CN116189439A - Urban intelligent management system - Google Patents
Urban intelligent management system Download PDFInfo
- Publication number
- CN116189439A CN116189439A CN202310493788.3A CN202310493788A CN116189439A CN 116189439 A CN116189439 A CN 116189439A CN 202310493788 A CN202310493788 A CN 202310493788A CN 116189439 A CN116189439 A CN 116189439A
- Authority
- CN
- China
- Prior art keywords
- module
- information
- road
- tracking
- log
- 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
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 230000000903 blocking effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000011144 upstream manufacturing Methods 0.000 claims description 4
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000004927 fusion Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/095—Traffic lights
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an urban intelligent management system, which belongs to the technical field of urban intelligent management and comprises a cloud control platform, an image acquisition module, an image processing module, a road network management control module, a cascade tracking module, a positioning module, an alarm feedback module and a log detection module, wherein the cloud control platform is used for verifying manager information and carrying out corresponding data display and function control according to a manager operation instruction; the invention can collect and forecast traffic flow information in each period in real time, ensures the accuracy of traffic signal control, does not need to manually maintain traffic flow, is beneficial to saving resident travel time, can perform full cross-equipment matching, avoids the condition of missed detection, greatly improves the accuracy of target detection, is convenient to use, reduces the difficulty of target analysis, and improves the working efficiency.
Description
Technical Field
The invention relates to the technical field of urban intelligent management, in particular to an urban intelligent management system.
Background
Intelligent city construction is a system engineering. In the intelligent city system, city management is intelligent firstly, an intelligent city management system is used for assisting in managing cities, and the intelligent city management system is used for assisting in intelligent management of infrastructures including intelligent traffic, intelligent power, intelligent buildings, intelligent safety and the like, and also comprises social intelligence such as intelligent medical treatment, intelligent families, intelligent education and the like and production intelligence of intelligent enterprises, intelligent banks and intelligent shops, so that the modernization level of city production, management and operation is comprehensively improved; the intelligent city intelligent network is a fusion of information economy and knowledge economy, a computer network of the information economy provides basic conditions for building intelligent cities, and human intelligence of the knowledge economy changes human intelligence into kinetic energy for city development, so that progress of science and technology and civilization of human society are promoted powerfully.
Through retrieval, chinese patent publication No. CN107481527A discloses an intelligent city management system, and the intelligent city management system is used for implementing real-time management and control on personnel, equipment and infrastructure in a network, particularly traffic, environment, public safety and the like through rapid calculation, analysis and processing, but has poor accuracy on traffic signal control, meanwhile, traffic flow is required to be manually maintained, and the travel time of residents is greatly increased; in addition, the existing urban intelligent management system cannot perform sufficient cross-equipment matching, the condition that targets are missed to be detected easily occurs, the use is inconvenient, the analysis difficulty is increased, and therefore the urban intelligent management system is provided.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides an urban intelligent management system.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the urban intelligent management system comprises a cloud control platform, an image acquisition module, an image processing module, a road network management module, a cascade tracking module, a positioning module, an alarm feedback module and a log detection module;
the cloud control platform is used for verifying the information of the manager and carrying out corresponding data display and function control according to the operation instruction of the manager;
the image acquisition module is used for acquiring image information of each road in the city;
the image processing module is used for optimizing and dividing the acquired image information;
the road network control module is used for controlling the traffic flow of each intersection;
the cascade tracking module is used for monitoring illegal conditions of all intersections and analyzing and tracking illegal personnel;
the positioning module is used for receiving the tracking information and positioning the position of the illegal person in real time;
the alarm feedback module is used for sending illegal alarm information to related department responsible personnel and feeding back the position information of the illegal personnel in real time;
the log detection module is used for monitoring risk of cloud control platform log data.
As a further scheme of the invention, the image processing module optimally divides the specific steps as follows:
step (1): the image processing module extracts each group of image data frame by frame to obtain road pictures, then carries out blocking processing according to the display proportion of each road picture, then carries out analysis and extraction on high-frequency components in the data on each group of road pictures after blocking through Fourier transformation, and carries out smoothing processing through Gaussian filtering;
step (2): and respectively calculating the average value of the gray values of each road picture, comparing the gray value of each group of pixels in each road picture after the block division with the calculated average value, forming a division target by all pixels with gray values larger than the average value, forming a background of the division image by all pixels with gray values smaller than the average value, and analyzing the division target and the background.
As a further aspect of the present invention, the specific transformation formula of the fourier transform in the step (1) is as follows:
wherein u and v are frequency variables, x and y are coordinates of each pixel point of the road picture, N is sampling frequency, formula (1) is Fourier positive transformation, and formula (2) is Fourier inverse transformation.
As a further scheme of the invention, the road network management control module traffic flow control comprises the following specific steps:
step one: the cloud control platform receives road image information, calculates the position and speed information of the vehicle in the phase green light time according to the received data, and constructs congestion index data sets of different congestion index road section flows under different grouping labels according to different road section flows;
step two: the road network management and control module updates the congestion index according to the road image information in each real-time interval, screens the road section flow direction of serious congestion and general congestion to determine a congestion area, and then determines the boundary of the congestion area and congestion interception points and untwining points in the area according to the congestion indexes of different flow directions of each road section and the upstream-downstream relation;
step three: constructing an urban road network map, filling the road missing information, generating a high-dimensional tensor input variable according to the space-time association relation between the upstream image acquisition module and the downstream image acquisition module, performing time sequence training on the high-dimensional tensor input variable through a recurrent neural network and an attention network, and recording the generated traffic flow predicted value;
step four: the road network management and control module acquires the queuing length and saturation of the vehicles and the track data of the tail of the vehicle team according to the image information, and simultaneously judges whether the queuing length exceeds the length of a road section, whether the saturation is over and whether the vehicles at the tail of the vehicle team are located outside the road section and the speed is zero in the green light duration of the phase, if so, the phenomenon of queuing overflow exists, the steering phase (the driving direction information of the vehicles such as from east to west, from north to east, from south to west and the like) takes the maximum green light duration, and otherwise, the phase is not changed.
As a further scheme of the invention, the specific analysis and tracking steps of the cascade tracking module are as follows:
step I: the cascade tracking module calculates the interval time of the actual video frames of each image information, records the calculated interval time of the actual video frames, establishes a motion model through a Kalman filtering theory, and simultaneously acquires the motion state of a tracking target in real time through the established motion model;
step II: a unique number is allocated to the tracking target, then the motion model defines the motion state of the tracking target in a video frame according to the linear motion assumption of the tracking target, collects the motion state of the tracking target in the current video frame, and constructs a prediction equation to estimate the motion state of each tracking target in the next video frame;
step III: extracting features of each image information, fusing the extracted features, classifying and regressing the fused results, outputting detection frames and categories, collecting target detection frame information in the image information, and generating corresponding detection frame coordinates;
step IV: and (3) carrying out enlarged cutting on related image information according to the detection frames, filtering out simple negative samples belonging to the background in each group of cut pictures through RPN, selecting a region possibly containing targets for classification and regression, then producing a corresponding number of anchor frames in each cut picture, classifying and regressing the anchor frames, extracting target information in each group of pictures through enlarged cutting, and then carrying out cross-equipment matching processing according to the estimation result and the target information.
As a further scheme of the invention, the specific calculation formula of the interval time in the step I is as follows:
in the method, in the process of the invention,
representing the interval time s between two groups of video frames; />
Representing the delay time s between the downsampled video frame and the original video stream; />
Representing the consumed time of the tracking algorithm for processing the video frames, s, T represents the current video frame time, s;
the specific definition form of the motion state in the step II is as follows:
in the method, in the process of the invention,
representing the state of motion of the tracked object,x,y,w,hcenter point coordinates representing a tracking target boundary bounding box and width and height +.>
Representing the corresponding tracking target speed value.
As a further scheme of the present invention, the specific steps of risk monitoring by the log detection module are as follows:
step (1): the log detection module deploys related log acquisition plug-ins on management platforms of different systems or acquires log data recorded in the management platforms of different systems through a syslog server, screens out log information meeting preset conditions of staff, and then processes the residual log data into log information in a uniform format;
step (2): matching the user operation behavior recorded in the processed log information with the abnormal behavior characteristics, generating corresponding alarm information according to the matching result, calculating the risk scores of the alarm information, outputting the calculation result, feeding back the alarm information to related staff, interrupting the related operation process, and recording and feeding back the IP address of related equipment and the user information.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the method, the position and speed information of the vehicle in the phase green time are calculated through the received data, different congestion index road section flow directions are constructed for different road section flows, a congestion index data set is constructed under different grouping labels, a road management control module updates the congestion index according to road image information in each real-time interval, road flow directions of severe congestion and general congestion are screened out to determine a congestion area, congestion flow interception points and untwisting points in the boundary and the area of the congestion area are determined, a city road network map is constructed to generate traffic flow predicted values, then the road management control module acquires track data of the queuing length, saturation and the tail of a vehicle team according to the image information, meanwhile judges whether the queuing length exceeds the road section length, whether the saturation is excessive and whether the speed of the vehicle at the tail of the vehicle team is zero in the phase green time, and adjusts the traffic light state according to the judging result, traffic flow information in each period can be collected and predicted in real time, travel accuracy of traffic signal control is guaranteed, manual maintenance of the vehicle flow is not needed, and resident time is saved.
2. The urban intelligent management system establishes a motion model through a Kalman filtering theory, acquires the motion state of a tracking target in real time through the established motion model, defines the motion state of the tracking target in a video frame according to the linear motion assumption of the tracking target, collects the motion state of the tracking target in the current video frame, estimates the motion state of each tracking target in the next video frame, fuses each image information characteristic, carries out classification regression on the fusion result to output a detection frame, carries out expansion cutting on related image information through the target detection frame, filters out simple negative samples belonging to the background in each group of cutting pictures through RPN, picks out regions possibly containing targets for classification and regression, then produces anchor frames with corresponding numbers in each cutting picture, carries out classification and regression on the anchor frames, extracts the target information in each group of pictures through expansion cutting, carries out cross-equipment matching processing according to the estimation result and the target information, can carry out full cross-equipment matching, avoids the occurrence of missed detection condition, is convenient to use, and simultaneously reduces the target analysis difficulty and improves the work efficiency.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
Fig. 1 is a system block diagram of an urban intelligent management system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Example 1
Referring to fig. 1, the city intelligent management system includes a cloud control platform, an image acquisition module, an image processing module, a road network management module, a cascade tracking module, a positioning module, an alarm feedback module and a log detection module.
The cloud control platform is used for verifying the information of the manager and carrying out corresponding data display and function control according to the operation instruction of the manager; the image acquisition module is used for acquiring image information of each road in the city; the image processing module is used for optimizing and dividing the acquired image information.
Specifically, the image processing module extracts each group of image data frame by frame to obtain road pictures, then carries out blocking processing according to the display ratio of each road picture, then carries out analysis and extraction on high-frequency components in the data through Fourier transform on each group of road pictures after blocking, carries out smoothing processing through Gaussian filtering, calculates the average value of gray values of each road picture, then compares the gray value of each group of pixels in each road picture after blocking with the calculated average value, forms a segmentation target with all pixels with gray values larger than the average value, forms a background of a segmentation image with all pixels with gray values smaller than the average value, and then carries out analysis on the segmentation target and the background.
It should be further noted that the specific transformation formula of the fourier transform is as follows:
wherein u and v are frequency variables, x and y are coordinates of each pixel point of the road picture, formula (1) is positive Fourier transform, and formula (2) is inverse Fourier transform.
The road network control module is used for controlling the traffic flow of each intersection.
Specifically, the cloud control platform receives road image information, meanwhile, position and speed information of vehicles in phase green time are calculated according to the received data, a congestion index data set of different congestion index road flows under different grouping labels is built according to different road flows, the road management control module updates the congestion index according to the road image information in each real-time interval, road flows of severely congested and commonly congested road sections are screened out to determine a congestion area, then congestion stop points and a decomposition point in the boundary and the area of the congestion area are determined according to the congestion index and the upstream and downstream relations of different flows of each road section, an urban road network map is built, road missing information is filled, a high-dimensional tensor input variable is generated according to the time-space association relation between the upstream and downstream image acquisition modules, time sequence training is carried out on the high-dimensional tensor input variable through a recurrent neural network and an attention network, the generated traffic flow predicted value is recorded, the road management control module acquires the track data of the vehicle queuing length, the vehicle saturation and the vehicle tail according to the image information, meanwhile, whether the queuing length exceeds the vehicle tail length, the saturation and the vehicle tail track data are located outside a traffic queue, if the traffic queue is in the phase position is changed, and the phase is not changed, and the phase is changed to the phase is not in the green, and the phase is changed, and the phase is not changed, and the phase is changed, and the green time is changed, and the phase is not changed, and the phase is in the state is changed.
Example 2
Referring to fig. 1, the city intelligent management system includes a cloud control platform, an image acquisition module, an image processing module, a road network management module, a cascade tracking module, a positioning module, an alarm feedback module and a log detection module.
The positioning module is used for receiving the tracking information and positioning the position of the illegal person in real time; the alarm feedback module is used for sending illegal alarm information to related department responsible personnel and feeding back the position information of the illegal personnel in real time.
The cascade tracking module is used for monitoring the illegal conditions of each intersection and analyzing and tracking illegal personnel.
Specifically, the cascade tracking module calculates the interval time of actual video frames of each image information, records the calculated interval time of the actual video frames, establishes a motion model through a Kalman filtering theory, acquires the motion state of a tracking target in real time through the established motion model, distributes a unique number for the tracking target, defines the motion state of the tracking target in the video frames according to the linear motion assumption of the tracking target, collects the motion state of the tracking target in the current video frames, constructs a prediction equation, estimates the motion state of each tracking target in the next video frame, extracts characteristics of each image information, fuses the extracted characteristics, carries out classification regression on the fusion result, outputs detection frames and categories, collects target detection frame information in the image information, generates corresponding detection frame coordinates, enlarges and cuts related image information, filters out simple negative samples belonging to the background in each group of cut pictures through RPN, selects areas possibly containing targets, carries out classification and regression, then produces corresponding numbers of anchor frames in each cut picture, carries out regression on the anchor frames, carries out characteristic extraction on the anchor frames, carries out classification and regression on the anchor frames, carries out classification and carries out classification regression on the anchor frames, carries out classification and expansion on the object information according to the expansion and expansion of each group of the target, and carries out cross-matching treatment on the target information.
Specifically, the specific calculation formula of the interval time is as follows:
in the method, in the process of the invention,
representing the interval time between two groups of video frames, < >>
Representing the delay time between the downsampled video frame and the original video stream, +.>
Representing the elapsed time for the tracking algorithm to process the video frames;
the specific definition form of the motion state is as follows:
in the method, in the process of the invention,
representing the state of motion of the tracked object, < >>
Center point coordinates representing a tracking target boundary bounding box and width and height +.>
Representing the corresponding tracking target speedAnd (5) a degree value.
The log detection module is used for monitoring risk of cloud control platform log data.
Specifically, the log detection module deploys related log acquisition plug-ins on management platforms of different systems or acquires log data recorded in the management platforms of different systems through a syslog server, screens out log information meeting preset conditions of workers, processes the residual log data into log information in a unified format, matches user operation behaviors recorded in the processed log information with abnormal behavior features, generates corresponding alarm information according to the matching result, calculates risk scores of the alarm information and outputs calculation results, feeds back the alarm information to related workers, interrupts related operation processes, and records and feeds back IP addresses of related equipment and user information.
Claims (7)
1. The urban intelligent management system is characterized by comprising a cloud control platform, an image acquisition module, an image processing module, a road network management module, a cascade tracking module, a positioning module, an alarm feedback module and a log detection module;
the cloud control platform is used for verifying the information of the manager and carrying out corresponding data display and function control according to the operation instruction of the manager;
the image acquisition module is used for acquiring image information of each road in the city;
the image processing module is used for optimizing and dividing the acquired image information;
the road network control module is used for controlling the traffic flow of each intersection;
the cascade tracking module is used for monitoring illegal conditions of all intersections and analyzing and tracking illegal personnel;
the positioning module is used for receiving the tracking information and positioning the position of the illegal person in real time;
the alarm feedback module is used for sending illegal alarm information to related department responsible personnel and feeding back the position information of the illegal personnel in real time;
the log detection module is used for monitoring risk of cloud control platform log data.
2. The urban intelligent management system according to claim 1, wherein the image processing module optimizes the segmentation as follows:
step (1): the image processing module extracts each group of image data frame by frame to obtain road pictures, then carries out blocking processing according to the display proportion of each road picture, then carries out analysis and extraction on high-frequency components in the data on each group of road pictures after blocking through Fourier transformation, and carries out smoothing processing through Gaussian filtering;
step (2): and respectively calculating the average value of the gray values of each road picture, comparing the gray value of each group of pixels in each road picture after the block division with the calculated average value, forming a division target by all pixels with gray values larger than the average value, forming a background of the division image by all pixels with gray values smaller than the average value, and analyzing the division target and the background.
3. The urban intelligent management system according to claim 2, wherein the fourier transform specific transformation formula in step (1) is as follows:
wherein u and v are frequency variables, x and y are coordinates of each pixel point of the road picture, N is sampling frequency, formula (1) is Fourier positive transformation, and formula (2) is Fourier inverse transformation.
4. The urban intelligent management system according to claim 2, wherein the road network management control module traffic flow control comprises the following specific steps:
step one: the cloud control platform receives road image information, calculates the position and speed information of the vehicle in the phase green light time according to the received data, and constructs congestion index data sets of different congestion index road section flows under different grouping labels according to different road section flows;
step two: the road network management and control module updates the congestion index according to the road image information in each real-time interval, screens the road section flow direction of serious congestion and general congestion to determine a congestion area, and then determines the boundary of the congestion area and congestion interception points and untwining points in the area according to the congestion indexes of different flow directions of each road section and the upstream-downstream relation;
step three: constructing an urban road network map, filling the road missing information, generating a high-dimensional tensor input variable according to the space-time association relation between the upstream image acquisition module and the downstream image acquisition module, performing time sequence training on the high-dimensional tensor input variable through a recurrent neural network and an attention network, and recording the generated traffic flow predicted value;
step four: the road network management and control module acquires the vehicle queuing length, the saturation and the track data of the tail of the vehicle team according to the image information, and simultaneously judges whether the queuing length exceeds the road section length, whether the saturation is over and whether the vehicle of the tail of the vehicle team is positioned outside the road section and the speed is zero in the phase green light duration, if so, the queuing overflow phenomenon exists, the steering phase takes the maximum green light duration, and otherwise, the phase is not changed.
5. The urban intelligent management system according to claim 1, wherein the specific analysis and tracking steps of the cascade tracking module are as follows:
step I: the cascade tracking module calculates the interval time of the actual video frames of each image information, records the calculated interval time of the actual video frames, establishes a motion model through a Kalman filtering theory, and simultaneously acquires the motion state of a tracking target in real time through the established motion model;
step II: a unique number is allocated to the tracking target, then the motion model defines the motion state of the tracking target in a video frame according to the linear motion assumption of the tracking target, collects the motion state of the tracking target in the current video frame, and constructs a prediction equation to estimate the motion state of each tracking target in the next video frame;
step III: extracting features of each image information, fusing the extracted features, classifying and regressing the fused results, outputting detection frames and categories, collecting target detection frame information in the image information, and generating corresponding detection frame coordinates;
step IV: and (3) carrying out enlarged cutting on related image information according to the detection frames, filtering out simple negative samples belonging to the background in each group of cut pictures through RPN, selecting a region possibly containing targets for classification and regression, then producing a corresponding number of anchor frames in each cut picture, classifying and regressing the anchor frames, extracting target information in each group of pictures through enlarged cutting, and then carrying out cross-equipment matching processing according to the estimation result and the target information.
6. The intelligent urban management system according to claim 5, wherein the specific calculation formula of the interval time in step i is as follows:
in the method, in the process of the invention,
representing the interval time s between two groups of video frames; />
Representing the delay time s between the downsampled video frame and the original video stream; />
Representing the consumed time of the tracking algorithm for processing the video frames, s, T represents the current video frame time, s;
the specific definition form of the motion state in the step II is as follows:
in the method, in the process of the invention,
representing the state of motion of the tracked object,x,y,w,hcenter point coordinates representing a tracking target boundary bounding box and width and height +.>
Representing the corresponding tracking target speed value.
7. The urban intelligent management system according to claim 1, wherein the specific steps of risk monitoring by the log detection module are as follows:
step (1): the log detection module deploys related log acquisition plug-ins on management platforms of different systems or acquires log data recorded in the management platforms of different systems through a syslog server, screens out log information meeting preset conditions of staff, and then processes the residual log data into log information in a uniform format;
step (2): matching the user operation behavior recorded in the processed log information with the abnormal behavior characteristics, generating corresponding alarm information according to the matching result, calculating the risk scores of the alarm information, outputting the calculation result, feeding back the alarm information to related staff, interrupting the related operation process, and recording and feeding back the IP address of related equipment and the user information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310493788.3A CN116189439A (en) | 2023-05-05 | 2023-05-05 | Urban intelligent management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310493788.3A CN116189439A (en) | 2023-05-05 | 2023-05-05 | Urban intelligent management system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116189439A true CN116189439A (en) | 2023-05-30 |
Family
ID=86442694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310493788.3A Pending CN116189439A (en) | 2023-05-05 | 2023-05-05 | Urban intelligent management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116189439A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681195A (en) * | 2023-06-06 | 2023-09-01 | 深圳启示智能科技有限公司 | Robot road-finding device based on artificial intelligence |
| CN116863708A (en) * | 2023-09-04 | 2023-10-10 | 成都市青羊大数据有限责任公司 | Smart city scheduling distribution system |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646557A (en) * | 2013-11-13 | 2014-03-19 | 重庆邮电大学 | Three-dimensional microform intelligent-traffic management system based on internet of things |
| CN107274667A (en) * | 2017-08-14 | 2017-10-20 | 公安部交通管理科学研究所 | Urban transportation intelligence managing and control system networking joint control framework and implementation |
| CN112818834A (en) * | 2021-01-29 | 2021-05-18 | 山东大学 | Method, device and medium for judging avoidance of emergency vehicle at intersection |
| CN113658436A (en) * | 2021-08-18 | 2021-11-16 | 刘哲鸣 | Traffic monitoring system based on wisdom traffic thing networking |
| CN113706862A (en) * | 2021-08-04 | 2021-11-26 | 同济大学 | Distributed active equalization management and control method considering road network capacity constraint |
| CN114639243A (en) * | 2022-03-31 | 2022-06-17 | 四川九洲视讯科技有限责任公司 | Intelligent traffic prediction and decision method, system and readable storage medium |
| CN114638860A (en) * | 2022-03-23 | 2022-06-17 | 浙江大华技术股份有限公司 | Traffic signal lamp tracking method and device and readable storage medium |
| CN114821114A (en) * | 2022-03-28 | 2022-07-29 | 南京业恒达智能系统股份有限公司 | Groove cutting robot image processing method based on visual system |
| CN115293606A (en) * | 2022-08-12 | 2022-11-04 | 深圳朗道智通科技有限公司 | Unmanned delivery vehicle system |
| CN115345021A (en) * | 2022-08-26 | 2022-11-15 | 国家海洋环境监测中心 | Measuring system for marine biofluid drag coefficient |
| CN115409992A (en) * | 2022-08-12 | 2022-11-29 | 深圳朗道智通科技有限公司 | Remote driving patrol car system |
| CN115564388A (en) * | 2022-10-19 | 2023-01-03 | 中国建筑第五工程局有限公司 | Green construction method for subway rail connecting main body |
| CN115588149A (en) * | 2022-08-31 | 2023-01-10 | 浙江大学 | Cross-camera multi-target cascade matching method based on matching priority |
| CN115719283A (en) * | 2022-11-28 | 2023-02-28 | 西京学院 | Intelligent accounting management system |
| CN115898845A (en) * | 2022-12-08 | 2023-04-04 | 刘倩倩 | Large-proportion double-liquid grouting automatic control system |
| CN116016869A (en) * | 2022-12-29 | 2023-04-25 | 济南幼儿师范高等专科学校 | Campus safety monitoring system based on artificial intelligence and Internet of things |
-
2023
- 2023-05-05 CN CN202310493788.3A patent/CN116189439A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646557A (en) * | 2013-11-13 | 2014-03-19 | 重庆邮电大学 | Three-dimensional microform intelligent-traffic management system based on internet of things |
| CN107274667A (en) * | 2017-08-14 | 2017-10-20 | 公安部交通管理科学研究所 | Urban transportation intelligence managing and control system networking joint control framework and implementation |
| CN112818834A (en) * | 2021-01-29 | 2021-05-18 | 山东大学 | Method, device and medium for judging avoidance of emergency vehicle at intersection |
| CN113706862A (en) * | 2021-08-04 | 2021-11-26 | 同济大学 | Distributed active equalization management and control method considering road network capacity constraint |
| CN113658436A (en) * | 2021-08-18 | 2021-11-16 | 刘哲鸣 | Traffic monitoring system based on wisdom traffic thing networking |
| CN114638860A (en) * | 2022-03-23 | 2022-06-17 | 浙江大华技术股份有限公司 | Traffic signal lamp tracking method and device and readable storage medium |
| CN114821114A (en) * | 2022-03-28 | 2022-07-29 | 南京业恒达智能系统股份有限公司 | Groove cutting robot image processing method based on visual system |
| CN114639243A (en) * | 2022-03-31 | 2022-06-17 | 四川九洲视讯科技有限责任公司 | Intelligent traffic prediction and decision method, system and readable storage medium |
| CN115293606A (en) * | 2022-08-12 | 2022-11-04 | 深圳朗道智通科技有限公司 | Unmanned delivery vehicle system |
| CN115409992A (en) * | 2022-08-12 | 2022-11-29 | 深圳朗道智通科技有限公司 | Remote driving patrol car system |
| CN115345021A (en) * | 2022-08-26 | 2022-11-15 | 国家海洋环境监测中心 | Measuring system for marine biofluid drag coefficient |
| CN115588149A (en) * | 2022-08-31 | 2023-01-10 | 浙江大学 | Cross-camera multi-target cascade matching method based on matching priority |
| CN115564388A (en) * | 2022-10-19 | 2023-01-03 | 中国建筑第五工程局有限公司 | Green construction method for subway rail connecting main body |
| CN115719283A (en) * | 2022-11-28 | 2023-02-28 | 西京学院 | Intelligent accounting management system |
| CN115898845A (en) * | 2022-12-08 | 2023-04-04 | 刘倩倩 | Large-proportion double-liquid grouting automatic control system |
| CN116016869A (en) * | 2022-12-29 | 2023-04-25 | 济南幼儿师范高等专科学校 | Campus safety monitoring system based on artificial intelligence and Internet of things |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681195A (en) * | 2023-06-06 | 2023-09-01 | 深圳启示智能科技有限公司 | Robot road-finding device based on artificial intelligence |
| CN116863708A (en) * | 2023-09-04 | 2023-10-10 | 成都市青羊大数据有限责任公司 | Smart city scheduling distribution system |
| CN116863708B (en) * | 2023-09-04 | 2024-01-12 | 成都市青羊大数据有限责任公司 | Smart city scheduling distribution system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116189439A (en) | Urban intelligent management system | |
| CN111696348B (en) | Multifunctional intelligent signal control system and method | |
| CN111047818A (en) | Forest fire early warning system based on video image | |
| US20130197790A1 (en) | Method and system for traffic performance analysis, network reconfiguration, and real-time traffic monitoring | |
| EP2884423A2 (en) | Video synopsis method and apparatus | |
| CN111818313A (en) | Vehicle real-time tracking method and device based on monitoring video | |
| CN116824859B (en) | Intelligent traffic big data analysis system based on Internet of things | |
| CN107992958A (en) | Population super-limit prewarning method based on ARMA | |
| CN113095301A (en) | Road occupation operation monitoring method, system and server | |
| Hu et al. | A traffic light dynamic control algorithm with deep reinforcement learning based on GNN prediction | |
| CN113627407B (en) | 5G emergency area crowd identification method, device and equipment | |
| CN115294519A (en) | Abnormal event detection and early warning method based on lightweight network | |
| Statsenko et al. | Developing software and hardware for automation of ground urban transport traffic management | |
| Chen et al. | A Novel Background Filtering Method with Automatic Parameter Adjustment for Real-Time Roadside LiDAR Sensing System | |
| CN111582191B (en) | Pouring amount estimation method in concrete pouring based on artificial intelligence video analysis | |
| CN117238145A (en) | Intelligent traffic management method and system based on big data | |
| CN116229396B (en) | High-speed pavement disease identification and warning method | |
| CN115512263A (en) | Dynamic visual monitoring method and device for falling object | |
| Xu et al. | Detecting pedestrian crossing events in large video data from traffic monitoring cameras | |
| CN107801150B (en) | GPS positioning polling base station alarm-based acquisition method and system | |
| CN117151423B (en) | Water conservancy river construction management system and management method based on data analysis | |
| CN115984077B (en) | Traffic abnormal flow causal detection method and equipment | |
| CN116823533B (en) | Intelligent visit guiding method and system for ecological garden | |
| Karnati et al. | Data Mining Algorithms for Traffic Interruption Detection. | |
| CN114093170B (en) | Generation method, system and device of annunciator control scheme and electronic equipment |
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: 20230530 |
|
| RJ01 | Rejection of invention patent application after publication |