintillation frequency information to obtain a signal scintillation abnormality result;
extracting image color features, brightness features and shape features based on the static signal features through the display abnormality identification sub-network, and carrying out image abnormality assessment by combining a plurality of standard image features to obtain an image abnormality assessment result;
and adding the signal flicker abnormal result and the image abnormality evaluation result to the signal display abnormal result.
It should be noted that the sequence of the embodiments of the present application is merely for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the present application is not intended to limit the invention to the particular embodiments of the present application, but to limit the scope of the invention to the particular embodiments of the present application.
The specification and drawings are merely exemplary of the application and are to be regarded as covering any and all modifications, variations, combinations, or equivalents that are within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (8)
1. The abnormal signal identification method based on the video monitoring system equipment is characterized by comprising the following steps of:
collecting light control information of each signal device in a target area, wherein the light control information comprises a light color sequence and a corresponding control duration, and the light control information is provided with a time mark;
collecting standard signal control parameters according to the light control information, and constructing an abnormal signal identification network by combining an abnormal signal judgment rule;
acquiring signal images of target signal equipment by using a video monitoring device to acquire a basic signal image set;
preprocessing the basic signal image set to obtain an initial signal image set;
extracting features based on the initial signal image set to obtain target signal features;
based on the target signal characteristics, combining an abnormal signal recognition network to perform abnormal signal recognition, acquiring an abnormal signal recognition result, and performing fault early warning according to the abnormal signal recognition result.
2. The method of claim 1, wherein the step of collecting standard signal control parameters according to the light control information and combining with an abnormal signal judgment rule to construct an abnormal signal recognition network comprises the steps of:
the abnormal signal identification network comprises a control abnormal identification sub-network and a display abnormal identification sub-network;
acquiring standard signal control parameters including a plurality of standard signal change parameters based on time nodes, a plurality of standard signal duration and a plurality of corresponding standard image features through the light control information;
constructing a control anomaly identification sub-network based on a plurality of standard signal change parameters and a plurality of standard signal duration;
constructing a display anomaly identification sub-network by combining a twin neural network through a plurality of standard image features;
and connecting the control abnormality identification sub-network with the display abnormality identification sub-network to obtain the abnormality signal identification network.
3. The method of claim 1, wherein preprocessing the base signal image set to obtain an initial signal image set comprises:
reading basic information of the basic signal image set, and setting a first operator;
acquiring a first central pixel point based on the basic signal image set, and combining the first operator to perform pixel mean value calculation to acquire a denoising pixel value of the first central pixel point;
and by analogy, traversing the basic signal image set to perform pixel mean value calculation to obtain a plurality of denoising pixel points, and obtaining the initial signal image set.
4. The method of claim 1, wherein the extracting features based on the initial signal image set to obtain target signal features comprises:
constructing a feature extraction model, wherein the feature extraction model comprises a dynamic capturing channel and a detail identifying channel;
based on the initial signal image set, combining the dynamic capturing channel to obtain dynamic signal characteristics, wherein the dynamic signal characteristics comprise display duration characteristics and display color characteristics;
based on the initial signal image set, combining the detail recognition channel to obtain static signal characteristics, wherein the static signal characteristics comprise brightness characteristics, color characteristics and shape characteristics;
and combining the dynamic signal characteristics and the static signal characteristics to obtain the target signal characteristics.
5. The method of claim 4, wherein the obtaining the abnormal signal recognition result, and performing fault pre-warning according to the abnormal signal recognition result, comprises:
the abnormal signal identification result comprises a signal control abnormal result and a signal display abnormal result;
based on the dynamic signal characteristics, carrying out control abnormality identification through the control abnormality identification sub-network to obtain a signal control abnormality result;
based on the dynamic signal characteristics and the static signal characteristics, carrying out display abnormality identification through the display abnormality identification sub-network to obtain a signal display abnormality result;
and carrying out signal lamp fault early warning based on the signal control abnormal result and the signal display abnormal result.
6. The method of claim 5, wherein the identifying the control anomalies through the control anomaly identification sub-network to obtain signal control anomalies comprises:
the control anomaly identification comprises node response anomaly evaluation and signal duration anomaly evaluation;
extracting signal change node information based on the dynamic signal characteristics through the control anomaly identification sub-network, wherein the signal change node information comprises color conversion information and response time information;
based on the color conversion information and the response time information, carrying out node response evaluation and signal duration evaluation by combining a plurality of standard signal change parameters and a plurality of standard signal duration to obtain node response efficiency and signal duration deviation;
and carrying out abnormality judgment by responding to the efficiency threshold and the signal duration deviation threshold to obtain a signal control abnormal result.
7. The method of claim 5, wherein the performing display anomaly identification through the display anomaly identification sub-network, obtaining a signal display anomaly result, comprises:
the display abnormality identification comprises flicker abnormality assessment and image abnormality assessment;
extracting image flicker frequency information based on the dynamic signal characteristics through the display abnormality identification sub-network;
performing scintillation abnormality assessment based on the scintillation frequency information to obtain a signal scintillation abnormality result;
extracting image color features, brightness features and shape features based on the static signal features through the display abnormality identification sub-network, and carrying out image abnormality assessment by combining a plurality of standard image features to obtain an image abnormality assessment result;
and adding the signal flicker abnormal result and the image abnormality evaluation result to the signal display abnormal result.
8. An abnormal signal identification system based on video monitoring system equipment, which is characterized in that the system comprises:
the light control information acquisition module is used for acquiring light control information of each signal device in the target area, wherein the light control information comprises a light color sequence and a corresponding control duration, and the light control information is provided with a time mark;
the abnormal signal identification network construction module is used for acquiring standard signal control parameters according to the lamplight control information and combining an abnormal signal judgment rule to construct an abnormal signal identification network;
the base signal image set acquisition module is used for acquiring signal images of target signal equipment by using the video monitoring device to acquire a base signal image set;
the initial signal image set acquisition module is used for preprocessing the basic signal image set to obtain an initial signal image set;
the target signal feature extraction module is used for carrying out feature extraction based on the initial signal image set to obtain target signal features;
the abnormal signal identification module is used for carrying out abnormal signal identification based on the target signal characteristics and combining an abnormal signal identification network, obtaining an abnormal signal identification result and carrying out fault early warning according to the abnormal signal identification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311534109.9A CN117475269A (en) | 2023-11-17 | 2023-11-17 | Abnormal signal identification method and system based on video monitoring system equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311534109.9A CN117475269A (en) | 2023-11-17 | 2023-11-17 | Abnormal signal identification method and system based on video monitoring system equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117475269A true CN117475269A (en) | 2024-01-30 |
Family
ID=89639544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311534109.9A Pending CN117475269A (en) | 2023-11-17 | 2023-11-17 | Abnormal signal identification method and system based on video monitoring system equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117475269A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118154380A (en) * | 2024-04-09 | 2024-06-07 | 潜山韵浩环保科技有限公司 | Intelligent campus safety monitoring prediction management system |
-
2023
- 2023-11-17 CN CN202311534109.9A patent/CN117475269A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118154380A (en) * | 2024-04-09 | 2024-06-07 | 潜山韵浩环保科技有限公司 | Intelligent campus safety monitoring prediction management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105744232B (en) | A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology | |
| KR101748121B1 (en) | System and method for detecting image in real-time based on object recognition | |
| CN110263686A (en) | A kind of construction site safety of image cap detection method based on deep learning | |
| CN110222672A (en) | The safety cap of construction site wears detection method, device, equipment and storage medium | |
| CN117172414A (en) | Building curtain construction management system based on BIM technology | |
| CN110070530A (en) | A kind of powerline ice-covering detection method based on deep neural network | |
| CN110769195B (en) | Intelligent monitoring and recognizing system for violation of regulations on power transmission line construction site | |
| KR101688218B1 (en) | System for managing traffic flow and incidents using image detection in real time based on object recognition and method for processing thereof | |
| CN117475269A (en) | Abnormal signal identification method and system based on video monitoring system equipment | |
| CN112487891B (en) | Visual intelligent dynamic identification model construction method applied to electric power operation site | |
| CN110852222A (en) | Campus corridor scene intelligent monitoring method based on target detection | |
| CN101833673A (en) | Electric power switchgear switch state image recognition system | |
| CN116805204B (en) | Intelligent plant monitoring method and system | |
| CN103152558B (en) | Based on the intrusion detection method of scene Recognition | |
| CN116055690B (en) | Method and equipment for processing machine room monitoring video | |
| CN113642403B (en) | Crowd abnormal intelligent safety detection system based on edge calculation | |
| CN113723300A (en) | Artificial intelligence-based fire monitoring method and device and storage medium | |
| CN113989874A (en) | Highway construction safety accident early warning system and method | |
| CN112532927A (en) | Intelligent safety management and control system for construction site | |
| CN117197713A (en) | Extraction method based on digital video monitoring system | |
| CN113569956A (en) | Mountain fire disaster investigation and identification method based on AI algorithm | |
| CN110543809A (en) | Electric power operation site risk supervision intrusion video identification method | |
| CN113095160B (en) | Power system personnel safety behavior identification method and system based on artificial intelligence and 5G | |
| CN106941580A (en) | Method and system of the teacher student from motion tracking is realized based on single detective camera lens | |
| CN116310922A (en) | Petrochemical plant area monitoring video risk identification method, system, 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 |