CN110047272A - A kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data - Google Patents
A kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data Download PDFInfo
- Publication number
- CN110047272A CN110047272A CN201910422943.6A CN201910422943A CN110047272A CN 110047272 A CN110047272 A CN 110047272A CN 201910422943 A CN201910422943 A CN 201910422943A CN 110047272 A CN110047272 A CN 110047272A
- Authority
- CN
- China
- Prior art keywords
- module
- pedestrian
- information
- image
- vehicle
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/005—Traffic control systems for road vehicles including pedestrian guidance indicator
-
- 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
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- 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
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- 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
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data, including with the one-to-one vehicle end of vehicle, crossing monitoring client and the cloud computing server end at crossing are set, by acquiring large-scale full-view image, to whether unlawful practice occurs judging, while generating the profiling information of party.And existing automobile data recorder, the image of acquisition multi-angle, short distance are cooperated by network.Compared to common crossing monitoring camera, train movement recording equipment widely available in vehicle is included in entire image acquisition system, so that the source of image capturing is more extensive, updating cost simultaneously can also be greatly reduced, facial characteristics from the video extraction of remote, single angle become from multi-angle, short distance multiple incidents when video in extract, it is more clear the acquisition of party's facial characteristics accurately, different alarm strategies is made according to harmfulness and is executed, and timely and effectively accident can be handled.
Description
Technical field
The present invention relates to intelligent transportation fields, and in particular to a kind of intelligent transportation pedestrian behavior monitoring report based on big data
Alert system.
Background technique
In the safety for ensureing road traffic, pedestrian abides by road rules and regulations and is also important a ring.Wherein rush
Red light and to cross fence be most common pedestrian's unlawful practice, such unlawful practice can frequently result in serious traffic accident, because
This needs to realize detection and the record of unlawful practice, in the prior art, Shen using having targetedly monitoring and alarm system
A kind of traffic intersection pedestrian behavior monitoring system please be disclosed in number patent document for being CN201610613568.X, by letter
The color of signal lamp identifies and the identification to traffic intersection pedestrian behavior, the row for obtaining the status of traffic intersection and going across the road in violation of rules and regulations
People, monitoring personnel can be by remote assistances, to realize the control to the crossing.
But in above-mentioned patent, function is more single, whether to be in violation of rules and regulations merely capable of pedestrian, and the image of crossing acquisition module is usual
It installs aloft, and visual angle is fixed, farther out, the facial characteristics of party is easily blocked distance, accurately can not clearly be obtained
The facial information of violation pedestrian, once traffic accident caused by occurring because of unlawful practice, fix duty and processing to the later period all can bands
It is inconvenient to come.
Summary of the invention
In order to solve the above technical problems, the purpose of the present invention is to provide a kind of intelligent transportation row based on big data
People's behavior monitoring alarm system cooperates existing automobile data recorder by network, so that the source of image capturing is more extensive, together
Shi Gengxin cost can also be greatly reduced.By the cooperation of vehicle tag module and label read module, make party's facial characteristics
Acquisition be more clear the accuracy for accurately helping to improve face recognition, and then facilitate the determination of party's personal information.
By being classified to the harmfulness of unlawful practice, after the personal information of party has been determined, difference is made according to harmfulness
Alarm strategy and execute, timely and effectively accident can be handled.
The technical problems to be solved by the invention are as follows:
(1) information of unlawful practice party how is accurately obtained.
(2) how different type of alarms is taken according to the harmfulness of unlawful practice.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data, including with the one-to-one vehicle of vehicle
Crossing monitoring client and the cloud computing server end at crossing are held, are arranged in, the vehicle end includes driving recording module, vehicle tag
Module, image processing module；The crossing monitoring client include first acquisition module, label read module, primary image analysis module,
Alarm policy generation module；The cloud computing server end includes image summarizing module, high vision analysis module, alarm execution
Module；
The just acquisition module is used to acquire pedestrian's motion image at entire crossing.
The label read module is arranged at the stop line at crossing, and by the region in label read module read range
It is divided into pickup area, when vehicle enters pickup area, reads the information of vehicles in vehicle tag module, and record the vehicle
Pass in and out the disengaging temporal information of pickup area；Wherein, information of vehicles is vehicle license, address, and disengaging temporal information is vehicle
Information, into moment, departure time, residence time section.
Whether there is or not disobey by pedestrian in pedestrian's motion image that the primary image analysis module is used to acquire by first acquisition module
Rule behavior, and after the unlawful practice of discovery pedestrian, the period that record unlawful practice occurs, by unlawful practice by harmfulness point
For basic, normal, high three grades, while generating the incident information of unlawful practice.
The alarm policy generation module makes alarm strategy according to the classification of unlawful practice harmfulness；Wherein, it alarms
Strategy specifically: the unlawful practice for less harmful, the alarm strategy for a traffic police department of putting up a notice, for middle harmfulness
Unlawful practice, the alarm strategy of put up a notice traffic police department and ambulance departments, the unlawful practice of corresponding high harmfulness are put up a notice
The alarm strategy of traffic police department, ambulance departments and party relatives；
Described image summarizing module according to incident information and disengaging temporal information for sieving after finding the unlawful practice of pedestrian
That selects that record has pedestrian's characteristic image when unlawful practice generation witnesses vehicle, and issues data uploading instructions, from witnessing vehicle
Driving recording module in collect through the processed pedestrian's characteristic image of image processing module, as characteristic image to be extracted；
The high vision analysis module be used for in characteristic image to be extracted pedestrian's facial characteristics and pedestrian's profiling information carry out
It extracts, the profiling information of pedestrian and the profiling information of party is compared, determine the facial characteristics of party, then by party's
The facial characteristics library stored in facial characteristics and cloud computing server end is compared, and then determines the party of unlawful practice,
And generate party's information；After the alarm execution module generates party's information for high vision analysis module, according to report
It is pithy to omit, by least one of party's information and incident information notice traffic police department, ambulance departments and party relatives.
Information of vehicles is sent to mark for storing information of vehicles and when entering pickup area by the vehicle tag module
Sign read module；The driving recording module is used for after vehicle enters pickup area, acquires pedestrian's feature shadow of vehicle front
Picture；Described image processing module be used for for image summarizing module issue data uploading instructions after, according to incident information to mesh
The pedestrian's characteristic image for hitting vehicle shooting carries out timi requirement, shearing and compression.
Further, the primary image analysis module is classified to unlawful practice and is generated the specific of incident information
Steps are as follows:
Step 1: being divided by the movement of human body in action recognition algorithm identifying rows human action image and standing still, go
Walk, climb, sit down and lie down this five kinds of motion morphologies；
Step 2: when unlawful practice occurs, the period and crossing that record unlawful practice occurs, at the same it is dynamic according to pedestrian
The color and motion morphology for making traffic lights in image determine the party of unlawful practice, and extract and work as from pedestrian's motion image
The profiling information of thing people；
Step 3: obtaining the motion morphology of party after unlawful practice generation, if standing still or walking, then endangering
Evil property is labeled as low, and if sitting down, then during harmfulness is labeled as, if lying down, then harmfulness is labeled as height；
Step 4: the period of unlawful practice generation and crossing, the profiling information of party, hazard gradation result are beaten
Packet generates the incident information of unlawful practice.
Further, described image summarizing module filters out the mesh for recording pedestrian's characteristic image when having unlawful practice generation
The step of hitting vehicle and sending data uploading instructions are as follows:
S1, period and crossing that unlawful practice occurs, then the disengaging temporal information acquired from label read module are obtained
In there are the disengaging temporal informations of time of coincidence section period for occurring with unlawful practice of the residence time section that filters out；
S2, believed according to the corresponding information of vehicles of disengaging temporal information acquisition there are time of coincidence section as vehicle is witnessed
Breath, and the corresponding vehicle conduct of information of vehicles will be witnessed and witness vehicle；
S3, to witness vehicle send comprising unlawful practice occur period data uploading instructions.
Further, described image processing module carries out the specific of timi requirement, shearing and compression to pedestrian's characteristic image
Steps are as follows:
SS1, after receiving data uploading instructions, according to the period that unlawful practice occurs, determine that pedestrian's characteristic image is sheared
At the beginning of and the end time；
SS2, pedestrian's characteristic image is sheared according to starting and end time and extracts the mesh at one section of vehicle visual angle
Hit image；
SS3, it image will be witnessed isolates independent video and independent audio, then the independent video isolated is uploaded to image
Summarizing module.
Beneficial effects of the present invention:
(1) large-scale full-view image is acquired by crossing monitoring client, to whether unlawful practice occurs judging, simultaneously
Generate the profiling information of party.And existing automobile data recorder is cooperated by network, the image of multi-angle, short distance is acquired,
It pops one's head in compared to existing crossing, train movement recording equipment widely available in vehicle is included in entire image acquisition system, is made
Image capturing source it is more extensive, while updating cost and can also be greatly reduced.
(2) by the cooperation of vehicle tag module and label read module, obtain crossing pickup area standing vehicle into
Temporal information out；Cloud computing server end obtains image when incident from the automobile data recorder for witness vehicle, is believed by appearance
The comparison of breath determines the party in video, and then determines the facial characteristics of party, determines party further according to facial characteristics
Personal information.Compared to common crossing monitoring camera, facial characteristics is by script from the video extraction of remote, single angle
Be changed into from multi-angle, short distance multiple incidents when video in extract, be more clear the acquisition of party's facial characteristics
Accurately, the accuracy of face recognition is helped to improve, and then facilitates the determination of party's personal information.
(3) by being classified to the harmfulness of unlawful practice, after the personal information of party has been determined, according to harm
Property is made different alarm strategies and is executed, and can timely and effectively handle accident.
Detailed description of the invention
The present invention will be further described below with reference to the drawings.
Fig. 1 is system block diagram of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts all other
Embodiment shall fall within the protection scope of the present invention.
Refering to Figure 1, present embodiments providing a kind of intelligent transportation pedestrian behavior monitoring alarm based on big data
System, including with the one-to-one vehicle end of vehicle, crossing monitoring client and the cloud computing server end at crossing, vehicle end are set
Including driving recording module, vehicle tag module, image processing module；Crossing monitoring client includes first acquisition module, label reading
Module, primary image analysis module, alarm policy generation module；Cloud computing server end includes image summarizing module, high-level diagram
As analysis module, alarm execution module；
First acquisition module is used to acquire pedestrian's motion image at entire crossing；Using wide-angle or full shot, monitoring range
Entire crossing is covered, the minimum standard of clarity is the limb action for capableing of distinguishing pedestrian.
Label read module is arranged at the stop line at crossing, and the stop line quantity of each road conditions is different, and label reads mould
The quantity of block is corresponding with stop line quantity, if crossroad all directions have a stop line, and T-type crossing then only there are three,
And by the region division in label read module read range be pickup area, therefore multiple angles can be collected, short distance
Image is witnessed, when vehicle enters pickup area, reads the information of vehicles in vehicle tag module, and record the vehicles while passing and adopt
Collect the disengaging temporal information in region；Wherein, information of vehicles be vehicle license, address, disengaging temporal information be information of vehicles,
Into moment, departure time, residence time section；Label read module uses RFID reader, and read range is no more than 8 meters,
Guarantee that the vehicle of a pickup area in the same time will not be excessive, the received invalid data of image summarizing module is avoided to increase.
Whether there is or not violation rows by pedestrian in pedestrian's motion image that primary image analysis module is used to acquire by first acquisition module
For, and after the unlawful practice of discovery pedestrian, the period that record unlawful practice occurs, unlawful practice is divided by harmfulness
Basic, normal, high three grades, while generating the incident information of unlawful practice；Less harmful shows not cause injury to personnel, guarantees to hand over
It is clear and coherent smooth, quickly handled after need to only recording, middle harmfulness shows not cause serious casualties, need in time to party into
Row treatment, high harmfulness show to cause serious casualties；Period duration totally two minutes of unlawful practice generation, specifically
For 120 seconds after since identifying unlawful practice.
Primary image analysis module is classified to unlawful practice and is generated incident information, and specific step is as follows:
Step 1: being the prior art, the movement of human body, is divided into identifying rows human action image by action recognition algorithm
Stand still, walk, climb, sit down and lie down this five kinds of motion morphologies；
Step 2: when unlawful practice occurs, the period and crossing that record unlawful practice occurs, at the same it is dynamic according to pedestrian
The color and motion morphology for making traffic lights in image determine the party of unlawful practice, and extract and work as from pedestrian's motion image
The profiling information of thing people, such as jacket color, lower dress color, the colour of skin, hair color；In zebra stripes uplink when such as passing through red light
It walks, can determine whether that, to make a dash across the red light, making climbing motion can determine whether to cross guardrail etc..
Step 3: the motion morphology of party is obtained after unlawful practice generation, and if standing still or walk, explanation
To cause casualties, then harmfulness is labeled as low, if sitting down, illustrates that party can keep awake, then harmfulness is labeled as
In, if lying down, illustrate that party falls down to the ground, can not stand up, then harmfulness is labeled as height；
Step 4: the period of unlawful practice generation and crossing, the profiling information of party, hazard gradation result are beaten
Packet generates the incident information of unlawful practice.
Policy generation module alarm according to the classification of unlawful practice harmfulness, makes alarm strategy；Wherein, alarm strategy
Specifically: the unlawful practice for less harmful, the alarm strategy for a traffic police department of putting up a notice, the violation for middle harmfulness
Behavior, the alarm strategy of put up a notice traffic police department and ambulance departments, the unlawful practice of corresponding high harmfulness, put up a notice traffic police
The alarm strategy of department, ambulance departments and party relatives；
Image summarizing module according to incident information and disengaging temporal information for filtering out after finding the unlawful practice of pedestrian
What record had pedestrian's characteristic image when unlawful practice generation witnesses vehicle, and issues data uploading instructions, from witnessing vehicle
It collects in driving recording module through the processed pedestrian's characteristic image of image processing module, as characteristic image to be extracted；
Image summarizing module, which filters out to record, witnessing vehicle and sending for pedestrian's characteristic image when unlawful practice generation
The step of data uploading instructions are as follows:
S1, period and crossing that unlawful practice occurs, then the disengaging temporal information acquired from label read module are obtained
In there are the disengaging temporal informations of time of coincidence section period for occurring with unlawful practice of the residence time section that filters out；As in violation of rules and regulations
The period that behavior occurs is 7:00:00-7:02:00, then filters out each pickup area in the crossing in 7:00:00-7:02:00
The information of vehicles stopped in this period, if vehicle dwell time section is 7:00:50-7:00:30, then for there are the times of coincidence
Section.The image when vehicle should record incident at this time.
S2, believed according to the corresponding information of vehicles of disengaging temporal information acquisition there are time of coincidence section as vehicle is witnessed
Breath, and the corresponding vehicle conduct of information of vehicles will be witnessed and witness vehicle；
S3, make to witness the corresponding vehicle end of vehicle and connection is established at cloud computing server end, include to vehicle transmission is witnessed
The data uploading instructions for the period that unlawful practice occurs.
High vision analysis module is used for the pedestrian's facial characteristics and pedestrian's profiling information in characteristic image to be extracted
It extracts, the profiling information of pedestrian and the profiling information of party is compared, determine the facial characteristics of party, then thing will be worked as
The facial characteristics library stored in the facial characteristics of people and cloud computing server end is compared, and then determines that thing is worked as in unlawful practice
People, and generate party's information；After execution module of alarming generates party's information for high vision analysis module, according to alarm
Strategy, by least one of party's information and incident information notice traffic police department, ambulance departments and party relatives.
Information of vehicles is sent to label and read by vehicle tag module for storing information of vehicles and when entering pickup area
Modulus block；Using RFID electronic label, it is set to position of the vehicle chassis close to driver's cabin.
Driving recording module is used for after vehicle enters pickup area, acquires pedestrian's characteristic image of vehicle front, such as vehicle
The intelligent travelling crane recorder installed in；Image processing module is used for for issuing data uploading instructions in image summarizing module
Afterwards, timi requirement, shearing and compression are carried out to the pedestrian's characteristic image for witnessing vehicle shooting according to incident information.
Image processing module carries out timi requirement, shearing and compression to pedestrian's characteristic image, and specific step is as follows:
SS1, after receiving data uploading instructions, according to the period that unlawful practice occurs, determine that pedestrian's characteristic image is sheared
At the beginning of and the end time；Determine the position of shearing image.
SS2, pedestrian's characteristic image is sheared according to starting and end time and extracts the mesh at one section of vehicle visual angle
Hit image；Image is sheared, the size for uploading image is reduced.
SS3, it image will be witnessed isolates independent video and independent audio, then the independent video isolated is uploaded to image
Summarizing module.Redundant data is further removed, and reduces the size of upper transmitting file.
The specific work process of the present embodiment is as follows:
1) limb action of the pedestrian at entire crossing is acquired by the first acquisition module of crossing monitoring client, and passed through
Whether primary image analysis module identifies the movement of pedestrian in image, only to unlawful practice occurs judging, simultaneously
Generate the profiling information of party.
2) cooperation for passing through vehicle tag module and label read module, obtains the disengaging of crossing pickup area standing vehicle
Temporal information；After unlawful practice occurs, according to incident information, cloud computing server end, which filters out, witnesses the multiple of unlawful practice
Vehicle, and from the automobile data recorder of vehicle obtain incident when image, by the profiling information to pedestrian in video file into
Row comparison determines the party in video, and then determines the facial characteristics of party, determines party's further according to facial characteristics
Personal information.Compared to common crossing monitoring camera, facial characteristics by script from the video extraction of remote, single angle turn
Become from multi-angle, short distance multiple incidents when video in extract, so that the acquisition of party's facial characteristics is more clear standard
Really, the accuracy of face recognition is helped to improve, and then facilitates the determination of party's personal information.
3) by being classified to the harmfulness of unlawful practice, after the personal information of party has been determined, according to harm
Property is made different alarm strategies and is executed, and can timely and effectively handle accident.
Above content is only to structure of the invention example and explanation, affiliated those skilled in the art couple
Described specific embodiment does various modifications or additions or is substituted in a similar manner, without departing from invention
Structure or beyond the scope defined by this claim, is within the scope of protection of the invention.
Claims (4)
1. a kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data, which is characterized in that including with vehicle one by one
Corresponding vehicle end, the crossing monitoring client that crossing is arranged in and cloud computing server end, the vehicle end include driving recording mould
Block, vehicle tag module, image processing module；The crossing monitoring client includes first acquisition module, label read module, primary figure
As analysis module, alarm policy generation module；The cloud computing server end includes image summarizing module, high vision analysis mould
Block, alarm execution module；
The just acquisition module is used to acquire pedestrian's motion image at entire crossing in real time；The label read module is arranged on road
At the stop line of mouth, and it is pickup area by the region division in label read module read range, enters acquisition zone in vehicle
When domain, the information of vehicles in vehicle tag module is read, and record the disengaging temporal information of the vehicles while passing pickup area；Its
In, information of vehicles is vehicle license, address, and disengaging temporal information is information of vehicles, into moment, departure time, stop
Period；
Whether there is or not violation rows by pedestrian in pedestrian's motion image that the primary image analysis module is used to acquire by first acquisition module
For, and after the unlawful practice of discovery pedestrian, the period that record unlawful practice occurs, unlawful practice is divided by harmfulness
Basic, normal, high three grades, while generating the incident information of unlawful practice；
The alarm policy generation module makes alarm strategy according to the classification of unlawful practice harmfulness；Wherein, alarm strategy
Specifically: the unlawful practice for less harmful, the alarm strategy for a traffic police department of putting up a notice, the violation for middle harmfulness
Behavior, the alarm strategy of put up a notice traffic police department and ambulance departments, the unlawful practice of corresponding high harmfulness, put up a notice traffic police
The alarm strategy of department, ambulance departments and party relatives；
Information of vehicles is sent to label and read by the vehicle tag module for storing information of vehicles and when entering pickup area
Modulus block；The driving recording module is used for after vehicle enters pickup area, acquires pedestrian's characteristic image of vehicle front；Institute
Image processing module is stated for for after image summarizing module issues data uploading instructions, according to incident information to witnessing vehicle
Pedestrian's characteristic image of shooting carries out timi requirement, shearing and compression；
Described image summarizing module according to incident information and disengaging temporal information for filtering out after finding the unlawful practice of pedestrian
What record had pedestrian's characteristic image when unlawful practice generation witnesses vehicle, and issues data uploading instructions, from witnessing vehicle
It collects in driving recording module through the processed pedestrian's characteristic image of image processing module, as characteristic image to be extracted；It is described
High vision analysis module be used for in characteristic image to be extracted pedestrian's facial characteristics and pedestrian's profiling information extract,
The profiling information of pedestrian and the profiling information of party are compared, determine the facial characteristics of party, then by the face of party
The facial characteristics library stored in feature and cloud computing server end is compared, and then determines the party of unlawful practice, and raw
At party's information；After the alarm execution module generates party's information for high vision analysis module, according to alarm plan
Slightly, by least one of party's information and incident information notice traffic police department, ambulance departments and party relatives.
2. a kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data according to claim 1, feature
It is, the primary image analysis module is classified to unlawful practice and is generated incident information, and specific step is as follows:
Step 1: being divided by the movement of human body in action recognition algorithm identifying rows human action image and standing still, walk, climbing
Climb, sit down and lie down this five kinds of motion morphologies；
Step 2: when unlawful practice occurs, the period and crossing that record unlawful practice occurs, while shadow is acted according to pedestrian
The color and motion morphology of traffic lights, determine the party of unlawful practice, and extract party from pedestrian's motion image as in
Profiling information；
Step 3: the motion morphology of party is obtained after unlawful practice generation, and if standing still or walking, then harmfulness
Labeled as low, if sitting down, then during harmfulness is labeled as, if lying down, then harmfulness is labeled as height；
Step 4: the period that unlawful practice is occurred and crossing, the profiling information of party, hazard gradation result are packaged life
At the incident information of unlawful practice.
3. a kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data according to claim 1, feature
It is, described image summarizing module, which filters out to record, witnessing vehicle and sending for pedestrian's characteristic image when unlawful practice generation
The step of data uploading instructions are as follows:
S1, period and crossing that unlawful practice occurs are obtained, then is sieved from the disengaging temporal information that label read module acquires
The period that the residence time section selected occurs with unlawful practice, there are the disengaging temporal informations of time of coincidence section；
S2, it is used as according to the corresponding information of vehicles of disengaging temporal information acquisition there are time of coincidence section and witnesses information of vehicles, and
The corresponding vehicle conduct of information of vehicles will be witnessed and witness vehicle；
S3, to witness vehicle send comprising unlawful practice occur period data uploading instructions.
4. a kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data according to claim 1, feature
It is, described image processing module carries out timi requirement, shearing and compression to pedestrian's characteristic image, and specific step is as follows:
SS1, after receiving data uploading instructions, according to the period that unlawful practice occurs, opening for pedestrian's characteristic image shearing is determined
Begin time and end time；
SS2, pedestrian's characteristic image is sheared according to starting and end time and extracts one section and witnesses image；
SS3, it image will be witnessed isolates independent video and independent audio, then the independent video isolated is uploaded to image and is summarized
Module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910422943.6A CN110047272B (en) | 2019-05-21 | 2019-05-21 | A kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910422943.6A CN110047272B (en) | 2019-05-21 | 2019-05-21 | A kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110047272A true CN110047272A (en) | 2019-07-23 |
| CN110047272B CN110047272B (en) | 2019-11-12 |
Family
ID=67282899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910422943.6A Active CN110047272B (en) | 2019-05-21 | 2019-05-21 | A kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110047272B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110658809A (en) * | 2019-08-15 | 2020-01-07 | 北京致行慕远科技有限公司 | Method and device for processing travelling of movable equipment and storage medium |
| CN110909707A (en) * | 2019-12-02 | 2020-03-24 | 天津大海云科技有限公司 | Video inspection system and method based on generating type countermeasure network |
| CN112712671A (en) * | 2020-12-18 | 2021-04-27 | 济南浪潮高新科技投资发展有限公司 | Intelligent alarm system and method based on 5G |
| CN113497917A (en) * | 2020-03-18 | 2021-10-12 | 东芝泰格有限公司 | Image processing device |
| CN113507588A (en) * | 2021-06-03 | 2021-10-15 | 山西三友和智慧信息技术股份有限公司 | Wisdom campus visitor flow monitoring system based on artificial intelligence |
| CN115116268A (en) * | 2022-06-13 | 2022-09-27 | 武汉理工大学 | Rural traffic early warning method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103680142A (en) * | 2013-12-23 | 2014-03-26 | 苏州君立软件有限公司 | Traffic intersection intelligent monitoring method |
| CN104320638A (en) * | 2014-11-24 | 2015-01-28 | 张宏鑫 | Intelligent integrated monitoring and controlling system and surveillance video processing method |
| CN207008863U (en) * | 2017-08-11 | 2018-02-13 | 李硕 | A kind of road traffic monitoring system based on drive recorder |
| CN107689158A (en) * | 2017-08-10 | 2018-02-13 | 五邑大学 | A kind of intellectual traffic control method based on image procossing |
| CN108257383A (en) * | 2018-01-16 | 2018-07-06 | 河南魏来网络科技有限公司 | A kind of car-mounted terminal and traffic are passed through the monitoring system of behavior |
| CN109712406A (en) * | 2019-02-12 | 2019-05-03 | 合肥极光科技股份有限公司 | A kind of pedestrian running red light and motor vehicle do not give precedence to pedestrian and monitor capturing system |
-
2019
- 2019-05-21 CN CN201910422943.6A patent/CN110047272B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103680142A (en) * | 2013-12-23 | 2014-03-26 | 苏州君立软件有限公司 | Traffic intersection intelligent monitoring method |
| CN104320638A (en) * | 2014-11-24 | 2015-01-28 | 张宏鑫 | Intelligent integrated monitoring and controlling system and surveillance video processing method |
| CN107689158A (en) * | 2017-08-10 | 2018-02-13 | 五邑大学 | A kind of intellectual traffic control method based on image procossing |
| CN207008863U (en) * | 2017-08-11 | 2018-02-13 | 李硕 | A kind of road traffic monitoring system based on drive recorder |
| CN108257383A (en) * | 2018-01-16 | 2018-07-06 | 河南魏来网络科技有限公司 | A kind of car-mounted terminal and traffic are passed through the monitoring system of behavior |
| CN109712406A (en) * | 2019-02-12 | 2019-05-03 | 合肥极光科技股份有限公司 | A kind of pedestrian running red light and motor vehicle do not give precedence to pedestrian and monitor capturing system |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110658809A (en) * | 2019-08-15 | 2020-01-07 | 北京致行慕远科技有限公司 | Method and device for processing travelling of movable equipment and storage medium |
| CN110909707A (en) * | 2019-12-02 | 2020-03-24 | 天津大海云科技有限公司 | Video inspection system and method based on generating type countermeasure network |
| CN113497917A (en) * | 2020-03-18 | 2021-10-12 | 东芝泰格有限公司 | Image processing device |
| CN112712671A (en) * | 2020-12-18 | 2021-04-27 | 济南浪潮高新科技投资发展有限公司 | Intelligent alarm system and method based on 5G |
| CN113507588A (en) * | 2021-06-03 | 2021-10-15 | 山西三友和智慧信息技术股份有限公司 | Wisdom campus visitor flow monitoring system based on artificial intelligence |
| CN115116268A (en) * | 2022-06-13 | 2022-09-27 | 武汉理工大学 | Rural traffic early warning method and system |
| CN115116268B (en) * | 2022-06-13 | 2023-11-17 | 武汉理工大学 | Rural traffic early warning method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110047272B (en) | 2019-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110047272B (en) | A kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data | |
| US9412268B2 (en) | Vehicle detection and counting | |
| CN103337176B (en) | Traffic violation snapshotting method with traffic violation snapshotting system | |
| US6985172B1 (en) | Model-based incident detection system with motion classification | |
| KR100956125B1 (en) | Integration security system of school zone and operating method thereof | |
| JP4569190B2 (en) | Suspicious person countermeasure system and suspicious person detection device | |
| CN104599443A (en) | Vehicle-mounted forewarning terminal for driving behaviors based on information fusion and forewarning method thereof | |
| CN113676702B (en) | Video stream-based target tracking and monitoring method, system, device and storage medium | |
| CN106534779A (en) | Intelligent monitoring system for early warning of security of scenic spot | |
| CN108376246A (en) | A kind of identification of plurality of human faces and tracking system and method | |
| CN101710446A (en) | Expressway serious lawbreaking action monitoring and early warning system and method | |
| CN105608906A (en) | System for monitoring illegal emergency lane occupancy of expressway motor vehicles and implementation method | |
| CN111564224A (en) | Intelligent monitoring system with health monitoring function and implementation method thereof | |
| CN203422846U (en) | Traffic violation snapshooting system | |
| CN109146914B (en) | Drunk driving behavior early warning method for expressway based on video analysis | |
| KR20080044812A (en) | The automatic guard system to prevent the crime and accident using computer video image analysis technology | |
| CN110866479A (en) | Method, device and system for detecting that motorcycle driver does not wear helmet | |
| CN110222596A (en) | A kind of driving behavior analysis anti-cheating method of view-based access control model | |
| CN211744615U (en) | Big data early warning system of campus security protection | |
| CN112241696A (en) | Image processing method and device, electronic device and storage medium | |
| CN110288823A (en) | A kind of break in traffic rules and regulations erroneous judgement recognition methods based on naive Bayesian network | |
| CN114023088B (en) | Intelligent street-crossing signal lamp system and illegal behavior evidence-obtaining and warning method | |
| CN113963252A (en) | Safety helmet wearing early warning method and system based on image recognition | |
| CN113870551B (en) | Road side monitoring system capable of identifying dangerous and non-dangerous driving behaviors | |
| KR102290353B1 (en) | Unauthorized alerting system and method using object recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |