CN114446062B - Dynamic allocation system and method based on big data service - Google Patents
Dynamic allocation system and method based on big data service Download PDFInfo
- Publication number
- CN114446062B CN114446062B CN202210107650.0A CN202210107650A CN114446062B CN 114446062 B CN114446062 B CN 114446062B CN 202210107650 A CN202210107650 A CN 202210107650A CN 114446062 B CN114446062 B CN 114446062B
- Authority
- CN
- China
- Prior art keywords
- road section
- vehicle
- picture
- vehicle target
- monitored
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G08G1/056—Detecting movement of traffic to be counted or controlled with provision for distinguishing direction of travel
-
- 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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to a dynamic allocation system based on big data service, comprising: the big data service mechanism is used for providing factory standard pictures corresponding to various vehicles respectively; an intelligent detection component for establishing a recurrent neural network for executing reference retrograde motion total prediction of a monitoring road section at a certain time on a future date, wherein the recurrent neural network takes a plurality of reference retrograde motion total of a plurality of days fixed days before the future date at the same time as the certain time as a plurality of input data; and the dynamic allocation component is used for sending out a signal for dispatching police officers. The invention also relates to a dynamic allocation method based on the big data service. The dynamic allocation system and method based on big data service are reliable in logic and stable in operation. The total number of the retrograde vehicles at each moment in the monitored road section can be obtained, and the prediction of the total number of the retrograde vehicles at the same moment on the future date is completed based on the total number of the retrograde vehicles at the same moment on the past date, so that the dynamic dispatch of the limited police force resource is realized.
Description
Technical Field
The invention relates to the field of big data service, in particular to a dynamic allocation system and a dynamic allocation method based on big data service.
Background
The big data service can accurately draw and describe the audience exhibition track and form by analyzing and matching the big data of the collected information, so that the attention key and habit of the audience can be known; and the data such as demographic characteristics, daily consumption capacity, consumption form, regional distribution and the like of the audience or target population are known in detail, so that accurate marketing and fine management are realized. In the prior art, because the traffic police management resources of a city are limited, the busy degree of each road section in the city is different, and the police force resources which need to be dispatched for each road section are also different, however, when the corresponding police force resources are dispatched according to the road section requirements, the traffic information of the road section needs to be known in advance, for example, the total number of possible retrograde vehicles, but the known traffic information is difficult to obtain accurately.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a dynamic allocation system and a dynamic allocation method based on big data service, which can adopt a customized detection mechanism to obtain the total number of the retrograde vehicles at each moment in a monitored road section, and introduce an artificial intelligence model to complete the prediction of the total number of the retrograde vehicles at the same moment on the future date based on the total number of the retrograde vehicles at the same moment on the past date, thereby providing reliable information for the dispatch of police force resources at any moment on the future date.
Compared with the prior art, the invention at least needs to have the following two prominent substantive characteristics:
(1) a big data service mechanism arranged in a control room of a road administration department of a city is adopted and used for providing factory standard pictures corresponding to various vehicles respectively and analyzing the total number of retrograde vehicles at each moment in a monitored road section based on the factory standard pictures;
(2) and intelligently predicting the total number of the retrograde vehicles at the same time on the future date based on the total number of the retrograde vehicles at the same time on the past date, and further determining the police force resource needing to be dispatched to the monitoring road section at any time on the future date.
According to an aspect of the present invention, there is provided a big data service-based dynamic provisioning system, the system including:
the big data service mechanism is arranged in a control room of a city road administration department and used for providing factory standard pictures corresponding to various vehicles;
the first capturing mechanism is arranged above the road surface of the monitored road section and used for completing the road surface information capturing action of the monitored road section by adopting the view field covering the whole monitored road section so as to obtain a corresponding road section capturing picture;
the second capturing mechanism is respectively connected with the big data service mechanism and the first capturing mechanism and used for searching each image sub-picture in which each vehicle target is respectively located in the road section capturing picture based on the factory standard pictures respectively corresponding to each vehicle;
the third capturing mechanism is respectively connected with the big data service mechanism and the second capturing mechanism and used for determining that each vehicle target belongs to a reverse vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target;
the information acquisition mechanism is connected with the third acquisition mechanism and is used for taking the moment when the road section acquisition picture is acquired as a reference acquisition moment and taking the number of retrograde vehicle targets in the road section acquisition picture as a reference retrograde total number;
the intelligent detection component is connected with the information acquisition mechanism and used for establishing a recurrent neural network for executing reference retrograde motion total prediction of the monitored road section at a certain moment on a future date, the recurrent neural network takes a plurality of reference retrograde motion total of a plurality of days which are fixed days before the future date and are at the same moment as the certain moment as a plurality of input data, and takes the reference retrograde motion total of the monitored road section at the certain moment on the future date as output data of the recurrent neural network, and the fixed days are positively associated with the road surface width of the monitored road section;
the dynamic allocation component is connected with the intelligent inspection component and is used for sending out a signal of dispatching police officers related to a certain time of the future date when the reference retrograde motion total number of the monitored road sections at a certain time of the future date is greater than or equal to a set number threshold value;
wherein the dynamic scheduling component is further configured to determine and issue a number of dispatch officers directly proportional to the reference retrograde total number at the same time as issuing dispatch officer signals.
According to another aspect of the present invention, there is also provided a dynamic recipe method based on big data service, the method including:
the system comprises a big data service mechanism, a big data service mechanism and a big data service mechanism, wherein the big data service mechanism is arranged in a control room of a city road administration department and is used for providing factory standard pictures corresponding to various vehicles;
the method comprises the steps that a first capturing mechanism is used and arranged above a road surface of a monitored road section and used for completing road surface information capturing action of the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture;
using a second capturing mechanism, respectively connected with the big data service mechanism and the first capturing mechanism, for searching each image sub-picture in which each vehicle target is respectively located in the road section capturing picture based on the delivery standard picture respectively corresponding to each vehicle;
using a third capturing mechanism, respectively connected with the big data service mechanism and the second capturing mechanism, for determining that each vehicle target belongs to a retrograde vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture where each vehicle target is located;
the using information acquisition mechanism is connected with the third capturing mechanism and used for taking the moment when the road section capturing picture is captured as a reference acquisition moment and taking the number of the retrograde vehicle targets in the road section capturing picture as a reference retrograde total number;
using an intelligent detection component, connected to the information acquisition mechanism, for establishing a recurrent neural network that performs prediction of a reference retrograde motion total of the monitored road segment at a certain time in a future date, the recurrent neural network taking as input data a plurality of reference retrograde motion total of a plurality of days of a fixed number of days before the future date at the same time as the certain time, and taking as output data of the recurrent neural network the reference retrograde motion total of the monitored road segment at the certain time in the future date, the fixed number of days being positively associated with a road surface width of the monitored road segment;
a dynamic allocation component is used and connected with the intelligent inspection component and used for sending a dispatching police officer signal related to a certain time of the future date when the received reference retrograde motion total number of the monitored road section at the certain time of the future date is more than or equal to a set number threshold value;
wherein the dynamic scheduling component is further configured to determine and issue a number of dispatch officers directly proportional to the reference retrograde total number at the same time as issuing dispatch officer signals.
The dynamic allocation system and method based on big data service are reliable in logic and stable in operation. The total number of the retrograde vehicles at each moment in the monitored road section can be obtained, and the prediction of the total number of the retrograde vehicles at the same moment on the future date is completed based on the total number of the retrograde vehicles at the same moment on the past date, so that the dynamic dispatch of the limited police force resource is realized.
Drawings
Embodiments of the invention will now be described with reference to the accompanying drawings, in which:
fig. 1 is an internal structural diagram of a recurrent neural network used in a big data service-based dynamic deployment system and method according to an embodiment of the present invention.
Detailed Description
Embodiments of the big data service based dynamic provisioning system and method of the present invention will be described in detail below with reference to the accompanying drawings.
The traffic policeman, called traffic policeman for short, has the main responsibility of checking illegal road traffic behaviors and traffic accidents according to law; maintaining the traffic order of urban and rural roads and the public security order of highways; the safety inspection, license issuing and driver examination and issuing work of the motor vehicle are carried out; developing road traffic safety propaganda education activities; road traffic management scientific research work; participate in urban construction, road traffic and the planning of safety facilities. The method is characterized by comprising the following steps of organizing and transmitting traffic laws and regulations, managing road traffic order according to laws, managing vehicles, drivers and pedestrians, educating traffic offenders, and surveying and processing traffic accidents to maintain normal traffic order and ensure the smoothness and safety of traffic transportation.
In the prior art, because the traffic police management resources of a city are limited, the busy degree of each road section in the city is different, and the police force resources required to be dispatched for each road section are also different, however, when the corresponding police force resources are dispatched according to the road section requirements, the traffic information of the road section needs to be known in advance, for example, the total number of possible vehicles in wrong direction, but the known traffic information is difficult to obtain accurately.
In order to overcome the defects, the invention builds a dynamic allocation system and a dynamic allocation method based on big data service, and can effectively solve the corresponding technical problems.
Fig. 1 is an internal structural diagram of a recurrent neural network used in a big data service-based dynamic deployment system and method according to an embodiment of the present invention.
First, a dynamic provisioning system based on a big data service shown in a first embodiment of the present invention will be described in detail as follows:
the big data service mechanism is arranged in a control room of a city road administration department and used for providing factory standard pictures corresponding to various vehicles;
the first capturing mechanism is arranged above the road surface of the monitored road section and used for completing the road surface information capturing action of the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture;
the second capturing mechanism is respectively connected with the big data service mechanism and the first capturing mechanism and used for searching each image sub-picture in which each vehicle target is respectively located in the road section capturing picture based on the factory standard pictures respectively corresponding to each vehicle;
the third capturing mechanism is respectively connected with the big data service mechanism and the second capturing mechanism and used for determining that each vehicle target belongs to a reverse vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target;
the information acquisition mechanism is connected with the third acquisition mechanism and is used for taking the moment when the road section acquisition picture is acquired as a reference acquisition moment and taking the number of retrograde vehicle targets in the road section acquisition picture as a reference retrograde total number;
an intelligent detection component, connected to the information acquisition mechanism, for establishing a recurrent neural network for performing prediction of reference retrograde motion sum of the monitored road segment at a certain time on a future date, wherein the recurrent neural network takes a plurality of reference retrograde motion sum of a plurality of days of a fixed number of days before the future date at the same time as the certain time as a plurality of input data, and takes a reference retrograde motion sum of the monitored road segment at the certain time on the future date as output data of the recurrent neural network, and the fixed number of days is positively associated with a road surface width of the monitored road segment, and an internal structure of the recurrent neural network is shown in fig. 1;
the dynamic allocation component is connected with the intelligent inspection component and is used for sending out a signal of dispatching police officers related to a certain time of the future date when the reference retrograde motion total number of the monitored road sections at a certain time of the future date is greater than or equal to a set number threshold value;
wherein the dynamic scheduling component is further configured to determine and issue a number of dispatch officers directly proportional to the reference retrograde total number at the same time as issuing dispatch officer signals.
Next, a dynamic provisioning system based on big data service according to a second embodiment of the present invention will be described in detail as follows:
the big data service mechanism is arranged in a control room of a city road administration department and is used for providing factory standard pictures corresponding to various vehicles;
the first capturing mechanism is arranged above the road surface of the monitored road section and used for completing the road surface information capturing action of the monitored road section by adopting the view field covering the whole monitored road section so as to obtain a corresponding road section capturing picture;
the second capturing mechanism is respectively connected with the big data service mechanism and the first capturing mechanism and used for searching each image sub-picture in which each vehicle target is respectively located in the road section capturing picture based on the factory standard pictures respectively corresponding to each vehicle;
the third capturing mechanism is respectively connected with the big data service mechanism and the second capturing mechanism and used for determining that each vehicle target belongs to a reverse vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target;
the information acquisition mechanism is connected with the third capture mechanism and is used for taking the moment when the road section capture picture is captured as a reference acquisition moment and taking the number of the retrograde vehicle targets in the road section capture picture as a reference retrograde total number;
the intelligent detection component is connected with the information acquisition mechanism and used for establishing a recurrent neural network for executing reference retrograde motion total prediction of the monitored road section at a certain moment on a future date, the recurrent neural network takes a plurality of reference retrograde motion total of a plurality of days which are fixed days before the future date and are at the same moment as the certain moment as a plurality of input data, and takes the reference retrograde motion total of the monitored road section at the certain moment on the future date as output data of the recurrent neural network, and the fixed days are positively associated with the road surface width of the monitored road section;
the dynamic allocation component is connected with the intelligent inspection component and is used for sending out a signal of dispatching police officers related to a certain time of the future date when the reference retrograde motion total number of the monitored road sections at a certain time of the future date is greater than or equal to a set number threshold value;
wherein the dynamic dispatching component is further configured to determine and issue a number of dispatch officers directly proportional to the reference retrograde total number while issuing a dispatch officer signal;
the training processing component is connected with the intelligent detection component and used for finishing each training of the cyclic neural network by adopting the reference retrograde motion total number of the monitoring road section at the same moment in each day as the input data or the output data of the cyclic neural network before the cyclic neural network is subjected to prediction;
wherein, the step of finishing each training of the recurrent neural network by using the reference retrograde motion total number of the monitoring road section at the same time in each day as the input data or the output data of the recurrent neural network comprises the following steps: the total area of the road surface of the monitoring road section is in direct proportion to the number of times of training.
The first embodiment or the second embodiment of the present invention shows a big data service-based dynamic provisioning system in which:
determining that each vehicle target belongs to a retrograde vehicle target or a antegrade vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target comprises: determining a road surface driving direction of the monitored road section based on the pointing direction of a road surface printed driving arrow in the monitored road section;
wherein determining that each vehicle target belongs to an inverse vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture in which each vehicle target is located further comprises: identifying a vehicle head part in an image sub-picture where the vehicle target is located based on vehicle head imaging characteristics in a factory standard picture corresponding to the vehicle target, and identifying a vehicle tail part in the image sub-picture where the vehicle target is located based on vehicle tail imaging characteristics in a factory standard picture corresponding to the vehicle target;
wherein determining that each vehicle target belongs to an inverse vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture in which each vehicle target is located further comprises: and when the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target are consistent with the road surface driving direction of the monitored road section, judging that the vehicle target belongs to the forward vehicle target.
The first embodiment or the second embodiment of the present invention shows a big data service-based dynamic provisioning system in which:
the dynamic dispatching component is further used for sending a pause dispatching signal associated with a certain time of the future date when the reference retrograde motion total number of the monitoring road sections at a certain time of the received future date is less than the set number threshold value;
the first capturing mechanism is arranged above the road surface of the monitored road section and used for completing road surface information capturing action on the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture, and comprises the following steps: the first capturing mechanism is internally provided with a photoelectric sensor and is used for completing road information capturing action on the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture.
Again, the dynamic recipe method based on big data service shown in the third embodiment of the present invention is explained in detail as follows:
the big data service mechanism is arranged in a control room of a city road administration department and used for providing delivery standard pictures corresponding to various vehicles;
the method comprises the steps that a first capturing mechanism is used and arranged above a road surface of a monitored road section and used for completing road surface information capturing action of the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture;
using a second capturing mechanism, respectively connected with the big data service mechanism and the first capturing mechanism, for searching each image sub-picture in which each vehicle target is respectively located in the road section capturing picture based on the delivery standard picture respectively corresponding to each vehicle;
using a third capturing mechanism, respectively connected with the big data service mechanism and the second capturing mechanism, for determining that each vehicle target belongs to a retrograde vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture where each vehicle target is located;
the using information acquisition mechanism is connected with the third capturing mechanism and used for taking the moment when the road section capturing picture is captured as a reference acquisition moment and taking the number of the retrograde vehicle targets in the road section capturing picture as a reference retrograde total number;
using an intelligent detection component, connected to the information acquisition mechanism, for establishing a recurrent neural network for performing prediction of a reference retrograde motion total of the monitored road segment at a certain time in a future date, the recurrent neural network taking a plurality of reference retrograde motion total of a plurality of days of a fixed number of days before the future date at the same time as the certain time as a plurality of input data, and taking the reference retrograde motion total of the monitored road segment at the certain time in the future date as output data of the recurrent neural network, the fixed number of days being positively associated with a road surface width of the monitored road segment, wherein an internal structure of the recurrent neural network is as shown in fig. 1;
the dynamic allocation component is connected with the intelligent inspection component and used for sending a signal of dispatching police officers related to a certain time of the future date when the reference retrograde motion total number of the monitored road sections at a certain time of the future date is greater than or equal to a set number threshold value;
wherein the dynamic scheduling component is further configured to determine and issue a number of dispatch officers directly proportional to the reference retrograde total number at the same time as issuing dispatch officer signals.
Finally, the dynamic recipe method based on big data service shown in the fourth embodiment of the present invention is explained in detail as follows:
the system comprises a big data service mechanism, a big data service mechanism and a big data service mechanism, wherein the big data service mechanism is arranged in a control room of a city road administration department and is used for providing factory standard pictures corresponding to various vehicles;
the method comprises the steps that a first capturing mechanism is used and arranged above a road surface of a monitored road section and used for completing road surface information capturing action of the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture;
using a second capturing mechanism, respectively connected with the big data service mechanism and the first capturing mechanism, for searching each image sub-picture in which each vehicle target is respectively located in the road section capturing picture based on the delivery standard picture respectively corresponding to each vehicle;
using a third capturing mechanism which is respectively connected with the big data service mechanism and the second capturing mechanism and is used for determining that each vehicle target belongs to a retrograde vehicle target or a antegrade vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target;
the using information acquisition mechanism is connected with the third capturing mechanism and used for taking the moment when the road section capturing picture is captured as a reference acquisition moment and taking the number of the retrograde vehicle targets in the road section capturing picture as a reference retrograde total number;
using an intelligent detection component, connected to the information acquisition mechanism, for establishing a recurrent neural network that performs prediction of a reference retrograde motion total of the monitored road segment at a certain time in a future date, the recurrent neural network taking as input data a plurality of reference retrograde motion total of a plurality of days of a fixed number of days before the future date at the same time as the certain time, and taking as output data of the recurrent neural network the reference retrograde motion total of the monitored road segment at the certain time in the future date, the fixed number of days being positively associated with a road surface width of the monitored road segment;
the dynamic allocation component is connected with the intelligent inspection component and used for sending a signal of dispatching police officers related to a certain time of the future date when the reference retrograde motion total number of the monitored road sections at a certain time of the future date is greater than or equal to a set number threshold value;
wherein the dynamic dispatching component is further configured to determine and issue a number of dispatch officers directly proportional to the reference retrograde total number while issuing dispatch officer signals;
the training processing component is connected with the intelligent detection component and used for finishing each training of the recurrent neural network by adopting the reference retrograde motion total number of the monitored road section at the same moment in each day as the input data or the output data of the recurrent neural network before the recurrent neural network is subjected to prediction;
wherein, the step of finishing each training of the recurrent neural network by using the reference retrograde motion total number of the monitoring road section at the same time in each day as the input data or the output data of the recurrent neural network comprises the following steps: the total area of the road surface of the monitored road section is in direct proportion to the number of times of training.
The third or fourth embodiment of the present invention shows a big data service-based dynamic provisioning system in which:
determining that each vehicle target belongs to a retrograde vehicle target or a antegrade vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target comprises: determining a road surface driving direction of the monitored road section based on the pointing direction of a road surface printed driving arrow in the monitored road section;
wherein determining that each vehicle target belongs to an inverse vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture in which each vehicle target is located further comprises: identifying a vehicle head part in an image sub-picture where the vehicle target is located based on vehicle head imaging characteristics in a factory standard picture corresponding to the vehicle target, and identifying a vehicle tail part in the image sub-picture where the vehicle target is located based on vehicle tail imaging characteristics in a factory standard picture corresponding to the vehicle target;
wherein determining that each vehicle target belongs to an inverse vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture in which each vehicle target is located further comprises: and when the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target are consistent with the road surface driving direction of the monitored road section, judging that the vehicle target belongs to the forward vehicle target.
The third or fourth embodiment of the present invention shows a big data service-based dynamic provisioning system in which:
the dynamic dispatching component is further used for sending a pause dispatching signal associated with a certain time of the future date when the reference retrograde motion total number of the monitoring road sections at a certain time of the received future date is less than the set number threshold value;
the first capturing mechanism is arranged above the road surface of the monitored road section and used for completing road surface information capturing action on the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture, and comprises the following steps: the first capturing mechanism is internally provided with a photoelectric sensor and is used for completing road information capturing action on the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture.
In addition, in the dynamic deployment system and method based on big data service, determining that each vehicle target belongs to a retrograde vehicle target or a antegrade vehicle target based on the road traveling direction of the monitored road section and the direction of the head part relative to the tail part in the image sub-picture where each vehicle target is located further comprises: and when the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target do not accord with the road surface driving direction of the monitored road section, judging that the vehicle target belongs to a retrograde vehicle target.
While the invention has been described in connection with preferred embodiments, it is to be understood that other similar embodiments may be used or modifications and additions may be made to the described embodiment for performing the same function of the present invention without deviating therefrom. For example, while exemplary embodiments of the present invention are described in the context of a digital device emulating the functionality of a personal computer, those skilled in the art will recognize that the present invention is not limited to such digital devices, as described in the present application, and that the present invention may apply to any number of existing or emerging computing devices or environments. Therefore, the present invention should not be limited to any single embodiment, but rather should be construed in breadth and scope in accordance with the appended claims.
Claims (10)
1. A big data service-based dynamic deployment system, the system comprising:
the big data service mechanism is arranged in a control room of a city road administration department and used for providing factory standard pictures corresponding to various vehicles;
the first capturing mechanism is arranged above the road surface of the monitored road section and used for completing the road surface information capturing action of the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture;
the second capturing mechanism is respectively connected with the big data service mechanism and the first capturing mechanism and used for searching each image sub-picture in which each vehicle target is respectively located in the road section capturing picture based on the factory standard pictures respectively corresponding to each vehicle;
the third capturing mechanism is respectively connected with the big data service mechanism and the second capturing mechanism and is used for determining that each vehicle target belongs to a reverse vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target;
the information acquisition mechanism is connected with the third capture mechanism and is used for taking the moment when the road section capture picture is captured as a reference acquisition moment and taking the number of the retrograde vehicle targets in the road section capture picture as a reference retrograde total number;
the intelligent detection component is connected with the information acquisition mechanism and is used for establishing a recurrent neural network for predicting the reference retrograde motion total number of the monitored road section at a certain moment on the future date, the recurrent neural network takes a plurality of reference retrograde motion total numbers of a plurality of days which are fixed days before the future date and are at the same moment as the certain moment as a plurality of input data, the reference retrograde motion total number of the monitored road section at the certain moment on the future date is taken as output data of the recurrent neural network, and the fixed days are positively associated with the road surface width of the monitored road section;
the dynamic allocation component is connected with the intelligent inspection component and is used for sending out a signal of dispatching police officers related to a certain time of the future date when the reference retrograde motion total number of the monitored road sections at a certain time of the future date is greater than or equal to a set number threshold value;
wherein the dynamic scheduling component is further configured to determine and issue a number of dispatch officers directly proportional to the reference retrograde total number at the same time as issuing dispatch officer signals.
2. The big data service-based dynamic provisioning system of claim 1, wherein said system further comprises:
the training processing component is connected with the intelligent detection component and used for finishing each training of the cyclic neural network by adopting the reference retrograde motion total number of the monitored road section at the same moment in each day as the input data or the output data of the cyclic neural network before the cyclic neural network is subjected to prediction;
wherein, the step of finishing each training of the recurrent neural network by using the reference retrograde motion total number of the monitoring road section at the same time in each day as the input data or the output data of the recurrent neural network comprises the following steps: the total area of the road surface of the monitoring road section is in direct proportion to the number of times of training.
3. A big data service based dynamic provisioning system according to any of claims 1-2, wherein:
determining that each vehicle target belongs to a retrograde vehicle target or a antegrade vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target comprises: determining a road surface driving direction of the monitored road section based on the pointing direction of a road surface printed driving arrow in the monitored road section;
wherein determining that each vehicle target belongs to a retrograde vehicle target or a antegrade vehicle target based on the road surface driving direction of the monitored road section and the direction of the head part relative to the tail part in the image sub-picture of each vehicle target further comprises: and identifying the vehicle head part in the image sub-picture where the vehicle target is located based on the vehicle head imaging characteristic in the factory standard picture corresponding to the vehicle target, and identifying the vehicle tail part in the image sub-picture where the vehicle target is located based on the vehicle tail imaging characteristic in the factory standard picture corresponding to the vehicle target.
4. The big data service-based dynamic provisioning system of claim 3, wherein:
determining that each vehicle target belongs to a retrograde vehicle target or a antegrade vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target further comprises: and when the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target are consistent with the road surface driving direction of the monitored road section, judging that the vehicle target belongs to the forward vehicle target.
5. A big data service based dynamic provisioning system according to any of claims 1-2, wherein:
the dynamic dispatching component is further used for sending a pause dispatching signal associated with a certain time of the future date when the reference retrograde motion total number of the monitoring road sections at a certain time of the received future date is less than the set number threshold value;
the first capturing mechanism is arranged above the road surface of the monitored road section and used for completing the road surface information capturing action of the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture, and comprises the following steps: the first capturing mechanism is internally provided with a photoelectric sensor and is used for completing road information capturing action on the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture.
6. A dynamic deployment method based on big data service is characterized in that the method comprises the following steps:
the system comprises a big data service mechanism, a big data service mechanism and a big data service mechanism, wherein the big data service mechanism is arranged in a control room of a city road administration department and is used for providing factory standard pictures corresponding to various vehicles;
the method comprises the steps that a first capturing mechanism is used, is arranged above a road surface of a monitored road section and is used for completing road surface information capturing action on the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture;
using a second capturing mechanism, respectively connected with the big data service mechanism and the first capturing mechanism, for searching each image sub-picture in which each vehicle target is respectively located in the road section capturing picture based on the delivery standard picture respectively corresponding to each vehicle;
using a third capturing mechanism, respectively connected with the big data service mechanism and the second capturing mechanism, for determining that each vehicle target belongs to a reverse vehicle target or a forward vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target;
the using information acquisition mechanism is connected with the third capturing mechanism and used for taking the moment when the road section capturing picture is captured as a reference acquisition moment and taking the number of the retrograde vehicle targets in the road section capturing picture as a reference retrograde total number;
using an intelligent detection component, connected to the information acquisition mechanism, for establishing a recurrent neural network for performing prediction of a reference retrograde motion total of the monitored road segment at a time on a future date, the recurrent neural network taking a plurality of reference retrograde motion total of a plurality of days on a fixed number of days before the future date at the same time as the time as a plurality of input data, taking the reference retrograde motion total of the monitored road segment at the time on the future date as output data of the recurrent neural network, the fixed number of days being positively associated with a road surface width of the monitored road segment;
a dynamic allocation component is used, is connected with the intelligent inspection component and is used for sending out a signal for dispatching police officers when the reference retrograde motion total number of the monitored road sections at a certain moment on a received future date is greater than or equal to a set number threshold value;
wherein the dynamic dispatch component is further configured to determine and issue a number of dispatch officers proportional to the reference retrograde total while issuing dispatch officer signals.
7. The big data service based dynamic provisioning method of claim 6, wherein said method further comprises:
the training processing component is connected with the intelligent detection component and used for finishing each training of the recurrent neural network by adopting the reference retrograde motion total number of the monitored road section at the same moment in each day as the input data or the output data of the recurrent neural network before the recurrent neural network is subjected to prediction;
wherein, the step of finishing each training of the recurrent neural network by using the reference retrograde motion total number of the monitoring road section at the same time in each day as the input data or the output data of the recurrent neural network comprises the following steps: the total area of the road surface of the monitoring road section is in direct proportion to the number of times of training.
8. A method for dynamic provisioning of data services based on claims 6-7 wherein:
determining that each vehicle target belongs to a retrograde vehicle target or a antegrade vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target comprises: determining a road surface driving direction of the monitored road section based on the pointing direction of a road surface printed driving arrow in the monitored road section;
wherein determining that each vehicle object belongs to a retrograde vehicle object or a antegrade vehicle object based on the road traveling direction of the monitored road section and the direction of the head part relative to the tail part in the image sub-picture of each vehicle object further comprises: and identifying the vehicle head part in the image sub-picture where the vehicle target is located based on the vehicle head imaging characteristic in the factory standard picture corresponding to the vehicle target, and identifying the vehicle tail part in the image sub-picture where the vehicle target is located based on the vehicle tail imaging characteristic in the factory standard picture corresponding to the vehicle target.
9. The big data service-based dynamic deployment method of claim 8, wherein:
determining that each vehicle target belongs to a retrograde motion vehicle target or a antegrade motion vehicle target based on the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target further comprises: and when the road surface driving direction of the monitored road section and the direction of the vehicle head part relative to the vehicle tail part in the image sub-picture of each vehicle target are consistent with the road surface driving direction of the monitored road section, judging that the vehicle target belongs to the forward vehicle target.
10. A method for dynamic provisioning of data services based on claims 6-7 wherein:
the dynamic allocation component is also used for sending a pause dispatching signal when the reference retrograde motion total number of the monitoring road section at a certain moment of the received future date is smaller than the set number threshold value;
the first capturing mechanism is arranged above the road surface of the monitored road section and used for completing the road surface information capturing action of the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture, and comprises the following steps: the first capturing mechanism is internally provided with a photoelectric sensor and is used for completing road information capturing action on the monitored road section by adopting a visual field covering the whole monitored road section so as to obtain a corresponding road section capturing picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210107650.0A CN114446062B (en) | 2022-01-28 | 2022-01-28 | Dynamic allocation system and method based on big data service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210107650.0A CN114446062B (en) | 2022-01-28 | 2022-01-28 | Dynamic allocation system and method based on big data service |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114446062A CN114446062A (en) | 2022-05-06 |
| CN114446062B true CN114446062B (en) | 2022-09-27 |
Family
ID=81372585
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210107650.0A Active CN114446062B (en) | 2022-01-28 | 2022-01-28 | Dynamic allocation system and method based on big data service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114446062B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015210713A (en) * | 2014-04-28 | 2015-11-24 | 大樹 谷口 | Driving recorder and cloud road-information operation system using the same |
| WO2019061933A1 (en) * | 2017-09-28 | 2019-04-04 | 孟卫平 | Traffic signal chord panning control method and system |
| CN110570664A (en) * | 2019-09-23 | 2019-12-13 | 山东科技大学 | automatic detection system for highway traffic incident |
| CN111126171A (en) * | 2019-12-04 | 2020-05-08 | 江西洪都航空工业集团有限责任公司 | Vehicle reverse running detection method and system |
| CN112749630A (en) * | 2020-12-17 | 2021-05-04 | 深圳英飞拓科技股份有限公司 | Intelligent video monitoring method and system for road conditions |
| CN112837535A (en) * | 2021-03-22 | 2021-05-25 | 北京百度网讯科技有限公司 | Traffic information processing method, device, system, equipment and storage medium |
-
2022
- 2022-01-28 CN CN202210107650.0A patent/CN114446062B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015210713A (en) * | 2014-04-28 | 2015-11-24 | 大樹 谷口 | Driving recorder and cloud road-information operation system using the same |
| WO2019061933A1 (en) * | 2017-09-28 | 2019-04-04 | 孟卫平 | Traffic signal chord panning control method and system |
| CN110570664A (en) * | 2019-09-23 | 2019-12-13 | 山东科技大学 | automatic detection system for highway traffic incident |
| CN111126171A (en) * | 2019-12-04 | 2020-05-08 | 江西洪都航空工业集团有限责任公司 | Vehicle reverse running detection method and system |
| CN112749630A (en) * | 2020-12-17 | 2021-05-04 | 深圳英飞拓科技股份有限公司 | Intelligent video monitoring method and system for road conditions |
| CN112837535A (en) * | 2021-03-22 | 2021-05-25 | 北京百度网讯科技有限公司 | Traffic information processing method, device, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114446062A (en) | 2022-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6813554B1 (en) | Method and apparatus for adding commercial value to traffic control systems | |
| CN108062857B (en) | Prediction technique for cab-getter's trip purpose | |
| Kurdi | Review of closed circuit television (cctv) techniques for vehicles traffic management | |
| WO2021036290A1 (en) | Method and apparatus for identifying operation behavior of vehicle, and computing device | |
| US20220148428A1 (en) | High innovation distributed system for the management of demarcated areas | |
| CN113442920A (en) | Control method and device for formation driving, computer readable medium and electronic equipment | |
| CN114492022A (en) | Road condition sensing data processing method, device, equipment, program and storage medium | |
| Luo et al. | Traffic signal transition time prediction based on aerial captures during peak hours | |
| Gowtham et al. | An efficient monitoring of real time traffic clearance for an emergency service vehicle using iot | |
| Salma et al. | Smart parking guidance system using 360o camera and haar-cascade classifier on iot system | |
| Khan et al. | Machine learning driven intelligent and self adaptive system for traffic management in smart cities | |
| CN114446062B (en) | Dynamic allocation system and method based on big data service | |
| CN116432956B (en) | Bus allocation method, system, equipment and medium based on passenger flow | |
| CN113111876A (en) | Method and system for obtaining evidence of traffic violation | |
| Petty | Incidents on the freeway: detection and management | |
| JP2002312886A (en) | Road traffic information management system | |
| Osabe et al. | Solutions to social problems leveraging image analysis technology based on machine learning | |
| Prasanth et al. | Intelligent traffic control system using WSN: a perspective | |
| Elmahalawy | A car monitoring system for self recording traffic violations | |
| Chaudhari et al. | Traffic violation detection and penalty generation system at a street intersection | |
| GB2586485A (en) | Lane information system and method | |
| CN110400466A (en) | A kind of traffic monitoring method and system based on double mirror | |
| KR102317311B1 (en) | System for analyzing information using video, and method thereof | |
| KR101611258B1 (en) | Remote real-time parking information system using image matching technique | |
| US11367348B2 (en) | Distributed hearing system for use with traffic signals |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220907 Address after: B907, building 9, zone 2, Shenzhen Bay science and technology ecological park, 3609 Baishi Road, high tech community, Yuehai street, Nanshan District, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Octa Cloud Computing Information Technology Co.,Ltd. Address before: 211400 No. 5, shiford Avenue, Kexue Second Road, Yizheng City, Yangzhou City, Jiangsu Province Applicant before: Liu Yinhuan |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 24/F, Building A1, China Vision Industrial Park, No. 99 Longchuan Road, Baohe District, Hefei City, Anhui Province, 230000 Patentee after: Badu Cloud Computing (Anhui) Co.,Ltd. Address before: B907, building 9, zone 2, Shenzhen Bay science and technology ecological park, 3609 Baishi Road, high tech community, Yuehai street, Nanshan District, Shenzhen, Guangdong 518000 Patentee before: Shenzhen Octa Cloud Computing Information Technology Co.,Ltd. |